summaryrefslogtreecommitdiffstats
path: root/llvm/test/DebugInfo/X86/pieces-3.ll
diff options
context:
space:
mode:
authorJuergen Ributzka <juergen@apple.com>2015-03-03 17:22:53 +0000
committerJuergen Ributzka <juergen@apple.com>2015-03-03 17:22:53 +0000
commit9baa03fc0793afd4d4cc6da553c13aa0b75ee91b (patch)
treead7c8a3cd00bc04ec7626abd96fc6b2e628853e1 /llvm/test/DebugInfo/X86/pieces-3.ll
parent773fa2cb0361d5dc27a7e6b13d65d8416be92d37 (diff)
downloadbcm5719-llvm-9baa03fc0793afd4d4cc6da553c13aa0b75ee91b.tar.gz
bcm5719-llvm-9baa03fc0793afd4d4cc6da553c13aa0b75ee91b.zip
Lower _mm256_broadcastsi128_si256 directly to a vector shuffle.
Originally we were using the same GCC builtins to lower this AVX2 vector intrinsic. Instead we will now lower it directly to a vector shuffle. This will not only allow LLVM to generate better code, but it will also allow us to remove the GCC intrinsics. Reviewed by Andrea This is related to rdar://problem/18742778. llvm-svn: 231081
Diffstat (limited to 'llvm/test/DebugInfo/X86/pieces-3.ll')
0 files changed, 0 insertions, 0 deletions
OpenPOWER on IntegriCloud