llvm-for-llvmta/test/CodeGen/PowerPC/vsx_builtins.ll

143 lines
4.3 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -relocation-model=static -verify-machineinstrs -mcpu=pwr9 \
; RUN: -mtriple=powerpc64le-unknown-linux-gnu \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck %s
; Function Attrs: nounwind readnone
define <4 x i32> @test1(i8* %a) {
; CHECK-LABEL: test1:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxvw4x v2, 0, r3
; CHECK-NEXT: blr
entry:
%0 = tail call <4 x i32> @llvm.ppc.vsx.lxvw4x.be(i8* %a)
ret <4 x i32> %0
}
; Function Attrs: nounwind readnone
declare <4 x i32> @llvm.ppc.vsx.lxvw4x.be(i8*)
; Function Attrs: nounwind readnone
define <2 x double> @test2(i8* %a) {
; CHECK-LABEL: test2:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxvd2x v2, 0, r3
; CHECK-NEXT: blr
entry:
%0 = tail call <2 x double> @llvm.ppc.vsx.lxvd2x.be(i8* %a)
ret <2 x double> %0
}
; Function Attrs: nounwind readnone
declare <2 x double> @llvm.ppc.vsx.lxvd2x.be(i8*)
; Function Attrs: nounwind readnone
define void @test3(<4 x i32> %a, i8* %b) {
; CHECK-LABEL: test3:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: stxvw4x v2, 0, r5
; CHECK-NEXT: blr
entry:
tail call void @llvm.ppc.vsx.stxvw4x.be(<4 x i32> %a, i8* %b)
ret void
}
; Function Attrs: nounwind readnone
declare void @llvm.ppc.vsx.stxvw4x.be(<4 x i32>, i8*)
; Function Attrs: nounwind readnone
define void @test4(<2 x double> %a, i8* %b) {
; CHECK-LABEL: test4:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: stxvd2x v2, 0, r5
; CHECK-NEXT: blr
entry:
tail call void @llvm.ppc.vsx.stxvd2x.be(<2 x double> %a, i8* %b)
ret void
}
; Function Attrs: nounwind readnone
declare void @llvm.ppc.vsx.stxvd2x.be(<2 x double>, i8*)
define i32 @test_vec_test_swdiv(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: test_vec_test_swdiv:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvtdivdp cr0, v2, v3
; CHECK-NEXT: mfocrf r3, 128
; CHECK-NEXT: srwi r3, r3, 28
; CHECK-NEXT: blr
entry:
%0 = tail call i32 @llvm.ppc.vsx.xvtdivdp(<2 x double> %a, <2 x double> %b)
ret i32 %0
}
declare i32 @llvm.ppc.vsx.xvtdivdp(<2 x double>, <2 x double>)
define i32 @test_vec_test_swdivs(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: test_vec_test_swdivs:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvtdivsp cr0, v2, v3
; CHECK-NEXT: mfocrf r3, 128
; CHECK-NEXT: srwi r3, r3, 28
; CHECK-NEXT: blr
entry:
%0 = tail call i32 @llvm.ppc.vsx.xvtdivsp(<4 x float> %a, <4 x float> %b)
ret i32 %0
}
declare i32 @llvm.ppc.vsx.xvtdivsp(<4 x float>, <4 x float>)
define i32 @test_vec_test_swsqrt(<2 x double> %a) {
; CHECK-LABEL: test_vec_test_swsqrt:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvtsqrtdp cr0, v2
; CHECK-NEXT: mfocrf r3, 128
; CHECK-NEXT: srwi r3, r3, 28
; CHECK-NEXT: blr
entry:
%0 = tail call i32 @llvm.ppc.vsx.xvtsqrtdp(<2 x double> %a)
ret i32 %0
}
declare i32 @llvm.ppc.vsx.xvtsqrtdp(<2 x double>)
define i32 @test_vec_test_swsqrts(<4 x float> %a) {
; CHECK-LABEL: test_vec_test_swsqrts:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvtsqrtsp cr0, v2
; CHECK-NEXT: mfocrf r3, 128
; CHECK-NEXT: srwi r3, r3, 28
; CHECK-NEXT: blr
entry:
%0 = tail call i32 @llvm.ppc.vsx.xvtsqrtsp(<4 x float> %a)
ret i32 %0
}
declare i32 @llvm.ppc.vsx.xvtsqrtsp(<4 x float>)
define i32 @xvtdivdp_andi(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: xvtdivdp_andi:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvtdivdp cr0, v2, v3
; CHECK-NEXT: li r4, 222
; CHECK-NEXT: mfocrf r3, 128
; CHECK-NEXT: srwi r3, r3, 28
; CHECK-NEXT: andi. r3, r3, 2
; CHECK-NEXT: li r3, 22
; CHECK-NEXT: iseleq r3, r4, r3
; CHECK-NEXT: blr
entry:
%0 = tail call i32 @llvm.ppc.vsx.xvtdivdp(<2 x double> %a, <2 x double> %b)
%1 = and i32 %0, 2
%cmp.not = icmp eq i32 %1, 0
%retval.0 = select i1 %cmp.not, i32 222, i32 22
ret i32 %retval.0
}
define i32 @xvtdivdp_shift(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: xvtdivdp_shift:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvtdivdp cr0, v2, v3
; CHECK-NEXT: mfocrf r3, 128
; CHECK-NEXT: srwi r3, r3, 28
; CHECK-NEXT: rlwinm r3, r3, 28, 31, 31
; CHECK-NEXT: blr
entry:
%0 = tail call i32 @llvm.ppc.vsx.xvtdivdp(<2 x double> %a, <2 x double> %b)
%1 = lshr i32 %0, 4
%.lobit = and i32 %1, 1
ret i32 %.lobit
}