mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-16 11:30:51 +00:00
c5f611404c
Summary: Implemented an InstCombine transformation that takes a blendv* intrinsic call and translates it into an IR select, if the mask is constant. This will eventually get lowered into blends with immediates if possible, or pblendvb (with an option to further optimize if we can transform the pblendvb into a blend+immediate instruction, depending on the selector). It will also enable optimizations by the IR passes, which give up on sight of the intrinsic. Both the transformation and the lowering of its result to asm got shiny new tests. The transformation is a bit convoluted because of blendvp[sd]'s definition: Its mask is a floating point value! This forces us to convert it and get the highest bit. I suppose this happened because the mask has type __m128 in Intel's intrinsic and v4sf (for blendps) in gcc's builtin. I will send an email to llvm-dev to discuss if we want to change this or not. Reviewers: grosbach, delena, nadav Differential Revision: http://reviews.llvm.org/D3859 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209643 91177308-0d34-0410-b5e6-96231b3b80d8
12 lines
689 B
LLVM
12 lines
689 B
LLVM
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=core-avx2 | FileCheck %s
|
|
|
|
define <32 x i8> @constant_pblendvb_avx2(<32 x i8> %xyzw, <32 x i8> %abcd) {
|
|
; CHECK-LABEL: constant_pblendvb_avx2:
|
|
; CHECK: vmovdqa
|
|
; CHECK: vpblendvb
|
|
%1 = select <32 x i1> <i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false>, <32 x i8> %xyzw, <32 x i8> %abcd
|
|
ret <32 x i8> %1
|
|
}
|
|
|
|
declare <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8>, <32 x i8>, <32 x i8>)
|