From 444dccecfc6c6d0dad4f400141a12f9ca76943d8 Mon Sep 17 00:00:00 2001 From: Benjamin Kramer Date: Sat, 13 Oct 2012 10:39:49 +0000 Subject: X86: Promote i8 cmov when both operands are coming from truncates of the same width. X86 doesn't have i8 cmovs so isel would emit a branch. Emitting branches at this level is often not a good idea because it's too late for many optimizations to kick in. This solution doesn't add any extensions (truncs are free) and tries to avoid introducing partial register stalls by filtering direct copyfromregs. I'm seeing a ~10% speedup on reading a random .png file with libpng15 via graphicsmagick on x86_64/westmere, but YMMV depending on the microarchitecture. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165868 91177308-0d34-0410-b5e6-96231b3b80d8 --- test/CodeGen/X86/select.ll | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'test/CodeGen/X86') diff --git a/test/CodeGen/X86/select.ll b/test/CodeGen/X86/select.ll index 2e39473057..f4c8d9e767 100644 --- a/test/CodeGen/X86/select.ll +++ b/test/CodeGen/X86/select.ll @@ -344,3 +344,16 @@ entry: ; ATOM: negw ; ATOM: sbbw } + +define i8 @test18(i32 %x, i8 zeroext %a, i8 zeroext %b) nounwind { + %cmp = icmp slt i32 %x, 15 + %sel = select i1 %cmp, i8 %a, i8 %b + ret i8 %sel +; CHECK: test18: +; CHECK: cmpl $15 +; CHECK: cmovll + +; ATOM: test18: +; ATOM: cmpl $15 +; ATOM: cmovll +} -- cgit v1.2.3