iswaalex commited on
Commit
aeac30a
·
verified ·
1 Parent(s): 77a12b9

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_706.bin +3 -0
  2. vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_708.bin +3 -0
  3. vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_710.bin +3 -0
  4. vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_713.bin +3 -0
  5. vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_714.bin +3 -0
  6. vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_715.bin +3 -0
  7. vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_716.bin +3 -0
  8. vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_717.bin +3 -0
  9. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable50/Release/1_3_reloadable50.txt +0 -0
  10. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable50/scripts/1_3_reloadable50.bcf +16 -0
  11. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable50/scripts/1_3_reloadable50.prx +13 -0
  12. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable50/src/1_3_reloadable50.cc +121 -0
  13. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.calltree +106 -0
  14. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.cmic2 +0 -0
  15. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.cmico +1 -0
  16. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.lst +0 -0
  17. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.map +347 -0
  18. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.sdr +130 -0
  19. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.srv +0 -0
  20. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.txt +0 -0
  21. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/scripts/1_3_reloadable51.bcf +16 -0
  22. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/scripts/1_3_reloadable51.prx +13 -0
  23. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/src/1_3_reloadable51.cc +122 -0
  24. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.calltree +100 -0
  25. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.cmic2 +0 -0
  26. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.cmico +1 -0
  27. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.lst +0 -0
  28. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.map +320 -0
  29. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.sdr +127 -0
  30. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.srv +0 -0
  31. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.txt +0 -0
  32. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/scripts/1_3_reloadable52.bcf +16 -0
  33. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/scripts/1_3_reloadable52.prx +13 -0
  34. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/src/1_3_reloadable52.cc +121 -0
  35. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.calltree +108 -0
  36. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.cmic2 +0 -0
  37. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.cmico +1 -0
  38. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.lst +0 -0
  39. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.map +382 -0
  40. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.sdr +140 -0
  41. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.srv +0 -0
  42. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.txt +0 -0
  43. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/scripts/1_3_reloadable53.bcf +16 -0
  44. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/scripts/1_3_reloadable53.prx +13 -0
  45. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/src/1_3_reloadable53.cc +123 -0
  46. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable54/Release/1_3_reloadable54.calltree +118 -0
  47. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable54/Release/1_3_reloadable54.cmic2 +0 -0
  48. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable54/Release/1_3_reloadable54.cmico +1 -0
  49. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable54/Release/1_3_reloadable54.lst +0 -0
  50. vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable54/Release/1_3_reloadable54.map +400 -0
vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_706.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1cbb7bc810aea157194ce162fb59a3bb9d1cb5067385cf99fb8dacf8c14652
3
+ size 376
vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_708.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1cbb7bc810aea157194ce162fb59a3bb9d1cb5067385cf99fb8dacf8c14652
3
+ size 376
vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_710.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1cbb7bc810aea157194ce162fb59a3bb9d1cb5067385cf99fb8dacf8c14652
3
+ size 376
vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_713.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1cbb7bc810aea157194ce162fb59a3bb9d1cb5067385cf99fb8dacf8c14652
3
+ size 376
vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_714.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1cbb7bc810aea157194ce162fb59a3bb9d1cb5067385cf99fb8dacf8c14652
3
+ size 376
vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_715.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1cbb7bc810aea157194ce162fb59a3bb9d1cb5067385cf99fb8dacf8c14652
3
+ size 376
vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_716.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1cbb7bc810aea157194ce162fb59a3bb9d1cb5067385cf99fb8dacf8c14652
3
+ size 376
vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_717.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1cbb7bc810aea157194ce162fb59a3bb9d1cb5067385cf99fb8dacf8c14652
3
+ size 376
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable50/Release/1_3_reloadable50.txt ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable50/scripts/1_3_reloadable50.bcf ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _reserved DMb 0x0 0x40000
2
+
3
+ _reserved PM 0x0 0x9e0 //reserved for main elf
4
+
5
+ _entry_point _Z13kernelWrapperPPvjjjj
6
+ _symbol _Z13kernelWrapperPPvjjjj 0x9e0
7
+
8
+ _reserved DMb 0x7b540 0x800 //reserved for lcp ping-pong buffers
9
+ _reserved DMb 0x7bd40 0x40 //reserved for sync buffer
10
+ _stack DM_stack 0x7bd80 0x440 //stack for core
11
+ _reserved DMb 0x7c1c0 0x40 //reserved for main elf heap
12
+ //space for synopsys compiler at 0x7c200 0x800//heap
13
+ _reserved DMb 0x40000 0x3b540
14
+
15
+ _reserved DMb 0x7ca00 0x3600
16
+ _reserved DMb 0x80000 0x80000 // And everything else the core can't see
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable50/scripts/1_3_reloadable50.prx ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <project name="Project" processor="me">
2
+ <issinit/>
3
+ <option id="cpp.define" value="__AIENGINE__ __AIE_ARCH__=21" inherit = "1"/>
4
+ <option id="llvm.xargs" value="-fno-jump-tables -fno-discard-value-names" inherit = "1"/>
5
+ <option id="llvm.lang" value="Follow file extension"/>
6
+ <option id="bridge.cfg" value="1_3_reloadable50.bcf"/>
7
+ <option id="bridge.alibs" value=" ../Release/1_3_reloadable50.o" inherit="1" cfg="Release_LLVM"/>
8
+ <option id="cpp.include" value="&lt;XILINX_VITIS_AIETOOLS&gt;/include /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/&lt;AIE_SRC_DIR&gt;/ /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/&lt;AIE_SRC_DIR&gt; " inherit="1"/>
9
+ <option id="project.dir" value="&lt;CONFIG&gt;/1_3_reloadable50"/>
10
+ <option id="project.name" value="1_3_reloadable50"/>
11
+ <option id="project.type" value="exe"/>
12
+ <option id="simrun.issca" value="&lt;XILINX_VITIS_AIETOOLS&gt;/bin/unwrapped/lnx64.o/aie2p/ca_udm_dbg" inherit="0"/>
13
+ </project>
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable50/src/1_3_reloadable50.cc ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ // Automatically generated processor driver using AIEngine tool-chain
2
+
3
+ #include <stdio.h>
4
+ #include <memory>
5
+ #include <adf.h>
6
+
7
+
8
+ // Declare Kernel functions and initializers
9
+ #include "transpose4d_adf_wrapper.cpp"
10
+ #include "buffer_pad_adf_wrapper.cpp"
11
+ #include "slice_generic_innermost_adf_wrapper.cpp"
12
+ void superkernel_conv2d_dwc(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
13
+ #include "buffer_unpad_adf_wrapper.cpp"
14
+ void superkernel_add1d_attribute_broadcasting(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
15
+ void superkernel_sigmoid1d(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
16
+ void superkernel_mul1d(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict,adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
17
+
18
+ // Declare Kernel objects and external arrays
19
+
20
+
21
+ void _b7835_wrapper(void* args[])
22
+ {
23
+ mllib_graphs::transpose4d_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
24
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
25
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
26
+ *reinterpret_cast<uint32 const(*)[7]>(args[2]));
27
+ }
28
+
29
+ void _b8148_wrapper(void* args[])
30
+ {
31
+ mllib_graphs::buffer_pad_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
32
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
33
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
34
+ *reinterpret_cast<uint32 const(*)[3]>(args[2]));
35
+ }
36
+
37
+ void _b8170_wrapper(void* args[])
38
+ {
39
+ mllib_graphs::slice_generic_innermost_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
40
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
41
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
42
+ *reinterpret_cast<uint32 const(*)[16]>(args[2]));
43
+ }
44
+
45
+ void _b14160_wrapper(void* args[])
46
+ {
47
+ superkernel_conv2d_dwc(
48
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
49
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
50
+ *reinterpret_cast<uint32 const(*)[16]>(args[3]),
51
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[2]));
52
+ }
53
+
54
+ void _b7876_wrapper(void* args[])
55
+ {
56
+ mllib_graphs::buffer_unpad_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
57
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
58
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
59
+ *reinterpret_cast<uint32 const(*)[3]>(args[2]));
60
+ }
61
+
62
+ void _b13739_wrapper(void* args[])
63
+ {
64
+ superkernel_add1d_attribute_broadcasting(
65
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
66
+ *reinterpret_cast<uint32 const(*)[16]>(args[2]),
67
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]));
68
+ }
69
+
70
+ void _b13744_wrapper(void* args[])
71
+ {
72
+ superkernel_sigmoid1d(
73
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
74
+ *reinterpret_cast<uint32 const(*)[16]>(args[2]),
75
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]));
76
+ }
77
+
78
+ void _b13749_wrapper(void* args[])
79
+ {
80
+ superkernel_mul1d(
81
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
82
+ *reinterpret_cast<uint32 const(*)[16]>(args[3]),
83
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]),
84
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[2]));
85
+ }
86
+
87
+ using UniformKernelFunc = void (*)(void **);
88
+
89
+ static UniformKernelFunc g_uniformKernelFuncs[8] = {
90
+ _b7835_wrapper,
91
+ _b8148_wrapper,
92
+ _b8170_wrapper,
93
+ _b14160_wrapper,
94
+ _b7876_wrapper,
95
+ _b13739_wrapper,
96
+ _b13744_wrapper,
97
+ _b13749_wrapper
98
+ };
99
+
100
+ __attribute__((always_inline)) void kernelWrapper(void* args[], uint32 kernelId, uint32 numSyncIn, uint32 numAsyncIn, uint32 numSyncOut)
101
+ {
102
+ uint32 idx = 0;
103
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::in>(numSyncIn > 0);
104
+ idx += (numSyncIn > 0) ? 1 : 0;
105
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::in>(numSyncIn > 1);
106
+ idx += (numSyncIn > 1) ? 1 : 0;
107
+ idx += numAsyncIn;
108
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::out>(numSyncOut > 0);
109
+ idx += (numSyncOut > 0) ? 1 : 0;
110
+
111
+ (*(g_uniformKernelFuncs[kernelId]))(args);
112
+
113
+ idx = 0;
114
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::in>(numSyncIn > 0);
115
+ idx += (numSyncIn > 0) ? 1 : 0;
116
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::in>(numSyncIn > 1);
117
+ idx += (numSyncIn > 1) ? 1 : 0;
118
+ idx += numAsyncIn;
119
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::out>(numSyncOut > 0);
120
+ idx += (numSyncOut > 0) ? 1 : 0;
121
+ }
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.calltree ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ // File generated by bridge version V-2024.06#84922c0d9f#241219, Fri May 30 11:33:41 2025
3
+ // Copyright 2014-2024 Synopsys, Inc. All rights reserved.
4
+ // bridge -o../Release/0_0_reloadable35 ../Release/0_0_reloadable35.o -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/isg -g -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxxabi-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0_reloadable35.bcf -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/softfloat/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork3589147 -pme
5
+
6
+
7
+ // Release: ipp V-2024.06-TGT-241219
8
+
9
+ _Z13kernelWrapperPPvjjjj
10
+ _Z15_b13786_wrapperPPv (referenced text)
11
+ _Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
12
+ _ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv
13
+ _Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params
14
+ _Z8init_accILt1EEvPaS0_iii
15
+ _Z12post_processPai
16
+ _Z15_b13811_wrapperPPv (referenced text)
17
+ _Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
18
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv
19
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv
20
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
21
+ _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE
22
+ _Z15_b13739_wrapperPPv (referenced text)
23
+ _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
24
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
25
+ _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
26
+ _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
27
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E
28
+ _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
29
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
30
+ _Z15_b13744_wrapperPPv (referenced text)
31
+ _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
32
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
33
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
34
+ _Z15_b13749_wrapperPPv (referenced text)
35
+ _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
36
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
37
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
38
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
39
+ _Z14_b8148_wrapperPPv (referenced text)
40
+ _ZN12mllib_graphs22buffer_pad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj
41
+ memset
42
+ _Z14_b7835_wrapperPPv (referenced text)
43
+ _ZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_Kj
44
+ _Z29setup_transposeshuffle_paramsI8bfloat16EvR23transposeshuffle_paramsRA7_Kj
45
+ _Z16transposeshuffleI8bfloat16Qsr5mllib5utilsE11is_one_of_vIT_aS0_7float16EEvPS1_S3_R23transposeshuffle_params
46
+ _Z14_b8170_wrapperPPv (referenced text)
47
+ _ZN12mllib_graphs35slice_generic_innermost_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA16_Kj
48
+ _ZL36setup_slice_generic_innermost_paramsI8bfloat16EvR30slice_generic_innermost_paramsRA16_Kj
49
+ _ZL32load_slice_generic_innermost_rtpR30slice_generic_innermost_paramsRA16_Kj
50
+ _ZL29setup_slice_generic_innermostI8bfloat16EvR30slice_generic_innermost_params
51
+ _Z23slice_generic_innermostI8bfloat16EvPT_S2_R30slice_generic_innermost_params
52
+
53
+
54
+ Call tree stack and functions sizes:
55
+
56
+ stack stack stack call func func function name
57
+ desc level level desc
58
+ ----- ----- ----- ----- ----- ----- --------------------------------------------------------------
59
+ 64 256 0 0 546 12270 _Z13kernelWrapperPPvjjjj
60
+ 0 192 1 1 36 3650 _Z15_b13786_wrapperPPv
61
+ 64 192 1 2 546 3614 _Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
62
+ 0 0 2 3 550 550 _ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv
63
+ 64 128 2 3 1930 2518 _Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params
64
+ 64 64 3 4 294 294 _Z8init_accILt1EEvPaS0_iii
65
+ 0 0 3 4 294 294 _Z12post_processPai
66
+ 0 128 1 1 36 1378 _Z15_b13811_wrapperPPv
67
+ 64 128 1 2 602 1342 _Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE <tail call>
68
+ 64 64 2 3 114 236 _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv
69
+ 0 0 3 4 122 122 _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv
70
+ 0 64 2 3 20 504 _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
71
+ 64 64 2 4 484 484 _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE <tail call>
72
+ 0 192 1 1 32 1282 _Z15_b13739_wrapperPPv
73
+ 64 192 1 2 488 1250 _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
74
+ 64 128 2 3 60 318 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
75
+ 64 64 3 4 178 202 _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
76
+ 0 0 4 5 24 24 _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
77
+ 0 0 2 4 56 56 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E <tail call>
78
+ 128 128 2 3 114 444 _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
79
+ 0 0 3 4 330 330 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
80
+ 0 64 1 1 32 966 _Z15_b13744_wrapperPPv
81
+ 64 64 1 2 488 934 _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
82
+ 0 0 2 3 68 68 _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
83
+ 0 0 2 3 378 378 _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
84
+ 0 128 1 1 36 1124 _Z15_b13749_wrapperPPv
85
+ 64 128 1 2 602 1088 _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE <tail call>
86
+ 64 64 2 3 154 178 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
87
+ 0 0 3 4 24 24 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
88
+ 0 0 2 3 308 308 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
89
+ 0 64 1 1 32 690 _Z14_b8148_wrapperPPv
90
+ 64 64 1 2 484 658 _ZN12mllib_graphs22buffer_pad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj <tail call>
91
+ 0 0 2 3 174 174 memset
92
+ 0 64 1 1 32 1646 _Z14_b7835_wrapperPPv
93
+ 64 64 1 2 202 1614 _ZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_Kj <tail call>
94
+ 0 0 2 3 262 262 _Z29setup_transposeshuffle_paramsI8bfloat16EvR23transposeshuffle_paramsRA7_Kj
95
+ 0 0 2 3 1150 1150 _Z16transposeshuffleI8bfloat16Qsr5mllib5utilsE11is_one_of_vIT_aS0_7float16EEvPS1_S3_R23transposeshuffle_params
96
+ 0 128 1 1 32 988 _Z14_b8170_wrapperPPv
97
+ 128 128 1 2 178 956 _ZN12mllib_graphs35slice_generic_innermost_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA16_Kj <tail call>
98
+ 0 0 2 3 52 298 _ZL36setup_slice_generic_innermost_paramsI8bfloat16EvR30slice_generic_innermost_paramsRA16_Kj
99
+ 0 0 3 4 162 162 _ZL32load_slice_generic_innermost_rtpR30slice_generic_innermost_paramsRA16_Kj
100
+ 0 0 2 4 84 84 _ZL29setup_slice_generic_innermostI8bfloat16EvR30slice_generic_innermost_params <tail call>
101
+ 0 0 2 3 480 480 _Z23slice_generic_innermostI8bfloat16EvPT_S2_R30slice_generic_innermost_params
102
+
103
+
104
+ Maximum call level : 5
105
+ Maximum stack level: 4
106
+ Maximum stack size : 256
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.cmic2 ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.cmico ADDED
@@ -0,0 +1 @@
 
 
1
+ +Mdec
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.lst ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.map ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ // File generated by bridge version V-2024.06#84922c0d9f#241219, Fri May 30 11:33:41 2025
3
+ // Copyright 2014-2024 Synopsys, Inc. All rights reserved.
4
+ // bridge -o../Release/0_0_reloadable35 ../Release/0_0_reloadable35.o -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/isg -g -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxxabi-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0_reloadable35.bcf -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/softfloat/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork3589147 -pme
5
+
6
+ // Release: ipp V-2024.06-TGT-241219
7
+
8
+ Memory map for memory 'DM_stack':
9
+
10
+ Size = 1048576
11
+ Width = 8 bits
12
+ Offset = 0
13
+ Used = 1088
14
+
15
+ 0x0007bd80..0x0007c1bf ( 1088 items) : Stack
16
+
17
+ Memory map for memory 'DMb':
18
+
19
+ Size = 1048576
20
+ Width = 8 bits
21
+ Offset = 0
22
+ Used = 1893
23
+
24
+ 0x00000000..0x0007bd7f ( 507264 items) : Reserved
25
+ 0x0007bd80..0x0007c1bf ( 1088 items) : Stack
26
+ 0x0007c1c0..0x0007c1ff ( 64 items) : Reserved
27
+ 0x0007c200..0x0007c35f ( 352 items) : ../Release/0_0_reloadable35.o::gem_bfp_param (Data, Global, .bss.DMb.32)
28
+ 0x0007c360..0x0007c363 ( 4 items) : ../Release/0_0_reloadable35.o::_ZL9curr_iter (Data, Local, .bss.DMb.4)
29
+ 0x0007c364..0x0007c367 ( 4 items) : ../Release/0_0_reloadable35.o::_ZL10depth_iter (Data, Local, .bss.DMb.4)
30
+ 0x0007c368..0x0007c36b ( 4 items) : ../Release/0_0_reloadable35.o::_ZL11total_iters (Data, Local, .bss.DMb.4)
31
+ 0x0007c36c..0x0007c36f ( 4 items) : ../Release/0_0_reloadable35.o::_ZL8core_row (Data, Local, .bss.DMb.4)
32
+ 0x0007c370..0x0007c373 ( 4 items) : ../Release/0_0_reloadable35.o::_ZL11ifm1_offset (Data, Local, .bss.DMb.4)
33
+ 0x0007c374..0x0007c377 ( 4 items) : ../Release/0_0_reloadable35.o::_ZL11ifm2_offset (Data, Local, .bss.DMb.4)
34
+ 0x0007c378..0x0007c37b ( 4 items) : ../Release/0_0_reloadable35.o::_ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6kn_rep (Data, Weak, .bss.DMb.4)
35
+ 0x0007c37c..0x0007c37f ( 4 items) : ../Release/0_0_reloadable35.o::_ZL8num_iter (Data, Local, .data.DMb.4)
36
+ 0x0007c380..0x0007c39f ( 32 items) : ../Release/0_0_reloadable35.o::_ZL20g_uniformKernelFuncs (Data, Local, .rodata.DMb.64)
37
+
38
+ Called functions : _Z15_b13786_wrapperPPv
39
+ _Z15_b13811_wrapperPPv
40
+ _Z15_b13739_wrapperPPv
41
+ _Z15_b13744_wrapperPPv
42
+ _Z15_b13749_wrapperPPv
43
+ _Z14_b8148_wrapperPPv
44
+ _Z14_b7835_wrapperPPv
45
+ _Z14_b8170_wrapperPPv
46
+
47
+ 0x0007c3a0..0x0007c3a3 ( 4 items) : me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)::_ZN12me_primitive11control_satE (Data, Global, .bss.DMb.4)
48
+ 0x0007c3a4..0x0007c3a4 ( 1 items) : me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)::_ZN12me_primitive11control_rndE (Data, Global, .bss.DMb.1)
49
+ 0x0007c3c0..0x0007c43f ( 128 items) : ../Release/0_0_reloadable35.o::_ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6params (Data, Weak, .bss.DMb.64)
50
+ 0x0007c440..0x0007c47f ( 64 items) : ../Release/0_0_reloadable35.o::add1d_attribute_broadcasting_params (Data, Global, .bss.DMb.64)
51
+ 0x0007c480..0x0007c4bf ( 64 items) : ../Release/0_0_reloadable35.o::add1d_params (Data, Global, .bss.DMb.64)
52
+ 0x0007c4c0..0x0007c4ff ( 64 items) : ../Release/0_0_reloadable35.o::mul1d_params (Data, Global, .bss.DMb.64)
53
+ 0x0007c500..0x0007c53f ( 64 items) : ../Release/0_0_reloadable35.o::sigmoid1d_params (Data, Global, .bss.DMb.64)
54
+ 0x0007ca00..0x000fffff ( 538112 items) : Reserved
55
+
56
+ Memory map for memory 'PM':
57
+
58
+ Size = 1048576
59
+ Width = 8 bits
60
+ Offset = 0
61
+ Used = 12270
62
+
63
+ 0x00000000..0x000009df ( 2528 items) : Reserved
64
+ 0x000009e0..0x00000c01 ( 546 items) : ../Release/0_0_reloadable35.o::_Z13kernelWrapperPPvjjjj (Function, Global, .text) (stack frame size = 64)
65
+
66
+ Referenced symbols: _ZL20g_uniformKernelFuncs
67
+
68
+ 0x00000c10..0x00000c27 ( 24 items) : ../Release/0_0_reloadable35.o::_ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
69
+
70
+ Referenced symbols: add1d_attribute_broadcasting_params
71
+
72
+ 0x00000c30..0x00000ce1 ( 178 items) : ../Release/0_0_reloadable35.o::_ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 64)
73
+
74
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
75
+
76
+ Referenced symbols: add1d_attribute_broadcasting_params
77
+
78
+ 0x00000cf0..0x00000d27 ( 56 items) : ../Release/0_0_reloadable35.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
79
+
80
+ Referenced symbols: add1d_attribute_broadcasting_params
81
+
82
+ 0x00000d30..0x00000d6b ( 60 items) : ../Release/0_0_reloadable35.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 64)
83
+
84
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
85
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E
86
+
87
+ Referenced symbols: add1d_attribute_broadcasting_params
88
+
89
+ 0x00000d70..0x00000eb9 ( 330 items) : ../Release/0_0_reloadable35.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
90
+
91
+ Referenced symbols: add1d_attribute_broadcasting_params
92
+ _ZN12me_primitive11control_rndE
93
+
94
+ 0x00000ec0..0x00000f31 ( 114 items) : ../Release/0_0_reloadable35.o::_ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 128)
95
+
96
+ Called functions : _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
97
+
98
+ Referenced symbols: add1d_attribute_broadcasting_params
99
+
100
+ 0x00000f40..0x00001127 ( 488 items) : ../Release/0_0_reloadable35.o::_Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
101
+
102
+ Called functions : _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
103
+ _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
104
+
105
+ Referenced symbols: _ZL9curr_iter
106
+ _ZL8core_row
107
+ add1d_attribute_broadcasting_params
108
+ _ZN12me_primitive11control_rndE
109
+ _ZN12me_primitive11control_satE
110
+ _ZL11ifm1_offset
111
+ _ZL8num_iter
112
+
113
+ 0x00001130..0x00001313 ( 484 items) : ../Release/0_0_reloadable35.o::_ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE (Function, Local, .text) (stack frame size = 64)
114
+
115
+ Referenced symbols: _ZN12me_primitive11control_rndE
116
+
117
+ 0x00001320..0x00001363 ( 68 items) : ../Release/0_0_reloadable35.o::_ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 0)
118
+
119
+ Referenced symbols: sigmoid1d_params
120
+
121
+ 0x00001370..0x000014e9 ( 378 items) : ../Release/0_0_reloadable35.o::_ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
122
+
123
+ Referenced symbols: sigmoid1d_params
124
+ _ZN12me_primitive11control_rndE
125
+
126
+ 0x000014f0..0x000016d7 ( 488 items) : ../Release/0_0_reloadable35.o::_Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
127
+
128
+ Called functions : _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
129
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
130
+
131
+ Referenced symbols: _ZL9curr_iter
132
+ _ZL8core_row
133
+ sigmoid1d_params
134
+ _ZN12me_primitive11control_rndE
135
+ _ZN12me_primitive11control_satE
136
+ _ZL11ifm1_offset
137
+ _ZL8num_iter
138
+
139
+ 0x000016e0..0x00001759 ( 122 items) : ../Release/0_0_reloadable35.o::_ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 0)
140
+
141
+ Referenced symbols: add1d_params
142
+
143
+ 0x00001760..0x000017d1 ( 114 items) : ../Release/0_0_reloadable35.o::_ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 64)
144
+
145
+ Called functions : _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv
146
+
147
+ Referenced symbols: add1d_params
148
+
149
+ 0x000017e0..0x000017f3 ( 20 items) : ../Release/0_0_reloadable35.o::_ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
150
+
151
+ Called functions : _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE
152
+
153
+ Referenced symbols: add1d_params
154
+
155
+ 0x00001800..0x00001a59 ( 602 items) : ../Release/0_0_reloadable35.o::_Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE (Function, Global, .text) (stack frame size = 64)
156
+
157
+ Called functions : _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv
158
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
159
+
160
+ Referenced symbols: _ZL9curr_iter
161
+ _ZL8core_row
162
+ add1d_params
163
+ _ZN12me_primitive11control_rndE
164
+ _ZN12me_primitive11control_satE
165
+ _ZL11ifm1_offset
166
+ _ZL11ifm2_offset
167
+ _ZL8num_iter
168
+
169
+ 0x00001a60..0x00001a77 ( 24 items) : ../Release/0_0_reloadable35.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
170
+
171
+ Referenced symbols: mul1d_params
172
+
173
+ 0x00001a80..0x00001b19 ( 154 items) : ../Release/0_0_reloadable35.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 64)
174
+
175
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
176
+
177
+ Referenced symbols: mul1d_params
178
+
179
+ 0x00001b20..0x00001c53 ( 308 items) : ../Release/0_0_reloadable35.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
180
+
181
+ Referenced symbols: mul1d_params
182
+ _ZN12me_primitive11control_rndE
183
+
184
+ 0x00001c60..0x00001eb9 ( 602 items) : ../Release/0_0_reloadable35.o::_Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE (Function, Global, .text) (stack frame size = 64)
185
+
186
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
187
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
188
+
189
+ Referenced symbols: _ZL9curr_iter
190
+ _ZL8core_row
191
+ mul1d_params
192
+ _ZN12me_primitive11control_rndE
193
+ _ZN12me_primitive11control_satE
194
+ _ZL11ifm1_offset
195
+ _ZL11ifm2_offset
196
+ _ZL8num_iter
197
+
198
+ 0x00001ec0..0x000020e5 ( 550 items) : ../Release/0_0_reloadable35.o::_ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv (Function, Local, .text) (stack frame size = 0)
199
+
200
+ Referenced symbols: gem_bfp_param
201
+
202
+ 0x000020f0..0x00002215 ( 294 items) : ../Release/0_0_reloadable35.o::_Z8init_accILt1EEvPaS0_iii (Function, Weak, .text) (stack frame size = 64)
203
+
204
+ Referenced symbols: _ZN12me_primitive11control_rndE
205
+
206
+ 0x00002220..0x00002345 ( 294 items) : ../Release/0_0_reloadable35.o::_Z12post_processPai (Function, Weak, .text) (stack frame size = 0)
207
+
208
+ Referenced symbols: _ZN12me_primitive11control_rndE
209
+
210
+ 0x00002350..0x00002ad9 ( 1930 items) : ../Release/0_0_reloadable35.o::_Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params (Function, Weak, .text) (stack frame size = 64)
211
+
212
+ Called functions : _Z8init_accILt1EEvPaS0_iii
213
+ _Z12post_processPai
214
+
215
+ Referenced symbols: gem_bfp_param
216
+ _ZN12me_primitive11control_satE
217
+ _ZN12me_primitive11control_rndE
218
+
219
+ 0x00002ae0..0x00002d01 ( 546 items) : ../Release/0_0_reloadable35.o::_Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
220
+
221
+ Called functions : _ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv
222
+ _Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params
223
+
224
+ Referenced symbols: _ZL9curr_iter
225
+ _ZN12me_primitive11control_rndE
226
+ _ZN12me_primitive11control_satE
227
+ _ZL11total_iters
228
+ _ZL10depth_iter
229
+ gem_bfp_param
230
+
231
+ 0x00002d10..0x00002d33 ( 36 items) : ../Release/0_0_reloadable35.o::_Z15_b13786_wrapperPPv (Function, Global, .text) (stack frame size = 0)
232
+
233
+ Called functions : _Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
234
+
235
+ 0x00002d40..0x00002d63 ( 36 items) : ../Release/0_0_reloadable35.o::_Z15_b13811_wrapperPPv (Function, Global, .text) (stack frame size = 0)
236
+
237
+ Called functions : _Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
238
+
239
+ 0x00002d70..0x00002d8f ( 32 items) : ../Release/0_0_reloadable35.o::_Z15_b13739_wrapperPPv (Function, Global, .text) (stack frame size = 0)
240
+
241
+ Called functions : _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
242
+
243
+ 0x00002d90..0x00002daf ( 32 items) : ../Release/0_0_reloadable35.o::_Z15_b13744_wrapperPPv (Function, Global, .text) (stack frame size = 0)
244
+
245
+ Called functions : _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
246
+
247
+ 0x00002db0..0x00002dd3 ( 36 items) : ../Release/0_0_reloadable35.o::_Z15_b13749_wrapperPPv (Function, Global, .text) (stack frame size = 0)
248
+
249
+ Called functions : _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
250
+
251
+ 0x00002de0..0x00002fc3 ( 484 items) : ../Release/0_0_reloadable35.o::_ZN12mllib_graphs22buffer_pad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj (Function, Weak, .text) (stack frame size = 64)
252
+
253
+ Called functions : memset
254
+
255
+ 0x00002fd0..0x00002fef ( 32 items) : ../Release/0_0_reloadable35.o::_Z14_b8148_wrapperPPv (Function, Global, .text) (stack frame size = 0)
256
+
257
+ Called functions : _ZN12mllib_graphs22buffer_pad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj
258
+
259
+ 0x00002ff0..0x000030f5 ( 262 items) : ../Release/0_0_reloadable35.o::_Z29setup_transposeshuffle_paramsI8bfloat16EvR23transposeshuffle_paramsRA7_Kj (Function, Weak, .text) (stack frame size = 0)
260
+
261
+ Referenced symbols: _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6params
262
+
263
+ 0x00003100..0x0000357d ( 1150 items) : ../Release/0_0_reloadable35.o::_Z16transposeshuffleI8bfloat16Qsr5mllib5utilsE11is_one_of_vIT_aS0_7float16EEvPS1_S3_R23transposeshuffle_params (Function, Weak, .text) (stack frame size = 0)
264
+
265
+ Referenced symbols: _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6params
266
+
267
+ 0x00003580..0x00003649 ( 202 items) : ../Release/0_0_reloadable35.o::_ZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_Kj (Function, Weak, .text) (stack frame size = 64)
268
+
269
+ Called functions : _Z29setup_transposeshuffle_paramsI8bfloat16EvR23transposeshuffle_paramsRA7_Kj
270
+ _Z16transposeshuffleI8bfloat16Qsr5mllib5utilsE11is_one_of_vIT_aS0_7float16EEvPS1_S3_R23transposeshuffle_params
271
+
272
+ Referenced symbols: _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6kn_rep
273
+ _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6params
274
+
275
+ 0x00003650..0x0000366f ( 32 items) : ../Release/0_0_reloadable35.o::_Z14_b7835_wrapperPPv (Function, Global, .text) (stack frame size = 0)
276
+
277
+ Called functions : _ZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_Kj
278
+
279
+ 0x00003670..0x00003711 ( 162 items) : ../Release/0_0_reloadable35.o::_ZL32load_slice_generic_innermost_rtpR30slice_generic_innermost_paramsRA16_Kj (Function, Local, .text) (stack frame size = 0)
280
+ 0x00003720..0x00003773 ( 84 items) : ../Release/0_0_reloadable35.o::_ZL29setup_slice_generic_innermostI8bfloat16EvR30slice_generic_innermost_params (Function, Local, .text) (stack frame size = 0)
281
+ 0x00003780..0x000037b3 ( 52 items) : ../Release/0_0_reloadable35.o::_ZL36setup_slice_generic_innermost_paramsI8bfloat16EvR30slice_generic_innermost_paramsRA16_Kj (Function, Local, .text) (stack frame size = 0)
282
+
283
+ Called functions : _ZL32load_slice_generic_innermost_rtpR30slice_generic_innermost_paramsRA16_Kj
284
+ _ZL29setup_slice_generic_innermostI8bfloat16EvR30slice_generic_innermost_params
285
+
286
+ 0x000037c0..0x0000399f ( 480 items) : ../Release/0_0_reloadable35.o::_Z23slice_generic_innermostI8bfloat16EvPT_S2_R30slice_generic_innermost_params (Function, Weak, .text) (stack frame size = 0)
287
+ 0x000039a0..0x00003a51 ( 178 items) : ../Release/0_0_reloadable35.o::_ZN12mllib_graphs35slice_generic_innermost_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA16_Kj (Function, Weak, .text) (stack frame size = 128)
288
+
289
+ Called functions : _ZL36setup_slice_generic_innermost_paramsI8bfloat16EvR30slice_generic_innermost_paramsRA16_Kj
290
+ _Z23slice_generic_innermostI8bfloat16EvPT_S2_R30slice_generic_innermost_params
291
+
292
+ 0x00003a60..0x00003a7f ( 32 items) : ../Release/0_0_reloadable35.o::_Z14_b8170_wrapperPPv (Function, Global, .text) (stack frame size = 0)
293
+
294
+ Called functions : _ZN12mllib_graphs35slice_generic_innermost_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA16_Kj
295
+
296
+ 0x00003a80..0x00003b2d ( 174 items) : string.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release/libc.a)::memset (Function, Global, .text) (stack frame size = 0)
297
+
298
+ External symbols:
299
+
300
+ __dso_handle = 0x0
301
+ _ctors_end = 0x0
302
+ _ctors_start = 0x0
303
+ _dtors_end = 0x0
304
+ _dtors_start = 0x0
305
+ _pc_end = 0x3b2e
306
+ _pc_start = 0x9e0
307
+ _sp_end_DM_stack = 0x7c1c0
308
+ _sp_start_DM_stack = 0x7bd80
309
+
310
+ Section summary for memory 'DM_stack':
311
+
312
+ .stack File
313
+ ---------- ----------
314
+ 1088
315
+ ---------- ----------
316
+ 1088 Total
317
+
318
+ Section summary for memory 'DMb':
319
+
320
+ .bss .data .rodata File
321
+ ---------- ---------- ---------- ----------
322
+ 764 4 32 ../Release/0_0_reloadable35.o
323
+ 5 0 0 me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
324
+ ---------- ---------- ---------- ----------
325
+ 769 4 32 Total
326
+
327
+ Section summary for memory 'PM':
328
+
329
+ .text File
330
+ ---------- ----------
331
+ 12096 ../Release/0_0_reloadable35.o
332
+ 174 string.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release/libc.a)
333
+ ---------- ----------
334
+ 12270 Total
335
+
336
+ File summary:
337
+
338
+ ../Release/0_0_reloadable35.o
339
+ DMb 800
340
+ PM 12096
341
+
342
+ me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
343
+ DMb 5
344
+
345
+ string.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release/libc.a)
346
+ PM 174
347
+
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.sdr ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ // File generated by bridge version V-2024.06#84922c0d9f#241219, Fri May 30 11:33:41 2025
3
+ // Copyright 2014-2024 Synopsys, Inc. All rights reserved.
4
+ // bridge -o../Release/0_0_reloadable35 ../Release/0_0_reloadable35.o -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/isg -g -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxxabi-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0_reloadable35.bcf -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/softfloat/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork3589147 -pme
5
+
6
+ // Release: ipp V-2024.06-TGT-241219
7
+
8
+ // Symbols in memory 'DM_bankA':
9
+ // Symbols in memory 'DM_bankAB':
10
+ // Symbols in memory 'DM_bankAC':
11
+ // Symbols in memory 'DM_bankAD':
12
+ // Symbols in memory 'DM_bankB':
13
+ // Symbols in memory 'DM_bankBC':
14
+ // Symbols in memory 'DM_bankBD':
15
+ // Symbols in memory 'DM_bankC':
16
+ // Symbols in memory 'DM_bankCD':
17
+ // Symbols in memory 'DM_bankD':
18
+ // Symbols in memory 'DM_stack':
19
+ // Symbols in memory 'DM_test':
20
+ // Symbols in memory 'DMb':
21
+ _symbol gem_bfp_param 0x0007c200
22
+ _symbol _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6kn_rep 0x0007c378
23
+ _symbol _ZN12me_primitive11control_satE 0x0007c3a0
24
+ _symbol _ZN12me_primitive11control_rndE 0x0007c3a4
25
+ _symbol _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6params 0x0007c3c0
26
+ _symbol add1d_attribute_broadcasting_params 0x0007c440
27
+ _symbol add1d_params 0x0007c480
28
+ _symbol mul1d_params 0x0007c4c0
29
+ _symbol sigmoid1d_params 0x0007c500
30
+ // Symbols in memory 'DMh':
31
+ // Symbols in memory 'DMh_bankA':
32
+ // Symbols in memory 'DMh_bankAB':
33
+ // Symbols in memory 'DMh_bankAC':
34
+ // Symbols in memory 'DMh_bankAD':
35
+ // Symbols in memory 'DMh_bankB':
36
+ // Symbols in memory 'DMh_bankBC':
37
+ // Symbols in memory 'DMh_bankBD':
38
+ // Symbols in memory 'DMh_bankC':
39
+ // Symbols in memory 'DMh_bankCD':
40
+ // Symbols in memory 'DMh_bankD':
41
+ // Symbols in memory 'DMh_stack':
42
+ // Symbols in memory 'DMs':
43
+ // Symbols in memory 'DMs_bankA':
44
+ // Symbols in memory 'DMs_bankAB':
45
+ // Symbols in memory 'DMs_bankAC':
46
+ // Symbols in memory 'DMs_bankAD':
47
+ // Symbols in memory 'DMs_bankB':
48
+ // Symbols in memory 'DMs_bankBC':
49
+ // Symbols in memory 'DMs_bankBD':
50
+ // Symbols in memory 'DMs_bankC':
51
+ // Symbols in memory 'DMs_bankCD':
52
+ // Symbols in memory 'DMs_bankD':
53
+ // Symbols in memory 'DMs_stack':
54
+ // Symbols in memory 'DMv':
55
+ // Symbols in memory 'DMv_bankA':
56
+ // Symbols in memory 'DMv_bankAB':
57
+ // Symbols in memory 'DMv_bankAC':
58
+ // Symbols in memory 'DMv_bankAD':
59
+ // Symbols in memory 'DMv_bankB':
60
+ // Symbols in memory 'DMv_bankBC':
61
+ // Symbols in memory 'DMv_bankBD':
62
+ // Symbols in memory 'DMv_bankC':
63
+ // Symbols in memory 'DMv_bankCD':
64
+ // Symbols in memory 'DMv_bankD':
65
+ // Symbols in memory 'DMv_stack':
66
+ // Symbols in memory 'DMw':
67
+ // Symbols in memory 'DMw_bankA':
68
+ // Symbols in memory 'DMw_bankAB':
69
+ // Symbols in memory 'DMw_bankAC':
70
+ // Symbols in memory 'DMw_bankAD':
71
+ // Symbols in memory 'DMw_bankB':
72
+ // Symbols in memory 'DMw_bankBC':
73
+ // Symbols in memory 'DMw_bankBD':
74
+ // Symbols in memory 'DMw_bankC':
75
+ // Symbols in memory 'DMw_bankCD':
76
+ // Symbols in memory 'DMw_bankD':
77
+ // Symbols in memory 'DMw_stack':
78
+ // Symbols in memory 'DMx':
79
+ // Symbols in memory 'DMx_bankA':
80
+ // Symbols in memory 'DMx_bankAB':
81
+ // Symbols in memory 'DMx_bankAC':
82
+ // Symbols in memory 'DMx_bankAD':
83
+ // Symbols in memory 'DMx_bankB':
84
+ // Symbols in memory 'DMx_bankBC':
85
+ // Symbols in memory 'DMx_bankBD':
86
+ // Symbols in memory 'DMx_bankC':
87
+ // Symbols in memory 'DMx_bankCD':
88
+ // Symbols in memory 'DMx_bankD':
89
+ // Symbols in memory 'DMx_stack':
90
+ // Symbols in memory 'PM':
91
+ _symbol _Z13kernelWrapperPPvjjjj 0x000009e0
92
+ _symbol _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E 0x00000c10
93
+ _symbol _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv 0x00000c30
94
+ _symbol _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E 0x00000cf0
95
+ _symbol _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv 0x00000d30
96
+ _symbol _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E 0x00000d70
97
+ _symbol _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E 0x00000ec0
98
+ _symbol _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE 0x00000f40
99
+ _symbol _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv 0x00001320
100
+ _symbol _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E 0x00001370
101
+ _symbol _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE 0x000014f0
102
+ _symbol _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv 0x000016e0
103
+ _symbol _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv 0x00001760
104
+ _symbol _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E 0x000017e0
105
+ _symbol _Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE 0x00001800
106
+ _symbol _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E 0x00001a60
107
+ _symbol _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv 0x00001a80
108
+ _symbol _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E 0x00001b20
109
+ _symbol _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE 0x00001c60
110
+ _symbol _Z8init_accILt1EEvPaS0_iii 0x000020f0
111
+ _symbol _Z12post_processPai 0x00002220
112
+ _symbol _Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params 0x00002350
113
+ _symbol _Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE 0x00002ae0
114
+ _symbol _Z15_b13786_wrapperPPv 0x00002d10
115
+ _symbol _Z15_b13811_wrapperPPv 0x00002d40
116
+ _symbol _Z15_b13739_wrapperPPv 0x00002d70
117
+ _symbol _Z15_b13744_wrapperPPv 0x00002d90
118
+ _symbol _Z15_b13749_wrapperPPv 0x00002db0
119
+ _symbol _ZN12mllib_graphs22buffer_pad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj 0x00002de0
120
+ _symbol _Z14_b8148_wrapperPPv 0x00002fd0
121
+ _symbol _Z29setup_transposeshuffle_paramsI8bfloat16EvR23transposeshuffle_paramsRA7_Kj 0x00002ff0
122
+ _symbol _Z16transposeshuffleI8bfloat16Qsr5mllib5utilsE11is_one_of_vIT_aS0_7float16EEvPS1_S3_R23transposeshuffle_params 0x00003100
123
+ _symbol _ZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_Kj 0x00003580
124
+ _symbol _Z14_b7835_wrapperPPv 0x00003650
125
+ _symbol _Z23slice_generic_innermostI8bfloat16EvPT_S2_R30slice_generic_innermost_params 0x000037c0
126
+ _symbol _ZN12mllib_graphs35slice_generic_innermost_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA16_Kj 0x000039a0
127
+ _symbol _Z14_b8170_wrapperPPv 0x00003a60
128
+ _symbol memset 0x00003a80
129
+ // Symbols in memory 'PMw':
130
+ // Symbols in memory 'TM4':
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.srv ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/Release/1_3_reloadable51.txt ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/scripts/1_3_reloadable51.bcf ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _reserved DMb 0x0 0x40000
2
+
3
+ _reserved PM 0x0 0x9e0 //reserved for main elf
4
+
5
+ _entry_point _Z13kernelWrapperPPvjjjj
6
+ _symbol _Z13kernelWrapperPPvjjjj 0x9e0
7
+
8
+ _reserved DMb 0x7b540 0x800 //reserved for lcp ping-pong buffers
9
+ _reserved DMb 0x7bd40 0x40 //reserved for sync buffer
10
+ _stack DM_stack 0x7bd80 0x440 //stack for core
11
+ _reserved DMb 0x7c1c0 0x40 //reserved for main elf heap
12
+ //space for synopsys compiler at 0x7c200 0x800//heap
13
+ _reserved DMb 0x40000 0x3b540
14
+
15
+ _reserved DMb 0x7ca00 0x3600
16
+ _reserved DMb 0x80000 0x80000 // And everything else the core can't see
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/scripts/1_3_reloadable51.prx ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <project name="Project" processor="me">
2
+ <issinit/>
3
+ <option id="cpp.define" value="__AIENGINE__ __AIE_ARCH__=21" inherit = "1"/>
4
+ <option id="llvm.xargs" value="-fno-jump-tables -fno-discard-value-names" inherit = "1"/>
5
+ <option id="llvm.lang" value="Follow file extension"/>
6
+ <option id="bridge.cfg" value="1_3_reloadable51.bcf"/>
7
+ <option id="bridge.alibs" value=" ../Release/1_3_reloadable51.o" inherit="1" cfg="Release_LLVM"/>
8
+ <option id="cpp.include" value="&lt;XILINX_VITIS_AIETOOLS&gt;/include /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/&lt;AIE_SRC_DIR&gt;/ /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/&lt;AIE_SRC_DIR&gt; " inherit="1"/>
9
+ <option id="project.dir" value="&lt;CONFIG&gt;/1_3_reloadable51"/>
10
+ <option id="project.name" value="1_3_reloadable51"/>
11
+ <option id="project.type" value="exe"/>
12
+ <option id="simrun.issca" value="&lt;XILINX_VITIS_AIETOOLS&gt;/bin/unwrapped/lnx64.o/aie2p/ca_udm_dbg" inherit="0"/>
13
+ </project>
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable51/src/1_3_reloadable51.cc ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ // Automatically generated processor driver using AIEngine tool-chain
2
+
3
+ #include <stdio.h>
4
+ #include <memory>
5
+ #include <adf.h>
6
+
7
+
8
+ // Declare Kernel functions and initializers
9
+ void superkernel_GemmBfp16(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[7],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
10
+ void superkernel_add1d(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict,adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
11
+ void superkernel_add1d_attribute_broadcasting(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
12
+ void superkernel_sigmoid1d(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
13
+ void superkernel_mul1d(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict,adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
14
+ #include "buffer_pad_adf_wrapper.cpp"
15
+ #include "transpose4d_adf_wrapper.cpp"
16
+ #include "slice_generic_innermost_adf_wrapper.cpp"
17
+
18
+ // Declare Kernel objects and external arrays
19
+
20
+
21
+ void _b13786_wrapper(void* args[])
22
+ {
23
+ superkernel_GemmBfp16(
24
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
25
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
26
+ *reinterpret_cast<uint32 const(*)[7]>(args[3]),
27
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[2]));
28
+ }
29
+
30
+ void _b13811_wrapper(void* args[])
31
+ {
32
+ superkernel_add1d(
33
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
34
+ *reinterpret_cast<uint32 const(*)[16]>(args[3]),
35
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]),
36
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[2]));
37
+ }
38
+
39
+ void _b13739_wrapper(void* args[])
40
+ {
41
+ superkernel_add1d_attribute_broadcasting(
42
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
43
+ *reinterpret_cast<uint32 const(*)[16]>(args[2]),
44
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]));
45
+ }
46
+
47
+ void _b13744_wrapper(void* args[])
48
+ {
49
+ superkernel_sigmoid1d(
50
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
51
+ *reinterpret_cast<uint32 const(*)[16]>(args[2]),
52
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]));
53
+ }
54
+
55
+ void _b13749_wrapper(void* args[])
56
+ {
57
+ superkernel_mul1d(
58
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
59
+ *reinterpret_cast<uint32 const(*)[16]>(args[3]),
60
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]),
61
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[2]));
62
+ }
63
+
64
+ void _b8148_wrapper(void* args[])
65
+ {
66
+ mllib_graphs::buffer_pad_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
67
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
68
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
69
+ *reinterpret_cast<uint32 const(*)[3]>(args[2]));
70
+ }
71
+
72
+ void _b7835_wrapper(void* args[])
73
+ {
74
+ mllib_graphs::transpose4d_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
75
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
76
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
77
+ *reinterpret_cast<uint32 const(*)[7]>(args[2]));
78
+ }
79
+
80
+ void _b8170_wrapper(void* args[])
81
+ {
82
+ mllib_graphs::slice_generic_innermost_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
83
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
84
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
85
+ *reinterpret_cast<uint32 const(*)[16]>(args[2]));
86
+ }
87
+
88
+ using UniformKernelFunc = void (*)(void **);
89
+
90
+ static UniformKernelFunc g_uniformKernelFuncs[8] = {
91
+ _b13786_wrapper,
92
+ _b13811_wrapper,
93
+ _b13739_wrapper,
94
+ _b13744_wrapper,
95
+ _b13749_wrapper,
96
+ _b8148_wrapper,
97
+ _b7835_wrapper,
98
+ _b8170_wrapper
99
+ };
100
+
101
+ __attribute__((always_inline)) void kernelWrapper(void* args[], uint32 kernelId, uint32 numSyncIn, uint32 numAsyncIn, uint32 numSyncOut)
102
+ {
103
+ uint32 idx = 0;
104
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::in>(numSyncIn > 0);
105
+ idx += (numSyncIn > 0) ? 1 : 0;
106
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::in>(numSyncIn > 1);
107
+ idx += (numSyncIn > 1) ? 1 : 0;
108
+ idx += numAsyncIn;
109
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::out>(numSyncOut > 0);
110
+ idx += (numSyncOut > 0) ? 1 : 0;
111
+
112
+ (*(g_uniformKernelFuncs[kernelId]))(args);
113
+
114
+ idx = 0;
115
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::in>(numSyncIn > 0);
116
+ idx += (numSyncIn > 0) ? 1 : 0;
117
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::in>(numSyncIn > 1);
118
+ idx += (numSyncIn > 1) ? 1 : 0;
119
+ idx += numAsyncIn;
120
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::out>(numSyncOut > 0);
121
+ idx += (numSyncOut > 0) ? 1 : 0;
122
+ }
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.calltree ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ // File generated by bridge version V-2024.06#84922c0d9f#241219, Fri May 30 11:33:37 2025
3
+ // Copyright 2014-2024 Synopsys, Inc. All rights reserved.
4
+ // bridge -o../Release/0_0_reloadable52 ../Release/0_0_reloadable52.o -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/isg -g -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxxabi-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0_reloadable52.bcf -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/softfloat/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork3589152 -pme
5
+
6
+
7
+ // Release: ipp V-2024.06-TGT-241219
8
+
9
+ _Z13kernelWrapperPPvjjjj
10
+ _Z15_b14160_wrapperPPv (referenced text)
11
+ _Z22superkernel_conv2d_dwcRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
12
+ _ZL27setup_conv2d_dw_params_bf16PKjR21conv2d_dw_bf16_paramsh
13
+ _ZN12me_primitive10udiv_dstepEjjRjS0_
14
+ _Z9conv2d_dwILh1E8bfloat16S0_S0_N3adf16io_buffer_configINS1_7extentsIJEEENS1_7locking4syncENS1_10addressing6linearENS1_6marginILj0EEEEESB_NS2_IS4_NS5_5asyncES8_SA_EEQsr3stdE9is_same_vIT0_S0_EEvRNS1_9io_bufferISE_NS1_9direction2inET3_EERNSF_IT1_SH_T4_EERNSF_IT2_NSG_3outET5_EER21conv2d_dw_bf16_params
15
+ _Z14conv2d_dw_coreI8bfloat16EvPT_S2_S2_S2_R21conv2d_dw_bf16_params
16
+ _Z17conv2d_dw_shuffleI8bfloat16EvPT_S2_S2_RK21conv2d_dw_bf16_params
17
+ _Z14_b7835_wrapperPPv (referenced text)
18
+ _ZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_Kj
19
+ _Z29setup_transposeshuffle_paramsI8bfloat16EvR23transposeshuffle_paramsRA7_Kj
20
+ _Z16transposeshuffleI8bfloat16Qsr5mllib5utilsE11is_one_of_vIT_aS0_7float16EEvPS1_S3_R23transposeshuffle_params
21
+ _Z14_b7876_wrapperPPv (referenced text)
22
+ _ZN12mllib_graphs24buffer_unpad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj
23
+ _Z14_b8148_wrapperPPv (referenced text)
24
+ _ZN12mllib_graphs22buffer_pad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj
25
+ memset
26
+ _Z15_b13739_wrapperPPv (referenced text)
27
+ _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
28
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
29
+ _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
30
+ _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
31
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E
32
+ _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
33
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
34
+ _Z15_b13744_wrapperPPv (referenced text)
35
+ _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
36
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
37
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
38
+ _Z15_b13749_wrapperPPv (referenced text)
39
+ _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
40
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
41
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
42
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
43
+ _Z14_b8170_wrapperPPv (referenced text)
44
+ _ZN12mllib_graphs35slice_generic_innermost_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA16_Kj
45
+ _ZL36setup_slice_generic_innermost_paramsI8bfloat16EvR30slice_generic_innermost_paramsRA16_Kj
46
+ _ZL32load_slice_generic_innermost_rtpR30slice_generic_innermost_paramsRA16_Kj
47
+ _ZL29setup_slice_generic_innermostI8bfloat16EvR30slice_generic_innermost_params
48
+ _Z23slice_generic_innermostI8bfloat16EvPT_S2_R30slice_generic_innermost_params
49
+
50
+
51
+ Call tree stack and functions sizes:
52
+
53
+ stack stack stack call func func function name
54
+ desc level level desc
55
+ ----- ----- ----- ----- ----- ----- --------------------------------------------------------------
56
+ 64 256 0 0 546 10280 _Z13kernelWrapperPPvjjjj
57
+ 0 192 1 1 36 2736 _Z15_b14160_wrapperPPv
58
+ 128 192 1 2 478 2700 _Z22superkernel_conv2d_dwcRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
59
+ 64 64 2 3 792 934 _ZL27setup_conv2d_dw_params_bf16PKjR21conv2d_dw_bf16_paramsh
60
+ 0 0 3 4 142 142 _ZN12me_primitive10udiv_dstepEjjRjS0_
61
+ 64 64 2 3 360 1288 _Z9conv2d_dwILh1E8bfloat16S0_S0_N3adf16io_buffer_configINS1_7extentsIJEEENS1_7locking4syncENS1_10addressing6linearENS1_6marginILj0EEEEESB_NS2_IS4_NS5_5asyncES8_SA_EEQsr3stdE9is_same_vIT0_S0_EEvRNS1_9io_bufferISE_NS1_9direction2inET3_EERNSF_IT1_SH_T4_EERNSF_IT2_NSG_3outET5_EER21conv2d_dw_bf16_params
62
+ 0 0 3 4 674 674 _Z14conv2d_dw_coreI8bfloat16EvPT_S2_S2_S2_R21conv2d_dw_bf16_params
63
+ 0 0 2 4 254 254 _Z17conv2d_dw_shuffleI8bfloat16EvPT_S2_S2_RK21conv2d_dw_bf16_params <tail call>
64
+ 0 64 1 1 32 1646 _Z14_b7835_wrapperPPv
65
+ 64 64 1 2 202 1614 _ZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_Kj <tail call>
66
+ 0 0 2 3 262 262 _Z29setup_transposeshuffle_paramsI8bfloat16EvR23transposeshuffle_paramsRA7_Kj
67
+ 0 0 2 3 1150 1150 _Z16transposeshuffleI8bfloat16Qsr5mllib5utilsE11is_one_of_vIT_aS0_7float16EEvPS1_S3_R23transposeshuffle_params
68
+ 0 0 1 1 32 302 _Z14_b7876_wrapperPPv
69
+ 0 0 1 2 270 270 _ZN12mllib_graphs24buffer_unpad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj <tail call>
70
+ 0 64 1 1 32 690 _Z14_b8148_wrapperPPv
71
+ 64 64 1 2 484 658 _ZN12mllib_graphs22buffer_pad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj <tail call>
72
+ 0 0 2 3 174 174 memset
73
+ 0 192 1 1 32 1282 _Z15_b13739_wrapperPPv
74
+ 64 192 1 2 488 1250 _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
75
+ 64 128 2 3 60 318 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
76
+ 64 64 3 4 178 202 _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
77
+ 0 0 4 5 24 24 _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
78
+ 0 0 2 4 56 56 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E <tail call>
79
+ 128 128 2 3 114 444 _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
80
+ 0 0 3 4 330 330 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
81
+ 0 64 1 1 32 966 _Z15_b13744_wrapperPPv
82
+ 64 64 1 2 488 934 _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
83
+ 0 0 2 3 68 68 _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
84
+ 0 0 2 3 378 378 _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
85
+ 0 128 1 1 36 1124 _Z15_b13749_wrapperPPv
86
+ 64 128 1 2 602 1088 _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE <tail call>
87
+ 64 64 2 3 154 178 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
88
+ 0 0 3 4 24 24 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
89
+ 0 0 2 3 308 308 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
90
+ 0 128 1 1 32 988 _Z14_b8170_wrapperPPv
91
+ 128 128 1 2 178 956 _ZN12mllib_graphs35slice_generic_innermost_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA16_Kj <tail call>
92
+ 0 0 2 3 52 298 _ZL36setup_slice_generic_innermost_paramsI8bfloat16EvR30slice_generic_innermost_paramsRA16_Kj
93
+ 0 0 3 4 162 162 _ZL32load_slice_generic_innermost_rtpR30slice_generic_innermost_paramsRA16_Kj
94
+ 0 0 2 4 84 84 _ZL29setup_slice_generic_innermostI8bfloat16EvR30slice_generic_innermost_params <tail call>
95
+ 0 0 2 3 480 480 _Z23slice_generic_innermostI8bfloat16EvPT_S2_R30slice_generic_innermost_params
96
+
97
+
98
+ Maximum call level : 5
99
+ Maximum stack level: 4
100
+ Maximum stack size : 256
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.cmic2 ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.cmico ADDED
@@ -0,0 +1 @@
 
 
1
+ +Mdec
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.lst ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.map ADDED
@@ -0,0 +1,320 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ // File generated by bridge version V-2024.06#84922c0d9f#241219, Fri May 30 11:33:37 2025
3
+ // Copyright 2014-2024 Synopsys, Inc. All rights reserved.
4
+ // bridge -o../Release/0_0_reloadable52 ../Release/0_0_reloadable52.o -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/isg -g -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxxabi-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0_reloadable52.bcf -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/softfloat/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork3589152 -pme
5
+
6
+ // Release: ipp V-2024.06-TGT-241219
7
+
8
+ Memory map for memory 'DM_stack':
9
+
10
+ Size = 1048576
11
+ Width = 8 bits
12
+ Offset = 0
13
+ Used = 1088
14
+
15
+ 0x0007bd80..0x0007c1bf ( 1088 items) : Stack
16
+
17
+ Memory map for memory 'DMb':
18
+
19
+ Size = 1048576
20
+ Width = 8 bits
21
+ Offset = 0
22
+ Used = 1729
23
+
24
+ 0x00000000..0x0007bd7f ( 507264 items) : Reserved
25
+ 0x0007bd80..0x0007c1bf ( 1088 items) : Stack
26
+ 0x0007c1c0..0x0007c1ff ( 64 items) : Reserved
27
+ 0x0007c200..0x0007c203 ( 4 items) : ../Release/0_0_reloadable52.o::_ZL9curr_iter (Data, Local, .bss.DMb.4)
28
+ 0x0007c204..0x0007c207 ( 4 items) : ../Release/0_0_reloadable52.o::_ZL8core_row (Data, Local, .bss.DMb.4)
29
+ 0x0007c208..0x0007c20b ( 4 items) : ../Release/0_0_reloadable52.o::_ZL11ifm1_offset (Data, Local, .bss.DMb.4)
30
+ 0x0007c20c..0x0007c20f ( 4 items) : ../Release/0_0_reloadable52.o::_ZL11ifm2_offset (Data, Local, .bss.DMb.4)
31
+ 0x0007c210..0x0007c213 ( 4 items) : ../Release/0_0_reloadable52.o::_ZL10ifmsv_size (Data, Local, .bss.DMb.4)
32
+ 0x0007c214..0x0007c217 ( 4 items) : ../Release/0_0_reloadable52.o::_ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6kn_rep (Data, Weak, .bss.DMb.4)
33
+ 0x0007c218..0x0007c21b ( 4 items) : ../Release/0_0_reloadable52.o::_ZL8num_iter (Data, Local, .data.DMb.4)
34
+ 0x0007c21c..0x0007c21f ( 4 items) : me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)::_ZN12me_primitive11control_satE (Data, Global, .bss.DMb.4)
35
+ 0x0007c220..0x0007c220 ( 1 items) : me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)::_ZN12me_primitive11control_rndE (Data, Global, .bss.DMb.1)
36
+ 0x0007c240..0x0007c25f ( 32 items) : ../Release/0_0_reloadable52.o::_ZL20g_uniformKernelFuncs (Data, Local, .rodata.DMb.64)
37
+
38
+ Called functions : _Z15_b14160_wrapperPPv
39
+ _Z14_b7835_wrapperPPv
40
+ _Z14_b7876_wrapperPPv
41
+ _Z14_b8148_wrapperPPv
42
+ _Z15_b13739_wrapperPPv
43
+ _Z15_b13744_wrapperPPv
44
+ _Z15_b13749_wrapperPPv
45
+ _Z14_b8170_wrapperPPv
46
+
47
+ 0x0007c280..0x0007c2ff ( 128 items) : ../Release/0_0_reloadable52.o::_ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6params (Data, Weak, .bss.DMb.64)
48
+ 0x0007c300..0x0007c33f ( 64 items) : ../Release/0_0_reloadable52.o::add1d_attribute_broadcasting_params (Data, Global, .bss.DMb.64)
49
+ 0x0007c340..0x0007c37f ( 64 items) : ../Release/0_0_reloadable52.o::mul1d_params (Data, Global, .bss.DMb.64)
50
+ 0x0007c380..0x0007c3bf ( 64 items) : ../Release/0_0_reloadable52.o::sigmoid1d_params (Data, Global, .bss.DMb.64)
51
+ 0x0007c3c0..0x0007c4bf ( 256 items) : ../Release/0_0_reloadable52.o::conv2d_dw_params (Data, Global, .bss.DMb.64)
52
+ 0x0007ca00..0x000fffff ( 538112 items) : Reserved
53
+
54
+ Memory map for memory 'PM':
55
+
56
+ Size = 1048576
57
+ Width = 8 bits
58
+ Offset = 0
59
+ Used = 10280
60
+
61
+ 0x00000000..0x000009df ( 2528 items) : Reserved
62
+ 0x000009e0..0x00000c01 ( 546 items) : ../Release/0_0_reloadable52.o::_Z13kernelWrapperPPvjjjj (Function, Global, .text) (stack frame size = 64)
63
+
64
+ Referenced symbols: _ZL20g_uniformKernelFuncs
65
+
66
+ 0x00000c10..0x00000c27 ( 24 items) : ../Release/0_0_reloadable52.o::_ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
67
+
68
+ Referenced symbols: add1d_attribute_broadcasting_params
69
+
70
+ 0x00000c30..0x00000ce1 ( 178 items) : ../Release/0_0_reloadable52.o::_ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 64)
71
+
72
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
73
+
74
+ Referenced symbols: add1d_attribute_broadcasting_params
75
+
76
+ 0x00000cf0..0x00000d27 ( 56 items) : ../Release/0_0_reloadable52.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
77
+
78
+ Referenced symbols: add1d_attribute_broadcasting_params
79
+
80
+ 0x00000d30..0x00000d6b ( 60 items) : ../Release/0_0_reloadable52.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 64)
81
+
82
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
83
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E
84
+
85
+ Referenced symbols: add1d_attribute_broadcasting_params
86
+
87
+ 0x00000d70..0x00000eb9 ( 330 items) : ../Release/0_0_reloadable52.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
88
+
89
+ Referenced symbols: add1d_attribute_broadcasting_params
90
+ _ZN12me_primitive11control_rndE
91
+
92
+ 0x00000ec0..0x00000f31 ( 114 items) : ../Release/0_0_reloadable52.o::_ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 128)
93
+
94
+ Called functions : _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
95
+
96
+ Referenced symbols: add1d_attribute_broadcasting_params
97
+
98
+ 0x00000f40..0x00001127 ( 488 items) : ../Release/0_0_reloadable52.o::_Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
99
+
100
+ Called functions : _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
101
+ _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
102
+
103
+ Referenced symbols: _ZL9curr_iter
104
+ _ZL8core_row
105
+ add1d_attribute_broadcasting_params
106
+ _ZN12me_primitive11control_rndE
107
+ _ZN12me_primitive11control_satE
108
+ _ZL11ifm1_offset
109
+ _ZL8num_iter
110
+
111
+ 0x00001130..0x00001173 ( 68 items) : ../Release/0_0_reloadable52.o::_ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 0)
112
+
113
+ Referenced symbols: sigmoid1d_params
114
+
115
+ 0x00001180..0x000012f9 ( 378 items) : ../Release/0_0_reloadable52.o::_ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
116
+
117
+ Referenced symbols: sigmoid1d_params
118
+ _ZN12me_primitive11control_rndE
119
+
120
+ 0x00001300..0x000014e7 ( 488 items) : ../Release/0_0_reloadable52.o::_Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
121
+
122
+ Called functions : _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
123
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
124
+
125
+ Referenced symbols: _ZL9curr_iter
126
+ _ZL8core_row
127
+ sigmoid1d_params
128
+ _ZN12me_primitive11control_rndE
129
+ _ZN12me_primitive11control_satE
130
+ _ZL11ifm1_offset
131
+ _ZL8num_iter
132
+
133
+ 0x000014f0..0x00001507 ( 24 items) : ../Release/0_0_reloadable52.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
134
+
135
+ Referenced symbols: mul1d_params
136
+
137
+ 0x00001510..0x000015a9 ( 154 items) : ../Release/0_0_reloadable52.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 64)
138
+
139
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
140
+
141
+ Referenced symbols: mul1d_params
142
+
143
+ 0x000015b0..0x000016e3 ( 308 items) : ../Release/0_0_reloadable52.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
144
+
145
+ Referenced symbols: mul1d_params
146
+ _ZN12me_primitive11control_rndE
147
+
148
+ 0x000016f0..0x00001949 ( 602 items) : ../Release/0_0_reloadable52.o::_Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE (Function, Global, .text) (stack frame size = 64)
149
+
150
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
151
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
152
+
153
+ Referenced symbols: _ZL9curr_iter
154
+ _ZL8core_row
155
+ mul1d_params
156
+ _ZN12me_primitive11control_rndE
157
+ _ZN12me_primitive11control_satE
158
+ _ZL11ifm1_offset
159
+ _ZL11ifm2_offset
160
+ _ZL8num_iter
161
+
162
+ 0x00001950..0x00001c67 ( 792 items) : ../Release/0_0_reloadable52.o::_ZL27setup_conv2d_dw_params_bf16PKjR21conv2d_dw_bf16_paramsh (Function, Local, .text) (stack frame size = 64)
163
+
164
+ Called functions : _ZN12me_primitive10udiv_dstepEjjRjS0_
165
+
166
+ Referenced symbols: conv2d_dw_params
167
+ _ZN12me_primitive11control_rndE
168
+
169
+ 0x00001c70..0x00001f11 ( 674 items) : ../Release/0_0_reloadable52.o::_Z14conv2d_dw_coreI8bfloat16EvPT_S2_S2_S2_R21conv2d_dw_bf16_params (Function, Weak, .text) (stack frame size = 0)
170
+
171
+ Referenced symbols: conv2d_dw_params
172
+ _ZN12me_primitive11control_rndE
173
+
174
+ 0x00001f20..0x0000201d ( 254 items) : ../Release/0_0_reloadable52.o::_Z17conv2d_dw_shuffleI8bfloat16EvPT_S2_S2_RK21conv2d_dw_bf16_params (Function, Weak, .text) (stack frame size = 0)
175
+
176
+ Referenced symbols: conv2d_dw_params
177
+
178
+ 0x00002020..0x00002187 ( 360 items) : ../Release/0_0_reloadable52.o::_Z9conv2d_dwILh1E8bfloat16S0_S0_N3adf16io_buffer_configINS1_7extentsIJEEENS1_7locking4syncENS1_10addressing6linearENS1_6marginILj0EEEEESB_NS2_IS4_NS5_5asyncES8_SA_EEQsr3stdE9is_same_vIT0_S0_EEvRNS1_9io_bufferISE_NS1_9direction2inET3_EERNSF_IT1_SH_T4_EERNSF_IT2_NSG_3outET5_EER21conv2d_dw_bf16_params (Function, Weak, .text) (stack frame size = 64)
179
+
180
+ Called functions : _Z14conv2d_dw_coreI8bfloat16EvPT_S2_S2_S2_R21conv2d_dw_bf16_params
181
+ _Z17conv2d_dw_shuffleI8bfloat16EvPT_S2_S2_RK21conv2d_dw_bf16_params
182
+
183
+ Referenced symbols: conv2d_dw_params
184
+
185
+ 0x00002190..0x0000236d ( 478 items) : ../Release/0_0_reloadable52.o::_Z22superkernel_conv2d_dwcRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 128)
186
+
187
+ Called functions : _ZL27setup_conv2d_dw_params_bf16PKjR21conv2d_dw_bf16_paramsh
188
+ _Z9conv2d_dwILh1E8bfloat16S0_S0_N3adf16io_buffer_configINS1_7extentsIJEEENS1_7locking4syncENS1_10addressing6linearENS1_6marginILj0EEEEESB_NS2_IS4_NS5_5asyncES8_SA_EEQsr3stdE9is_same_vIT0_S0_EEvRNS1_9io_bufferISE_NS1_9direction2inET3_EERNSF_IT1_SH_T4_EERNSF_IT2_NSG_3outET5_EER21conv2d_dw_bf16_params
189
+
190
+ Referenced symbols: _ZL9curr_iter
191
+ _ZL8core_row
192
+ _ZN12me_primitive11control_rndE
193
+ _ZN12me_primitive11control_satE
194
+ _ZL8num_iter
195
+ _ZL10ifmsv_size
196
+ conv2d_dw_params
197
+
198
+ 0x00002370..0x00002393 ( 36 items) : ../Release/0_0_reloadable52.o::_Z15_b14160_wrapperPPv (Function, Global, .text) (stack frame size = 0)
199
+
200
+ Called functions : _Z22superkernel_conv2d_dwcRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
201
+
202
+ 0x000023a0..0x000024a5 ( 262 items) : ../Release/0_0_reloadable52.o::_Z29setup_transposeshuffle_paramsI8bfloat16EvR23transposeshuffle_paramsRA7_Kj (Function, Weak, .text) (stack frame size = 0)
203
+
204
+ Referenced symbols: _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6params
205
+
206
+ 0x000024b0..0x0000292d ( 1150 items) : ../Release/0_0_reloadable52.o::_Z16transposeshuffleI8bfloat16Qsr5mllib5utilsE11is_one_of_vIT_aS0_7float16EEvPS1_S3_R23transposeshuffle_params (Function, Weak, .text) (stack frame size = 0)
207
+
208
+ Referenced symbols: _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6params
209
+
210
+ 0x00002930..0x000029f9 ( 202 items) : ../Release/0_0_reloadable52.o::_ZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_Kj (Function, Weak, .text) (stack frame size = 64)
211
+
212
+ Called functions : _Z29setup_transposeshuffle_paramsI8bfloat16EvR23transposeshuffle_paramsRA7_Kj
213
+ _Z16transposeshuffleI8bfloat16Qsr5mllib5utilsE11is_one_of_vIT_aS0_7float16EEvPS1_S3_R23transposeshuffle_params
214
+
215
+ Referenced symbols: _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6kn_rep
216
+ _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6params
217
+
218
+ 0x00002a00..0x00002a1f ( 32 items) : ../Release/0_0_reloadable52.o::_Z14_b7835_wrapperPPv (Function, Global, .text) (stack frame size = 0)
219
+
220
+ Called functions : _ZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_Kj
221
+
222
+ 0x00002a20..0x00002b2d ( 270 items) : ../Release/0_0_reloadable52.o::_ZN12mllib_graphs24buffer_unpad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj (Function, Weak, .text) (stack frame size = 0)
223
+ 0x00002b30..0x00002b4f ( 32 items) : ../Release/0_0_reloadable52.o::_Z14_b7876_wrapperPPv (Function, Global, .text) (stack frame size = 0)
224
+
225
+ Called functions : _ZN12mllib_graphs24buffer_unpad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj
226
+
227
+ 0x00002b50..0x00002d33 ( 484 items) : ../Release/0_0_reloadable52.o::_ZN12mllib_graphs22buffer_pad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj (Function, Weak, .text) (stack frame size = 64)
228
+
229
+ Called functions : memset
230
+
231
+ 0x00002d40..0x00002d5f ( 32 items) : ../Release/0_0_reloadable52.o::_Z14_b8148_wrapperPPv (Function, Global, .text) (stack frame size = 0)
232
+
233
+ Called functions : _ZN12mllib_graphs22buffer_pad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj
234
+
235
+ 0x00002d60..0x00002d7f ( 32 items) : ../Release/0_0_reloadable52.o::_Z15_b13739_wrapperPPv (Function, Global, .text) (stack frame size = 0)
236
+
237
+ Called functions : _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
238
+
239
+ 0x00002d80..0x00002d9f ( 32 items) : ../Release/0_0_reloadable52.o::_Z15_b13744_wrapperPPv (Function, Global, .text) (stack frame size = 0)
240
+
241
+ Called functions : _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
242
+
243
+ 0x00002da0..0x00002dc3 ( 36 items) : ../Release/0_0_reloadable52.o::_Z15_b13749_wrapperPPv (Function, Global, .text) (stack frame size = 0)
244
+
245
+ Called functions : _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
246
+
247
+ 0x00002dd0..0x00002e71 ( 162 items) : ../Release/0_0_reloadable52.o::_ZL32load_slice_generic_innermost_rtpR30slice_generic_innermost_paramsRA16_Kj (Function, Local, .text) (stack frame size = 0)
248
+ 0x00002e80..0x00002ed3 ( 84 items) : ../Release/0_0_reloadable52.o::_ZL29setup_slice_generic_innermostI8bfloat16EvR30slice_generic_innermost_params (Function, Local, .text) (stack frame size = 0)
249
+ 0x00002ee0..0x00002f13 ( 52 items) : ../Release/0_0_reloadable52.o::_ZL36setup_slice_generic_innermost_paramsI8bfloat16EvR30slice_generic_innermost_paramsRA16_Kj (Function, Local, .text) (stack frame size = 0)
250
+
251
+ Called functions : _ZL32load_slice_generic_innermost_rtpR30slice_generic_innermost_paramsRA16_Kj
252
+ _ZL29setup_slice_generic_innermostI8bfloat16EvR30slice_generic_innermost_params
253
+
254
+ 0x00002f20..0x000030ff ( 480 items) : ../Release/0_0_reloadable52.o::_Z23slice_generic_innermostI8bfloat16EvPT_S2_R30slice_generic_innermost_params (Function, Weak, .text) (stack frame size = 0)
255
+ 0x00003100..0x000031b1 ( 178 items) : ../Release/0_0_reloadable52.o::_ZN12mllib_graphs35slice_generic_innermost_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA16_Kj (Function, Weak, .text) (stack frame size = 128)
256
+
257
+ Called functions : _ZL36setup_slice_generic_innermost_paramsI8bfloat16EvR30slice_generic_innermost_paramsRA16_Kj
258
+ _Z23slice_generic_innermostI8bfloat16EvPT_S2_R30slice_generic_innermost_params
259
+
260
+ 0x000031c0..0x000031df ( 32 items) : ../Release/0_0_reloadable52.o::_Z14_b8170_wrapperPPv (Function, Global, .text) (stack frame size = 0)
261
+
262
+ Called functions : _ZN12mllib_graphs35slice_generic_innermost_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA16_Kj
263
+
264
+ 0x000031e0..0x0000326d ( 142 items) : me_div.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)::_ZN12me_primitive10udiv_dstepEjjRjS0_ (Function, Global, .text) (stack frame size = 0)
265
+ 0x00003270..0x0000331d ( 174 items) : string.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release/libc.a)::memset (Function, Global, .text) (stack frame size = 0)
266
+
267
+ External symbols:
268
+
269
+ __dso_handle = 0x0
270
+ _ctors_end = 0x0
271
+ _ctors_start = 0x0
272
+ _dtors_end = 0x0
273
+ _dtors_start = 0x0
274
+ _pc_end = 0x331e
275
+ _pc_start = 0x9e0
276
+ _sp_end_DM_stack = 0x7c1c0
277
+ _sp_start_DM_stack = 0x7bd80
278
+
279
+ Section summary for memory 'DM_stack':
280
+
281
+ .stack File
282
+ ---------- ----------
283
+ 1088
284
+ ---------- ----------
285
+ 1088 Total
286
+
287
+ Section summary for memory 'DMb':
288
+
289
+ .bss .data .rodata File
290
+ ---------- ---------- ---------- ----------
291
+ 600 4 32 ../Release/0_0_reloadable52.o
292
+ 5 0 0 me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
293
+ ---------- ---------- ---------- ----------
294
+ 605 4 32 Total
295
+
296
+ Section summary for memory 'PM':
297
+
298
+ .text File
299
+ ---------- ----------
300
+ 9964 ../Release/0_0_reloadable52.o
301
+ 142 me_div.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
302
+ 174 string.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release/libc.a)
303
+ ---------- ----------
304
+ 10280 Total
305
+
306
+ File summary:
307
+
308
+ ../Release/0_0_reloadable52.o
309
+ DMb 636
310
+ PM 9964
311
+
312
+ me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
313
+ DMb 5
314
+
315
+ me_div.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
316
+ PM 142
317
+
318
+ string.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release/libc.a)
319
+ PM 174
320
+
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.sdr ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ // File generated by bridge version V-2024.06#84922c0d9f#241219, Fri May 30 11:33:37 2025
3
+ // Copyright 2014-2024 Synopsys, Inc. All rights reserved.
4
+ // bridge -o../Release/0_0_reloadable52 ../Release/0_0_reloadable52.o -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/isg -g -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxxabi-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0_reloadable52.bcf -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/softfloat/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork3589152 -pme
5
+
6
+ // Release: ipp V-2024.06-TGT-241219
7
+
8
+ // Symbols in memory 'DM_bankA':
9
+ // Symbols in memory 'DM_bankAB':
10
+ // Symbols in memory 'DM_bankAC':
11
+ // Symbols in memory 'DM_bankAD':
12
+ // Symbols in memory 'DM_bankB':
13
+ // Symbols in memory 'DM_bankBC':
14
+ // Symbols in memory 'DM_bankBD':
15
+ // Symbols in memory 'DM_bankC':
16
+ // Symbols in memory 'DM_bankCD':
17
+ // Symbols in memory 'DM_bankD':
18
+ // Symbols in memory 'DM_stack':
19
+ // Symbols in memory 'DM_test':
20
+ // Symbols in memory 'DMb':
21
+ _symbol _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6kn_rep 0x0007c214
22
+ _symbol _ZN12me_primitive11control_satE 0x0007c21c
23
+ _symbol _ZN12me_primitive11control_rndE 0x0007c220
24
+ _symbol _ZZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_KjE6params 0x0007c280
25
+ _symbol add1d_attribute_broadcasting_params 0x0007c300
26
+ _symbol mul1d_params 0x0007c340
27
+ _symbol sigmoid1d_params 0x0007c380
28
+ _symbol conv2d_dw_params 0x0007c3c0
29
+ // Symbols in memory 'DMh':
30
+ // Symbols in memory 'DMh_bankA':
31
+ // Symbols in memory 'DMh_bankAB':
32
+ // Symbols in memory 'DMh_bankAC':
33
+ // Symbols in memory 'DMh_bankAD':
34
+ // Symbols in memory 'DMh_bankB':
35
+ // Symbols in memory 'DMh_bankBC':
36
+ // Symbols in memory 'DMh_bankBD':
37
+ // Symbols in memory 'DMh_bankC':
38
+ // Symbols in memory 'DMh_bankCD':
39
+ // Symbols in memory 'DMh_bankD':
40
+ // Symbols in memory 'DMh_stack':
41
+ // Symbols in memory 'DMs':
42
+ // Symbols in memory 'DMs_bankA':
43
+ // Symbols in memory 'DMs_bankAB':
44
+ // Symbols in memory 'DMs_bankAC':
45
+ // Symbols in memory 'DMs_bankAD':
46
+ // Symbols in memory 'DMs_bankB':
47
+ // Symbols in memory 'DMs_bankBC':
48
+ // Symbols in memory 'DMs_bankBD':
49
+ // Symbols in memory 'DMs_bankC':
50
+ // Symbols in memory 'DMs_bankCD':
51
+ // Symbols in memory 'DMs_bankD':
52
+ // Symbols in memory 'DMs_stack':
53
+ // Symbols in memory 'DMv':
54
+ // Symbols in memory 'DMv_bankA':
55
+ // Symbols in memory 'DMv_bankAB':
56
+ // Symbols in memory 'DMv_bankAC':
57
+ // Symbols in memory 'DMv_bankAD':
58
+ // Symbols in memory 'DMv_bankB':
59
+ // Symbols in memory 'DMv_bankBC':
60
+ // Symbols in memory 'DMv_bankBD':
61
+ // Symbols in memory 'DMv_bankC':
62
+ // Symbols in memory 'DMv_bankCD':
63
+ // Symbols in memory 'DMv_bankD':
64
+ // Symbols in memory 'DMv_stack':
65
+ // Symbols in memory 'DMw':
66
+ // Symbols in memory 'DMw_bankA':
67
+ // Symbols in memory 'DMw_bankAB':
68
+ // Symbols in memory 'DMw_bankAC':
69
+ // Symbols in memory 'DMw_bankAD':
70
+ // Symbols in memory 'DMw_bankB':
71
+ // Symbols in memory 'DMw_bankBC':
72
+ // Symbols in memory 'DMw_bankBD':
73
+ // Symbols in memory 'DMw_bankC':
74
+ // Symbols in memory 'DMw_bankCD':
75
+ // Symbols in memory 'DMw_bankD':
76
+ // Symbols in memory 'DMw_stack':
77
+ // Symbols in memory 'DMx':
78
+ // Symbols in memory 'DMx_bankA':
79
+ // Symbols in memory 'DMx_bankAB':
80
+ // Symbols in memory 'DMx_bankAC':
81
+ // Symbols in memory 'DMx_bankAD':
82
+ // Symbols in memory 'DMx_bankB':
83
+ // Symbols in memory 'DMx_bankBC':
84
+ // Symbols in memory 'DMx_bankBD':
85
+ // Symbols in memory 'DMx_bankC':
86
+ // Symbols in memory 'DMx_bankCD':
87
+ // Symbols in memory 'DMx_bankD':
88
+ // Symbols in memory 'DMx_stack':
89
+ // Symbols in memory 'PM':
90
+ _symbol _Z13kernelWrapperPPvjjjj 0x000009e0
91
+ _symbol _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E 0x00000c10
92
+ _symbol _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv 0x00000c30
93
+ _symbol _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E 0x00000cf0
94
+ _symbol _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv 0x00000d30
95
+ _symbol _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E 0x00000d70
96
+ _symbol _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E 0x00000ec0
97
+ _symbol _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE 0x00000f40
98
+ _symbol _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv 0x00001130
99
+ _symbol _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E 0x00001180
100
+ _symbol _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE 0x00001300
101
+ _symbol _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E 0x000014f0
102
+ _symbol _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv 0x00001510
103
+ _symbol _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E 0x000015b0
104
+ _symbol _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE 0x000016f0
105
+ _symbol _Z14conv2d_dw_coreI8bfloat16EvPT_S2_S2_S2_R21conv2d_dw_bf16_params 0x00001c70
106
+ _symbol _Z17conv2d_dw_shuffleI8bfloat16EvPT_S2_S2_RK21conv2d_dw_bf16_params 0x00001f20
107
+ _symbol _Z9conv2d_dwILh1E8bfloat16S0_S0_N3adf16io_buffer_configINS1_7extentsIJEEENS1_7locking4syncENS1_10addressing6linearENS1_6marginILj0EEEEESB_NS2_IS4_NS5_5asyncES8_SA_EEQsr3stdE9is_same_vIT0_S0_EEvRNS1_9io_bufferISE_NS1_9direction2inET3_EERNSF_IT1_SH_T4_EERNSF_IT2_NSG_3outET5_EER21conv2d_dw_bf16_params 0x00002020
108
+ _symbol _Z22superkernel_conv2d_dwcRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE 0x00002190
109
+ _symbol _Z15_b14160_wrapperPPv 0x00002370
110
+ _symbol _Z29setup_transposeshuffle_paramsI8bfloat16EvR23transposeshuffle_paramsRA7_Kj 0x000023a0
111
+ _symbol _Z16transposeshuffleI8bfloat16Qsr5mllib5utilsE11is_one_of_vIT_aS0_7float16EEvPS1_S3_R23transposeshuffle_params 0x000024b0
112
+ _symbol _ZN12mllib_graphs23transpose4d_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA7_Kj 0x00002930
113
+ _symbol _Z14_b7835_wrapperPPv 0x00002a00
114
+ _symbol _ZN12mllib_graphs24buffer_unpad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj 0x00002a20
115
+ _symbol _Z14_b7876_wrapperPPv 0x00002b30
116
+ _symbol _ZN12mllib_graphs22buffer_pad_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA3_Kj 0x00002b50
117
+ _symbol _Z14_b8148_wrapperPPv 0x00002d40
118
+ _symbol _Z15_b13739_wrapperPPv 0x00002d60
119
+ _symbol _Z15_b13744_wrapperPPv 0x00002d80
120
+ _symbol _Z15_b13749_wrapperPPv 0x00002da0
121
+ _symbol _Z23slice_generic_innermostI8bfloat16EvPT_S2_R30slice_generic_innermost_params 0x00002f20
122
+ _symbol _ZN12mllib_graphs35slice_generic_innermost_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_NSF_3outET1_EERA16_Kj 0x00003100
123
+ _symbol _Z14_b8170_wrapperPPv 0x000031c0
124
+ _symbol _ZN12me_primitive10udiv_dstepEjjRjS0_ 0x000031e0
125
+ _symbol memset 0x00003270
126
+ // Symbols in memory 'PMw':
127
+ // Symbols in memory 'TM4':
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.srv ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/Release/1_3_reloadable52.txt ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/scripts/1_3_reloadable52.bcf ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _reserved DMb 0x0 0x40000
2
+
3
+ _reserved PM 0x0 0x9e0 //reserved for main elf
4
+
5
+ _entry_point _Z13kernelWrapperPPvjjjj
6
+ _symbol _Z13kernelWrapperPPvjjjj 0x9e0
7
+
8
+ _reserved DMb 0x7b540 0x800 //reserved for lcp ping-pong buffers
9
+ _reserved DMb 0x7bd40 0x40 //reserved for sync buffer
10
+ _stack DM_stack 0x7bd80 0x440 //stack for core
11
+ _reserved DMb 0x7c1c0 0x40 //reserved for main elf heap
12
+ //space for synopsys compiler at 0x7c200 0x800//heap
13
+ _reserved DMb 0x40000 0x3b540
14
+
15
+ _reserved DMb 0x7ca00 0x3600
16
+ _reserved DMb 0x80000 0x80000 // And everything else the core can't see
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/scripts/1_3_reloadable52.prx ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <project name="Project" processor="me">
2
+ <issinit/>
3
+ <option id="cpp.define" value="__AIENGINE__ __AIE_ARCH__=21" inherit = "1"/>
4
+ <option id="llvm.xargs" value="-fno-jump-tables -fno-discard-value-names" inherit = "1"/>
5
+ <option id="llvm.lang" value="Follow file extension"/>
6
+ <option id="bridge.cfg" value="1_3_reloadable52.bcf"/>
7
+ <option id="bridge.alibs" value=" ../Release/1_3_reloadable52.o" inherit="1" cfg="Release_LLVM"/>
8
+ <option id="cpp.include" value="&lt;XILINX_VITIS_AIETOOLS&gt;/include /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/&lt;AIE_SRC_DIR&gt;/ /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/&lt;AIE_SRC_DIR&gt; " inherit="1"/>
9
+ <option id="project.dir" value="&lt;CONFIG&gt;/1_3_reloadable52"/>
10
+ <option id="project.name" value="1_3_reloadable52"/>
11
+ <option id="project.type" value="exe"/>
12
+ <option id="simrun.issca" value="&lt;XILINX_VITIS_AIETOOLS&gt;/bin/unwrapped/lnx64.o/aie2p/ca_udm_dbg" inherit="0"/>
13
+ </project>
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable52/src/1_3_reloadable52.cc ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ // Automatically generated processor driver using AIEngine tool-chain
2
+
3
+ #include <stdio.h>
4
+ #include <memory>
5
+ #include <adf.h>
6
+
7
+
8
+ // Declare Kernel functions and initializers
9
+ void superkernel_conv2d_dwc(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
10
+ #include "transpose4d_adf_wrapper.cpp"
11
+ #include "buffer_unpad_adf_wrapper.cpp"
12
+ #include "buffer_pad_adf_wrapper.cpp"
13
+ void superkernel_add1d_attribute_broadcasting(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
14
+ void superkernel_sigmoid1d(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
15
+ void superkernel_mul1d(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict,adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
16
+ #include "slice_generic_innermost_adf_wrapper.cpp"
17
+
18
+ // Declare Kernel objects and external arrays
19
+
20
+
21
+ void _b14160_wrapper(void* args[])
22
+ {
23
+ superkernel_conv2d_dwc(
24
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
25
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
26
+ *reinterpret_cast<uint32 const(*)[16]>(args[3]),
27
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[2]));
28
+ }
29
+
30
+ void _b7835_wrapper(void* args[])
31
+ {
32
+ mllib_graphs::transpose4d_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
33
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
34
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
35
+ *reinterpret_cast<uint32 const(*)[7]>(args[2]));
36
+ }
37
+
38
+ void _b7876_wrapper(void* args[])
39
+ {
40
+ mllib_graphs::buffer_unpad_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
41
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
42
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
43
+ *reinterpret_cast<uint32 const(*)[3]>(args[2]));
44
+ }
45
+
46
+ void _b8148_wrapper(void* args[])
47
+ {
48
+ mllib_graphs::buffer_pad_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
49
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
50
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
51
+ *reinterpret_cast<uint32 const(*)[3]>(args[2]));
52
+ }
53
+
54
+ void _b13739_wrapper(void* args[])
55
+ {
56
+ superkernel_add1d_attribute_broadcasting(
57
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
58
+ *reinterpret_cast<uint32 const(*)[16]>(args[2]),
59
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]));
60
+ }
61
+
62
+ void _b13744_wrapper(void* args[])
63
+ {
64
+ superkernel_sigmoid1d(
65
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
66
+ *reinterpret_cast<uint32 const(*)[16]>(args[2]),
67
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]));
68
+ }
69
+
70
+ void _b13749_wrapper(void* args[])
71
+ {
72
+ superkernel_mul1d(
73
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
74
+ *reinterpret_cast<uint32 const(*)[16]>(args[3]),
75
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]),
76
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[2]));
77
+ }
78
+
79
+ void _b8170_wrapper(void* args[])
80
+ {
81
+ mllib_graphs::slice_generic_innermost_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
82
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
83
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
84
+ *reinterpret_cast<uint32 const(*)[16]>(args[2]));
85
+ }
86
+
87
+ using UniformKernelFunc = void (*)(void **);
88
+
89
+ static UniformKernelFunc g_uniformKernelFuncs[8] = {
90
+ _b14160_wrapper,
91
+ _b7835_wrapper,
92
+ _b7876_wrapper,
93
+ _b8148_wrapper,
94
+ _b13739_wrapper,
95
+ _b13744_wrapper,
96
+ _b13749_wrapper,
97
+ _b8170_wrapper
98
+ };
99
+
100
+ __attribute__((always_inline)) void kernelWrapper(void* args[], uint32 kernelId, uint32 numSyncIn, uint32 numAsyncIn, uint32 numSyncOut)
101
+ {
102
+ uint32 idx = 0;
103
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::in>(numSyncIn > 0);
104
+ idx += (numSyncIn > 0) ? 1 : 0;
105
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::in>(numSyncIn > 1);
106
+ idx += (numSyncIn > 1) ? 1 : 0;
107
+ idx += numAsyncIn;
108
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::out>(numSyncOut > 0);
109
+ idx += (numSyncOut > 0) ? 1 : 0;
110
+
111
+ (*(g_uniformKernelFuncs[kernelId]))(args);
112
+
113
+ idx = 0;
114
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::in>(numSyncIn > 0);
115
+ idx += (numSyncIn > 0) ? 1 : 0;
116
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::in>(numSyncIn > 1);
117
+ idx += (numSyncIn > 1) ? 1 : 0;
118
+ idx += numAsyncIn;
119
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::out>(numSyncOut > 0);
120
+ idx += (numSyncOut > 0) ? 1 : 0;
121
+ }
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.calltree ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ // File generated by bridge version V-2024.06#84922c0d9f#241219, Fri May 30 11:30:05 2025
3
+ // Copyright 2014-2024 Synopsys, Inc. All rights reserved.
4
+ // bridge -o../Release/0_0_reloadable5 ../Release/0_0_reloadable5.o -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/isg -g -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxxabi-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0_reloadable5.bcf -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/softfloat/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork3577694 -pme
5
+
6
+
7
+ // Release: ipp V-2024.06-TGT-241219
8
+
9
+ _Z13kernelWrapperPPvjjjj
10
+ _Z15_b13786_wrapperPPv (referenced text)
11
+ _Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
12
+ _ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv
13
+ _Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params
14
+ _Z8init_accILt1EEvPaS0_iii
15
+ _Z12post_processPai
16
+ _Z15_b13811_wrapperPPv (referenced text)
17
+ _Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
18
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv
19
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv
20
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
21
+ _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE
22
+ _Z15_b13739_wrapperPPv (referenced text)
23
+ _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
24
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
25
+ _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
26
+ _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
27
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E
28
+ _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
29
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
30
+ _Z15_b13744_wrapperPPv (referenced text)
31
+ _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
32
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
33
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
34
+ _Z15_b13749_wrapperPPv (referenced text)
35
+ _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
36
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
37
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
38
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
39
+ _Z14_b8292_wrapperPPv (referenced text)
40
+ _ZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EE
41
+ _ZL30setup_rmsnorm_row_major_paramsR33rmsnorm_row_major_internal_paramsRA10_Kj
42
+ _ZN12me_primitive10udiv_dstepEjjRjS0_
43
+ _Z23rmsnorm_row_major_part1I8bfloat16EvPT_S2_R33rmsnorm_row_major_internal_params
44
+ _ZN12me_primitive10udiv_dstepEjjRjS0_ (*)
45
+ _ZN12me_primitive10udiv_dstepEjjRjS0_ (*)
46
+ _Z14_b8300_wrapperPPv (referenced text)
47
+ _ZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EE
48
+ _ZL30setup_rmsnorm_row_major_paramsR33rmsnorm_row_major_internal_paramsRA10_Kj (*)
49
+ _Z14_b8308_wrapperPPv (referenced text)
50
+ _ZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EE
51
+ _ZL30setup_rmsnorm_row_major_paramsR33rmsnorm_row_major_internal_paramsRA10_Kj (*)
52
+ _Z23rmsnorm_row_major_part2I8bfloat16EvPT_S2_S2_S2_R33rmsnorm_row_major_internal_params
53
+
54
+
55
+ Call tree stack and functions sizes:
56
+
57
+ stack stack stack call func func function name
58
+ desc level level desc
59
+ ----- ----- ----- ----- ----- ----- --------------------------------------------------------------
60
+ 64 320 0 0 546 12986 _Z13kernelWrapperPPvjjjj
61
+ 0 192 1 1 36 3650 _Z15_b13786_wrapperPPv
62
+ 64 192 1 2 546 3614 _Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
63
+ 0 0 2 3 550 550 _ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv
64
+ 64 128 2 3 1930 2518 _Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params
65
+ 64 64 3 4 294 294 _Z8init_accILt1EEvPaS0_iii
66
+ 0 0 3 4 294 294 _Z12post_processPai
67
+ 0 128 1 1 36 1378 _Z15_b13811_wrapperPPv
68
+ 64 128 1 2 602 1342 _Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE <tail call>
69
+ 64 64 2 3 114 236 _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv
70
+ 0 0 3 4 122 122 _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv
71
+ 0 64 2 3 20 504 _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
72
+ 64 64 2 4 484 484 _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE <tail call>
73
+ 0 192 1 1 32 1282 _Z15_b13739_wrapperPPv
74
+ 64 192 1 2 488 1250 _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
75
+ 64 128 2 3 60 318 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
76
+ 64 64 3 4 178 202 _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
77
+ 0 0 4 5 24 24 _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
78
+ 0 0 2 4 56 56 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E <tail call>
79
+ 128 128 2 3 114 444 _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
80
+ 0 0 3 4 330 330 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
81
+ 0 64 1 1 32 966 _Z15_b13744_wrapperPPv
82
+ 64 64 1 2 488 934 _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
83
+ 0 0 2 3 68 68 _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
84
+ 0 0 2 3 378 378 _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
85
+ 0 128 1 1 36 1124 _Z15_b13749_wrapperPPv
86
+ 64 128 1 2 602 1088 _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE <tail call>
87
+ 64 64 2 3 154 178 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
88
+ 0 0 3 4 24 24 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
89
+ 0 0 2 3 308 308 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
90
+ 0 256 1 1 36 2088 _Z14_b8292_wrapperPPv
91
+ 128 256 1 2 668 2052 _ZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EE <tail call>
92
+ 64 64 2 3 390 532 _ZL30setup_rmsnorm_row_major_paramsR33rmsnorm_row_major_internal_paramsRA10_Kj
93
+ 0 0 3 4 142 142 _ZN12me_primitive10udiv_dstepEjjRjS0_
94
+ 128 128 2 3 852 994 _Z23rmsnorm_row_major_part1I8bfloat16EvPT_S2_R33rmsnorm_row_major_internal_params
95
+ 0 0 3 4 142 142 _ZN12me_primitive10udiv_dstepEjjRjS0_
96
+ 0 0 2 3 142 142 _ZN12me_primitive10udiv_dstepEjjRjS0_
97
+ 0 192 1 1 36 1254 _Z14_b8300_wrapperPPv
98
+ 128 192 1 2 686 1218 _ZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EE <tail call>
99
+ 64 64 2 3 390 532 _ZL30setup_rmsnorm_row_major_paramsR33rmsnorm_row_major_internal_paramsRA10_Kj (*)
100
+ 0 192 1 1 36 1762 _Z14_b8308_wrapperPPv
101
+ 128 192 1 2 536 1726 _ZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EE <tail call>
102
+ 64 64 2 3 390 532 _ZL30setup_rmsnorm_row_major_paramsR33rmsnorm_row_major_internal_paramsRA10_Kj (*)
103
+ 64 64 2 3 658 658 _Z23rmsnorm_row_major_part2I8bfloat16EvPT_S2_S2_S2_R33rmsnorm_row_major_internal_params
104
+
105
+
106
+ Maximum call level : 5
107
+ Maximum stack level: 4
108
+ Maximum stack size : 320
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.cmic2 ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.cmico ADDED
@@ -0,0 +1 @@
 
 
1
+ +Mdec
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.lst ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.map ADDED
@@ -0,0 +1,382 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ // File generated by bridge version V-2024.06#84922c0d9f#241219, Fri May 30 11:30:05 2025
3
+ // Copyright 2014-2024 Synopsys, Inc. All rights reserved.
4
+ // bridge -o../Release/0_0_reloadable5 ../Release/0_0_reloadable5.o -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/isg -g -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxxabi-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0_reloadable5.bcf -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/softfloat/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork3577694 -pme
5
+
6
+ // Release: ipp V-2024.06-TGT-241219
7
+
8
+ Memory map for memory 'DM_stack':
9
+
10
+ Size = 1048576
11
+ Width = 8 bits
12
+ Offset = 0
13
+ Used = 1088
14
+
15
+ 0x0007bd80..0x0007c1bf ( 1088 items) : Stack
16
+
17
+ Memory map for memory 'DMb':
18
+
19
+ Size = 1048576
20
+ Width = 8 bits
21
+ Offset = 0
22
+ Used = 1905
23
+
24
+ 0x00000000..0x0007bd7f ( 507264 items) : Reserved
25
+ 0x0007bd80..0x0007c1bf ( 1088 items) : Stack
26
+ 0x0007c1c0..0x0007c1ff ( 64 items) : Reserved
27
+ 0x0007c200..0x0007c35f ( 352 items) : ../Release/0_0_reloadable5.o::gem_bfp_param (Data, Global, .bss.DMb.32)
28
+ 0x0007c360..0x0007c3bf ( 96 items) : ../Release/0_0_reloadable5.o::_ZN11ns_rms_norm5paramE (Data, Global, .bss.DMb.32)
29
+ 0x0007c3c0..0x0007c3c3 ( 4 items) : ../Release/0_0_reloadable5.o::_ZL9curr_iter (Data, Local, .bss.DMb.4)
30
+ 0x0007c3c4..0x0007c3c7 ( 4 items) : ../Release/0_0_reloadable5.o::_ZL10depth_iter (Data, Local, .bss.DMb.4)
31
+ 0x0007c3c8..0x0007c3cb ( 4 items) : ../Release/0_0_reloadable5.o::_ZL11total_iters (Data, Local, .bss.DMb.4)
32
+ 0x0007c3cc..0x0007c3cf ( 4 items) : ../Release/0_0_reloadable5.o::_ZL8core_row (Data, Local, .bss.DMb.4)
33
+ 0x0007c3d0..0x0007c3d3 ( 4 items) : ../Release/0_0_reloadable5.o::_ZL11ifm1_offset (Data, Local, .bss.DMb.4)
34
+ 0x0007c3d4..0x0007c3d7 ( 4 items) : ../Release/0_0_reloadable5.o::_ZL11ifm2_offset (Data, Local, .bss.DMb.4)
35
+ 0x0007c3d8..0x0007c3db ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE7core_id (Data, Weak, .bss.DMb.4)
36
+ 0x0007c3dc..0x0007c3df ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE8core_row (Data, Weak, .bss.DMb.4)
37
+ 0x0007c3e0..0x0007c3e3 ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE8core_col (Data, Weak, .bss.DMb.4)
38
+ 0x0007c3e4..0x0007c3e7 ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE11kernel_iter (Data, Weak, .bss.DMb.4)
39
+ 0x0007c3e8..0x0007c3eb ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE7core_id (Data, Weak, .bss.DMb.4)
40
+ 0x0007c3ec..0x0007c3ef ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_row (Data, Weak, .bss.DMb.4)
41
+ 0x0007c3f0..0x0007c3f3 ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_col (Data, Weak, .bss.DMb.4)
42
+ 0x0007c3f4..0x0007c3f7 ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE11kernel_iter (Data, Weak, .bss.DMb.4)
43
+ 0x0007c3f8..0x0007c3fb ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE7core_id (Data, Weak, .bss.DMb.4)
44
+ 0x0007c3fc..0x0007c3ff ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_row (Data, Weak, .bss.DMb.4)
45
+ 0x0007c400..0x0007c403 ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_col (Data, Weak, .bss.DMb.4)
46
+ 0x0007c404..0x0007c407 ( 4 items) : ../Release/0_0_reloadable5.o::_ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE11kernel_iter (Data, Weak, .bss.DMb.4)
47
+ 0x0007c408..0x0007c40b ( 4 items) : ../Release/0_0_reloadable5.o::_ZL8num_iter (Data, Local, .data.DMb.4)
48
+ 0x0007c40c..0x0007c40f ( 4 items) : me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)::_ZN12me_primitive11control_satE (Data, Global, .bss.DMb.4)
49
+ 0x0007c410..0x0007c410 ( 1 items) : me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)::_ZN12me_primitive11control_rndE (Data, Global, .bss.DMb.1)
50
+ 0x0007c440..0x0007c45f ( 32 items) : ../Release/0_0_reloadable5.o::_ZL20g_uniformKernelFuncs (Data, Local, .rodata.DMb.64)
51
+
52
+ Called functions : _Z15_b13786_wrapperPPv
53
+ _Z15_b13811_wrapperPPv
54
+ _Z15_b13739_wrapperPPv
55
+ _Z15_b13744_wrapperPPv
56
+ _Z15_b13749_wrapperPPv
57
+ _Z14_b8292_wrapperPPv
58
+ _Z14_b8300_wrapperPPv
59
+ _Z14_b8308_wrapperPPv
60
+
61
+ 0x0007c480..0x0007c4bf ( 64 items) : ../Release/0_0_reloadable5.o::add1d_attribute_broadcasting_params (Data, Global, .bss.DMb.64)
62
+ 0x0007c4c0..0x0007c4ff ( 64 items) : ../Release/0_0_reloadable5.o::add1d_params (Data, Global, .bss.DMb.64)
63
+ 0x0007c500..0x0007c53f ( 64 items) : ../Release/0_0_reloadable5.o::mul1d_params (Data, Global, .bss.DMb.64)
64
+ 0x0007c540..0x0007c57f ( 64 items) : ../Release/0_0_reloadable5.o::sigmoid1d_params (Data, Global, .bss.DMb.64)
65
+ 0x0007ca00..0x000fffff ( 538112 items) : Reserved
66
+
67
+ Memory map for memory 'PM':
68
+
69
+ Size = 1048576
70
+ Width = 8 bits
71
+ Offset = 0
72
+ Used = 12986
73
+
74
+ 0x00000000..0x000009df ( 2528 items) : Reserved
75
+ 0x000009e0..0x00000c01 ( 546 items) : ../Release/0_0_reloadable5.o::_Z13kernelWrapperPPvjjjj (Function, Global, .text) (stack frame size = 64)
76
+
77
+ Referenced symbols: _ZL20g_uniformKernelFuncs
78
+
79
+ 0x00000c10..0x00000c27 ( 24 items) : ../Release/0_0_reloadable5.o::_ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
80
+
81
+ Referenced symbols: add1d_attribute_broadcasting_params
82
+
83
+ 0x00000c30..0x00000ce1 ( 178 items) : ../Release/0_0_reloadable5.o::_ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 64)
84
+
85
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
86
+
87
+ Referenced symbols: add1d_attribute_broadcasting_params
88
+
89
+ 0x00000cf0..0x00000d27 ( 56 items) : ../Release/0_0_reloadable5.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
90
+
91
+ Referenced symbols: add1d_attribute_broadcasting_params
92
+
93
+ 0x00000d30..0x00000d6b ( 60 items) : ../Release/0_0_reloadable5.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 64)
94
+
95
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
96
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E
97
+
98
+ Referenced symbols: add1d_attribute_broadcasting_params
99
+
100
+ 0x00000d70..0x00000eb9 ( 330 items) : ../Release/0_0_reloadable5.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
101
+
102
+ Referenced symbols: add1d_attribute_broadcasting_params
103
+ _ZN12me_primitive11control_rndE
104
+
105
+ 0x00000ec0..0x00000f31 ( 114 items) : ../Release/0_0_reloadable5.o::_ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 128)
106
+
107
+ Called functions : _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
108
+
109
+ Referenced symbols: add1d_attribute_broadcasting_params
110
+
111
+ 0x00000f40..0x00001127 ( 488 items) : ../Release/0_0_reloadable5.o::_Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
112
+
113
+ Called functions : _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
114
+ _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
115
+
116
+ Referenced symbols: _ZL9curr_iter
117
+ _ZL8core_row
118
+ add1d_attribute_broadcasting_params
119
+ _ZN12me_primitive11control_rndE
120
+ _ZN12me_primitive11control_satE
121
+ _ZL11ifm1_offset
122
+ _ZL8num_iter
123
+
124
+ 0x00001130..0x00001313 ( 484 items) : ../Release/0_0_reloadable5.o::_ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE (Function, Local, .text) (stack frame size = 64)
125
+
126
+ Referenced symbols: _ZN12me_primitive11control_rndE
127
+
128
+ 0x00001320..0x00001363 ( 68 items) : ../Release/0_0_reloadable5.o::_ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 0)
129
+
130
+ Referenced symbols: sigmoid1d_params
131
+
132
+ 0x00001370..0x000014e9 ( 378 items) : ../Release/0_0_reloadable5.o::_ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
133
+
134
+ Referenced symbols: sigmoid1d_params
135
+ _ZN12me_primitive11control_rndE
136
+
137
+ 0x000014f0..0x000016d7 ( 488 items) : ../Release/0_0_reloadable5.o::_Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
138
+
139
+ Called functions : _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
140
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
141
+
142
+ Referenced symbols: _ZL9curr_iter
143
+ _ZL8core_row
144
+ sigmoid1d_params
145
+ _ZN12me_primitive11control_rndE
146
+ _ZN12me_primitive11control_satE
147
+ _ZL11ifm1_offset
148
+ _ZL8num_iter
149
+
150
+ 0x000016e0..0x00001759 ( 122 items) : ../Release/0_0_reloadable5.o::_ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 0)
151
+
152
+ Referenced symbols: add1d_params
153
+
154
+ 0x00001760..0x000017d1 ( 114 items) : ../Release/0_0_reloadable5.o::_ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 64)
155
+
156
+ Called functions : _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv
157
+
158
+ Referenced symbols: add1d_params
159
+
160
+ 0x000017e0..0x000017f3 ( 20 items) : ../Release/0_0_reloadable5.o::_ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
161
+
162
+ Called functions : _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE
163
+
164
+ Referenced symbols: add1d_params
165
+
166
+ 0x00001800..0x00001a59 ( 602 items) : ../Release/0_0_reloadable5.o::_Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE (Function, Global, .text) (stack frame size = 64)
167
+
168
+ Called functions : _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv
169
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
170
+
171
+ Referenced symbols: _ZL9curr_iter
172
+ _ZL8core_row
173
+ add1d_params
174
+ _ZN12me_primitive11control_rndE
175
+ _ZN12me_primitive11control_satE
176
+ _ZL11ifm1_offset
177
+ _ZL11ifm2_offset
178
+ _ZL8num_iter
179
+
180
+ 0x00001a60..0x00001a77 ( 24 items) : ../Release/0_0_reloadable5.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
181
+
182
+ Referenced symbols: mul1d_params
183
+
184
+ 0x00001a80..0x00001b19 ( 154 items) : ../Release/0_0_reloadable5.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 64)
185
+
186
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
187
+
188
+ Referenced symbols: mul1d_params
189
+
190
+ 0x00001b20..0x00001c53 ( 308 items) : ../Release/0_0_reloadable5.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
191
+
192
+ Referenced symbols: mul1d_params
193
+ _ZN12me_primitive11control_rndE
194
+
195
+ 0x00001c60..0x00001eb9 ( 602 items) : ../Release/0_0_reloadable5.o::_Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE (Function, Global, .text) (stack frame size = 64)
196
+
197
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
198
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
199
+
200
+ Referenced symbols: _ZL9curr_iter
201
+ _ZL8core_row
202
+ mul1d_params
203
+ _ZN12me_primitive11control_rndE
204
+ _ZN12me_primitive11control_satE
205
+ _ZL11ifm1_offset
206
+ _ZL11ifm2_offset
207
+ _ZL8num_iter
208
+
209
+ 0x00001ec0..0x000020e5 ( 550 items) : ../Release/0_0_reloadable5.o::_ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv (Function, Local, .text) (stack frame size = 0)
210
+
211
+ Referenced symbols: gem_bfp_param
212
+
213
+ 0x000020f0..0x00002215 ( 294 items) : ../Release/0_0_reloadable5.o::_Z8init_accILt1EEvPaS0_iii (Function, Weak, .text) (stack frame size = 64)
214
+
215
+ Referenced symbols: _ZN12me_primitive11control_rndE
216
+
217
+ 0x00002220..0x00002345 ( 294 items) : ../Release/0_0_reloadable5.o::_Z12post_processPai (Function, Weak, .text) (stack frame size = 0)
218
+
219
+ Referenced symbols: _ZN12me_primitive11control_rndE
220
+
221
+ 0x00002350..0x00002ad9 ( 1930 items) : ../Release/0_0_reloadable5.o::_Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params (Function, Weak, .text) (stack frame size = 64)
222
+
223
+ Called functions : _Z8init_accILt1EEvPaS0_iii
224
+ _Z12post_processPai
225
+
226
+ Referenced symbols: gem_bfp_param
227
+ _ZN12me_primitive11control_satE
228
+ _ZN12me_primitive11control_rndE
229
+
230
+ 0x00002ae0..0x00002d01 ( 546 items) : ../Release/0_0_reloadable5.o::_Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
231
+
232
+ Called functions : _ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv
233
+ _Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params
234
+
235
+ Referenced symbols: _ZL9curr_iter
236
+ _ZN12me_primitive11control_rndE
237
+ _ZN12me_primitive11control_satE
238
+ _ZL11total_iters
239
+ _ZL10depth_iter
240
+ gem_bfp_param
241
+
242
+ 0x00002d10..0x00002d33 ( 36 items) : ../Release/0_0_reloadable5.o::_Z15_b13786_wrapperPPv (Function, Global, .text) (stack frame size = 0)
243
+
244
+ Called functions : _Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
245
+
246
+ 0x00002d40..0x00002d63 ( 36 items) : ../Release/0_0_reloadable5.o::_Z15_b13811_wrapperPPv (Function, Global, .text) (stack frame size = 0)
247
+
248
+ Called functions : _Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
249
+
250
+ 0x00002d70..0x00002d8f ( 32 items) : ../Release/0_0_reloadable5.o::_Z15_b13739_wrapperPPv (Function, Global, .text) (stack frame size = 0)
251
+
252
+ Called functions : _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
253
+
254
+ 0x00002d90..0x00002daf ( 32 items) : ../Release/0_0_reloadable5.o::_Z15_b13744_wrapperPPv (Function, Global, .text) (stack frame size = 0)
255
+
256
+ Called functions : _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
257
+
258
+ 0x00002db0..0x00002dd3 ( 36 items) : ../Release/0_0_reloadable5.o::_Z15_b13749_wrapperPPv (Function, Global, .text) (stack frame size = 0)
259
+
260
+ Called functions : _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
261
+
262
+ 0x00002de0..0x00002f65 ( 390 items) : ../Release/0_0_reloadable5.o::_ZL30setup_rmsnorm_row_major_paramsR33rmsnorm_row_major_internal_paramsRA10_Kj (Function, Local, .text) (stack frame size = 64)
263
+
264
+ Called functions : _ZN12me_primitive10udiv_dstepEjjRjS0_
265
+
266
+ Referenced symbols: _ZN11ns_rms_norm5paramE
267
+
268
+ 0x00002f70..0x000032c3 ( 852 items) : ../Release/0_0_reloadable5.o::_Z23rmsnorm_row_major_part1I8bfloat16EvPT_S2_R33rmsnorm_row_major_internal_params (Function, Weak, .text) (stack frame size = 128)
269
+
270
+ Called functions : _ZN12me_primitive10udiv_dstepEjjRjS0_
271
+
272
+ Referenced symbols: _ZN12me_primitive11control_rndE
273
+ _ZN11ns_rms_norm5paramE
274
+
275
+ 0x000032d0..0x0000356b ( 668 items) : ../Release/0_0_reloadable5.o::_ZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EE (Function, Weak, .text) (stack frame size = 128)
276
+
277
+ Called functions : _ZL30setup_rmsnorm_row_major_paramsR33rmsnorm_row_major_internal_paramsRA10_Kj
278
+ _ZN12me_primitive10udiv_dstepEjjRjS0_
279
+ _Z23rmsnorm_row_major_part1I8bfloat16EvPT_S2_R33rmsnorm_row_major_internal_params
280
+
281
+ Referenced symbols: _ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE11kernel_iter
282
+ _ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE7core_id
283
+ _ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE8core_row
284
+ _ZN12me_primitive11control_rndE
285
+ _ZN12me_primitive11control_satE
286
+ _ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE8core_col
287
+ _ZN11ns_rms_norm5paramE
288
+
289
+ 0x00003570..0x00003593 ( 36 items) : ../Release/0_0_reloadable5.o::_Z14_b8292_wrapperPPv (Function, Global, .text) (stack frame size = 0)
290
+
291
+ Called functions : _ZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EE
292
+
293
+ 0x000035a0..0x0000384d ( 686 items) : ../Release/0_0_reloadable5.o::_ZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EE (Function, Weak, .text) (stack frame size = 128)
294
+
295
+ Called functions : _ZL30setup_rmsnorm_row_major_paramsR33rmsnorm_row_major_internal_paramsRA10_Kj
296
+
297
+ Referenced symbols: _ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE11kernel_iter
298
+ _ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE7core_id
299
+ _ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_row
300
+ _ZN12me_primitive11control_rndE
301
+ _ZN12me_primitive11control_satE
302
+ _ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_col
303
+ _ZN11ns_rms_norm5paramE
304
+
305
+ 0x00003850..0x00003873 ( 36 items) : ../Release/0_0_reloadable5.o::_Z14_b8300_wrapperPPv (Function, Global, .text) (stack frame size = 0)
306
+
307
+ Called functions : _ZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EE
308
+
309
+ 0x00003880..0x00003b11 ( 658 items) : ../Release/0_0_reloadable5.o::_Z23rmsnorm_row_major_part2I8bfloat16EvPT_S2_S2_S2_R33rmsnorm_row_major_internal_params (Function, Weak, .text) (stack frame size = 64)
310
+
311
+ Referenced symbols: _ZN11ns_rms_norm5paramE
312
+ _ZN12me_primitive11control_rndE
313
+
314
+ 0x00003b20..0x00003d37 ( 536 items) : ../Release/0_0_reloadable5.o::_ZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EE (Function, Weak, .text) (stack frame size = 128)
315
+
316
+ Called functions : _ZL30setup_rmsnorm_row_major_paramsR33rmsnorm_row_major_internal_paramsRA10_Kj
317
+ _Z23rmsnorm_row_major_part2I8bfloat16EvPT_S2_S2_S2_R33rmsnorm_row_major_internal_params
318
+
319
+ Referenced symbols: _ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE11kernel_iter
320
+ _ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE7core_id
321
+ _ZN12me_primitive11control_satE
322
+ _ZN12me_primitive11control_rndE
323
+ _ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_row
324
+ _ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_col
325
+ _ZN11ns_rms_norm5paramE
326
+
327
+ 0x00003d40..0x00003d63 ( 36 items) : ../Release/0_0_reloadable5.o::_Z14_b8308_wrapperPPv (Function, Global, .text) (stack frame size = 0)
328
+
329
+ Called functions : _ZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EE
330
+
331
+ 0x00003d70..0x00003dfd ( 142 items) : me_div.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)::_ZN12me_primitive10udiv_dstepEjjRjS0_ (Function, Global, .text) (stack frame size = 0)
332
+
333
+ External symbols:
334
+
335
+ __dso_handle = 0x0
336
+ _ctors_end = 0x0
337
+ _ctors_start = 0x0
338
+ _dtors_end = 0x0
339
+ _dtors_start = 0x0
340
+ _pc_end = 0x3dfe
341
+ _pc_start = 0x9e0
342
+ _sp_end_DM_stack = 0x7c1c0
343
+ _sp_start_DM_stack = 0x7bd80
344
+
345
+ Section summary for memory 'DM_stack':
346
+
347
+ .stack File
348
+ ---------- ----------
349
+ 1088
350
+ ---------- ----------
351
+ 1088 Total
352
+
353
+ Section summary for memory 'DMb':
354
+
355
+ .bss .data .rodata File
356
+ ---------- ---------- ---------- ----------
357
+ 776 4 32 ../Release/0_0_reloadable5.o
358
+ 5 0 0 me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
359
+ ---------- ---------- ---------- ----------
360
+ 781 4 32 Total
361
+
362
+ Section summary for memory 'PM':
363
+
364
+ .text File
365
+ ---------- ----------
366
+ 12844 ../Release/0_0_reloadable5.o
367
+ 142 me_div.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
368
+ ---------- ----------
369
+ 12986 Total
370
+
371
+ File summary:
372
+
373
+ ../Release/0_0_reloadable5.o
374
+ DMb 812
375
+ PM 12844
376
+
377
+ me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
378
+ DMb 5
379
+
380
+ me_div.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
381
+ PM 142
382
+
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.sdr ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ // File generated by bridge version V-2024.06#84922c0d9f#241219, Fri May 30 11:30:05 2025
3
+ // Copyright 2014-2024 Synopsys, Inc. All rights reserved.
4
+ // bridge -o../Release/0_0_reloadable5 ../Release/0_0_reloadable5.o -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/isg -g -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxxabi-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0_reloadable5.bcf -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/softfloat/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork3577694 -pme
5
+
6
+ // Release: ipp V-2024.06-TGT-241219
7
+
8
+ // Symbols in memory 'DM_bankA':
9
+ // Symbols in memory 'DM_bankAB':
10
+ // Symbols in memory 'DM_bankAC':
11
+ // Symbols in memory 'DM_bankAD':
12
+ // Symbols in memory 'DM_bankB':
13
+ // Symbols in memory 'DM_bankBC':
14
+ // Symbols in memory 'DM_bankBD':
15
+ // Symbols in memory 'DM_bankC':
16
+ // Symbols in memory 'DM_bankCD':
17
+ // Symbols in memory 'DM_bankD':
18
+ // Symbols in memory 'DM_stack':
19
+ // Symbols in memory 'DM_test':
20
+ // Symbols in memory 'DMb':
21
+ _symbol gem_bfp_param 0x0007c200
22
+ _symbol _ZN11ns_rms_norm5paramE 0x0007c360
23
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE7core_id 0x0007c3d8
24
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE8core_row 0x0007c3dc
25
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE8core_col 0x0007c3e0
26
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EEE11kernel_iter 0x0007c3e4
27
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE7core_id 0x0007c3e8
28
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_row 0x0007c3ec
29
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_col 0x0007c3f0
30
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE11kernel_iter 0x0007c3f4
31
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE7core_id 0x0007c3f8
32
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_row 0x0007c3fc
33
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE8core_col 0x0007c400
34
+ _symbol _ZZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EEE11kernel_iter 0x0007c404
35
+ _symbol _ZN12me_primitive11control_satE 0x0007c40c
36
+ _symbol _ZN12me_primitive11control_rndE 0x0007c410
37
+ _symbol add1d_attribute_broadcasting_params 0x0007c480
38
+ _symbol add1d_params 0x0007c4c0
39
+ _symbol mul1d_params 0x0007c500
40
+ _symbol sigmoid1d_params 0x0007c540
41
+ // Symbols in memory 'DMh':
42
+ // Symbols in memory 'DMh_bankA':
43
+ // Symbols in memory 'DMh_bankAB':
44
+ // Symbols in memory 'DMh_bankAC':
45
+ // Symbols in memory 'DMh_bankAD':
46
+ // Symbols in memory 'DMh_bankB':
47
+ // Symbols in memory 'DMh_bankBC':
48
+ // Symbols in memory 'DMh_bankBD':
49
+ // Symbols in memory 'DMh_bankC':
50
+ // Symbols in memory 'DMh_bankCD':
51
+ // Symbols in memory 'DMh_bankD':
52
+ // Symbols in memory 'DMh_stack':
53
+ // Symbols in memory 'DMs':
54
+ // Symbols in memory 'DMs_bankA':
55
+ // Symbols in memory 'DMs_bankAB':
56
+ // Symbols in memory 'DMs_bankAC':
57
+ // Symbols in memory 'DMs_bankAD':
58
+ // Symbols in memory 'DMs_bankB':
59
+ // Symbols in memory 'DMs_bankBC':
60
+ // Symbols in memory 'DMs_bankBD':
61
+ // Symbols in memory 'DMs_bankC':
62
+ // Symbols in memory 'DMs_bankCD':
63
+ // Symbols in memory 'DMs_bankD':
64
+ // Symbols in memory 'DMs_stack':
65
+ // Symbols in memory 'DMv':
66
+ // Symbols in memory 'DMv_bankA':
67
+ // Symbols in memory 'DMv_bankAB':
68
+ // Symbols in memory 'DMv_bankAC':
69
+ // Symbols in memory 'DMv_bankAD':
70
+ // Symbols in memory 'DMv_bankB':
71
+ // Symbols in memory 'DMv_bankBC':
72
+ // Symbols in memory 'DMv_bankBD':
73
+ // Symbols in memory 'DMv_bankC':
74
+ // Symbols in memory 'DMv_bankCD':
75
+ // Symbols in memory 'DMv_bankD':
76
+ // Symbols in memory 'DMv_stack':
77
+ // Symbols in memory 'DMw':
78
+ // Symbols in memory 'DMw_bankA':
79
+ // Symbols in memory 'DMw_bankAB':
80
+ // Symbols in memory 'DMw_bankAC':
81
+ // Symbols in memory 'DMw_bankAD':
82
+ // Symbols in memory 'DMw_bankB':
83
+ // Symbols in memory 'DMw_bankBC':
84
+ // Symbols in memory 'DMw_bankBD':
85
+ // Symbols in memory 'DMw_bankC':
86
+ // Symbols in memory 'DMw_bankCD':
87
+ // Symbols in memory 'DMw_bankD':
88
+ // Symbols in memory 'DMw_stack':
89
+ // Symbols in memory 'DMx':
90
+ // Symbols in memory 'DMx_bankA':
91
+ // Symbols in memory 'DMx_bankAB':
92
+ // Symbols in memory 'DMx_bankAC':
93
+ // Symbols in memory 'DMx_bankAD':
94
+ // Symbols in memory 'DMx_bankB':
95
+ // Symbols in memory 'DMx_bankBC':
96
+ // Symbols in memory 'DMx_bankBD':
97
+ // Symbols in memory 'DMx_bankC':
98
+ // Symbols in memory 'DMx_bankCD':
99
+ // Symbols in memory 'DMx_bankD':
100
+ // Symbols in memory 'DMx_stack':
101
+ // Symbols in memory 'PM':
102
+ _symbol _Z13kernelWrapperPPvjjjj 0x000009e0
103
+ _symbol _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E 0x00000c10
104
+ _symbol _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv 0x00000c30
105
+ _symbol _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E 0x00000cf0
106
+ _symbol _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv 0x00000d30
107
+ _symbol _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E 0x00000d70
108
+ _symbol _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E 0x00000ec0
109
+ _symbol _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE 0x00000f40
110
+ _symbol _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv 0x00001320
111
+ _symbol _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E 0x00001370
112
+ _symbol _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE 0x000014f0
113
+ _symbol _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv 0x000016e0
114
+ _symbol _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv 0x00001760
115
+ _symbol _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E 0x000017e0
116
+ _symbol _Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE 0x00001800
117
+ _symbol _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E 0x00001a60
118
+ _symbol _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv 0x00001a80
119
+ _symbol _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E 0x00001b20
120
+ _symbol _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE 0x00001c60
121
+ _symbol _Z8init_accILt1EEvPaS0_iii 0x000020f0
122
+ _symbol _Z12post_processPai 0x00002220
123
+ _symbol _Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params 0x00002350
124
+ _symbol _Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE 0x00002ae0
125
+ _symbol _Z15_b13786_wrapperPPv 0x00002d10
126
+ _symbol _Z15_b13811_wrapperPPv 0x00002d40
127
+ _symbol _Z15_b13739_wrapperPPv 0x00002d70
128
+ _symbol _Z15_b13744_wrapperPPv 0x00002d90
129
+ _symbol _Z15_b13749_wrapperPPv 0x00002db0
130
+ _symbol _Z23rmsnorm_row_major_part1I8bfloat16EvPT_S2_R33rmsnorm_row_major_internal_params 0x00002f70
131
+ _symbol _ZN12mllib_graphs35rmsnorm_row_major_part1_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_NS3_IS5_NS6_5asyncES9_SB_EEEEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSF_ISG_SI_T1_EERA11_KjRNSF_ISG_NSH_3outET2_EE 0x000032d0
132
+ _symbol _Z14_b8292_wrapperPPv 0x00003570
133
+ _symbol _ZN12mllib_graphs35rmsnorm_row_major_part2_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EE 0x000035a0
134
+ _symbol _Z14_b8300_wrapperPPv 0x00003850
135
+ _symbol _Z23rmsnorm_row_major_part2I8bfloat16EvPT_S2_S2_S2_R33rmsnorm_row_major_internal_params 0x00003880
136
+ _symbol _ZN12mllib_graphs35rmsnorm_row_major_part3_4x4_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_SC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERNSD_ISE_SG_T1_EERA11_KjRNSD_ISE_NSF_3outET2_EE 0x00003b20
137
+ _symbol _Z14_b8308_wrapperPPv 0x00003d40
138
+ _symbol _ZN12me_primitive10udiv_dstepEjjRjS0_ 0x00003d70
139
+ // Symbols in memory 'PMw':
140
+ // Symbols in memory 'TM4':
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.srv ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/Release/1_3_reloadable53.txt ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/scripts/1_3_reloadable53.bcf ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _reserved DMb 0x0 0x40000
2
+
3
+ _reserved PM 0x0 0x9e0 //reserved for main elf
4
+
5
+ _entry_point _Z13kernelWrapperPPvjjjj
6
+ _symbol _Z13kernelWrapperPPvjjjj 0x9e0
7
+
8
+ _reserved DMb 0x7b540 0x800 //reserved for lcp ping-pong buffers
9
+ _reserved DMb 0x7bd40 0x40 //reserved for sync buffer
10
+ _stack DM_stack 0x7bd80 0x440 //stack for core
11
+ _reserved DMb 0x7c1c0 0x40 //reserved for main elf heap
12
+ //space for synopsys compiler at 0x7c200 0x800//heap
13
+ _reserved DMb 0x40000 0x3b540
14
+
15
+ _reserved DMb 0x7ca00 0x3600
16
+ _reserved DMb 0x80000 0x80000 // And everything else the core can't see
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/scripts/1_3_reloadable53.prx ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <project name="Project" processor="me">
2
+ <issinit/>
3
+ <option id="cpp.define" value="__AIENGINE__ __AIE_ARCH__=21" inherit = "1"/>
4
+ <option id="llvm.xargs" value="-fno-jump-tables -fno-discard-value-names" inherit = "1"/>
5
+ <option id="llvm.lang" value="Follow file extension"/>
6
+ <option id="bridge.cfg" value="1_3_reloadable53.bcf"/>
7
+ <option id="bridge.alibs" value=" ../Release/1_3_reloadable53.o" inherit="1" cfg="Release_LLVM"/>
8
+ <option id="cpp.include" value="&lt;XILINX_VITIS_AIETOOLS&gt;/include /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc /proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/&lt;AIE_SRC_DIR&gt;/ /proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/&lt;AIE_SRC_DIR&gt; " inherit="1"/>
9
+ <option id="project.dir" value="&lt;CONFIG&gt;/1_3_reloadable53"/>
10
+ <option id="project.name" value="1_3_reloadable53"/>
11
+ <option id="project.type" value="exe"/>
12
+ <option id="simrun.issca" value="&lt;XILINX_VITIS_AIETOOLS&gt;/bin/unwrapped/lnx64.o/aie2p/ca_udm_dbg" inherit="0"/>
13
+ </project>
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable53/src/1_3_reloadable53.cc ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ // Automatically generated processor driver using AIEngine tool-chain
2
+
3
+ #include <stdio.h>
4
+ #include <memory>
5
+ #include <adf.h>
6
+
7
+
8
+ // Declare Kernel functions and initializers
9
+ void superkernel_GemmBfp16(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[7],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
10
+ void superkernel_add1d(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict,adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
11
+ void superkernel_add1d_attribute_broadcasting(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
12
+ void superkernel_sigmoid1d(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
13
+ void superkernel_mul1d(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict,const unsigned int (&)[16],adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict,adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict);
14
+ #include "rms_norm_adf_wrapper.cpp"
15
+
16
+ // Declare Kernel objects and external arrays
17
+
18
+
19
+ void _b13786_wrapper(void* args[])
20
+ {
21
+ superkernel_GemmBfp16(
22
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
23
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
24
+ *reinterpret_cast<uint32 const(*)[7]>(args[3]),
25
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[2]));
26
+ }
27
+
28
+ void _b13811_wrapper(void* args[])
29
+ {
30
+ superkernel_add1d(
31
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
32
+ *reinterpret_cast<uint32 const(*)[16]>(args[3]),
33
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]),
34
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[2]));
35
+ }
36
+
37
+ void _b13739_wrapper(void* args[])
38
+ {
39
+ superkernel_add1d_attribute_broadcasting(
40
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
41
+ *reinterpret_cast<uint32 const(*)[16]>(args[2]),
42
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]));
43
+ }
44
+
45
+ void _b13744_wrapper(void* args[])
46
+ {
47
+ superkernel_sigmoid1d(
48
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
49
+ *reinterpret_cast<uint32 const(*)[16]>(args[2]),
50
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]));
51
+ }
52
+
53
+ void _b13749_wrapper(void* args[])
54
+ {
55
+ superkernel_mul1d(
56
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
57
+ *reinterpret_cast<uint32 const(*)[16]>(args[3]),
58
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[1]),
59
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[2]));
60
+ }
61
+
62
+ void _b8292_wrapper(void* args[])
63
+ {
64
+ mllib_graphs::rmsnorm_row_major_part1_4x4_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>, adf::locking::async>>(
65
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
66
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
67
+ *reinterpret_cast<uint32 const(*)[11]>(args[3]),
68
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_async_0d>*>(args[2]));
69
+ }
70
+
71
+ void _b8300_wrapper(void* args[])
72
+ {
73
+ mllib_graphs::rmsnorm_row_major_part2_4x4_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
74
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
75
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
76
+ *reinterpret_cast<uint32 const(*)[11]>(args[3]),
77
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[2]));
78
+ }
79
+
80
+ void _b8308_wrapper(void* args[])
81
+ {
82
+ mllib_graphs::rmsnorm_row_major_part3_4x4_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(
83
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[0]),
84
+ *reinterpret_cast<adf::input_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[1]),
85
+ *reinterpret_cast<uint32 const(*)[11]>(args[3]),
86
+ *reinterpret_cast<adf::output_buffer_conf<bfloat16, adf::bpc_sync_0d>*>(args[2]));
87
+ }
88
+
89
+ using UniformKernelFunc = void (*)(void **);
90
+
91
+ static UniformKernelFunc g_uniformKernelFuncs[8] = {
92
+ _b13786_wrapper,
93
+ _b13811_wrapper,
94
+ _b13739_wrapper,
95
+ _b13744_wrapper,
96
+ _b13749_wrapper,
97
+ _b8292_wrapper,
98
+ _b8300_wrapper,
99
+ _b8308_wrapper
100
+ };
101
+
102
+ __attribute__((always_inline)) void kernelWrapper(void* args[], uint32 kernelId, uint32 numSyncIn, uint32 numAsyncIn, uint32 numSyncOut)
103
+ {
104
+ uint32 idx = 0;
105
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::in>(numSyncIn > 0);
106
+ idx += (numSyncIn > 0) ? 1 : 0;
107
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::in>(numSyncIn > 1);
108
+ idx += (numSyncIn > 1) ? 1 : 0;
109
+ idx += numAsyncIn;
110
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->acquire<adf::direction::out>(numSyncOut > 0);
111
+ idx += (numSyncOut > 0) ? 1 : 0;
112
+
113
+ (*(g_uniformKernelFuncs[kernelId]))(args);
114
+
115
+ idx = 0;
116
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::in>(numSyncIn > 0);
117
+ idx += (numSyncIn > 0) ? 1 : 0;
118
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::in>(numSyncIn > 1);
119
+ idx += (numSyncIn > 1) ? 1 : 0;
120
+ idx += numAsyncIn;
121
+ reinterpret_cast<adf::_io_buffer_light_weight_generic*>(args[idx])->release<adf::direction::out>(numSyncOut > 0);
122
+ idx += (numSyncOut > 0) ? 1 : 0;
123
+ }
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable54/Release/1_3_reloadable54.calltree ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ // File generated by bridge version V-2024.06#84922c0d9f#241219, Fri May 30 11:30:02 2025
3
+ // Copyright 2014-2024 Synopsys, Inc. All rights reserved.
4
+ // bridge -o../Release/0_0_reloadable6 ../Release/0_0_reloadable6.o -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/isg -g -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxxabi-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0_reloadable6.bcf -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/softfloat/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork3577696 -pme
5
+
6
+
7
+ // Release: ipp V-2024.06-TGT-241219
8
+
9
+ _Z13kernelWrapperPPvjjjj
10
+ _Z15_b14285_wrapperPPv (referenced text)
11
+ _Z17superkernel_sub1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
12
+ _ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE5setupER27elementwise_binary_params_tIS4_EPKv
13
+ _ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE21shared_setup_backboneER27elementwise_binary_params_tIS4_EPKv
14
+ _ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS4_E
15
+ _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE
16
+ _Z15_b14290_wrapperPPv (referenced text)
17
+ _Z40superkernel_mul1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
18
+ _ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE5setupER27elementwise_binary_params_tIS4_EPKv
19
+ _ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE21shared_setup_backboneER27elementwise_binary_params_tIS4_EPKv
20
+ _ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE3runEPS0_S7_R27elementwise_binary_params_tIS4_E
21
+ _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE (*)
22
+ _Z15_b13811_wrapperPPv (referenced text)
23
+ _Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
24
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv
25
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv
26
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
27
+ _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE (*)
28
+ _Z15_b13786_wrapperPPv (referenced text)
29
+ _Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
30
+ _ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv
31
+ _Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params
32
+ _Z8init_accILt1EEvPaS0_iii
33
+ _Z12post_processPai
34
+ _Z15_b13739_wrapperPPv (referenced text)
35
+ _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
36
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
37
+ _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
38
+ _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
39
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E
40
+ _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
41
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
42
+ _Z15_b13744_wrapperPPv (referenced text)
43
+ _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
44
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
45
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
46
+ _Z15_b13749_wrapperPPv (referenced text)
47
+ _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
48
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
49
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
50
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
51
+ _Z14_b8096_wrapperPPv (referenced text)
52
+ _ZN12mllib_graphs14expand_wrapperI8bfloat16EEvRN3adf9io_bufferIT_NS2_9direction2inENS2_16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEEEERA3_KjRNS3_IS4_NS5_3outESG_EE
53
+ _Z14_b8127_wrapperPPv (referenced text)
54
+ _Z27gather_elements_adf_wrapperI8bfloat16iN3adf16io_buffer_configINS1_7extentsIJEEENS1_7locking4syncENS1_10addressing6linearENS1_6marginILj0EEEEESB_SB_EvRNS1_9io_bufferIT_NS1_9direction2inET1_EERNSC_IT0_SF_T2_EERA16_KjRNSC_ISD_NSE_3outET3_EE
55
+ _Z14_b8134_wrapperPPv (referenced text)
56
+ _ZN12mllib_graphs19softmax_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERA8_KjRNSD_ISE_NSF_3outET1_EE
57
+ _Z17softmax_row_majorILi1E8bfloat16S0_Lt1EEvPT0_PT1_33softmax_row_major_internal_params
58
+
59
+
60
+ Call tree stack and functions sizes:
61
+
62
+ stack stack stack call func func function name
63
+ desc level level desc
64
+ ----- ----- ----- ----- ----- ----- --------------------------------------------------------------
65
+ 64 256 0 0 546 13068 _Z13kernelWrapperPPvjjjj
66
+ 0 128 1 1 36 1340 _Z15_b14285_wrapperPPv
67
+ 64 128 1 2 602 1304 _Z17superkernel_sub1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE <tail call>
68
+ 64 64 2 3 76 198 _ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE5setupER27elementwise_binary_params_tIS4_EPKv
69
+ 0 0 3 4 122 122 _ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE21shared_setup_backboneER27elementwise_binary_params_tIS4_EPKv
70
+ 0 64 2 3 20 504 _ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS4_E
71
+ 64 64 2 4 484 484 _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE <tail call>
72
+ 0 192 1 1 32 1352 _Z15_b14290_wrapperPPv
73
+ 64 192 1 2 488 1320 _Z40superkernel_mul1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
74
+ 64 64 2 3 76 198 _ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE5setupER27elementwise_binary_params_tIS4_EPKv
75
+ 0 0 3 4 122 122 _ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE21shared_setup_backboneER27elementwise_binary_params_tIS4_EPKv
76
+ 64 128 2 3 150 634 _ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE3runEPS0_S7_R27elementwise_binary_params_tIS4_E
77
+ 64 64 3 4 484 484 _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE
78
+ 0 128 1 1 36 1378 _Z15_b13811_wrapperPPv
79
+ 64 128 1 2 602 1342 _Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE <tail call>
80
+ 64 64 2 3 114 236 _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv
81
+ 0 0 3 4 122 122 _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv
82
+ 0 64 2 3 20 504 _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
83
+ 64 64 2 4 484 484 _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE <tail call>
84
+ 0 192 1 1 36 3650 _Z15_b13786_wrapperPPv
85
+ 64 192 1 2 546 3614 _Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
86
+ 0 0 2 3 550 550 _ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv
87
+ 64 128 2 3 1930 2518 _Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params
88
+ 64 64 3 4 294 294 _Z8init_accILt1EEvPaS0_iii
89
+ 0 0 3 4 294 294 _Z12post_processPai
90
+ 0 192 1 1 32 1282 _Z15_b13739_wrapperPPv
91
+ 64 192 1 2 488 1250 _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
92
+ 64 128 2 3 60 318 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
93
+ 64 64 3 4 178 202 _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
94
+ 0 0 4 5 24 24 _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
95
+ 0 0 2 4 56 56 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E <tail call>
96
+ 128 128 2 3 114 444 _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
97
+ 0 0 3 4 330 330 _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
98
+ 0 64 1 1 32 966 _Z15_b13744_wrapperPPv
99
+ 64 64 1 2 488 934 _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE <tail call>
100
+ 0 0 2 3 68 68 _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
101
+ 0 0 2 3 378 378 _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
102
+ 0 128 1 1 36 1124 _Z15_b13749_wrapperPPv
103
+ 64 128 1 2 602 1088 _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE <tail call>
104
+ 64 64 2 3 154 178 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
105
+ 0 0 3 4 24 24 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
106
+ 0 0 2 3 308 308 _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
107
+ 0 0 1 1 32 434 _Z14_b8096_wrapperPPv
108
+ 0 0 1 2 402 402 _ZN12mllib_graphs14expand_wrapperI8bfloat16EEvRN3adf9io_bufferIT_NS2_9direction2inENS2_16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEEEERA3_KjRNS3_IS4_NS5_3outESG_EE <tail call>
109
+ 0 0 1 1 36 436 _Z14_b8127_wrapperPPv
110
+ 0 0 1 2 400 400 _Z27gather_elements_adf_wrapperI8bfloat16iN3adf16io_buffer_configINS1_7extentsIJEEENS1_7locking4syncENS1_10addressing6linearENS1_6marginILj0EEEEESB_SB_EvRNS1_9io_bufferIT_NS1_9direction2inET1_EERNSC_IT0_SF_T2_EERA16_KjRNSC_ISD_NSE_3outET3_EE <tail call>
111
+ 0 128 1 1 32 1528 _Z14_b8134_wrapperPPv
112
+ 128 128 1 2 456 1496 _ZN12mllib_graphs19softmax_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERA8_KjRNSD_ISE_NSF_3outET1_EE <tail call>
113
+ 0 0 2 3 1040 1040 _Z17softmax_row_majorILi1E8bfloat16S0_Lt1EEvPT0_PT1_33softmax_row_major_internal_params
114
+
115
+
116
+ Maximum call level : 5
117
+ Maximum stack level: 4
118
+ Maximum stack size : 256
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable54/Release/1_3_reloadable54.cmic2 ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable54/Release/1_3_reloadable54.cmico ADDED
@@ -0,0 +1 @@
 
 
1
+ +Mdec
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable54/Release/1_3_reloadable54.lst ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/aie/1_3_reloadable54/Release/1_3_reloadable54.map ADDED
@@ -0,0 +1,400 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ // File generated by bridge version V-2024.06#84922c0d9f#241219, Fri May 30 11:30:02 2025
3
+ // Copyright 2014-2024 Synopsys, Inc. All rights reserved.
4
+ // bridge -o../Release/0_0_reloadable6 ../Release/0_0_reloadable6.o -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/isg -g -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/./encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/backend -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/include/aie_api -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/include/common -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L1/include/misc -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/vitis_mllib/L2/src/ml_adf -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/vaiml_int/staff/praveeni/csr_iswarya_zoom_models/run/results_6562/2025.2_PCIE_ISV_BF16_O2_STX_WIN_hw_lin_lin_x86/encoder-epoch-99-avg-1-T-151_static_20250527144825/TEST_WORK_20250529_154000_CSR_6562_IPU_STX_WIN_flexml_rai_1_4_lnx64/encoder-epoch-99-avg-1-T-151_static_20250527144825/vaiml_par_0/0/aiecompiler/. -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libs/libcxxabi-16/include -I/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0_reloadable6.bcf -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/softfloat/lib/Release -L/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork3577696 -pme
5
+
6
+ // Release: ipp V-2024.06-TGT-241219
7
+
8
+ Memory map for memory 'DM_stack':
9
+
10
+ Size = 1048576
11
+ Width = 8 bits
12
+ Offset = 0
13
+ Used = 1088
14
+
15
+ 0x0007bd80..0x0007c1bf ( 1088 items) : Stack
16
+
17
+ Memory map for memory 'DMb':
18
+
19
+ Size = 1048576
20
+ Width = 8 bits
21
+ Offset = 0
22
+ Used = 1969
23
+
24
+ 0x00000000..0x0007bd7f ( 507264 items) : Reserved
25
+ 0x0007bd80..0x0007c1bf ( 1088 items) : Stack
26
+ 0x0007c1c0..0x0007c1ff ( 64 items) : Reserved
27
+ 0x0007c200..0x0007c35f ( 352 items) : ../Release/0_0_reloadable6.o::gem_bfp_param (Data, Global, .bss.DMb.32)
28
+ 0x0007c360..0x0007c363 ( 4 items) : ../Release/0_0_reloadable6.o::_ZL9curr_iter (Data, Local, .bss.DMb.4)
29
+ 0x0007c364..0x0007c367 ( 4 items) : ../Release/0_0_reloadable6.o::_ZL10depth_iter (Data, Local, .bss.DMb.4)
30
+ 0x0007c368..0x0007c36b ( 4 items) : ../Release/0_0_reloadable6.o::_ZL11total_iters (Data, Local, .bss.DMb.4)
31
+ 0x0007c36c..0x0007c36f ( 4 items) : ../Release/0_0_reloadable6.o::_ZL8core_row (Data, Local, .bss.DMb.4)
32
+ 0x0007c370..0x0007c373 ( 4 items) : ../Release/0_0_reloadable6.o::_ZL11ifm1_offset (Data, Local, .bss.DMb.4)
33
+ 0x0007c374..0x0007c377 ( 4 items) : ../Release/0_0_reloadable6.o::_ZL11ifm2_offset (Data, Local, .bss.DMb.4)
34
+ 0x0007c378..0x0007c37b ( 4 items) : ../Release/0_0_reloadable6.o::_ZN12mllib_graphs9ns_expandL11kernel_iterE (Data, Local, .bss.DMb.4)
35
+ 0x0007c37c..0x0007c37f ( 4 items) : ../Release/0_0_reloadable6.o::_ZN12mllib_graphs9ns_expandL8core_rowE (Data, Local, .bss.DMb.4)
36
+ 0x0007c380..0x0007c383 ( 4 items) : ../Release/0_0_reloadable6.o::_ZL8num_iter (Data, Local, .data.DMb.4)
37
+ 0x0007c384..0x0007c387 ( 4 items) : me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)::_ZN12me_primitive11control_satE (Data, Global, .bss.DMb.4)
38
+ 0x0007c388..0x0007c388 ( 1 items) : me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)::_ZN12me_primitive11control_rndE (Data, Global, .bss.DMb.1)
39
+ 0x0007c3c0..0x0007c3e7 ( 40 items) : ../Release/0_0_reloadable6.o::_ZL20g_uniformKernelFuncs (Data, Local, .rodata.DMb.64)
40
+
41
+ Called functions : _Z15_b14285_wrapperPPv
42
+ _Z15_b14290_wrapperPPv
43
+ _Z15_b13811_wrapperPPv
44
+ _Z15_b13786_wrapperPPv
45
+ _Z15_b13739_wrapperPPv
46
+ _Z15_b13744_wrapperPPv
47
+ _Z15_b13749_wrapperPPv
48
+ _Z14_b8096_wrapperPPv
49
+ _Z14_b8127_wrapperPPv
50
+ _Z14_b8134_wrapperPPv
51
+
52
+ 0x0007c400..0x0007c43f ( 64 items) : ../Release/0_0_reloadable6.o::_ZZN12mllib_graphs19softmax_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERA8_KjRNSD_ISE_NSF_3outET1_EEE9sm_params (Data, Weak, .data.DMb.32)
53
+ 0x0007c440..0x0007c47f ( 64 items) : ../Release/0_0_reloadable6.o::add1d_attribute_broadcasting_params (Data, Global, .bss.DMb.64)
54
+ 0x0007c480..0x0007c4bf ( 64 items) : ../Release/0_0_reloadable6.o::mul1d_attribute_broadcasting_params (Data, Global, .bss.DMb.64)
55
+ 0x0007c4c0..0x0007c4ff ( 64 items) : ../Release/0_0_reloadable6.o::add1d_params (Data, Global, .bss.DMb.64)
56
+ 0x0007c500..0x0007c53f ( 64 items) : ../Release/0_0_reloadable6.o::mul1d_params (Data, Global, .bss.DMb.64)
57
+ 0x0007c540..0x0007c57f ( 64 items) : ../Release/0_0_reloadable6.o::sub1d_params (Data, Global, .bss.DMb.64)
58
+ 0x0007c580..0x0007c5bf ( 64 items) : ../Release/0_0_reloadable6.o::sigmoid1d_params (Data, Global, .bss.DMb.64)
59
+ 0x0007ca00..0x000fffff ( 538112 items) : Reserved
60
+
61
+ Memory map for memory 'PM':
62
+
63
+ Size = 1048576
64
+ Width = 8 bits
65
+ Offset = 0
66
+ Used = 13068
67
+
68
+ 0x00000000..0x000009df ( 2528 items) : Reserved
69
+ 0x000009e0..0x00000c01 ( 546 items) : ../Release/0_0_reloadable6.o::_Z13kernelWrapperPPvjjjj (Function, Global, .text) (stack frame size = 64)
70
+
71
+ Referenced symbols: _ZL20g_uniformKernelFuncs
72
+
73
+ 0x00000c10..0x00000c27 ( 24 items) : ../Release/0_0_reloadable6.o::_ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
74
+
75
+ Referenced symbols: add1d_attribute_broadcasting_params
76
+
77
+ 0x00000c30..0x00000ce1 ( 178 items) : ../Release/0_0_reloadable6.o::_ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 64)
78
+
79
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_E
80
+
81
+ Referenced symbols: add1d_attribute_broadcasting_params
82
+
83
+ 0x00000cf0..0x00000d27 ( 56 items) : ../Release/0_0_reloadable6.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
84
+
85
+ Referenced symbols: add1d_attribute_broadcasting_params
86
+
87
+ 0x00000d30..0x00000d6b ( 60 items) : ../Release/0_0_reloadable6.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 64)
88
+
89
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS5_EPKv
90
+ _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_E
91
+
92
+ Referenced symbols: add1d_attribute_broadcasting_params
93
+
94
+ 0x00000d70..0x00000eb9 ( 330 items) : ../Release/0_0_reloadable6.o::_ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
95
+
96
+ Referenced symbols: add1d_attribute_broadcasting_params
97
+ _ZN12me_primitive11control_rndE
98
+
99
+ 0x00000ec0..0x00000f31 ( 114 items) : ../Release/0_0_reloadable6.o::_ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 128)
100
+
101
+ Called functions : _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
102
+
103
+ Referenced symbols: add1d_attribute_broadcasting_params
104
+
105
+ 0x00000f40..0x00001127 ( 488 items) : ../Release/0_0_reloadable6.o::_Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
106
+
107
+ Called functions : _ZN31elementwise_binary_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE5setupER27elementwise_binary_params_tIS5_EPKv
108
+ _ZN41elementwise_binary_attribute_broadcastingI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_EE3runEPS0_S7_R27elementwise_binary_params_tIS5_E
109
+
110
+ Referenced symbols: _ZL9curr_iter
111
+ _ZL8core_row
112
+ add1d_attribute_broadcasting_params
113
+ _ZN12me_primitive11control_rndE
114
+ _ZN12me_primitive11control_satE
115
+ _ZL11ifm1_offset
116
+ _ZL8num_iter
117
+
118
+ 0x00001130..0x000011a9 ( 122 items) : ../Release/0_0_reloadable6.o::_ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE21shared_setup_backboneER27elementwise_binary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 0)
119
+
120
+ Referenced symbols: mul1d_attribute_broadcasting_params
121
+
122
+ 0x000011b0..0x000011fb ( 76 items) : ../Release/0_0_reloadable6.o::_ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE5setupER27elementwise_binary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 64)
123
+
124
+ Called functions : _ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE21shared_setup_backboneER27elementwise_binary_params_tIS4_EPKv
125
+
126
+ Referenced symbols: mul1d_attribute_broadcasting_params
127
+
128
+ 0x00001200..0x000013e3 ( 484 items) : ../Release/0_0_reloadable6.o::_ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE (Function, Local, .text) (stack frame size = 64)
129
+
130
+ Referenced symbols: _ZN12me_primitive11control_rndE
131
+
132
+ 0x000013f0..0x00001485 ( 150 items) : ../Release/0_0_reloadable6.o::_ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE3runEPS0_S7_R27elementwise_binary_params_tIS4_E (Function, Weak, .text) (stack frame size = 64)
133
+
134
+ Called functions : _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE
135
+
136
+ Referenced symbols: mul1d_attribute_broadcasting_params
137
+
138
+ 0x00001490..0x00001677 ( 488 items) : ../Release/0_0_reloadable6.o::_Z40superkernel_mul1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
139
+
140
+ Called functions : _ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE5setupER27elementwise_binary_params_tIS4_EPKv
141
+ _ZN25elementwise_binary_sharedI8bfloat1626mul_impl_broadcasting_attrIS0_E15shared_params_tIS0_EL5act_t0EE3runEPS0_S7_R27elementwise_binary_params_tIS4_E
142
+
143
+ Referenced symbols: _ZL9curr_iter
144
+ _ZL8core_row
145
+ mul1d_attribute_broadcasting_params
146
+ _ZN12me_primitive11control_rndE
147
+ _ZN12me_primitive11control_satE
148
+ _ZL11ifm1_offset
149
+ _ZL8num_iter
150
+
151
+ 0x00001680..0x000016c3 ( 68 items) : ../Release/0_0_reloadable6.o::_ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 0)
152
+
153
+ Referenced symbols: sigmoid1d_params
154
+
155
+ 0x000016d0..0x00001849 ( 378 items) : ../Release/0_0_reloadable6.o::_ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
156
+
157
+ Referenced symbols: sigmoid1d_params
158
+ _ZN12me_primitive11control_rndE
159
+
160
+ 0x00001850..0x00001a37 ( 488 items) : ../Release/0_0_reloadable6.o::_Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
161
+
162
+ Called functions : _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE5setupER26elementwise_unary_params_tIS4_EPKv
163
+ _ZN17elementwise_unaryI8bfloat1619elementwise_sigmoidIS0_E26sigmoid_templated_params_tIS0_EE3runEPS0_S6_R26elementwise_unary_params_tIS4_E
164
+
165
+ Referenced symbols: _ZL9curr_iter
166
+ _ZL8core_row
167
+ sigmoid1d_params
168
+ _ZN12me_primitive11control_rndE
169
+ _ZN12me_primitive11control_satE
170
+ _ZL11ifm1_offset
171
+ _ZL8num_iter
172
+
173
+ 0x00001a40..0x00001ab9 ( 122 items) : ../Release/0_0_reloadable6.o::_ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 0)
174
+
175
+ Referenced symbols: add1d_params
176
+
177
+ 0x00001ac0..0x00001b31 ( 114 items) : ../Release/0_0_reloadable6.o::_ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv (Function, Weak, .text) (stack frame size = 64)
178
+
179
+ Called functions : _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE21shared_setup_backboneER27elementwise_binary_params_tIS5_EPKv
180
+
181
+ Referenced symbols: add1d_params
182
+
183
+ 0x00001b40..0x00001b53 ( 20 items) : ../Release/0_0_reloadable6.o::_ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E (Function, Weak, .text) (stack frame size = 0)
184
+
185
+ Called functions : _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE
186
+
187
+ Referenced symbols: add1d_params
188
+
189
+ 0x00001b60..0x00001db9 ( 602 items) : ../Release/0_0_reloadable6.o::_Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE (Function, Global, .text) (stack frame size = 64)
190
+
191
+ Called functions : _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE5setupER27elementwise_binary_params_tIS5_EPKv
192
+ _ZN25elementwise_binary_sharedI8bfloat168add_implIS0_L5act_t0EE15shared_params_tIS0_ELS2_0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS5_E
193
+
194
+ Referenced symbols: _ZL9curr_iter
195
+ _ZL8core_row
196
+ add1d_params
197
+ _ZN12me_primitive11control_rndE
198
+ _ZN12me_primitive11control_satE
199
+ _ZL11ifm1_offset
200
+ _ZL11ifm2_offset
201
+ _ZL8num_iter
202
+
203
+ 0x00001dc0..0x00001dd7 ( 24 items) : ../Release/0_0_reloadable6.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
204
+
205
+ Referenced symbols: mul1d_params
206
+
207
+ 0x00001de0..0x00001e79 ( 154 items) : ../Release/0_0_reloadable6.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 64)
208
+
209
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_E
210
+
211
+ Referenced symbols: mul1d_params
212
+
213
+ 0x00001e80..0x00001fb3 ( 308 items) : ../Release/0_0_reloadable6.o::_ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
214
+
215
+ Referenced symbols: mul1d_params
216
+ _ZN12me_primitive11control_rndE
217
+
218
+ 0x00001fc0..0x00002219 ( 602 items) : ../Release/0_0_reloadable6.o::_Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE (Function, Global, .text) (stack frame size = 64)
219
+
220
+ Called functions : _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE5setupER27elementwise_binary_params_tIS4_EPKv
221
+ _ZN18elementwise_binaryIJ8bfloat168mul_implIS0_E15shared_params_tIS0_EEE3runEPS0_S6_S6_R27elementwise_binary_params_tIS4_E
222
+
223
+ Referenced symbols: _ZL9curr_iter
224
+ _ZL8core_row
225
+ mul1d_params
226
+ _ZN12me_primitive11control_rndE
227
+ _ZN12me_primitive11control_satE
228
+ _ZL11ifm1_offset
229
+ _ZL11ifm2_offset
230
+ _ZL8num_iter
231
+
232
+ 0x00002220..0x00002299 ( 122 items) : ../Release/0_0_reloadable6.o::_ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE21shared_setup_backboneER27elementwise_binary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 0)
233
+
234
+ Referenced symbols: sub1d_params
235
+
236
+ 0x000022a0..0x000022eb ( 76 items) : ../Release/0_0_reloadable6.o::_ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE5setupER27elementwise_binary_params_tIS4_EPKv (Function, Weak, .text) (stack frame size = 64)
237
+
238
+ Called functions : _ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE21shared_setup_backboneER27elementwise_binary_params_tIS4_EPKv
239
+
240
+ Referenced symbols: sub1d_params
241
+
242
+ 0x000022f0..0x00002303 ( 20 items) : ../Release/0_0_reloadable6.o::_ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS4_E (Function, Weak, .text) (stack frame size = 0)
243
+
244
+ Called functions : _ZL19shared_run_backboneI8bfloat16L5act_t0EEKvPT_S4_S4_R27elementwise_binary_params_tI15shared_params_tIS3_EE
245
+
246
+ Referenced symbols: sub1d_params
247
+
248
+ 0x00002310..0x00002569 ( 602 items) : ../Release/0_0_reloadable6.o::_Z17superkernel_sub1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE (Function, Global, .text) (stack frame size = 64)
249
+
250
+ Called functions : _ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE5setupER27elementwise_binary_params_tIS4_EPKv
251
+ _ZN25elementwise_binary_sharedI8bfloat168sub_implIS0_E15shared_params_tIS0_EL5act_t0EE3runEPS0_S7_S7_R27elementwise_binary_params_tIS4_E
252
+
253
+ Referenced symbols: _ZL9curr_iter
254
+ _ZL8core_row
255
+ sub1d_params
256
+ _ZN12me_primitive11control_rndE
257
+ _ZN12me_primitive11control_satE
258
+ _ZL11ifm1_offset
259
+ _ZL11ifm2_offset
260
+ _ZL8num_iter
261
+
262
+ 0x00002570..0x00002795 ( 550 items) : ../Release/0_0_reloadable6.o::_ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv (Function, Local, .text) (stack frame size = 0)
263
+
264
+ Referenced symbols: gem_bfp_param
265
+
266
+ 0x000027a0..0x000028c5 ( 294 items) : ../Release/0_0_reloadable6.o::_Z8init_accILt1EEvPaS0_iii (Function, Weak, .text) (stack frame size = 64)
267
+
268
+ Referenced symbols: _ZN12me_primitive11control_rndE
269
+
270
+ 0x000028d0..0x000029f5 ( 294 items) : ../Release/0_0_reloadable6.o::_Z12post_processPai (Function, Weak, .text) (stack frame size = 0)
271
+
272
+ Referenced symbols: _ZN12me_primitive11control_rndE
273
+
274
+ 0x00002a00..0x00003189 ( 1930 items) : ../Release/0_0_reloadable6.o::_Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params (Function, Weak, .text) (stack frame size = 64)
275
+
276
+ Called functions : _Z8init_accILt1EEvPaS0_iii
277
+ _Z12post_processPai
278
+
279
+ Referenced symbols: gem_bfp_param
280
+ _ZN12me_primitive11control_satE
281
+ _ZN12me_primitive11control_rndE
282
+
283
+ 0x00003190..0x000033b1 ( 546 items) : ../Release/0_0_reloadable6.o::_Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE (Function, Global, .text) (stack frame size = 64)
284
+
285
+ Called functions : _ZL23setup_gemm_bfp16_paramsR17gemm_bfp16_paramsPKv
286
+ _Z10gemm_bfp16I8bfloat16Lt1ELj1EQsr3stdE9is_same_vIT_S0_EEvPS1_S2_S2_S2_R17gemm_bfp16_params
287
+
288
+ Referenced symbols: _ZL9curr_iter
289
+ _ZN12me_primitive11control_rndE
290
+ _ZN12me_primitive11control_satE
291
+ _ZL11total_iters
292
+ _ZL10depth_iter
293
+ gem_bfp_param
294
+
295
+ 0x000033c0..0x000033e3 ( 36 items) : ../Release/0_0_reloadable6.o::_Z15_b14285_wrapperPPv (Function, Global, .text) (stack frame size = 0)
296
+
297
+ Called functions : _Z17superkernel_sub1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
298
+
299
+ 0x000033f0..0x0000340f ( 32 items) : ../Release/0_0_reloadable6.o::_Z15_b14290_wrapperPPv (Function, Global, .text) (stack frame size = 0)
300
+
301
+ Called functions : _Z40superkernel_mul1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
302
+
303
+ 0x00003410..0x00003433 ( 36 items) : ../Release/0_0_reloadable6.o::_Z15_b13811_wrapperPPv (Function, Global, .text) (stack frame size = 0)
304
+
305
+ Called functions : _Z17superkernel_add1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
306
+
307
+ 0x00003440..0x00003463 ( 36 items) : ../Release/0_0_reloadable6.o::_Z15_b13786_wrapperPPv (Function, Global, .text) (stack frame size = 0)
308
+
309
+ Called functions : _Z21superkernel_GemmBfp16RN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEESF_RA7_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
310
+
311
+ 0x00003470..0x0000348f ( 32 items) : ../Release/0_0_reloadable6.o::_Z15_b13739_wrapperPPv (Function, Global, .text) (stack frame size = 0)
312
+
313
+ Called functions : _Z40superkernel_add1d_attribute_broadcastingRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
314
+
315
+ 0x00003490..0x000034af ( 32 items) : ../Release/0_0_reloadable6.o::_Z15_b13744_wrapperPPv (Function, Global, .text) (stack frame size = 0)
316
+
317
+ Called functions : _Z21superkernel_sigmoid1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_NS2_3outENS4_IS6_NS7_5asyncESA_SC_EEEE
318
+
319
+ 0x000034b0..0x000034d3 ( 36 items) : ../Release/0_0_reloadable6.o::_Z15_b13749_wrapperPPv (Function, Global, .text) (stack frame size = 0)
320
+
321
+ Called functions : _Z17superkernel_mul1dRN3adf9io_bufferI8bfloat16NS_9direction2inENS_16io_buffer_configINS_7extentsIJEEENS_7locking4syncENS_10addressing6linearENS_6marginILj0EEEEEEERA16_KjRNS0_IS1_S3_NS4_IS6_NS7_5asyncESA_SC_EEEERNS0_IS1_NS2_3outESK_EE
322
+
323
+ 0x000034e0..0x00003671 ( 402 items) : ../Release/0_0_reloadable6.o::_ZN12mllib_graphs14expand_wrapperI8bfloat16EEvRN3adf9io_bufferIT_NS2_9direction2inENS2_16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEEEERA3_KjRNS3_IS4_NS5_3outESG_EE (Function, Weak, .text) (stack frame size = 0)
324
+
325
+ Referenced symbols: _ZN12mllib_graphs9ns_expandL11kernel_iterE
326
+ _ZN12mllib_graphs9ns_expandL8core_rowE
327
+ _ZN12me_primitive11control_rndE
328
+
329
+ 0x00003680..0x0000369f ( 32 items) : ../Release/0_0_reloadable6.o::_Z14_b8096_wrapperPPv (Function, Global, .text) (stack frame size = 0)
330
+
331
+ Called functions : _ZN12mllib_graphs14expand_wrapperI8bfloat16EEvRN3adf9io_bufferIT_NS2_9direction2inENS2_16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEEEERA3_KjRNS3_IS4_NS5_3outESG_EE
332
+
333
+ 0x000036a0..0x0000382f ( 400 items) : ../Release/0_0_reloadable6.o::_Z27gather_elements_adf_wrapperI8bfloat16iN3adf16io_buffer_configINS1_7extentsIJEEENS1_7locking4syncENS1_10addressing6linearENS1_6marginILj0EEEEESB_SB_EvRNS1_9io_bufferIT_NS1_9direction2inET1_EERNSC_IT0_SF_T2_EERA16_KjRNSC_ISD_NSE_3outET3_EE (Function, Weak, .text) (stack frame size = 0)
334
+ 0x00003830..0x00003853 ( 36 items) : ../Release/0_0_reloadable6.o::_Z14_b8127_wrapperPPv (Function, Global, .text) (stack frame size = 0)
335
+
336
+ Called functions : _Z27gather_elements_adf_wrapperI8bfloat16iN3adf16io_buffer_configINS1_7extentsIJEEENS1_7locking4syncENS1_10addressing6linearENS1_6marginILj0EEEEESB_SB_EvRNS1_9io_bufferIT_NS1_9direction2inET1_EERNSC_IT0_SF_T2_EERA16_KjRNSC_ISD_NSE_3outET3_EE
337
+
338
+ 0x00003860..0x00003c6f ( 1040 items) : ../Release/0_0_reloadable6.o::_Z17softmax_row_majorILi1E8bfloat16S0_Lt1EEvPT0_PT1_33softmax_row_major_internal_params (Function, Weak, .text) (stack frame size = 0)
339
+
340
+ Referenced symbols: _ZN12me_primitive11control_rndE
341
+
342
+ 0x00003c70..0x00003e37 ( 456 items) : ../Release/0_0_reloadable6.o::_ZN12mllib_graphs19softmax_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERA8_KjRNSD_ISE_NSF_3outET1_EE (Function, Weak, .text) (stack frame size = 128)
343
+
344
+ Called functions : _Z17softmax_row_majorILi1E8bfloat16S0_Lt1EEvPT0_PT1_33softmax_row_major_internal_params
345
+
346
+ Referenced symbols: _ZZN12mllib_graphs19softmax_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERA8_KjRNSD_ISE_NSF_3outET1_EEE9sm_params
347
+ _ZN12me_primitive11control_rndE
348
+ _ZN12me_primitive11control_satE
349
+
350
+ 0x00003e40..0x00003e5f ( 32 items) : ../Release/0_0_reloadable6.o::_Z14_b8134_wrapperPPv (Function, Global, .text) (stack frame size = 0)
351
+
352
+ Called functions : _ZN12mllib_graphs19softmax_adf_wrapperI8bfloat16N3adf16io_buffer_configINS2_7extentsIJEEENS2_7locking4syncENS2_10addressing6linearENS2_6marginILj0EEEEESC_EEvRNS2_9io_bufferIT_NS2_9direction2inET0_EERA8_KjRNSD_ISE_NSF_3outET1_EE
353
+
354
+
355
+ External symbols:
356
+
357
+ __dso_handle = 0x0
358
+ _ctors_end = 0x0
359
+ _ctors_start = 0x0
360
+ _dtors_end = 0x0
361
+ _dtors_start = 0x0
362
+ _pc_end = 0x3e60
363
+ _pc_start = 0x9e0
364
+ _sp_end_DM_stack = 0x7c1c0
365
+ _sp_start_DM_stack = 0x7bd80
366
+
367
+ Section summary for memory 'DM_stack':
368
+
369
+ .stack File
370
+ ---------- ----------
371
+ 1088
372
+ ---------- ----------
373
+ 1088 Total
374
+
375
+ Section summary for memory 'DMb':
376
+
377
+ .bss .data .rodata File
378
+ ---------- ---------- ---------- ----------
379
+ 768 68 40 ../Release/0_0_reloadable6.o
380
+ 5 0 0 me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
381
+ ---------- ---------- ---------- ----------
382
+ 773 68 40 Total
383
+
384
+ Section summary for memory 'PM':
385
+
386
+ .text File
387
+ ---------- ----------
388
+ 13068 ../Release/0_0_reloadable6.o
389
+ ---------- ----------
390
+ 13068 Total
391
+
392
+ File summary:
393
+
394
+ ../Release/0_0_reloadable6.o
395
+ DMb 876
396
+ PM 13068
397
+
398
+ me_defs.o(/proj/aiebuilds/ryzen-ai/ryzen-ai-TA/main/ryzenai_1.5.0_2025_05_28_6217/lnx64/lib/python3.10/site-packages/data/aie2p/lib/Release/libme.a)
399
+ DMb 5
400
+