diff options
author | Rasmus Munk Larsen <rmlarsen@google.com> | 2020-05-08 15:41:50 -0700 |
---|---|---|
committer | Rasmus Munk Larsen <rmlarsen@google.com> | 2020-05-08 15:41:50 -0700 |
commit | c1d944dd913d05180b7d2d1229072c9c52a11f29 (patch) | |
tree | 80a936a6403af21079445e000c897c7357c122bf /Eigen/src/Core/functors | |
parent | 5c4e19fbe7ea19d9d8b51243515f972237a49267 (diff) |
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.
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)
Diffstat (limited to 'Eigen/src/Core/functors')
-rw-r--r-- | Eigen/src/Core/functors/NullaryFunctors.h | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/Eigen/src/Core/functors/NullaryFunctors.h b/Eigen/src/Core/functors/NullaryFunctors.h index a3b737ad8..4aa33a19f 100644 --- a/Eigen/src/Core/functors/NullaryFunctors.h +++ b/Eigen/src/Core/functors/NullaryFunctors.h @@ -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)); } } |