[PATCH] D27203: [X86] Prefer reduced width multiplication over pmulld on Silvermont

[Zvi Rackover via Phabricator via llvm-commits]

zvi created this revision.
zvi added reviewers: mkuper, delena, wmi.
zvi added a subscriber: llvm-commits.
zvi set the repository for this revision to rL LLVM.

Prefer expansions such as: pmullw,pmulhw,unpacklwd,unpackhwd over pmulld.
On Silvermont [source: Optimization Reference Manual]:
PMULLD has a throughput of 1/11 [instruction/cycles].
PMULHUW/PMULHW/PMULLW have a throughput of 1/2 [instruction/cycles].

Fixes pr31202.

Analysis of this issue was done by Fahana Aleen.


Repository:
  rL LLVM

https://reviews.llvm.org/D27203

Files:
  lib/Target/X86/X86.td
  lib/Target/X86/X86ISelLowering.cpp
  lib/Target/X86/X86Subtarget.cpp
  lib/Target/X86/X86Subtarget.h
  test/CodeGen/X86/slow-pmulld.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D27203.79519.patch
Type: text/x-patch
Size: 5737 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20161129/ad0f584f/attachment.bin>