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

bug #955 - Implement a rotating kernel alternative in the 3px4 gebp path

Browse Source 
This is substantially faster on ARM, where it's important to minimize the number of loads.

This is specific to the case where all packet types are of size 4. I made my best attempt to minimize how dirty this is... opinions welcome.

Eventually one could have a generic rotated kernel, but it would take some work to get there. Also, on sandy bridge, in my experience, it's not beneficial (even about 1% slower).
This commit is contained in:
Benoit Jacob
2015-02-18 15:03:35 -05:00
parent ee27d50633
commit 9bd8a4bab5
5 changed files with 133 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
Eigen/src/Core/arch/SSE/PacketMath.h
View File

@@ -462,6 +462,29 @@ template<> EIGEN_STRONG_INLINE Packet2d preverse(const Packet2d& a)
template<> EIGEN_STRONG_INLINE Packet4i preverse(const Packet4i& a)
{ return _mm_shuffle_epi32(a,0x1B); }
template<size_t offset>
struct protate_impl<offset, Packet4f>
{
static Packet4f run(const Packet4f& a) {
return vec4f_swizzle1(a, offset, (offset + 1) % 4, (offset + 2) % 4, (offset + 3) % 4);
}
};
template<size_t offset>
struct protate_impl<offset, Packet4i>
{
static Packet4i run(const Packet4i& a) {
return vec4i_swizzle1(a, offset, (offset + 1) % 4, (offset + 2) % 4, (offset + 3) % 4);
}
};
template<size_t offset>
struct protate_impl<offset, Packet2d>
{
static Packet2d run(const Packet2d& a) {
return vec2d_swizzle1(a, offset, (offset + 1) % 2);
}
};
template<> EIGEN_STRONG_INLINE Packet4f pabs(const Packet4f& a)
{