projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 3614662) | patch
[X86][SSE] Keep 32-bit target i64 vector shifts on SSE unit.
authorSimon Pilgrim <llvm-dev@redking.me.uk>
Wed, 29 Jul 2015 21:44:27 +0000 (21:44 +0000)
committerSimon Pilgrim <llvm-dev@redking.me.uk>
Wed, 29 Jul 2015 21:44:27 +0000 (21:44 +0000)
commitf66eda96ebf7b2071c95347d1911d68ebcc41102
tree0e1f25d0f73036a858db61e0e64859af2aa7ebe9tree | snapshot
parent3614662adbe10c4e83338a23e020cd4874c92320commit | diff
[X86][SSE] Keep 32-bit target i64 vector shifts on SSE unit.

This patch improves the 32-bit target i64 constant matching to detect the shuffle vector splats that are introduced by i64 vector shift vectorization (D8416).

Differential Revision: http://reviews.llvm.org/D11327

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243577 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/X86/X86ISelLowering.cpp diff | blob | history
test/CodeGen/X86/vector-shift-ashr-128.ll diff | blob | history
test/CodeGen/X86/vector-shift-lshr-128.ll diff | blob | history
test/CodeGen/X86/vector-shift-shl-128.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors