diff options
author | Nadav Rotem <nadav.rotem@intel.com> | 2012-02-03 13:18:25 +0000 |
---|---|---|
committer | Nadav Rotem <nadav.rotem@intel.com> | 2012-02-03 13:18:25 +0000 |
commit | 7e413e9c94294f17daa64ac9fda09a738e20caa5 (patch) | |
tree | 12f308bb55bb90e39616f35c56c49dda0597f793 /test/CodeGen/X86/2011-12-8-bitcastintprom.ll | |
parent | a02556679e685280bd59e0197d9e4aa51d40480c (diff) | |
download | external_llvm-7e413e9c94294f17daa64ac9fda09a738e20caa5.zip external_llvm-7e413e9c94294f17daa64ac9fda09a738e20caa5.tar.gz external_llvm-7e413e9c94294f17daa64ac9fda09a738e20caa5.tar.bz2 |
The type-legalizer often scalarizes code. One of the common patterns is extract-and-truncate.
In this patch we optimize this pattern and convert the sequence into extract op of a narrow type.
This allows the BUILD_VECTOR dag optimizations to construct efficient shuffle operations in many cases.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149692 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/X86/2011-12-8-bitcastintprom.ll')
-rw-r--r-- | test/CodeGen/X86/2011-12-8-bitcastintprom.ll | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/test/CodeGen/X86/2011-12-8-bitcastintprom.ll b/test/CodeGen/X86/2011-12-8-bitcastintprom.ll index ceee8e6..e2b3ebc 100644 --- a/test/CodeGen/X86/2011-12-8-bitcastintprom.ll +++ b/test/CodeGen/X86/2011-12-8-bitcastintprom.ll @@ -2,8 +2,8 @@ ; Make sure that the conversion between v4i8 to v2i16 is not a simple bitcast. ; CHECK: prom_bug -; CHECK: movd ; CHECK: shufb +; CHECK: movd ; CHECK: movw ; CHECK: ret define void @prom_bug(<4 x i8> %t, i16* %p) { |