60508ffda9
Co-authored-by: Faraz Shahsavan <faraz.shahsavan@gmail.com> Co-authored-by: ilmarkov <markovilya197@gmail.com> Co-authored-by: Rahul Tuli <rahul@neuralmagic.com> Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
36 lines
1.1 KiB
C++
36 lines
1.1 KiB
C++
#pragma once
|
|
|
|
#include "cutlass/cutlass.h"
|
|
#include <climits>
|
|
#include "cuda_runtime.h"
|
|
#include <iostream>
|
|
|
|
/**
|
|
* Helper function for checking CUTLASS errors
|
|
*/
|
|
#define CUTLASS_CHECK(status) \
|
|
{ \
|
|
cutlass::Status error = status; \
|
|
TORCH_CHECK(error == cutlass::Status::kSuccess, \
|
|
cutlassGetStatusString(error)); \
|
|
}
|
|
|
|
/**
|
|
* Panic wrapper for unwinding CUDA runtime errors
|
|
*/
|
|
#define CUDA_CHECK(status) \
|
|
{ \
|
|
cudaError_t error = status; \
|
|
TORCH_CHECK(error == cudaSuccess, cudaGetErrorString(error)); \
|
|
}
|
|
|
|
inline int get_cuda_max_shared_memory_per_block_opt_in(int const device) {
|
|
int max_shared_mem_per_block_opt_in = 0;
|
|
cudaDeviceGetAttribute(&max_shared_mem_per_block_opt_in,
|
|
cudaDevAttrMaxSharedMemoryPerBlockOptin,
|
|
device);
|
|
return max_shared_mem_per_block_opt_in;
|
|
}
|
|
|
|
int32_t get_sm_version_num();
|