Skip to content

Commit

Permalink
Merge pull request eigenteam#5 from ericcano/myf612df273689a19d25b45c…
Browse files Browse the repository at this point in the history
…a4f8269463207c4fee

Re-adding last commit of "Re-import and update of Eigen patches for CUDA" eigenteam#4
  • Loading branch information
smuzaffar authored Aug 3, 2021
2 parents 4fc3872 + daa09a4 commit 5419f5b
Showing 1 changed file with 2 additions and 0 deletions.
2 changes: 2 additions & 0 deletions Eigen/src/Core/products/GeneralBlockPanelKernel.h
Original file line number Diff line number Diff line change
Expand Up @@ -1312,6 +1312,7 @@ struct lhs_process_one_packet
{
typedef typename GEBPTraits::RhsPacketx4 RhsPacketx4;

EIGEN_DEVICE_FUNC
EIGEN_STRONG_INLINE void peeled_kc_onestep(Index K, const LhsScalar* blA, const RhsScalar* blB, GEBPTraits traits, LhsPacket *A0, RhsPacketx4 *rhs_panel, RhsPacket *T0, AccPacket *C0, AccPacket *C1, AccPacket *C2, AccPacket *C3)
{
EIGEN_ASM_COMMENT("begin step of gebp micro kernel 1X4");
Expand All @@ -1328,6 +1329,7 @@ struct lhs_process_one_packet
EIGEN_ASM_COMMENT("end step of gebp micro kernel 1X4");
}

EIGEN_DEVICE_FUNC
EIGEN_STRONG_INLINE void operator()(
const DataMapper& res, const LhsScalar* blockA, const RhsScalar* blockB, ResScalar alpha,
Index peelStart, Index peelEnd, Index strideA, Index strideB, Index offsetA, Index offsetB,
Expand Down

0 comments on commit 5419f5b

Please sign in to comment.