mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-28 19:31:58 +00:00
b2f47c6a34
ConstantSDNodes (or UNDEFs) into a simple BUILD_VECTOR. For example, given the following sequence of dag nodes: i32 C = Constant<1> v4i32 V = BUILD_VECTOR C, C, C, C v4i32 Result = SIGN_EXTEND_INREG V, ValueType:v4i1 The SIGN_EXTEND_INREG node can be folded into a build_vector since the vector in input is a BUILD_VECTOR of constants. The optimized sequence is: i32 C = Constant<-1> v4i32 Result = BUILD_VECTOR C, C, C, C git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@198084 91177308-0d34-0410-b5e6-96231b3b80d8
40 lines
1.2 KiB
LLVM
40 lines
1.2 KiB
LLVM
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -mattr=+sse4.1 | 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-LABEL: vsel_float:
|
|
;CHECK: movl $-1
|
|
;CHECK-NEXT: movd
|
|
;CHECK-NEXT: blendvps
|
|
;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: movl $-1
|
|
;CHECK-NEXT: movd
|
|
;CHECK-NEXT: blendvps
|
|
;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
|
|
}
|
|
|
|
|
|
; 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
|
|
; reduce the mask in this case.
|
|
;CHECK-LABEL: vsel_8xi16:
|
|
;CHECK: andps
|
|
;CHECK: andps
|
|
;CHECK: orps
|
|
;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
|
|
}
|