Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
fused_weight_gradient_dense.cu 3.12 KB
Newer Older
Sangkug Lym's avatar
gradient accumulation fusion  
Sangkug Lym committed
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 
#include <ATen/ATen.h>
#include <ATen/cuda/CUDAContext.h>
#include <assert.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <torch/torch.h>

/* Includes, cuda */
#include <cublas_v2.h>
#include <cuda_runtime.h>


// BF16 Tensor core wrapper around cublas GEMMEx
cublasStatus_t gemmex_wrapper(
    cublasHandle_t handle,
    cublasOperation_t transa,
    cublasOperation_t transb,
    int m,
    int n,
    int k,
    const float* alpha,
    at::BFloat16* A,
    int lda,
    at::BFloat16* B,
    int ldb,
    const float* beta,
    float* C,
    int ldc) {
  return cublasGemmEx(
      handle,
      transa,
      transb,
      m,
      n,
      k,
      alpha,
      A,
      CUDA_R_16BF,
      lda,
      B,
      CUDA_R_16BF,
      ldb,
      beta,
      C,
      CUDA_R_32F,
      ldc,
      CUDA_R_32F,
      CUBLAS_GEMM_DEFAULT_TENSOR_OP);
}

// FP16 Tensor core wrapper around cublas GEMMEx
cublasStatus_t gemmex_wrapper(
    cublasHandle_t handle,
    cublasOperation_t transa,
    cublasOperation_t transb,
    int m,
    int n,
    int k,
    const float* alpha,
    at::Half* A,
    int lda,
    at::Half* B,
    int ldb,
    const float* beta,
    float* C,
    int ldc) {
  return cublasGemmEx(
      handle,
      transa,
      transb,
      m,
      n,
      k,
      alpha,
      A,
      CUDA_R_16F,
      lda,
      B,
      CUDA_R_16F,
      ldb,
      beta,
      C,
      CUDA_R_32F,
      ldc,
      CUDA_R_32F,
      CUBLAS_GEMM_DEFAULT_TENSOR_OP);
}
Sangkug Lym's avatar
support fp32 training and fix embedding update  
Sangkug Lym committed
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 
// FP32 Tensor core wrapper around cublas GEMMEx
cublasStatus_t gemmex_wrapper(
    cublasHandle_t handle,
    cublasOperation_t transa,
    cublasOperation_t transb,
    int m,
    int n,
    int k,
    const float* alpha,
    float* A,
    int lda,
    float* B,
    int ldb,
    const float* beta,
    float* C,
    int ldc) {
  return cublasGemmEx(
      handle,
      transa,
      transb,
      m,
      n,
      k,
      alpha,
      A,
      CUDA_R_32F,
      lda,
      B,
      CUDA_R_32F,
      ldb,
      beta,
      C,
      CUDA_R_32F,
      ldc,
      CUDA_R_32F,
      CUBLAS_GEMM_DEFAULT_TENSOR_OP);
}
Sangkug Lym's avatar
gradient accumulation fusion  
Sangkug Lym committed
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 
template <typename T>
int wgrad_gemm_accum_fp32_cuda(T *input, T *d_output, float *d_weight, int in_dim, int hidden_dim, int out_dim) {
    cublasHandle_t handle = at::cuda::getCurrentCUDABlasHandle();
    cudaStream_t stream;
    cublasGetStream(handle, &stream);
    const float alpha = 1.0;
    const float beta  = 1.0;
    int status = 1;

    status = gemmex_wrapper(
        handle,
        CUBLAS_OP_N,
        CUBLAS_OP_T,
        in_dim,
        out_dim,
        hidden_dim,
        &alpha,
        input,
        in_dim,
        d_output,
        out_dim,
        &beta,
        d_weight,
        in_dim);
    return status;
}

template int wgrad_gemm_accum_fp32_cuda<at::Half>(at::Half *input, at::Half *d_output, float *d_weight, int in_dim, int hidden_dim, int out_dim);
template int wgrad_gemm_accum_fp32_cuda<at::BFloat16>(at::BFloat16 *input, at::BFloat16 *d_output, float *d_weight, int in_dim, int hidden_dim, int out_dim);
Sangkug Lym's avatar
support fp32 training and fix embedding update  
Sangkug Lym committed
157 
template int wgrad_gemm_accum_fp32_cuda<float>(float *input, float *d_output, float *d_weight, int in_dim, int hidden_dim, int out_dim);