Home / Class/ xsyevd_bufferSize Class — pytorch Architecture

xsyevd_bufferSize Class — pytorch Architecture

Architecture documentation for the xsyevd_bufferSize class in CUDASolver.cpp from the pytorch codebase.

Entity Profile

Source Code

aten/src/ATen/native/cuda/linalg/CUDASolver.cpp lines 1709–1735

template <>
void xsyevd_bufferSize<float>(
    cusolverDnHandle_t handle,
    cusolverDnParams_t params,
    cusolverEigMode_t jobz,
    cublasFillMode_t uplo,
    int64_t n,
    const float* A,
    int64_t lda,
    const float* W,
    size_t* workspaceInBytesOnDevice,
    size_t* workspaceInBytesOnHost) {
  TORCH_CUSOLVER_CHECK(cusolverDnXsyevd_bufferSize(
      handle,
      params,
      jobz,
      uplo,
      n,
      CUDA_R_32F,
      reinterpret_cast<const void*>(A),
      lda,
      CUDA_R_32F,
      reinterpret_cast<const void*>(W),
      CUDA_R_32F,
      workspaceInBytesOnDevice,
      workspaceInBytesOnHost));
}

Analyze Your Own Codebase

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

Try Supermodel Free