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)
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

View File

@@ -288,26 +288,6 @@ template<typename Scalar,typename Packet> void packetmath()
}
}
if (PacketTraits::HasInsert || g_vectorize_sse) {
// pinsertfirst
for (int i=0; i<PacketSize; ++i)
ref[i] = data1[i];
Scalar s = internal::random<Scalar>();
ref[0] = s;
internal::pstore(data2, internal::pinsertfirst(internal::pload<Packet>(data1),s));
VERIFY(test::areApprox(ref, data2, PacketSize) && "internal::pinsertfirst");
}
if (PacketTraits::HasInsert || g_vectorize_sse) {
// pinsertlast
for (int i=0; i<PacketSize; ++i)
ref[i] = data1[i];
Scalar s = internal::random<Scalar>();
ref[PacketSize-1] = s;
internal::pstore(data2, internal::pinsertlast(internal::pload<Packet>(data1),s));
VERIFY(test::areApprox(ref, data2, PacketSize) && "internal::pinsertlast");
}
{
for (int i = 0; i < PacketSize; ++i) {
// "if" mask