pytorch Architecture Docs
Home / Class/ bgemm_internal Class — pytorch Architecture

bgemm_internal Class — pytorch Architecture

Architecture documentation for the bgemm_internal class in CUDABlas.cpp from the pytorch codebase.

Class cpp

Entity Profile

Source Code

aten/src/ATen/cuda/CUDABlas.cpp lines 779–795

template <>
void bgemm_internal<double>(CUDABLAS_BGEMM_ARGTYPES(double))
{
  if (at::globalContext().blasPreferredBackend() == BlasBackend::Cublaslt) {
#ifdef USE_ROCM
    // hipblaslt does not support double gemm yet
    bgemm_internal_cublas<double>(CUDABLAS_BGEMM_ARGS(double));
#else
    if (!bgemm_internal_cublaslt<double>(CUDABLAS_BGEMM_ARGS(double))) {
      bgemm_internal_cublas<double>(CUDABLAS_BGEMM_ARGS(double));
    }
#endif
  }
  else {
    bgemm_internal_cublas<double>(CUDABLAS_BGEMM_ARGS(double));
  }
}

Source

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free