mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-11-11 23:05:31 +00:00
b26c7727c9
DomainValues that are only used by "don't care" instructions are now collapsed to the first possible execution domain after all basic blocks have been processed. This typically means the PS domain on x86. For example, the vsel_i64 and vsel_double functions in sse2-blend.ll are completely collapsed to the PS domain instead of containing a mix of execution domains created by isel. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@144037 91177308-0d34-0410-b5e6-96231b3b80d8
62 lines
1.6 KiB
LLVM
62 lines
1.6 KiB
LLVM
; RUN: llc < %s -march=x86 -mcpu=yonah -mattr=+sse2,-sse41 | FileCheck %s
|
|
|
|
; CHECK: vsel_float
|
|
; CHECK: pandn
|
|
; CHECK: pand
|
|
; CHECK: por
|
|
; CHECK: ret
|
|
define void@vsel_float(<4 x float>* %v1, <4 x float>* %v2) {
|
|
%A = load <4 x float>* %v1
|
|
%B = load <4 x float>* %v2
|
|
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x float> %A, <4 x float> %B
|
|
store <4 x float > %vsel, <4 x float>* %v1
|
|
ret void
|
|
}
|
|
|
|
; CHECK: vsel_i32
|
|
; CHECK: pandn
|
|
; CHECK: pand
|
|
; CHECK: por
|
|
; CHECK: ret
|
|
define void@vsel_i32(<4 x i32>* %v1, <4 x i32>* %v2) {
|
|
%A = load <4 x i32>* %v1
|
|
%B = load <4 x i32>* %v2
|
|
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i32> %A, <4 x i32> %B
|
|
store <4 x i32 > %vsel, <4 x i32>* %v1
|
|
ret void
|
|
}
|
|
|
|
; Without forcing instructions, fall back to the preferred PS domain.
|
|
; CHECK: vsel_i64
|
|
; CHECK: xorps
|
|
; CHECK: andps
|
|
; CHECK: andnps
|
|
; CHECK: orps
|
|
; CHECK: ret
|
|
|
|
define void@vsel_i64(<4 x i64>* %v1, <4 x i64>* %v2) {
|
|
%A = load <4 x i64>* %v1
|
|
%B = load <4 x i64>* %v2
|
|
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i64> %A, <4 x i64> %B
|
|
store <4 x i64 > %vsel, <4 x i64>* %v1
|
|
ret void
|
|
}
|
|
|
|
; Without forcing instructions, fall back to the preferred PS domain.
|
|
; CHECK: vsel_double
|
|
; CHECK: xorps
|
|
; CHECK: andps
|
|
; CHECK: andnps
|
|
; CHECK: orps
|
|
; CHECK: ret
|
|
|
|
define void@vsel_double(<4 x double>* %v1, <4 x double>* %v2) {
|
|
%A = load <4 x double>* %v1
|
|
%B = load <4 x double>* %v2
|
|
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x double> %A, <4 x double> %B
|
|
store <4 x double > %vsel, <4 x double>* %v1
|
|
ret void
|
|
}
|
|
|
|
|