leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

CUTLASS 2.1 (#83)

Browse Source 
CUTLASS 2.1 contributes:
- BLAS-style host-side API added to CUTLASS Library
- Planar Complex GEMM kernels targeting Volta and Turing Tensor Cores
- Minor enhancements and bug fixes
This commit is contained in:
Andrew Kerr
2020-04-07 13:51:25 -07:00
committed by GitHub
parent 7c0cd26d13
commit 96dab34ad9
196 changed files with 20653 additions and 1995 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
examples/06_splitK_gemm/splitk_gemm.cu
View File

@@ -173,14 +173,35 @@ using Gemm = cutlass::gemm::device::GemmSplitKParallel<ElementInputA,
EpilogueOp>;
int main() {
//
// Volta Tensor Core operations exposed with mma.sync are first available in CUDA 10.1.
//
// CUTLASS must be compiled with CUDA 10.1 Toolkit to run these examples.
//
if (!(__CUDACC_VER_MAJOR__ > 10 || (__CUDACC_VER_MAJOR__ == 10 && __CUDACC_VER_MINOR__ >= 1))) {
std::cerr << "Volta Tensor Core operations must be compiled with CUDA 10.1 Toolkit or later." << std::endl;
return -1;
}
cudaDeviceProp props;
CUDA_CHECK(cudaGetDeviceProperties(&props, 0));
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)) {
std::cerr << "Volta Tensor Ops must be run on a machine with compute capability at least 70."
<< std::endl;
return 0;
return -1;
}
//
// Define problem size
//
const int length_m = 5120;
const int length_n = 4096;
const int length_k = 4096;