Hugging Face's logo

aigdat
/
ASR_NPU_TB

ONNX
Model card Files Community
iswaalex commited on
Commit
537a748
·
verified ·
1 Parent(s): aeac30a

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_2/lcp/0_2_1481.bin +3 -0
  2. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1482.bin +3 -0
  3. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1483.bin +3 -0
  4. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1484.bin +3 -0
  5. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1487.bin +3 -0
  6. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1488.bin +3 -0
  7. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1489.bin +3 -0
  8. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_149.bin +3 -0
  9. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1490.bin +3 -0
  10. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1491.bin +3 -0
  11. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1492.bin +3 -0
  12. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1493.bin +3 -0
  13. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1494.bin +3 -0
  14. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1495.bin +3 -0
  15. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1496.bin +3 -0
  16. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1497.bin +3 -0
  17. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1498.bin +3 -0
  18. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1499.bin +3 -0
  19. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1500.bin +3 -0
  20. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1501.bin +3 -0
  21. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1502.bin +3 -0
  22. vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1503.bin +3 -0
  23. vaiml_par_0/0/aiecompiler/Work/reports/report_pm.txt +0 -0
  24. vaiml_par_0/0/aiecompiler/Work/reports/report_stack.txt +0 -0
  25. vaiml_par_0/0/aiecompiler/Work/temp/kernel_stubs.h +32 -0
  26. vaiml_par_0/0/aiecompiler/Work/temp/top_partition.json +0 -0
  27. vaiml_par_0/0/backend/0.dag_before_general_L2L3_buffer_insertion.dot +0 -0
  28. vaiml_par_0/0/backend/1.dag_after_general_L2L3_buffer_insertion.dot +0 -0
  29. vaiml_par_0/0/backend/10.dag_after_TGOptimizeForO2.dot +0 -0
  30. vaiml_par_0/0/backend/11.dag_after_InactiveSpilling_pass_O2.dot +0 -0
  31. vaiml_par_0/0/backend/12.dag_after_TGNodeSpillingForO2_pass_O2.dot +0 -0
  32. vaiml_par_0/0/backend/13.dag_after_ReshapeHandlingPass.dot +0 -0
  33. vaiml_par_0/0/backend/14.dag_before_L2Placement.dot +0 -0
  34. vaiml_par_0/0/backend/15.dag_After_L2flushout.dot +0 -0
  35. vaiml_par_0/0/backend/16.dag_After_layerwisestamping.dot +0 -0
  36. vaiml_par_0/0/backend/17.dag_before_ADFgen.dot +0 -0
  37. vaiml_par_0/0/backend/2.dag_AfterL3concat_fanout.dot +0 -0
  38. vaiml_par_0/0/backend/3.dag_AfterTGtoConcatPass.dot +0 -0
  39. vaiml_par_0/0/backend/4.dag_AfterConcatoffsetComputePass.dot +0 -0
  40. vaiml_par_0/0/backend/5.dag_after_tg_pass.dot +0 -0
  41. vaiml_par_0/0/backend/6.dag_after_RemoveL2L3Buffer_pass_O2.dot +0 -0
  42. vaiml_par_0/0/backend/7.dag_after_AddControlEdge_pass_O2.dot +0 -0
  43. vaiml_par_0/0/backend/8.dag_after_ReplaceL3ByL2concat_pass_O2.dot +0 -0
  44. vaiml_par_0/0/backend/9.dag_after_L2_SpillFMOverflow_pass_O2.dot +0 -0
  45. vaiml_par_0/0/backend/BE_postcheck_log.txt +0 -0
  46. vaiml_par_0/0/backend/InactiveSpillingDebug_Dump_0.dot +0 -0
  47. vaiml_par_0/0/backend/TGNodeSpilling_Dump_0.dot +0 -0
  48. vaiml_par_0/0/backend/TGNodeSpilling_Dump_1.dot +0 -0
  49. vaiml_par_0/0/backend/TGNodeSpilling_Dump_10.dot +0 -0
  50. vaiml_par_0/0/backend/TGNodeSpilling_Dump_100.dot +0 -0
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1481.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02f23643b7fb3790cbaf3425e8080e698ee243d955f581ef3ef9cb42be0f75b2
3
+ size 384
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1482.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e746703685b9d674309ebd90c4eaa7ebb247bcae5ba24689aeb97ff3db961098
3
+ size 376
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1483.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96f138c7be056a7fffdaefeca0d04b29e1f4504680888efeda4c615c73e0326d
3
+ size 264
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1484.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:befe49b6eb216d0687a361dfdaf6dc9020d90aebb0e257e8935dd5f9192daf96
3
+ size 348
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1487.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b497ffdfdd8fa3a5897c165c6f5e7eebb2245d9c262fefa27ed48309822fc4
3
+ size 260
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1488.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e341d4e142f7922e6134ac8979076a1c87f3aa00817fc135424bd21bee97c53
3
+ size 244
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1489.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503917d4e5a2f37d335b35f18211b1f9f407f7d4a169e2484e2534deb9fe2142
3
+ size 348
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_149.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999ce13aca08dfc0364089a90d9f8d1d670878edab24f5e91e8d56a60e86a777
3
+ size 260
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1490.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a1067a4e148fb4d772636ce1e2ff9fc58cfe42fa9b03d7d59b0fd70cd5d26e
3
+ size 296
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1491.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d223ef3fce6fbed5560bd0c3d3023633b397d8614611b0d72f6ce69c90f1f2
3
+ size 376
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1492.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05804e71b0e897e153633f43bedc51408a1ed4d0cca5fa5eeaa056e3345ba822
3
+ size 244
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1493.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:621daab1b36b5b2d0d9f9d4e59098028a936921e423bb78f7d3cc257f7bc2f52
3
+ size 296
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1494.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c33b8be639d270c6953c7ab6e7e1d2b5b402aad29960a032b71e0dec5af0c2
3
+ size 260
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1495.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd8ea6aa61e10c4fc8b26fd085f4706bd314d0e5b957f144868b3521aaa9374
3
+ size 260
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1496.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d35c512706b8587ee71c3994802890e9dff3ce30f6e4de6016642c136d2247a
3
+ size 384
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1497.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95738b9d6328e4f5fc532c7cd6092e18b401c5d51c4b5337bbbd0180c4a37252
3
+ size 260
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1498.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05804e71b0e897e153633f43bedc51408a1ed4d0cca5fa5eeaa056e3345ba822
3
+ size 244
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1499.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e40c435419ee1ac0d52925c1b51504a4f0844adc6311893ab7338471acb9bb
3
+ size 296
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1500.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d86d29759f2785bc9e5425bb6e581efeace13ace63114b99ae21b78a526ad62
3
+ size 296
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1501.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e98dde8600e0d949299a92243e5f91fea826235412df5f0e13a18f28cdf703e2
3
+ size 376
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1502.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72fa29e048525188268e47c416bdad632fc6255892cfb893f9e7655951f172b2
3
+ size 296
vaiml_par_0/0/aiecompiler/Work/aie/0_2/lcp/0_2_1503.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4999af9a4ada89c3c8ab3472cc09586b27611c63fd0eedf72f6a81937c66ed4a
3
+ size 260
vaiml_par_0/0/aiecompiler/Work/reports/report_pm.txt ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/reports/report_stack.txt ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/aiecompiler/Work/temp/kernel_stubs.h ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ template<typename dtype, typename config_ifm, typename config_ofm> void mllib_graphs::buffer_pad_adf_wrapper(adf::input_buffer_conf<dtype, config_ifm> &__restrict ifm, adf::output_buffer_conf<dtype, config_ofm> &__restrict ofm, const uint32_t (&layer_params)[3]) { /* Stub */ }
2
+ template<typename dtype, typename config_ifm, typename config_ofm> void mllib_graphs::buffer_unpad_adf_wrapper(adf::input_buffer_conf<dtype, config_ifm> &__restrict ifm, adf::output_buffer_conf<dtype, config_ofm> &__restrict ofm, const uint32_t (&layer_params)[3]) { /* Stub */ }
3
+ template<typename dtype, typename config_ifm, typename config_ofm> void mllib_graphs::slice_generic_innermost_adf_wrapper(adf::input_buffer_conf<dtype, config_ifm> &__restrict ifm, adf::output_buffer_conf<dtype, config_ofm> &__restrict ofm, const uint32_t (&lp)[16]) { /* Stub */ }
4
+ template<typename dtype, typename config_ifm, typename config_ofm> void mllib_graphs::softmax_adf_wrapper(adf::input_buffer_conf<dtype, config_ifm> &__restrict ifm, const uint32_t (&layer_params)[8], adf::output_buffer_conf<dtype, config_ofm> &__restrict ofm) { /* Stub */ }
5
+ template<typename dtype, typename config_ifm, typename config_ofm> void mllib_graphs::transpose4d_adf_wrapper(adf::input_buffer_conf<dtype, config_ifm> &__restrict ifm, adf::output_buffer_conf<dtype, config_ofm> &__restrict ofm, const uint32_t (&layer_params)[7]) { /* Stub */ }
6
+ template<typename dtype, typename config_ifm, typename config_wts, typename config_ofm> void mllib_graphs::rmsnorm_row_major_part1_4x4_wrapper(adf::input_buffer_conf<dtype, config_ifm> &__restrict ifm, adf::input_buffer_conf<dtype, config_wts> &__restrict wts, const uint32_t (&layer_params)[11], adf::output_buffer_conf<dtype, config_ofm> &__restrict ofm) { /* Stub */ }
7
+ template<typename dtype, typename config_ifm, typename config_wts, typename config_ofm> void mllib_graphs::rmsnorm_row_major_part2_4x4_wrapper(adf::input_buffer_conf<dtype, config_ifm> &__restrict ifm, adf::input_buffer_conf<dtype, config_wts> &__restrict wts, const uint32_t (&layer_params)[11], adf::output_buffer_conf<dtype, config_ofm> &__restrict ofm) { /* Stub */ }
8
+ template<typename dtype, typename config_ifm, typename config_wts, typename config_ofm> void mllib_graphs::rmsnorm_row_major_part3_4x4_wrapper(adf::input_buffer_conf<dtype, config_ifm> &__restrict ifm, adf::input_buffer_conf<dtype, config_wts> &__restrict wts, const uint32_t (&layer_params)[11], adf::output_buffer_conf<dtype, config_ofm> &__restrict ofm) { /* Stub */ }
9
+ template<typename dtype, typename config_ifm1, typename config_ifm2, typename config_ofm> void mllib_graphs::concat_adf_wrapper(adf::input_buffer_conf<dtype, config_ifm1> &__restrict ifm1, adf::input_buffer_conf<dtype, config_ifm2> &__restrict ifm2, adf::output_buffer_conf<dtype, config_ofm> &__restrict ofm, const uint32_t (&layer_params)[9]) { /* Stub */ }
10
+ template<typename dtype> void mllib_graphs::expand_wrapper(adf::input_buffer_conf<dtype, adf::bpc_sync_0d> &__restrict ifm, const uint32_t (&lp)[3], adf::output_buffer_conf<dtype, adf::bpc_sync_0d> &__restrict ofm) { /* Stub */ }
11
+ template<typename dtype_io, typename dtype_wts, typename config_ifm, typename config_wts, typename config_ofm> void gather_elements_adf_wrapper(adf::input_buffer_conf<dtype_io, config_ifm> &__restrict ifm, adf::input_buffer_conf<dtype_wts, config_wts> &__restrict wts, const uint32_t (&layer_params)[16], adf::output_buffer_conf<dtype_io, config_ofm> &__restrict ofm) { /* Stub */ }
12
+ void conv2d_maxpool(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) { /* Stub */ }
13
+ 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) { /* Stub */ }
14
+ 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) { /* Stub */ }
15
+ 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) { /* Stub */ }
16
+ 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) { /* Stub */ }
17
+ 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) { /* Stub */ }
18
+ void superkernel_mul1d_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) { /* Stub */ }
19
+ void superkernel_reducesum(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict, const unsigned int (&)[18], adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict) { /* Stub */ }
20
+ 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) { /* Stub */ }
21
+ void superkernel_sub1d(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) { /* Stub */ }
22
+ template void gather_elements_adf_wrapper<bfloat16, int, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict, adf::io_buffer<int, 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<>>> &__restrict); /* explicit template instantiation */
23
+ template void mllib_graphs::buffer_pad_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict, adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>>> &__restrict, const unsigned int (&)[3]); /* explicit template instantiation */
24
+ template void mllib_graphs::buffer_unpad_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict, adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>>> &__restrict, const unsigned int (&)[3]); /* explicit template instantiation */
25
+ template void mllib_graphs::concat_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(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, adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>>> &__restrict, const unsigned int (&)[9]); /* explicit template instantiation */
26
+ template void mllib_graphs::expand_wrapper<bfloat16>(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict, const unsigned int (&)[3], adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>>> &__restrict); /* explicit template instantiation */
27
+ template void 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>>(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 (&)[11], adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>, adf::locking::async>> &__restrict); /* explicit template instantiation */
28
+ template void 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<>>>(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 (&)[11], adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>>> &__restrict); /* explicit template instantiation */
29
+ template void 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<>>>(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 (&)[11], adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>>> &__restrict); /* explicit template instantiation */
30
+ template void mllib_graphs::slice_generic_innermost_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict, adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>>> &__restrict, const unsigned int (&)[16]); /* explicit template instantiation */
31
+ template void mllib_graphs::softmax_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict, const unsigned int (&)[8], adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>>> &__restrict); /* explicit template instantiation */
32
+ template void mllib_graphs::transpose4d_adf_wrapper<bfloat16, adf::io_buffer_config<adf::extents<>>, adf::io_buffer_config<adf::extents<>>>(adf::io_buffer<bfloat16, adf::direction::in, adf::io_buffer_config<adf::extents<>>> &__restrict, adf::io_buffer<bfloat16, adf::direction::out, adf::io_buffer_config<adf::extents<>>> &__restrict, const unsigned int (&)[7]); /* explicit template instantiation */
vaiml_par_0/0/aiecompiler/Work/temp/top_partition.json ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/0.dag_before_general_L2L3_buffer_insertion.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/1.dag_after_general_L2L3_buffer_insertion.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/10.dag_after_TGOptimizeForO2.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/11.dag_after_InactiveSpilling_pass_O2.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/12.dag_after_TGNodeSpillingForO2_pass_O2.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/13.dag_after_ReshapeHandlingPass.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/14.dag_before_L2Placement.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/15.dag_After_L2flushout.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/16.dag_After_layerwisestamping.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/17.dag_before_ADFgen.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/2.dag_AfterL3concat_fanout.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/3.dag_AfterTGtoConcatPass.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/4.dag_AfterConcatoffsetComputePass.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/5.dag_after_tg_pass.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/6.dag_after_RemoveL2L3Buffer_pass_O2.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/7.dag_after_AddControlEdge_pass_O2.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/8.dag_after_ReplaceL3ByL2concat_pass_O2.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/9.dag_after_L2_SpillFMOverflow_pass_O2.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/BE_postcheck_log.txt ADDED
File without changes
vaiml_par_0/0/backend/InactiveSpillingDebug_Dump_0.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/TGNodeSpilling_Dump_0.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/TGNodeSpilling_Dump_1.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/TGNodeSpilling_Dump_10.dot ADDED
The diff for this file is too large to render. See raw diff
 
vaiml_par_0/0/backend/TGNodeSpilling_Dump_100.dot ADDED
The diff for this file is too large to render. See raw diff