[PATCH] [X86] Integer multiplication improvements

[Michael Kuperstein]

Hi nadav, delena,

This makes the x86-specific DAG combine for (imul -> shl + lea) more generic, allowing it to handle some cases it could not handle before (e.g. x * -81 or x * 1920).

http://reviews.llvm.org/D7320

Files:
  lib/Target/X86/X86ISelLowering.cpp
  test/CodeGen/X86/imul-lea-2.ll
  test/CodeGen/X86/imul.ll

EMAIL PREFERENCES
  http://reviews.llvm.org/settings/panel/emailpreferences/
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D7320.19111.patch
Type: text/x-patch
Size: 7187 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20150201/781b7ada/attachment.bin>