cutlass/examples/13_two_tensor_op_fusion/fused_gemm.cu

/***************************************************************************************************
 * Copyright (c) 2017-2021, NVIDIA CORPORATION.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without modification, are permitted
 * provided that the following conditions are met:
 *     * Redistributions of source code must retain the above copyright notice, this list of
 *       conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright notice, this list of
 *       conditions and the following disclaimer in the documentation and/or other materials
 *       provided with the distribution.
 *     * Neither the name of the NVIDIA CORPORATION nor the names of its contributors may be used
 *       to endorse or promote products derived from this software without specific prior written
 *       permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR
 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
 * FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
 * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
 * STRICT LIABILITY, OR TOR (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 **************************************************************************************************/

#include "b2b_gemm_f16t_f16n_f16t_tensor_op_f16_sm75.h"
#include "b2b_gemm_f16t_f16n_f16t_tensor_op_f16_sm80.h"
#include "b2b_gemm_s8n_s8t_s8n_tensor_op_s32_sm75.h"
#include "b2b_gemm_s8n_s8t_s8n_tensor_op_s32_sm80.h"

int run_sm75() {
  bool notSupported = false;

  // Turing Tensor Core operations exposed with mma.sync are first available in CUDA 10.2.
  //
  // CUTLASS must be compiled with CUDA 10.2 Toolkit to run these examples.
  if (!(__CUDACC_VER_MAJOR__ > 10 || (__CUDACC_VER_MAJOR__ == 10 && __CUDACC_VER_MINOR__ >= 2))) {
    notSupported = true;

  }

  cudaDeviceProp props;

  cudaError_t error = cudaGetDeviceProperties(&props, 0);
  if (error != cudaSuccess) {
    std::cerr << "cudaGetDeviceProperties() returned an error: " << cudaGetErrorString(error) << std::endl;
    return -1;
  }

  if (!(props.major == 7 && props.minor >= 5)) {
    notSupported = true;
  }

  if (notSupported) {
    // Returning zero so this test passes on older Toolkits. Its actions are no-op.
    return 0;
  }

  bool pass = true;
 
  std::cout << "Running on SM75" << std::endl;
  pass &= run_nonfused_gemm_f16();
  pass &= run_fused_gemm_f16();
  pass &= run_nonfused_gemm_s8();
  pass &= run_fused_gemm_s8();

  if(pass)
    return 1;
  else
    return -1;
    

}

int run_sm80() {
  bool notSupported = false;

  // Ampere Tensor Core operations exposed with mma.sync are first available in CUDA 11.0.
  //
  // CUTLASS must be compiled with CUDA 11 Toolkit to run Conv2dFprop examples.
  if (!(__CUDACC_VER_MAJOR__ > 11 || (__CUDACC_VER_MAJOR__ == 11 && __CUDACC_VER_MINOR__ >= 0))) {
    notSupported = true;

  }

  cudaDeviceProp props;

  cudaError_t error = cudaGetDeviceProperties(&props, 0);
  if (error != cudaSuccess) {
    std::cerr << "cudaGetDeviceProperties() returned an error: " << cudaGetErrorString(error) << std::endl;
    return -1;
  }

  if (!(props.major == 8 && props.minor >= 0)) {
    notSupported = true;
  }

  if (notSupported) {
    // Returning zero so this test passes on older Toolkits. Its actions are no-op.
    return 0;
  }

  bool pass = true;
 
  std::cout << "Running on SM80" << std::endl;
  pass &= run_nonfused_gemm_f16_sm80();
  pass &= run_fused_gemm_f16_sm80();
  pass &= run_nonfused_gemm_s8_sm80();
  pass &= run_fused_gemm_s8_sm80();

  if(pass)
    return 1;
  else
    return -1;

}


int main() {

  int result = 0;

  result = run_sm80();

  if(!result) { // not supported
    result = run_sm75();

    if(!result) {
      std::cout << "This example isn't supported on current architecture" << std::endl;
    }

  }

  if(result >= 0)
    return 0;
  else
    return -1;
}