GitHub-Proxy/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2025-06-04 18:54:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

ptranspose is not a template.

Browse Source
This commit is contained in:
Benoit Steiner 2016-05-23 19:55:55 -07:00
parent a5a3ba2b80
commit 283e33dea4
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Eigen/src/Core/arch/CUDA/PacketMathHalf.h
View File

@ -688,7 +688,7 @@ template<> EIGEN_DEVICE_FUNC inline void pscatter<half, Packet4h>(half* to, cons
to[stride*3].x = static_cast<unsigned short>(a >> 48); to[stride*3].x = static_cast<unsigned short>(a >> 48);
} }
template<> EIGEN_DEVICE_FUNC inline void EIGEN_DEVICE_FUNC inline void
ptranspose(PacketBlock<Packet4h,4>& kernel) { ptranspose(PacketBlock<Packet4h,4>& kernel) {
__m64 T0 = _mm_unpacklo_pi16(kernel.packet[0].x, kernel.packet[1].x); __m64 T0 = _mm_unpacklo_pi16(kernel.packet[0].x, kernel.packet[1].x);
__m64 T1 = _mm_unpacklo_pi16(kernel.packet[2].x, kernel.packet[3].x); __m64 T1 = _mm_unpacklo_pi16(kernel.packet[2].x, kernel.packet[3].x);