From cc6165695fa1713230184d743368b8b3642faa5d Mon Sep 17 00:00:00 2001 From: Nadav Rotem Date: Sun, 15 Jan 2012 19:27:55 +0000 Subject: [AVX] Optimize x86 VSELECT instructions using SimplifyDemandedBits. We know that the blend instructions only use the MSB, so if the mask is sign-extended then we can convert it into a SHL instruction. This is a common pattern because the type-legalizer sign-extends the i1 type which is used by the LLVM-IR for the condition. Added a new optimization in SimplifyDemandedBits for SIGN_EXTEND_INREG -> SHL. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@148225 91177308-0d34-0410-b5e6-96231b3b80d8 --- test/CodeGen/X86/blend-msb.ll | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 test/CodeGen/X86/blend-msb.ll (limited to 'test/CodeGen/X86/blend-msb.ll') diff --git a/test/CodeGen/X86/blend-msb.ll b/test/CodeGen/X86/blend-msb.ll new file mode 100644 index 0000000000..3a10c70ada --- /dev/null +++ b/test/CodeGen/X86/blend-msb.ll @@ -0,0 +1,37 @@ +; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -promote-elements -mattr=+sse41 | FileCheck %s + + +; In this test we check that sign-extend of the mask bit is performed by +; shifting the needed bit to the MSB, and not using shl+sra. + +;CHECK: vsel_float +;CHECK: pslld +;CHECK-NEXT: blendvps +;CHECK: ret +define <4 x float> @vsel_float(<4 x float> %v1, <4 x float> %v2) { + %vsel = select <4 x i1> , <4 x float> %v1, <4 x float> %v2 + ret <4 x float> %vsel +} + +;CHECK: vsel_4xi8 +;CHECK: pslld +;CHECK-NEXT: blendvps +;CHECK: ret +define <4 x i8> @vsel_4xi8(<4 x i8> %v1, <4 x i8> %v2) { + %vsel = select <4 x i1> , <4 x i8> %v1, <4 x i8> %v2 + ret <4 x i8> %vsel +} + + +; We do not have native support for v8i16 blends and we have to use the +; blendvb instruction or a sequence of NAND/OR/AND. Make sure that we do not r +; reduce the mask in this case. +;CHECK: vsel_8xi16 +;CHECK: psllw +;CHECK: psraw +;CHECK: pblendvb +;CHECK: ret +define <8 x i16> @vsel_8xi16(<8 x i16> %v1, <8 x i16> %v2) { + %vsel = select <8 x i1> , <8 x i16> %v1, <8 x i16> %v2 + ret <8 x i16> %vsel +} -- cgit v1.2.3