projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: a99cd39) | patch
Change the generation of the vmuluwm instruction to be based on the MUL opcode.
authorKit Barton <kbarton@ca.ibm.com>
Tue, 10 Mar 2015 19:49:38 +0000 (19:49 +0000)
committerKit Barton <kbarton@ca.ibm.com>
Tue, 10 Mar 2015 19:49:38 +0000 (19:49 +0000)
commit1f9ea3a230a5cbebb20c30aad34d6cabade898e1
treecf045e7674a2c2880375549c76269087426b8412tree | snapshot
parenta99cd39362381881c114f28263e15dd40202c729commit | diff
Change the generation of the vmuluwm instruction to be based on the MUL opcode.

Phabricator review: http://reviews.llvm.org/D8185

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@231827 91177308-0d34-0410-b5e6-96231b3b80d8
include/llvm/IR/IntrinsicsPowerPC.td diff | blob | history
lib/Target/PowerPC/PPCISelLowering.cpp diff | blob | history
lib/Target/PowerPC/PPCInstrAltivec.td diff | blob | history
test/CodeGen/PowerPC/vec_mul.ll diff | blob | history
test/CodeGen/PowerPC/vec_mul_even_odd.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors