+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=arm-eabi -mattr=+neon %s -o - | FileCheck %s
define <4 x i32> @test1(<4 x i32> %a) nounwind {
; CHECK-LABEL: test1:
-; CHECK: vabs.s32 q
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d17, r2, r3
+; CHECK-NEXT: vmov d16, r0, r1
+; CHECK-NEXT: vabs.s32 q8, q8
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: vmov r2, r3, d17
+; CHECK-NEXT: mov pc, lr
%tmp1neg = sub <4 x i32> zeroinitializer, %a
%b = icmp sgt <4 x i32> %a, <i32 -1, i32 -1, i32 -1, i32 -1>
%abs = select <4 x i1> %b, <4 x i32> %a, <4 x i32> %tmp1neg
define <4 x i32> @test2(<4 x i32> %a) nounwind {
; CHECK-LABEL: test2:
-; CHECK: vabs.s32 q
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d17, r2, r3
+; CHECK-NEXT: vmov d16, r0, r1
+; CHECK-NEXT: vabs.s32 q8, q8
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: vmov r2, r3, d17
+; CHECK-NEXT: mov pc, lr
%tmp1neg = sub <4 x i32> zeroinitializer, %a
%b = icmp sge <4 x i32> %a, zeroinitializer
%abs = select <4 x i1> %b, <4 x i32> %a, <4 x i32> %tmp1neg
define <8 x i16> @test3(<8 x i16> %a) nounwind {
; CHECK-LABEL: test3:
-; CHECK: vabs.s16 q
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d17, r2, r3
+; CHECK-NEXT: vmov d16, r0, r1
+; CHECK-NEXT: vabs.s16 q8, q8
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: vmov r2, r3, d17
+; CHECK-NEXT: mov pc, lr
%tmp1neg = sub <8 x i16> zeroinitializer, %a
%b = icmp sgt <8 x i16> %a, zeroinitializer
%abs = select <8 x i1> %b, <8 x i16> %a, <8 x i16> %tmp1neg
define <16 x i8> @test4(<16 x i8> %a) nounwind {
; CHECK-LABEL: test4:
-; CHECK: vabs.s8 q
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d17, r2, r3
+; CHECK-NEXT: vmov d16, r0, r1
+; CHECK-NEXT: vabs.s8 q8, q8
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: vmov r2, r3, d17
+; CHECK-NEXT: mov pc, lr
%tmp1neg = sub <16 x i8> zeroinitializer, %a
%b = icmp slt <16 x i8> %a, zeroinitializer
%abs = select <16 x i1> %b, <16 x i8> %tmp1neg, <16 x i8> %a
define <4 x i32> @test5(<4 x i32> %a) nounwind {
; CHECK-LABEL: test5:
-; CHECK: vabs.s32 q
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d17, r2, r3
+; CHECK-NEXT: vmov d16, r0, r1
+; CHECK-NEXT: vabs.s32 q8, q8
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: vmov r2, r3, d17
+; CHECK-NEXT: mov pc, lr
%tmp1neg = sub <4 x i32> zeroinitializer, %a
%b = icmp sle <4 x i32> %a, zeroinitializer
%abs = select <4 x i1> %b, <4 x i32> %tmp1neg, <4 x i32> %a
define <2 x i32> @test6(<2 x i32> %a) nounwind {
; CHECK-LABEL: test6:
-; CHECK: vabs.s32 d
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d16, r0, r1
+; CHECK-NEXT: vabs.s32 d16, d16
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: mov pc, lr
%tmp1neg = sub <2 x i32> zeroinitializer, %a
%b = icmp sgt <2 x i32> %a, <i32 -1, i32 -1>
%abs = select <2 x i1> %b, <2 x i32> %a, <2 x i32> %tmp1neg
define <2 x i32> @test7(<2 x i32> %a) nounwind {
; CHECK-LABEL: test7:
-; CHECK: vabs.s32 d
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d16, r0, r1
+; CHECK-NEXT: vabs.s32 d16, d16
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: mov pc, lr
%tmp1neg = sub <2 x i32> zeroinitializer, %a
%b = icmp sge <2 x i32> %a, zeroinitializer
%abs = select <2 x i1> %b, <2 x i32> %a, <2 x i32> %tmp1neg
define <4 x i16> @test8(<4 x i16> %a) nounwind {
; CHECK-LABEL: test8:
-; CHECK: vabs.s16 d
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d16, r0, r1
+; CHECK-NEXT: vabs.s16 d16, d16
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: mov pc, lr
%tmp1neg = sub <4 x i16> zeroinitializer, %a
%b = icmp sgt <4 x i16> %a, zeroinitializer
%abs = select <4 x i1> %b, <4 x i16> %a, <4 x i16> %tmp1neg
define <8 x i8> @test9(<8 x i8> %a) nounwind {
; CHECK-LABEL: test9:
-; CHECK: vabs.s8 d
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d16, r0, r1
+; CHECK-NEXT: vabs.s8 d16, d16
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: mov pc, lr
%tmp1neg = sub <8 x i8> zeroinitializer, %a
%b = icmp slt <8 x i8> %a, zeroinitializer
%abs = select <8 x i1> %b, <8 x i8> %tmp1neg, <8 x i8> %a
define <2 x i32> @test10(<2 x i32> %a) nounwind {
; CHECK-LABEL: test10:
-; CHECK: vabs.s32 d
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d16, r0, r1
+; CHECK-NEXT: vabs.s32 d16, d16
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: mov pc, lr
%tmp1neg = sub <2 x i32> zeroinitializer, %a
%b = icmp sle <2 x i32> %a, zeroinitializer
%abs = select <2 x i1> %b, <2 x i32> %tmp1neg, <2 x i32> %a
define <4 x i32> @test11(<4 x i16> %a, <4 x i16> %b) nounwind {
; CHECK-LABEL: test11:
-; CHECK: vabdl.u16 q
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d16, r2, r3
+; CHECK-NEXT: vmov d17, r0, r1
+; CHECK-NEXT: vabdl.u16 q8, d17, d16
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: vmov r2, r3, d17
+; CHECK-NEXT: mov pc, lr
%zext1 = zext <4 x i16> %a to <4 x i32>
%zext2 = zext <4 x i16> %b to <4 x i32>
%diff = sub <4 x i32> %zext1, %zext2
}
define <8 x i16> @test12(<8 x i8> %a, <8 x i8> %b) nounwind {
; CHECK-LABEL: test12:
-; CHECK: vabdl.u8 q
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d16, r2, r3
+; CHECK-NEXT: vmov d17, r0, r1
+; CHECK-NEXT: vabdl.u8 q8, d17, d16
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: vmov r2, r3, d17
+; CHECK-NEXT: mov pc, lr
%zext1 = zext <8 x i8> %a to <8 x i16>
%zext2 = zext <8 x i8> %b to <8 x i16>
%diff = sub <8 x i16> %zext1, %zext2
define <2 x i64> @test13(<2 x i32> %a, <2 x i32> %b) nounwind {
; CHECK-LABEL: test13:
-; CHECK: vabdl.u32 q
+; CHECK: @ BB#0:
+; CHECK-NEXT: vmov d16, r2, r3
+; CHECK-NEXT: vmov d17, r0, r1
+; CHECK-NEXT: vabdl.u32 q8, d17, d16
+; CHECK-NEXT: vmov r0, r1, d16
+; CHECK-NEXT: vmov r2, r3, d17
+; CHECK-NEXT: mov pc, lr
%zext1 = zext <2 x i32> %a to <2 x i64>
%zext2 = zext <2 x i32> %b to <2 x i64>
%diff = sub <2 x i64> %zext1, %zext2
-; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64-apple-darwin | grep extsw | count 2
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64le-unknown-linux-gnu | FileCheck %s
@lens = external global i8* ; <i8**> [#uses=1]
@vals = external global i32* ; <i32**> [#uses=1]
define i32 @test(i32 %i) {
- %tmp = load i8*, i8** @lens ; <i8*> [#uses=1]
- %tmp1 = getelementptr i8, i8* %tmp, i32 %i ; <i8*> [#uses=1]
- %tmp.upgrd.1 = load i8, i8* %tmp1 ; <i8> [#uses=1]
- %tmp2 = zext i8 %tmp.upgrd.1 to i32 ; <i32> [#uses=1]
- %tmp3 = load i32*, i32** @vals ; <i32*> [#uses=1]
- %tmp5 = sub i32 1, %tmp2 ; <i32> [#uses=1]
- %tmp6 = getelementptr i32, i32* %tmp3, i32 %tmp5 ; <i32*> [#uses=1]
- %tmp7 = load i32, i32* %tmp6 ; <i32> [#uses=1]
- ret i32 %tmp7
+; CHECK-LABEL: test:
+; CHECK: # BB#0:
+; CHECK-NEXT: addis 4, 2, .LC0@toc@ha
+; CHECK-NEXT: extsw 3, 3
+; CHECK-NEXT: addis 5, 2, .LC1@toc@ha
+; CHECK-NEXT: ld 4, .LC0@toc@l(4)
+; CHECK-NEXT: ld 4, 0(4)
+; CHECK-NEXT: lbzx 3, 4, 3
+; CHECK-NEXT: ld 4, .LC1@toc@l(5)
+; CHECK-NEXT: subfic 3, 3, 1
+; CHECK-NEXT: extsw 3, 3
+; CHECK-NEXT: ld 4, 0(4)
+; CHECK-NEXT: sldi 3, 3, 2
+; CHECK-NEXT: lwzx 3, 4, 3
+; CHECK-NEXT: blr
+ %tmp = load i8*, i8** @lens ; <i8*> [#uses=1]
+ %tmp1 = getelementptr i8, i8* %tmp, i32 %i ; <i8*> [#uses=1]
+ %tmp.upgrd.1 = load i8, i8* %tmp1 ; <i8> [#uses=1]
+ %tmp2 = zext i8 %tmp.upgrd.1 to i32 ; <i32> [#uses=1]
+ %tmp3 = load i32*, i32** @vals ; <i32*> [#uses=1]
+ %tmp5 = sub i32 1, %tmp2 ; <i32> [#uses=1]
+ %tmp6 = getelementptr i32, i32* %tmp3, i32 %tmp5 ; <i32*> [#uses=1]
+ %tmp7 = load i32, i32* %tmp6 ; <i32> [#uses=1]
+ ret i32 %tmp7
}
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
; RUN: -mcpu=pwr8 < %s | FileCheck %s
; Function Attrs: norecurse nounwind readonly
define zeroext i1 @test1(%class.PB2* %s_a, %class.PB2* %s_b) local_unnamed_addr #0 {
+; CHECK-LABEL: test1:
+; CHECK: # BB#0: # %entry
+; CHECK-NEXT: lwz 3, 0(3)
+; CHECK-NEXT: lwz 4, 0(4)
+; CHECK-NEXT: rlwinm 3, 3, 0, 28, 28
+; CHECK-NEXT: rlwinm 4, 4, 0, 28, 28
+; CHECK-NEXT: sub 3, 3, 4
+; CHECK-NEXT: rldicl 3, 3, 1, 63
+; CHECK-NEXT: blr
entry:
%arrayidx.i6 = bitcast %class.PB2* %s_a to i32*
%0 = load i32, i32* %arrayidx.i6, align 8, !tbaa !1
%and.i4 = and i32 %1, 8
%cmp.i5 = icmp ult i32 %and.i, %and.i4
ret i1 %cmp.i5
-
-; CHECK-LABEL: @test1
-; CHECK: rlwinm [[REG1:[0-9]*]]
-; CHECK-NEXT: rlwinm [[REG2:[0-9]*]]
-; CHECK-NEXT: sub [[REG3:[0-9]*]], [[REG1]], [[REG2]]
-; CHECK-NEXT: rldicl 3, [[REG3]]
-; CHECK: blr
-
}
; Function Attrs: norecurse nounwind readonly
define zeroext i1 @test2(%class.PB2* %s_a, %class.PB2* %s_b) local_unnamed_addr #0 {
+; CHECK-LABEL: test2:
+; CHECK: # BB#0: # %entry
+; CHECK-NEXT: lwz 3, 0(3)
+; CHECK-NEXT: lwz 4, 0(4)
+; CHECK-NEXT: rlwinm 3, 3, 0, 28, 28
+; CHECK-NEXT: rlwinm 4, 4, 0, 28, 28
+; CHECK-NEXT: sub 3, 4, 3
+; CHECK-NEXT: rldicl 3, 3, 1, 63
+; CHECK-NEXT: xori 3, 3, 1
+; CHECK-NEXT: blr
entry:
%arrayidx.i6 = bitcast %class.PB2* %s_a to i32*
%0 = load i32, i32* %arrayidx.i6, align 8, !tbaa !1
%and.i4 = and i32 %1, 8
%cmp.i5 = icmp ule i32 %and.i, %and.i4
ret i1 %cmp.i5
-
-; CHECK-LABEL: @test2
-; CHECK: rlwinm [[REG1:[0-9]*]]
-; CHECK-NEXT: rlwinm [[REG2:[0-9]*]]
-; CHECK-NEXT: sub [[REG3:[0-9]*]], [[REG2]], [[REG1]]
-; CHECK-NEXT: rldicl [[REG4:[0-9]*]], [[REG3]]
-; CHECK-NEXT: xori 3, [[REG4]], 1
-; CHECK: blr
-
}
; Function Attrs: norecurse nounwind readonly
define zeroext i1 @test3(%class.PB2* %s_a, %class.PB2* %s_b) local_unnamed_addr #0 {
+; CHECK-LABEL: test3:
+; CHECK: # BB#0: # %entry
+; CHECK-NEXT: lwz 3, 0(3)
+; CHECK-NEXT: lwz 4, 0(4)
+; CHECK-NEXT: rlwinm 3, 3, 0, 28, 28
+; CHECK-NEXT: rlwinm 4, 4, 0, 28, 28
+; CHECK-NEXT: sub 3, 4, 3
+; CHECK-NEXT: rldicl 3, 3, 1, 63
+; CHECK-NEXT: blr
entry:
%arrayidx.i6 = bitcast %class.PB2* %s_a to i32*
%0 = load i32, i32* %arrayidx.i6, align 8, !tbaa !1
%and.i4 = and i32 %1, 8
%cmp.i5 = icmp ugt i32 %and.i, %and.i4
ret i1 %cmp.i5
-
-; CHECK-LABEL: @test3
-; CHECK: rlwinm [[REG1:[0-9]*]]
-; CHECK-NEXT: rlwinm [[REG2:[0-9]*]]
-; CHECK-NEXT: sub [[REG3:[0-9]*]], [[REG2]], [[REG1]]
-; CHECK-NEXT: rldicl 3, [[REG3]]
-; CHECK: blr
-
}
; Function Attrs: norecurse nounwind readonly
define zeroext i1 @test4(%class.PB2* %s_a, %class.PB2* %s_b) local_unnamed_addr #0 {
+; CHECK-LABEL: test4:
+; CHECK: # BB#0: # %entry
+; CHECK-NEXT: lwz 3, 0(3)
+; CHECK-NEXT: lwz 4, 0(4)
+; CHECK-NEXT: rlwinm 3, 3, 0, 28, 28
+; CHECK-NEXT: rlwinm 4, 4, 0, 28, 28
+; CHECK-NEXT: sub 3, 3, 4
+; CHECK-NEXT: rldicl 3, 3, 1, 63
+; CHECK-NEXT: xori 3, 3, 1
+; CHECK-NEXT: blr
entry:
%arrayidx.i6 = bitcast %class.PB2* %s_a to i32*
%0 = load i32, i32* %arrayidx.i6, align 8, !tbaa !1
%and.i4 = and i32 %1, 8
%cmp.i5 = icmp uge i32 %and.i, %and.i4
ret i1 %cmp.i5
-
-; CHECK-LABEL: @test4
-; CHECK: rlwinm [[REG1:[0-9]*]]
-; CHECK-NEXT: rlwinm [[REG2:[0-9]*]]
-; CHECK-NEXT: sub [[REG3:[0-9]*]], [[REG1]], [[REG2]]
-; CHECK-NEXT: rldicl [[REG4:[0-9]*]], [[REG3]]
-; CHECK-NEXT: xori 3, [[REG4]], 1
-; CHECK: blr
-
}
!1 = !{!2, !2, i64 0}