mirror of
https://gitlab.com/libeigen/eigen.git
synced 2026-04-10 11:34:33 +08:00
Fix defines in AVX512 custom TRSM kernel.
<!-- Thanks for contributing a merge request! We recommend that first-time contributors read our [contribution guidelines](https://eigen.tuxfamily.org/index.php?title=Contributing_to_Eigen). Before submitting the MR, please complete the following checks: - Create one PR per feature or bugfix, - Run the test suite to verify your changes. See our [test guidelines](https://eigen.tuxfamily.org/index.php?title=Tests). - Add tests to cover the bug addressed or any new feature. - Document new features. If it is a substantial change, add it to the [Changelog](https://gitlab.com/libeigen/eigen/-/blob/master/CHANGELOG.md). - Leave the following box checked when submitting: `Allow commits from members who can merge to the target branch`. This allows us to rebase and merge your change. Note that we are a team of volunteers; we appreciate your patience during the review process. --> ### Description <!--Please explain your changes.--> Broken at head by !2063. See merge request libeigen/eigen!2066
This commit is contained in:
@@ -44,7 +44,7 @@
|
||||
namespace Eigen {
|
||||
namespace internal {
|
||||
|
||||
#if (EIGEN_USE_AVX512_TRSM_KERNELS) && (EIGEN_COMP_CLANG != 0)
|
||||
#if (EIGEN_USE_AVX512_TRSM_KERNELS)
|
||||
|
||||
#define EIGEN_AVX_MAX_NUM_ACC (int64_t(24))
|
||||
#define EIGEN_AVX_MAX_NUM_ROW (int64_t(8)) // Denoted L in code.
|
||||
@@ -60,6 +60,8 @@ typedef Packet4d vecHalfDouble;
|
||||
// Note: this depends on macros and typedefs above.
|
||||
#include "TrsmUnrolls.inc"
|
||||
|
||||
#if (EIGEN_COMP_CLANG != 0)
|
||||
|
||||
/**
|
||||
* For smaller problem sizes, and certain compilers, using the optimized kernels trsmKernelL/R directly
|
||||
* is faster than the packed versions in TriangularSolverMatrix.h.
|
||||
@@ -1061,7 +1063,6 @@ void triSolve(Scalar *A_arr, Scalar *B_arr, int64_t M, int64_t numRHS, int64_t L
|
||||
}
|
||||
|
||||
// Template specializations of trsmKernelL/R for float/double and inner strides of 1.
|
||||
#if (EIGEN_USE_AVX512_TRSM_KERNELS)
|
||||
#if (EIGEN_USE_AVX512_TRSM_R_KERNELS)
|
||||
template <typename Scalar, typename Index, int Mode, bool Conjugate, int TriStorageOrder, int OtherInnerStride,
|
||||
bool Specialized>
|
||||
@@ -1162,7 +1163,9 @@ EIGEN_DONT_INLINE void trsmKernelL<double, Index, Mode, false, TriStorageOrder,
|
||||
const_cast<double *>(_tri), _other, size, otherSize, triStride, otherStride);
|
||||
}
|
||||
#endif // EIGEN_USE_AVX512_TRSM_L_KERNELS
|
||||
|
||||
#endif // EIGEN_USE_AVX512_TRSM_KERNELS
|
||||
|
||||
} // namespace internal
|
||||
} // namespace Eigen
|
||||
#endif // EIGEN_CORE_ARCH_AVX512_TRSM_KERNEL_H
|
||||
|
||||
Reference in New Issue
Block a user