MCPcopy Create free account
hub / github.com/DeepRec-AI/DeepRec / DoBlasTrmm

Method DoBlasTrmm

tensorflow/stream_executor/cuda/cuda_blas.cc:3062–3072  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

3060}
3061
3062bool CUDABlas::DoBlasTrmm(Stream *stream, blas::Side side,
3063 blas::UpperLower uplo, blas::Transpose transa,
3064 blas::Diagonal diag, uint64 m, uint64 n, float alpha,
3065 const DeviceMemory<float> &a, int lda,
3066 DeviceMemory<float> *b, int ldb) {
3067 return DoBlasInternal<float>(
3068 cublasStrmm, stream, true /* = pointer_mode_host */, CUDABlasSide(side),
3069 CUDABlasUpperLower(uplo), CUDABlasTranspose(transa),
3070 CUDABlasDiagonal(diag), m, n, &alpha, GpuMemory(a), lda,
3071 GpuMemoryMutable(b), ldb, GpuMemoryMutable(b), ldb);
3072}
3073
3074bool CUDABlas::DoBlasTrmm(Stream *stream, blas::Side side,
3075 blas::UpperLower uplo, blas::Transpose transa,

Callers

nothing calls this directly

Calls 7

CUDABlasSideFunction · 0.85
CUDABlasTransposeFunction · 0.85
CUDABlasDiagonalFunction · 0.85
GpuMemoryFunction · 0.85
GpuMemoryMutableFunction · 0.85
GpuComplexFunction · 0.85
CUDABlasUpperLowerFunction · 0.70

Tested by

no test coverage detected