devtools/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2026-04-10 11:34:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merged in deven-amd/eigen/HIP_fixes (pull request PR-518)

Browse Source 
PR with HIP specific fixes (for the eigen nightly regression failures in HIP mode)
This commit is contained in:
Christoph Hertzberg
2018-10-01 16:51:04 +00:00
parent 2088c0897f 94898488a6
commit 564ca71e39
5 changed files with 26 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
unsupported/Eigen/CXX11/src/Tensor/TensorContraction.h
View File

@@ -186,21 +186,21 @@ struct TensorContractionKernel {
/*ConjugateLhs*/ false, /*ConjugateRhs*/ false>
GebpKernel;
EIGEN_DONT_INLINE
EIGEN_DEVICE_FUNC EIGEN_DONT_INLINE
static void packLhs(LhsScalar* lhsBlock,
const typename LhsMapper::SubMapper& data_mapper,
const StorageIndex depth, const StorageIndex rows) {
LhsPacker()(lhsBlock, data_mapper, depth, rows, /*stride*/ 0, /*offset*/ 0);
}
EIGEN_DONT_INLINE
EIGEN_DEVICE_FUNC EIGEN_DONT_INLINE
static void packRhs(RhsScalar* rhsBlock,
const typename RhsMapper::SubMapper& data_mapper,
const StorageIndex depth, const StorageIndex cols) {
RhsPacker()(rhsBlock, data_mapper, depth, cols);
}
EIGEN_DONT_INLINE
EIGEN_DEVICE_FUNC EIGEN_DONT_INLINE
static void invoke(const OutputMapper& output_mapper,
const LhsScalar* lhsBlock, const RhsScalar* rhsBlock,
const StorageIndex rows, const StorageIndex depth,

4
unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h
View File

@@ -218,6 +218,7 @@ struct InnerMostDimReducer<Self, Op, false, true> {
}
};
#if !defined(EIGEN_HIPCC)
template <typename Self, typename Op>
struct InnerMostDimReducer<Self, Op, true, true> {
static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE typename Self::CoeffReturnType
@@ -257,7 +258,8 @@ struct InnerMostDimReducer<Self, Op, true, true> {
}
}
};
#endif
template <int DimIndex, typename Self, typename Op, bool vectorizable = (Self::InputPacketAccess && Self::ReducerTraits::PacketAccess)>
struct InnerMostDimPreserver {
static EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE void reduce(const Self&, typename Self::Index, Op&, typename Self::PacketReturnType*) {

2
unsupported/Eigen/CXX11/src/Tensor/TensorReductionGpu.h
View File

@@ -292,7 +292,7 @@ __global__ void FullReductionKernelHalfFloat(Reducer reducer, const Self input,
}
template <typename Op>
__global__ void ReductionCleanupKernelHalfFloat(Op& reducer, half* output, half2* scratch) {
__global__ void ReductionCleanupKernelHalfFloat(Op reducer, half* output, half2* scratch) {
eigen_assert(threadIdx.x == 1);
half tmp = __low2half(*scratch);
reducer.reduce(__high2half(*scratch), &tmp);