[PATCH] D48936: [X86][SSE] Prefer BLEND(SHL(v, c1), SHL(v, c2)) over MUL(v, c3)

Simon Pilgrim via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Tue Jul 10 01:03:41 PDT 2018


This revision was automatically updated to reflect the committed changes.
Closed by commit rL336642: [X86][SSE] Prefer BLEND(SHL(v,c1),SHL(v,c2)) over MUL(v, c3) (authored by RKSimon, committed by ).

Changed prior to commit:
  https://reviews.llvm.org/D48936?vs=154525&id=154764#toc

Repository:
  rL LLVM

https://reviews.llvm.org/D48936

Files:
  llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
  llvm/trunk/test/CodeGen/X86/combine-shl.ll
  llvm/trunk/test/CodeGen/X86/lower-vec-shift.ll
  llvm/trunk/test/CodeGen/X86/vec_shift6.ll
  llvm/trunk/test/CodeGen/X86/widen_arith-4.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D48936.154764.patch
Type: text/x-patch
Size: 10366 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180710/dddadbba/attachment.bin>


More information about the llvm-commits mailing list