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

Remove packet ops pinsertfirst and pinsertlast that are only used in a single place, and can be replaced by other ops when constructing the first/final packet in linspaced_op_impl::packetOp.

Browse Source 
I cannot measure any performance changes for SSE, AVX, or AVX512.

name                                 old time/op             new time/op             delta
BM_LinSpace<float>/1                 1.63ns ± 0%             1.63ns ± 0%   ~             (p=0.762 n=5+5)
BM_LinSpace<float>/8                 4.92ns ± 3%             4.89ns ± 3%   ~             (p=0.421 n=5+5)
BM_LinSpace<float>/64                34.6ns ± 0%             34.6ns ± 0%   ~             (p=0.841 n=5+5)
BM_LinSpace<float>/512                217ns ± 0%              217ns ± 0%   ~             (p=0.421 n=5+5)
BM_LinSpace<float>/4k                1.68µs ± 0%             1.68µs ± 0%   ~             (p=1.000 n=5+5)
BM_LinSpace<float>/32k               13.3µs ± 0%             13.3µs ± 0%   ~             (p=0.905 n=5+4)
BM_LinSpace<float>/256k               107µs ± 0%              107µs ± 0%   ~             (p=0.841 n=5+5)
BM_LinSpace<float>/1M                 427µs ± 0%              427µs ± 0%   ~             (p=0.690 n=5+5)
This commit is contained in:
Rasmus Munk Larsen
2020-05-08 15:41:50 -07:00
parent 5c4e19fbe7
commit c1d944dd91
11 changed files with 6 additions and 270 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
Eigen/src/Core/functors/NullaryFunctors.h
View File

@@ -66,17 +66,17 @@ struct linspaced_op_impl<Scalar,/*IsInteger*/false>
{
Packet pi = plset<Packet>(Scalar(i-m_size1));
Packet res = padd(pset1<Packet>(m_high), pmul(pset1<Packet>(m_step), pi));
if(i==0)
res = pinsertfirst(res, m_low);
return res;
if (EIGEN_PREDICT_TRUE(i != 0)) return res;
Packet mask = pcmp_lt(pset1<Packet>(0), plset<Packet>(0));
return pselect<Packet>(mask, res, pset1<Packet>(m_low));
}
else
{
Packet pi = plset<Packet>(Scalar(i));
Packet res = padd(pset1<Packet>(m_low), pmul(pset1<Packet>(m_step), pi));
if(i==m_size1-unpacket_traits<Packet>::size+1)
res = pinsertlast(res, m_high);
return res;
if(EIGEN_PREDICT_TRUE(i != m_size1-unpacket_traits<Packet>::size+1)) return res;
Packet mask = pcmp_lt(plset<Packet>(0), pset1<Packet>(unpacket_traits<Packet>::size-1));
return pselect<Packet>(mask, res, pset1<Packet>(m_high));
}
}