mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 20:29:48 +00:00
86425451e5
Predicate UseAVX depricates pattern selection on AVX-512. This predicate is necessary for DAG selection to select EVEX form. But mapping SSE intrinsics to AVX-512 instructions is not ready yet. So I replaced UseAVX with HasAVX for intrinsics patterns. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@237903 91177308-0d34-0410-b5e6-96231b3b80d8
328 lines
12 KiB
LLVM
328 lines
12 KiB
LLVM
; RUN: llc < %s -mtriple=i386-apple-darwin -mattr=-avx,+sse4.1 | FileCheck %s
|
|
; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=knl | FileCheck %s
|
|
|
|
define <2 x double> @test_x86_sse41_blendpd(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK: blendpd
|
|
%res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
|
|
ret <2 x double> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone
|
|
|
|
|
|
define <4 x float> @test_x86_sse41_blendps(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK: blendps
|
|
%res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone
|
|
|
|
|
|
define <2 x double> @test_x86_sse41_blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2) {
|
|
; CHECK: blendvpd
|
|
%res = call <2 x double> @llvm.x86.sse41.blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2) ; <<2 x double>> [#uses=1]
|
|
ret <2 x double> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.sse41.blendvpd(<2 x double>, <2 x double>, <2 x double>) nounwind readnone
|
|
|
|
|
|
define <4 x float> @test_x86_sse41_blendvps(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2) {
|
|
; CHECK: blendvps
|
|
%res = call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2) ; <<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x float>) nounwind readnone
|
|
|
|
|
|
define <2 x double> @test_x86_sse41_dppd(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK: dppd
|
|
%res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
|
|
ret <2 x double> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i8) nounwind readnone
|
|
|
|
|
|
define <4 x float> @test_x86_sse41_dpps(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK: dpps
|
|
%res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i8) nounwind readnone
|
|
|
|
|
|
define <4 x float> @test_x86_sse41_insertps(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK: insertps
|
|
%res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i8) nounwind readnone
|
|
|
|
|
|
|
|
define <8 x i16> @test_x86_sse41_mpsadbw(<16 x i8> %a0, <16 x i8> %a1) {
|
|
; CHECK: mpsadbw
|
|
%res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i8) nounwind readnone
|
|
|
|
|
|
define <8 x i16> @test_x86_sse41_packusdw(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK: packusdw
|
|
%res = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a0, <4 x i32> %a1) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
|
|
define <16 x i8> @test_x86_sse41_pblendvb(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> %a2) {
|
|
; CHECK: pblendvb
|
|
%res = call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> %a2) ; <<16 x i8>> [#uses=1]
|
|
ret <16 x i8> %res
|
|
}
|
|
declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone
|
|
|
|
|
|
define <8 x i16> @test_x86_sse41_pblendw(<8 x i16> %a0, <8 x i16> %a1) {
|
|
; CHECK: pblendw
|
|
%res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i8 7) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone
|
|
|
|
|
|
define <8 x i16> @test_x86_sse41_phminposuw(<8 x i16> %a0) {
|
|
; CHECK: phminposuw
|
|
%res = call <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16>) nounwind readnone
|
|
|
|
|
|
define <16 x i8> @test_x86_sse41_pmaxsb(<16 x i8> %a0, <16 x i8> %a1) {
|
|
; CHECK: pmaxsb
|
|
%res = call <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
|
|
ret <16 x i8> %res
|
|
}
|
|
declare <16 x i8> @llvm.x86.sse41.pmaxsb(<16 x i8>, <16 x i8>) nounwind readnone
|
|
|
|
|
|
define <4 x i32> @test_x86_sse41_pmaxsd(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK: pmaxsd
|
|
%res = call <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %res
|
|
}
|
|
declare <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
|
|
define <4 x i32> @test_x86_sse41_pmaxud(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK: pmaxud
|
|
%res = call <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %res
|
|
}
|
|
declare <4 x i32> @llvm.x86.sse41.pmaxud(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
|
|
define <8 x i16> @test_x86_sse41_pmaxuw(<8 x i16> %a0, <8 x i16> %a1) {
|
|
; CHECK: pmaxuw
|
|
%res = call <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.sse41.pmaxuw(<8 x i16>, <8 x i16>) nounwind readnone
|
|
|
|
|
|
define <16 x i8> @test_x86_sse41_pminsb(<16 x i8> %a0, <16 x i8> %a1) {
|
|
; CHECK: pminsb
|
|
%res = call <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8> %a0, <16 x i8> %a1) ; <<16 x i8>> [#uses=1]
|
|
ret <16 x i8> %res
|
|
}
|
|
declare <16 x i8> @llvm.x86.sse41.pminsb(<16 x i8>, <16 x i8>) nounwind readnone
|
|
|
|
|
|
define <4 x i32> @test_x86_sse41_pminsd(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK: pminsd
|
|
%res = call <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %res
|
|
}
|
|
declare <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
|
|
define <4 x i32> @test_x86_sse41_pminud(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK: pminud
|
|
%res = call <4 x i32> @llvm.x86.sse41.pminud(<4 x i32> %a0, <4 x i32> %a1) ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %res
|
|
}
|
|
declare <4 x i32> @llvm.x86.sse41.pminud(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
|
|
define <8 x i16> @test_x86_sse41_pminuw(<8 x i16> %a0, <8 x i16> %a1) {
|
|
; CHECK: pminuw
|
|
%res = call <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16> %a0, <8 x i16> %a1) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.sse41.pminuw(<8 x i16>, <8 x i16>) nounwind readnone
|
|
|
|
|
|
define <4 x i32> @test_x86_sse41_pmovsxbd(<16 x i8> %a0) {
|
|
; CHECK: pmovsxbd
|
|
%res = call <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %res
|
|
}
|
|
declare <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8>) nounwind readnone
|
|
|
|
|
|
define <2 x i64> @test_x86_sse41_pmovsxbq(<16 x i8> %a0) {
|
|
; CHECK: pmovsxbq
|
|
%res = call <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
|
|
ret <2 x i64> %res
|
|
}
|
|
declare <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8>) nounwind readnone
|
|
|
|
|
|
define <8 x i16> @test_x86_sse41_pmovsxbw(<16 x i8> %a0) {
|
|
; CHECK: pmovsxbw
|
|
%res = call <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8>) nounwind readnone
|
|
|
|
|
|
define <2 x i64> @test_x86_sse41_pmovsxdq(<4 x i32> %a0) {
|
|
; CHECK: pmovsxdq
|
|
%res = call <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
|
|
ret <2 x i64> %res
|
|
}
|
|
declare <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32>) nounwind readnone
|
|
|
|
|
|
define <4 x i32> @test_x86_sse41_pmovsxwd(<8 x i16> %a0) {
|
|
; CHECK: pmovsxwd
|
|
%res = call <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %res
|
|
}
|
|
declare <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16>) nounwind readnone
|
|
|
|
|
|
define <2 x i64> @test_x86_sse41_pmovsxwq(<8 x i16> %a0) {
|
|
; CHECK: pmovsxwq
|
|
%res = call <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
|
|
ret <2 x i64> %res
|
|
}
|
|
declare <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16>) nounwind readnone
|
|
|
|
|
|
define <4 x i32> @test_x86_sse41_pmovzxbd(<16 x i8> %a0) {
|
|
; CHECK: pmovzxbd
|
|
%res = call <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8> %a0) ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %res
|
|
}
|
|
declare <4 x i32> @llvm.x86.sse41.pmovzxbd(<16 x i8>) nounwind readnone
|
|
|
|
|
|
define <2 x i64> @test_x86_sse41_pmovzxbq(<16 x i8> %a0) {
|
|
; CHECK: pmovzxbq
|
|
%res = call <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8> %a0) ; <<2 x i64>> [#uses=1]
|
|
ret <2 x i64> %res
|
|
}
|
|
declare <2 x i64> @llvm.x86.sse41.pmovzxbq(<16 x i8>) nounwind readnone
|
|
|
|
|
|
define <8 x i16> @test_x86_sse41_pmovzxbw(<16 x i8> %a0) {
|
|
; CHECK: pmovzxbw
|
|
%res = call <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8> %a0) ; <<8 x i16>> [#uses=1]
|
|
ret <8 x i16> %res
|
|
}
|
|
declare <8 x i16> @llvm.x86.sse41.pmovzxbw(<16 x i8>) nounwind readnone
|
|
|
|
|
|
define <2 x i64> @test_x86_sse41_pmovzxdq(<4 x i32> %a0) {
|
|
; CHECK: pmovzxdq
|
|
%res = call <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32> %a0) ; <<2 x i64>> [#uses=1]
|
|
ret <2 x i64> %res
|
|
}
|
|
declare <2 x i64> @llvm.x86.sse41.pmovzxdq(<4 x i32>) nounwind readnone
|
|
|
|
|
|
define <4 x i32> @test_x86_sse41_pmovzxwd(<8 x i16> %a0) {
|
|
; CHECK: pmovzxwd
|
|
%res = call <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16> %a0) ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %res
|
|
}
|
|
declare <4 x i32> @llvm.x86.sse41.pmovzxwd(<8 x i16>) nounwind readnone
|
|
|
|
|
|
define <2 x i64> @test_x86_sse41_pmovzxwq(<8 x i16> %a0) {
|
|
; CHECK: pmovzxwq
|
|
%res = call <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16> %a0) ; <<2 x i64>> [#uses=1]
|
|
ret <2 x i64> %res
|
|
}
|
|
declare <2 x i64> @llvm.x86.sse41.pmovzxwq(<8 x i16>) nounwind readnone
|
|
|
|
|
|
define <2 x i64> @test_x86_sse41_pmuldq(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK: pmuldq
|
|
%res = call <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32> %a0, <4 x i32> %a1) ; <<2 x i64>> [#uses=1]
|
|
ret <2 x i64> %res
|
|
}
|
|
declare <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
|
|
define i32 @test_x86_sse41_ptestc(<2 x i64> %a0, <2 x i64> %a1) {
|
|
; CHECK: ptest
|
|
; CHECK: sbbl
|
|
%res = call i32 @llvm.x86.sse41.ptestc(<2 x i64> %a0, <2 x i64> %a1) ; <i32> [#uses=1]
|
|
ret i32 %res
|
|
}
|
|
declare i32 @llvm.x86.sse41.ptestc(<2 x i64>, <2 x i64>) nounwind readnone
|
|
|
|
|
|
define i32 @test_x86_sse41_ptestnzc(<2 x i64> %a0, <2 x i64> %a1) {
|
|
; CHECK: ptest
|
|
; CHECK: seta
|
|
; CHECK: movzbl
|
|
%res = call i32 @llvm.x86.sse41.ptestnzc(<2 x i64> %a0, <2 x i64> %a1) ; <i32> [#uses=1]
|
|
ret i32 %res
|
|
}
|
|
declare i32 @llvm.x86.sse41.ptestnzc(<2 x i64>, <2 x i64>) nounwind readnone
|
|
|
|
|
|
define i32 @test_x86_sse41_ptestz(<2 x i64> %a0, <2 x i64> %a1) {
|
|
; CHECK: ptest
|
|
; CHECK: sete
|
|
; CHECK: movzbl
|
|
%res = call i32 @llvm.x86.sse41.ptestz(<2 x i64> %a0, <2 x i64> %a1) ; <i32> [#uses=1]
|
|
ret i32 %res
|
|
}
|
|
declare i32 @llvm.x86.sse41.ptestz(<2 x i64>, <2 x i64>) nounwind readnone
|
|
|
|
|
|
define <2 x double> @test_x86_sse41_round_pd(<2 x double> %a0) {
|
|
; CHECK: roundpd
|
|
%res = call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %a0, i32 7) ; <<2 x double>> [#uses=1]
|
|
ret <2 x double> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.sse41.round.pd(<2 x double>, i32) nounwind readnone
|
|
|
|
|
|
define <4 x float> @test_x86_sse41_round_ps(<4 x float> %a0) {
|
|
; CHECK: roundps
|
|
%res = call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %a0, i32 7) ; <<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
declare <4 x float> @llvm.x86.sse41.round.ps(<4 x float>, i32) nounwind readnone
|
|
|
|
|
|
define <2 x double> @test_x86_sse41_round_sd(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK: roundsd
|
|
%res = call <2 x double> @llvm.x86.sse41.round.sd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
|
|
ret <2 x double> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.sse41.round.sd(<2 x double>, <2 x double>, i32) nounwind readnone
|
|
|
|
|
|
define <4 x float> @test_x86_sse41_round_ss(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK: roundss
|
|
%res = call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
declare <4 x float> @llvm.x86.sse41.round.ss(<4 x float>, <4 x float>, i32) nounwind readnone
|