File size: 8,318 Bytes
b4cad21
 
 
 
 
0da5bf5
 
b4cad21
 
 
 
0da5bf5
b4cad21
 
 
 
 
0da5bf5
b4cad21
 
 
 
 
0da5bf5
b4cad21
 
 
 
 
 
0da5bf5
b4cad21
 
 
 
 
 
 
0da5bf5
 
b4cad21
 
 
 
 
 
0da5bf5
 
b4cad21
 
 
 
 
 
0da5bf5
 
b4cad21
 
 
 
 
 
 
0da5bf5
 
b4cad21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0da5bf5
b4cad21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0da5bf5
 
b4cad21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
#include <cudaTypedefs.h>

#include <c10/cuda/CUDAGuard.h>
#include <torch/all.h>

#include "cutlass_extensions/common.hpp"

void cutlass_scaled_mm_sm75(torch::Tensor& c, torch::Tensor const& a,
                            torch::Tensor const& b,
                            torch::Tensor const& a_scales,
                            torch::Tensor const& b_scales,
                            std::optional<torch::Tensor> const& bias);

void cutlass_scaled_mm_sm80(torch::Tensor& c, torch::Tensor const& a,
                            torch::Tensor const& b,
                            torch::Tensor const& a_scales,
                            torch::Tensor const& b_scales,
                            std::optional<torch::Tensor> const& bias);

void cutlass_scaled_mm_sm89(torch::Tensor& c, torch::Tensor const& a,
                            torch::Tensor const& b,
                            torch::Tensor const& a_scales,
                            torch::Tensor const& b_scales,
                            std::optional<torch::Tensor> const& bias);

#if defined CUDA_VERSION && CUDA_VERSION >= 12000
void cutlass_scaled_mm_sm90(torch::Tensor& c, torch::Tensor const& a,
                            torch::Tensor const& b,
                            torch::Tensor const& a_scales,
                            torch::Tensor const& b_scales,
                            std::optional<torch::Tensor> const& bias);
#endif

void cutlass_scaled_mm_azp_sm75(torch::Tensor& c, torch::Tensor const& a,
                                torch::Tensor const& b,
                                torch::Tensor const& a_scales,
                                torch::Tensor const& b_scales,
                                torch::Tensor const& azp_adj,
                                std::optional<torch::Tensor> const& azp,
                                std::optional<torch::Tensor> const& bias);

void cutlass_scaled_mm_azp_sm80(torch::Tensor& c, torch::Tensor const& a,
                                torch::Tensor const& b,
                                torch::Tensor const& a_scales,
                                torch::Tensor const& b_scales,
                                torch::Tensor const& azp_adj,
                                std::optional<torch::Tensor> const& azp,
                                std::optional<torch::Tensor> const& bias);

void cutlass_scaled_mm_azp_sm89(torch::Tensor& c, torch::Tensor const& a,
                                torch::Tensor const& b,
                                torch::Tensor const& a_scales,
                                torch::Tensor const& b_scales,
                                torch::Tensor const& azp_adj,
                                std::optional<torch::Tensor> const& azp,
                                std::optional<torch::Tensor> const& bias);

#if defined CUDA_VERSION && CUDA_VERSION >= 12000
void cutlass_scaled_mm_azp_sm90(torch::Tensor& c, torch::Tensor const& a,
                                torch::Tensor const& b,
                                torch::Tensor const& a_scales,
                                torch::Tensor const& b_scales,
                                torch::Tensor const& azp_adj,
                                std::optional<torch::Tensor> const& azp,
                                std::optional<torch::Tensor> const& bias);
#endif

bool cutlass_scaled_mm_supports_fp8(int64_t cuda_device_capability) {
  // CUTLASS FP8 kernels need at least
  //   CUDA 12.0 on SM90 systems (Hopper)
  //   CUDA 12.4 on SM89 systems (Lovelace)

#if defined CUDA_VERSION
  if (cuda_device_capability >= 90) {
    return CUDA_VERSION >= 12000;
  } else if (cuda_device_capability >= 89) {
    return CUDA_VERSION >= 12040;
  }
#endif

  return false;
}

void cutlass_scaled_mm(torch::Tensor& c, torch::Tensor const& a,
                       torch::Tensor const& b, torch::Tensor const& a_scales,
                       torch::Tensor const& b_scales,
                       std::optional<torch::Tensor> const& bias) {
  // Checks for conformality
  TORCH_CHECK(a.dim() == 2 && b.dim() == 2 && c.dim() == 2);
  TORCH_CHECK(c.size(0) == a.size(0) && a.size(1) == b.size(0) &&
              b.size(1) == c.size(1));
  TORCH_CHECK(a_scales.numel() == 1 || a_scales.numel() == a.size(0));
  TORCH_CHECK(b_scales.numel() == 1 || b_scales.numel() == b.size(1));

  // Check for strides and alignment
  TORCH_CHECK(a.stride(1) == 1 && c.stride(1) == 1);  // Row-major
  TORCH_CHECK(b.stride(0) == 1);                      // Column-major
  TORCH_CHECK(c.stride(0) % 16 == 0 &&
              b.stride(1) % 16 == 0);  // 16 Byte Alignment
  TORCH_CHECK(a_scales.is_contiguous() && b_scales.is_contiguous());

  if (bias) {
    TORCH_CHECK(bias->numel() == b.size(1) && bias->is_contiguous() &&
                bias->dim() == 1);
  }

  at::cuda::OptionalCUDAGuard const device_guard(device_of(a));
  int32_t version_num = get_sm_version_num();
  // Hopper

  // Guard against compilation issues for sm90 kernels
  #if defined CUDA_VERSION && CUDA_VERSION >= 12000
  if (version_num >= 90) {
    cutlass_scaled_mm_sm90(c, a, b, a_scales, b_scales, bias);
    return;
  }
  #endif

  if (version_num == 89) {
    // Ada Lovelace
    cutlass_scaled_mm_sm89(c, a, b, a_scales, b_scales, bias);
    return;
  }

  if (version_num >= 80) {
    // Ampere
    cutlass_scaled_mm_sm80(c, a, b, a_scales, b_scales, bias);
    return;
  }

  if (version_num >= 75) {
    // Turing
    cutlass_scaled_mm_sm75(c, a, b, a_scales, b_scales, bias);
    return;
  }

  TORCH_CHECK_NOT_IMPLEMENTED(
      false,
      "No compiled cutlass_scaled_mm for a compute capability less than "
      "CUDA device capability: ",
      version_num);
}

void cutlass_scaled_mm_azp(torch::Tensor& c, torch::Tensor const& a,
                           torch::Tensor const& b,
                           torch::Tensor const& a_scales,
                           torch::Tensor const& b_scales,
                           torch::Tensor const& azp_adj,
                           std::optional<torch::Tensor> const& azp,
                           std::optional<torch::Tensor> const& bias) {
  // Checks for conformality
  TORCH_CHECK(a.dim() == 2 && b.dim() == 2 && c.dim() == 2);
  TORCH_CHECK(c.size(0) == a.size(0) && a.size(1) == b.size(0) &&
              b.size(1) == c.size(1));
  TORCH_CHECK(a_scales.numel() == 1 || a_scales.numel() == a.size(0));
  TORCH_CHECK(b_scales.numel() == 1 || b_scales.numel() == b.size(1));

  // Check for strides and alignment
  TORCH_CHECK(a.stride(1) == 1 && c.stride(1) == 1);  // Row-major
  TORCH_CHECK(b.stride(0) == 1);                      // Column-major
  TORCH_CHECK(c.stride(0) % 16 == 0 &&
              b.stride(1) % 16 == 0);  // 16 Byte Alignment
  TORCH_CHECK(a_scales.is_contiguous() && b_scales.is_contiguous());

  // bias, azp, azp_adj are all 1d
  // bias and azp_adj have n elements, azp has m elements
  if (bias) {
    TORCH_CHECK(bias->numel() == b.size(1) && bias->is_contiguous());
  }
  if (azp) {
    TORCH_CHECK(azp->numel() == a.size(0) && azp->is_contiguous());
  }
  TORCH_CHECK(azp_adj.numel() == b.size(1) && azp_adj.is_contiguous());

  // azp & bias types
  TORCH_CHECK(azp_adj.dtype() == torch::kInt32);
  TORCH_CHECK(!azp || azp->dtype() == torch::kInt32);
  TORCH_CHECK(!bias || bias->dtype() == c.dtype(),
              "currently bias dtype must match output dtype ", c.dtype());

  at::cuda::OptionalCUDAGuard const device_guard(device_of(a));

  int32_t version_num = get_sm_version_num();

  #if defined CUDA_VERSION && CUDA_VERSION >= 12000
  if (version_num >= 90) {
    cutlass_scaled_mm_azp_sm90(c, a, b, a_scales, b_scales, azp_adj, azp, bias);
    return;
  }
  #endif

  if (version_num == 89) {
    // Ada Lovelace
    cutlass_scaled_mm_azp_sm89(c, a, b, a_scales, b_scales, azp_adj, azp, bias);
    return;
  }

  if (version_num >= 80) {
    // Ampere
    cutlass_scaled_mm_azp_sm80(c, a, b, a_scales, b_scales, azp_adj, azp, bias);
    return;
  }

  // Turing
  TORCH_CHECK(version_num >= 75);
  cutlass_scaled_mm_azp_sm75(c, a, b, a_scales, b_scales, azp_adj, azp, bias);
  return;

  TORCH_CHECK_NOT_IMPLEMENTED(
      false,
      "No compiled cutlass_scaled_mm_azp for a compute capability less than "
      "CUDA device capability: ",
      version_num);
}