mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-03 02:30:00 +00:00
X86 target-specific DAG combining that tried to convert VSELECT nodes into VECTOR_SHUFFLE nodes that it "knew" would lower into immediate-controlled blend nodes. Turns out, we have perfectly good lowering of all these VSELECT nodes, and indeed that lowering already knows how to handle lowering through BLENDI to immediate-controlled blend nodes. The code just wasn't getting used much because this thing forced the world to go through the vector shuffle lowering. Yuck. This also exposes that I was too aggressive in avoiding domain crossing in v218588 with that lowering -- when the other option is to expand into two 128-bit vectors, it is worth domain crossing. Restore that behavior now that we have nice tests covering it. The test updates here fall into two camps. One is where previously we ended up with an unsigned encoding of the blend operand and now we get a signed encoding. In most of those places there were elaborate comments explaining exactly what these operands really mean. Rather than that, just switch these tests to use the nicely decoded comments that make it obvious that the final shuffle matches. The other updates are just removing pointless domain crossing by blending integers with PBLENDW rather than BLENDPS. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218589 91177308-0d34-0410-b5e6-96231b3b80d8
31 lines
996 B
LLVM
31 lines
996 B
LLVM
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -mattr=+sse4.1 | FileCheck %s
|
|
|
|
|
|
; Verify that we produce movss instead of blendvps when possible.
|
|
|
|
;CHECK-LABEL: vsel_float:
|
|
;CHECK-NOT: blend
|
|
;CHECK: movss
|
|
;CHECK: ret
|
|
define <4 x float> @vsel_float(<4 x float> %v1, <4 x float> %v2) {
|
|
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x float> %v1, <4 x float> %v2
|
|
ret <4 x float> %vsel
|
|
}
|
|
|
|
;CHECK-LABEL: vsel_4xi8:
|
|
;CHECK-NOT: blend
|
|
;CHECK: movss
|
|
;CHECK: ret
|
|
define <4 x i8> @vsel_4xi8(<4 x i8> %v1, <4 x i8> %v2) {
|
|
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i8> %v1, <4 x i8> %v2
|
|
ret <4 x i8> %vsel
|
|
}
|
|
|
|
;CHECK-LABEL: vsel_8xi16:
|
|
;CHECK: pblendw {{.*}} ## xmm0 = xmm0[0],xmm1[1,2,3],xmm0[4],xmm1[5,6,7]
|
|
;CHECK: ret
|
|
define <8 x i16> @vsel_8xi16(<8 x i16> %v1, <8 x i16> %v2) {
|
|
%vsel = select <8 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <8 x i16> %v1, <8 x i16> %v2
|
|
ret <8 x i16> %vsel
|
|
}
|