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)

1 files changed, 0 insertions, 28 deletions

diff --git a/Eigen/src/Core/GenericPacketMath.h b/Eigen/src/Core/GenericPacketMath.h
index 0ed5d2cc5..449793372 100644
--- a/Eigen/src/Core/GenericPacketMath.h
+++ b/Eigen/src/Core/GenericPacketMath.h
@@ -727,34 +727,6 @@ pblend(const Selector<unpacket_traits<Packet>::size>& ifPacket, const Packet& th
   return ifPacket.select[0] ? thenPacket : elsePacket;
 }
 
-/** \internal \returns \a a with the first coefficient replaced by the scalar b */
-template<typename Packet> EIGEN_DEVICE_FUNC inline Packet
-pinsertfirst(const Packet& a, typename unpacket_traits<Packet>::type b)
-{
-  // Default implementation based on pblend.
-  // It must be specialized for higher performance.
-  Selector<unpacket_traits<Packet>::size> mask;
-  mask.select[0] = true;
-  // This for loop should be optimized away by the compiler.
-  for(Index i=1; i<unpacket_traits<Packet>::size; ++i)
-    mask.select[i] = false;
-  return pblend(mask, pset1<Packet>(b), a);
-}
-
-/** \internal \returns \a a with the last coefficient replaced by the scalar b */
-template<typename Packet> EIGEN_DEVICE_FUNC inline Packet
-pinsertlast(const Packet& a, typename unpacket_traits<Packet>::type b)
-{
-  // Default implementation based on pblend.
-  // It must be specialized for higher performance.
-  Selector<unpacket_traits<Packet>::size> mask;
-  // This for loop should be optimized away by the compiler.
-  for(Index i=0; i<unpacket_traits<Packet>::size-1; ++i)
-    mask.select[i] = false;
-  mask.select[unpacket_traits<Packet>::size-1] = true;
-  return pblend(mask, pset1<Packet>(b), a);
-}
-
 /***************************************************************************
  * Some generic implementations to be used by implementors
 ***************************************************************************/