9ca33cf4d5
Sources (all CUDA 10.2 compatible, no CUTLASS/Triton dependency): - leimao/CUDA-GEMM-Optimization: v00-v07, fp16 WMMA variant, double buffered - siboehm/SGEMM_CUDA: kernel 1-12, warp tiling + double buffering - wangzyon/NVIDIA_SGEMM_PRACTICE: kernel 1-7 - edtallison/sgemm-cuda: kernel 1-12 (reimplementation with notes) Key porting issue: ALL kernels hardcode WARPSIZE=32. BI-V100 has warp_size=64. Need to: 1. Replace all 32U / WARPSIZE constants with 64 2. Adjust warp subtile decomposition (WMITER, WNITER, WSUBM, WSUBN) 3. Adjust shared memory bank conflict avoidance (may have different bank count) 4. Test __shfl_down_sync with mask=0xFFFFFFFFFFFFFFFF (64-bit)
30 lines
793 B
Plaintext
30 lines
793 B
Plaintext
#include <iostream>
|
|
|
|
#include <cuda_runtime.h>
|
|
|
|
#include "cuda_gemm_utils.hpp"
|
|
|
|
void check_cuda(cudaError_t err, const char* const func, const char* const file,
|
|
const int line)
|
|
{
|
|
if (err != cudaSuccess)
|
|
{
|
|
std::cerr << "CUDA Runtime Error at: " << file << ":" << line
|
|
<< std::endl;
|
|
std::cerr << cudaGetErrorString(err) << " " << func << std::endl;
|
|
std::exit(EXIT_FAILURE);
|
|
}
|
|
}
|
|
|
|
void check_cuda_last(const char* const file, const int line)
|
|
{
|
|
cudaError_t const err{cudaGetLastError()};
|
|
if (err != cudaSuccess)
|
|
{
|
|
std::cerr << "CUDA Runtime Error at: " << file << ":" << line
|
|
<< std::endl;
|
|
std::cerr << cudaGetErrorString(err) << std::endl;
|
|
std::exit(EXIT_FAILURE);
|
|
}
|
|
}
|