aboutsummaryrefslogtreecommitdiffstats
path: root/test/Transforms/LoopVectorize
diff options
context:
space:
mode:
Diffstat (limited to 'test/Transforms/LoopVectorize')
-rw-r--r--test/Transforms/LoopVectorize/X86/avx1.ll4
-rw-r--r--test/Transforms/LoopVectorize/X86/reduction-crash.ll35
-rw-r--r--test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll66
-rw-r--r--test/Transforms/LoopVectorize/dbg.value.ll70
-rw-r--r--test/Transforms/LoopVectorize/global_alias.ll40
-rw-r--r--test/Transforms/LoopVectorize/intrinsic.ll24
-rw-r--r--test/Transforms/LoopVectorize/phi-hang.ll29
-rw-r--r--test/Transforms/LoopVectorize/vectorize-once.ll75
8 files changed, 321 insertions, 22 deletions
diff --git a/test/Transforms/LoopVectorize/X86/avx1.ll b/test/Transforms/LoopVectorize/X86/avx1.ll
index a85c6fe..6c0366e 100644
--- a/test/Transforms/LoopVectorize/X86/avx1.ll
+++ b/test/Transforms/LoopVectorize/X86/avx1.ll
@@ -27,7 +27,7 @@ define i32 @read_mod_write_single_ptr(float* nocapture %a, i32 %n) nounwind uwta
;CHECK: @read_mod_i64
-;CHECK: load <4 x i64>
+;CHECK: load <2 x i64>
;CHECK: ret i32
define i32 @read_mod_i64(i64* nocapture %a, i32 %n) nounwind uwtable ssp {
%1 = icmp sgt i32 %n, 0
@@ -37,7 +37,7 @@ define i32 @read_mod_i64(i64* nocapture %a, i32 %n) nounwind uwtable ssp {
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
%2 = getelementptr inbounds i64* %a, i64 %indvars.iv
%3 = load i64* %2, align 4
- %4 = mul i64 %3, 3
+ %4 = add i64 %3, 3
store i64 %4, i64* %2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
diff --git a/test/Transforms/LoopVectorize/X86/reduction-crash.ll b/test/Transforms/LoopVectorize/X86/reduction-crash.ll
new file mode 100644
index 0000000..f580846
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/reduction-crash.ll
@@ -0,0 +1,35 @@
+; RUN: opt -S -loop-vectorize -mcpu=prescott < %s | FileCheck %s
+
+target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32-S128"
+target triple = "i386-apple-darwin"
+
+; PR15344
+define void @test1(float* nocapture %arg, i32 %arg1) nounwind {
+; CHECK: @test1
+; CHECK: preheader
+; CHECK: insertelement <2 x double> zeroinitializer, double %tmp, i32 0
+; CHECK: vector.memcheck
+
+bb:
+ br label %bb2
+
+bb2: ; preds = %bb
+ %tmp = load double* null, align 8
+ br i1 undef, label %bb3, label %bb12
+
+bb3: ; preds = %bb3, %bb2
+ %tmp4 = phi double [ %tmp9, %bb3 ], [ %tmp, %bb2 ]
+ %tmp5 = phi i32 [ %tmp8, %bb3 ], [ 0, %bb2 ]
+ %tmp6 = getelementptr inbounds [16 x double]* undef, i32 0, i32 %tmp5
+ %tmp7 = load double* %tmp6, align 4
+ %tmp8 = add nsw i32 %tmp5, 1
+ %tmp9 = fadd fast double %tmp4, undef
+ %tmp10 = getelementptr inbounds float* %arg, i32 %tmp5
+ store float undef, float* %tmp10, align 4
+ %tmp11 = icmp eq i32 %tmp8, %arg1
+ br i1 %tmp11, label %bb12, label %bb3
+
+bb12: ; preds = %bb3, %bb2
+ %tmp13 = phi double [ %tmp, %bb2 ], [ %tmp9, %bb3 ]
+ ret void
+}
diff --git a/test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll b/test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll
new file mode 100644
index 0000000..3b3a787
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/vector-scalar-select-cost.ll
@@ -0,0 +1,66 @@
+; RUN: opt < %s -loop-vectorize -mcpu=core2 -debug-only=loop-vectorize 2>&1 -S | FileCheck %s
+; REQUIRES: asserts
+; Make sure we use the right select kind when querying select costs.
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+@a = common global [2048 x i32] zeroinitializer, align 16
+@b = common global [2048 x i32] zeroinitializer, align 16
+@c = common global [2048 x i32] zeroinitializer, align 16
+
+; CHECK: Checking a loop in "scalarselect"
+define void @scalarselect(i1 %cond) {
+ br label %1
+
+; <label>:1
+ %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
+ %2 = getelementptr inbounds [2048 x i32]* @b, i64 0, i64 %indvars.iv
+ %3 = load i32* %2, align 4
+ %4 = getelementptr inbounds [2048 x i32]* @c, i64 0, i64 %indvars.iv
+ %5 = load i32* %4, align 4
+ %6 = add nsw i32 %5, %3
+ %7 = getelementptr inbounds [2048 x i32]* @a, i64 0, i64 %indvars.iv
+
+; A scalar select has a cost of 1 on core2
+; CHECK: cost of 1 for VF 2 {{.*}} select i1 %cond, i32 %6, i32 0
+
+ %sel = select i1 %cond, i32 %6, i32 zeroinitializer
+ store i32 %sel, i32* %7, align 4
+ %indvars.iv.next = add i64 %indvars.iv, 1
+ %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+ %exitcond = icmp eq i32 %lftr.wideiv, 256
+ br i1 %exitcond, label %8, label %1
+
+; <label>:8
+ ret void
+}
+
+; CHECK: Checking a loop in "vectorselect"
+define void @vectorselect(i1 %cond) {
+ br label %1
+
+; <label>:1
+ %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
+ %2 = getelementptr inbounds [2048 x i32]* @b, i64 0, i64 %indvars.iv
+ %3 = load i32* %2, align 4
+ %4 = getelementptr inbounds [2048 x i32]* @c, i64 0, i64 %indvars.iv
+ %5 = load i32* %4, align 4
+ %6 = add nsw i32 %5, %3
+ %7 = getelementptr inbounds [2048 x i32]* @a, i64 0, i64 %indvars.iv
+ %8 = icmp ult i64 %indvars.iv, 8
+
+; A vector select has a cost of 4 on core2
+; CHECK: cost of 4 for VF 2 {{.*}} select i1 %8, i32 %6, i32 0
+
+ %sel = select i1 %8, i32 %6, i32 zeroinitializer
+ store i32 %sel, i32* %7, align 4
+ %indvars.iv.next = add i64 %indvars.iv, 1
+ %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+ %exitcond = icmp eq i32 %lftr.wideiv, 256
+ br i1 %exitcond, label %9, label %1
+
+; <label>:9
+ ret void
+}
+
diff --git a/test/Transforms/LoopVectorize/dbg.value.ll b/test/Transforms/LoopVectorize/dbg.value.ll
new file mode 100644
index 0000000..a2ea951
--- /dev/null
+++ b/test/Transforms/LoopVectorize/dbg.value.ll
@@ -0,0 +1,70 @@
+; RUN: opt < %s -S -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine | FileCheck %s
+; Make sure we vectorize with debugging turned on.
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+@A = global [1024 x i32] zeroinitializer, align 16
+@B = global [1024 x i32] zeroinitializer, align 16
+@C = global [1024 x i32] zeroinitializer, align 16
+
+; CHECK: @test
+define i32 @test() #0 {
+entry:
+ tail call void @llvm.dbg.value(metadata !1, i64 0, metadata !9), !dbg !18
+ br label %for.body, !dbg !18
+
+for.body:
+ ;CHECK: load <4 x i32>
+ %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+ %arrayidx = getelementptr inbounds [1024 x i32]* @B, i64 0, i64 %indvars.iv, !dbg !19
+ %0 = load i32* %arrayidx, align 4, !dbg !19, !tbaa !21
+ %arrayidx2 = getelementptr inbounds [1024 x i32]* @C, i64 0, i64 %indvars.iv, !dbg !19
+ %1 = load i32* %arrayidx2, align 4, !dbg !19, !tbaa !21
+ %add = add nsw i32 %1, %0, !dbg !19
+ %arrayidx4 = getelementptr inbounds [1024 x i32]* @A, i64 0, i64 %indvars.iv, !dbg !19
+ store i32 %add, i32* %arrayidx4, align 4, !dbg !19, !tbaa !21
+ %indvars.iv.next = add i64 %indvars.iv, 1, !dbg !18
+ tail call void @llvm.dbg.value(metadata !{null}, i64 0, metadata !9), !dbg !18
+ %lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !18
+ %exitcond = icmp ne i32 %lftr.wideiv, 1024, !dbg !18
+ br i1 %exitcond, label %for.body, label %for.end, !dbg !18
+
+for.end:
+ ret i32 0, !dbg !24
+}
+
+declare void @llvm.dbg.declare(metadata, metadata) #1
+
+declare void @llvm.dbg.value(metadata, i64, metadata) #1
+
+attributes #0 = { nounwind ssp uwtable "fp-contract-model"="standard" "no-frame-pointer-elim" "no-frame-pointer-elim-non-leaf" "realign-stack" "relocation-model"="pic" "ssp-buffers-size"="8" }
+attributes #1 = { nounwind readnone }
+
+!llvm.dbg.cu = !{!0}
+
+!0 = metadata !{i32 786449, i32 0, i32 4, metadata !"test", metadata !"/path/to/somewhere", metadata !"clang", i1 true, i1 true, metadata !"", i32 0, metadata !1, metadata !1, metadata !2, metadata !11, metadata !""}
+!1 = metadata !{i32 0}
+!2 = metadata !{metadata !3}
+!3 = metadata !{i32 786478, i32 0, metadata !4, metadata !"test", metadata !"test", metadata !"test", metadata !4, i32 5, metadata !5, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, i32 ()* @test, null, null, metadata !8, i32 5}
+!4 = metadata !{i32 786473, metadata !"test", metadata !"/path/to/somewhere", null}
+!5 = metadata !{i32 786453, i32 0, metadata !"", i32 0, i32 0, i64 0, i64 0, i64 0, i32 0, null, metadata !6, i32 0, i32 0}
+!6 = metadata !{metadata !7}
+!7 = metadata !{i32 786468, null, metadata !"int", null, i32 0, i64 32, i64 32, i64 0, i32 0, i32 5}
+!8 = metadata !{metadata !9}
+!9 = metadata !{i32 786688, metadata !10, metadata !"i", metadata !4, i32 6, metadata !7, i32 0, i32 0}
+!10 = metadata !{i32 786443, metadata !3, i32 6, i32 0, metadata !4, i32 0}
+!11 = metadata !{metadata !12, metadata !16, metadata !17}
+!12 = metadata !{i32 786484, i32 0, null, metadata !"A", metadata !"A", metadata !"", metadata !4, i32 1, metadata !13, i32 0, i32 1, [1024 x i32]* @A, null}
+!13 = metadata !{i32 786433, null, metadata !"", null, i32 0, i64 32768, i64 32, i32 0, i32 0, metadata !7, metadata !14, i32 0, i32 0}
+!14 = metadata !{metadata !15}
+!15 = metadata !{i32 786465, i64 0, i64 1024}
+!16 = metadata !{i32 786484, i32 0, null, metadata !"B", metadata !"B", metadata !"", metadata !4, i32 2, metadata !13, i32 0, i32 1, [1024 x i32]* @B, null}
+!17 = metadata !{i32 786484, i32 0, null, metadata !"C", metadata !"C", metadata !"", metadata !4, i32 3, metadata !13, i32 0, i32 1, [1024 x i32]* @C, null}
+!18 = metadata !{i32 6, i32 0, metadata !10, null}
+!19 = metadata !{i32 7, i32 0, metadata !20, null}
+!20 = metadata !{i32 786443, metadata !10, i32 6, i32 0, metadata !4, i32 1}
+!21 = metadata !{metadata !"int", metadata !22}
+!22 = metadata !{metadata !"omnipotent char", metadata !23}
+!23 = metadata !{metadata !"Simple C/C++ TBAA"}
+!24 = metadata !{i32 9, i32 0, metadata !3, null}
diff --git a/test/Transforms/LoopVectorize/global_alias.ll b/test/Transforms/LoopVectorize/global_alias.ll
index 24e698b..121da8b 100644
--- a/test/Transforms/LoopVectorize/global_alias.ll
+++ b/test/Transforms/LoopVectorize/global_alias.ll
@@ -24,7 +24,7 @@ target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3
; }
; CHECK: define i32 @noAlias01
; CHECK: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias01(i32 %a) nounwind {
entry:
@@ -72,7 +72,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias02
; CHECK: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias02(i32 %a) {
entry:
@@ -121,7 +121,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias03
; CHECK: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias03(i32 %a) {
entry:
@@ -170,7 +170,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias04
; CHECK-NOT: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
;
; TODO: This test vectorizes (with run-time check) on real targets with -O3)
; Check why it's not being vectorized even when forcing vectorization
@@ -224,7 +224,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias05
; CHECK: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias05(i32 %a) #0 {
entry:
@@ -280,7 +280,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias06
; CHECK: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias06(i32 %a) #0 {
entry:
@@ -337,7 +337,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias07
; CHECK: sub nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias07(i32 %a) #0 {
entry:
@@ -389,7 +389,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias08
; CHECK: sub nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias08(i32 %a) #0 {
entry:
@@ -441,7 +441,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias09
; CHECK: sub nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias09(i32 %a) #0 {
entry:
@@ -493,7 +493,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias10
; CHECK-NOT: sub nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
;
; TODO: This test vectorizes (with run-time check) on real targets with -O3)
; Check why it's not being vectorized even when forcing vectorization
@@ -553,7 +553,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias11
; CHECK: sub nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias11(i32 %a) #0 {
entry:
@@ -613,7 +613,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias12
; CHECK: sub nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias12(i32 %a) #0 {
entry:
@@ -674,7 +674,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias13
; CHECK: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias13(i32 %a) #0 {
entry:
@@ -723,7 +723,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @noAlias14
; CHECK: sub nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @noAlias14(i32 %a) #0 {
entry:
@@ -779,7 +779,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @mayAlias01
; CHECK-NOT: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @mayAlias01(i32 %a) nounwind {
entry:
@@ -829,7 +829,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @mayAlias02
; CHECK-NOT: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @mayAlias02(i32 %a) nounwind {
entry:
@@ -879,7 +879,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @mayAlias03
; CHECK-NOT: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @mayAlias03(i32 %a) nounwind {
entry:
@@ -936,7 +936,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @mustAlias01
; CHECK-NOT: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @mustAlias01(i32 %a) nounwind {
entry:
@@ -986,7 +986,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @mustAlias02
; CHECK-NOT: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @mustAlias02(i32 %a) nounwind {
entry:
@@ -1035,7 +1035,7 @@ for.end: ; preds = %for.cond
; }
; CHECK: define i32 @mustAlias03
; CHECK-NOT: add nsw <4 x i32>
-; CHECK ret
+; CHECK: ret
define i32 @mustAlias03(i32 %a) nounwind {
entry:
diff --git a/test/Transforms/LoopVectorize/intrinsic.ll b/test/Transforms/LoopVectorize/intrinsic.ll
index 7d5a5d7..e79d78d 100644
--- a/test/Transforms/LoopVectorize/intrinsic.ll
+++ b/test/Transforms/LoopVectorize/intrinsic.ll
@@ -902,6 +902,30 @@ for.end: ; preds = %for.body, %entry
ret void
}
+; CHECK: fabs_libm
+; CHECK: call <4 x float> @llvm.fabs.v4f32
+; CHECK: ret void
+define void @fabs_libm(float* nocapture %x) nounwind {
+entry:
+ br label %for.body
+
+for.body: ; preds = %entry, %for.body
+ %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+ %arrayidx = getelementptr inbounds float* %x, i64 %indvars.iv
+ %0 = load float* %arrayidx, align 4
+ %call = tail call float @fabsf(float %0) nounwind readnone
+ store float %call, float* %arrayidx, align 4
+ %indvars.iv.next = add i64 %indvars.iv, 1
+ %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+ %exitcond = icmp eq i32 %lftr.wideiv, 1024
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body
+ ret void
+}
+
+declare float @fabsf(float) nounwind readnone
+
declare double @llvm.pow.f64(double, double) nounwind readnone
!0 = metadata !{metadata !"float", metadata !1}
diff --git a/test/Transforms/LoopVectorize/phi-hang.ll b/test/Transforms/LoopVectorize/phi-hang.ll
new file mode 100644
index 0000000..b80d459
--- /dev/null
+++ b/test/Transforms/LoopVectorize/phi-hang.ll
@@ -0,0 +1,29 @@
+; RUN: opt -S -loop-vectorize < %s
+
+; PR15384
+define void @test1(i32 %arg) {
+bb:
+ br label %bb1
+
+bb1: ; preds = %bb5, %bb
+ %tmp = phi i32 [ 1, %bb ], [ %tmp7, %bb5 ]
+ %tmp2 = phi i32 [ %arg, %bb ], [ %tmp9, %bb5 ]
+ br i1 true, label %bb5, label %bb3
+
+bb3: ; preds = %bb1
+ br label %bb4
+
+bb4: ; preds = %bb3
+ br label %bb5
+
+bb5: ; preds = %bb4, %bb1
+ %tmp6 = phi i32 [ 0, %bb4 ], [ %tmp, %bb1 ]
+ %tmp7 = phi i32 [ 0, %bb4 ], [ %tmp6, %bb1 ]
+ %tmp8 = phi i32 [ 0, %bb4 ], [ %tmp, %bb1 ]
+ %tmp9 = add nsw i32 %tmp2, 1
+ %tmp10 = icmp eq i32 %tmp9, 0
+ br i1 %tmp10, label %bb11, label %bb1
+
+bb11: ; preds = %bb5
+ ret void
+}
diff --git a/test/Transforms/LoopVectorize/vectorize-once.ll b/test/Transforms/LoopVectorize/vectorize-once.ll
new file mode 100644
index 0000000..ac16948
--- /dev/null
+++ b/test/Transforms/LoopVectorize/vectorize-once.ll
@@ -0,0 +1,75 @@
+; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S -simplifycfg | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+;
+; We want to make sure that we are vectorizeing the scalar loop only once
+; even if the pass manager runs the vectorizer multiple times due to inlining.
+
+
+; This test checks that we add metadata to vectorized loops
+; CHECK: _Z4foo1Pii
+; CHECK: <4 x i32>
+; CHECK: llvm.vectorizer.already_vectorized
+; CHECK: ret
+
+; This test comes from the loop:
+;
+;int foo (int *A, int n) {
+; return std::accumulate(A, A + n, 0);
+;}
+define i32 @_Z4foo1Pii(i32* %A, i32 %n) #0 {
+entry:
+ %idx.ext = sext i32 %n to i64
+ %add.ptr = getelementptr inbounds i32* %A, i64 %idx.ext
+ %cmp3.i = icmp eq i32 %n, 0
+ br i1 %cmp3.i, label %_ZSt10accumulateIPiiET0_T_S2_S1_.exit, label %for.body.i
+
+for.body.i: ; preds = %entry, %for.body.i
+ %__init.addr.05.i = phi i32 [ %add.i, %for.body.i ], [ 0, %entry ]
+ %__first.addr.04.i = phi i32* [ %incdec.ptr.i, %for.body.i ], [ %A, %entry ]
+ %0 = load i32* %__first.addr.04.i, align 4, !tbaa !0
+ %add.i = add nsw i32 %0, %__init.addr.05.i
+ %incdec.ptr.i = getelementptr inbounds i32* %__first.addr.04.i, i64 1
+ %cmp.i = icmp eq i32* %incdec.ptr.i, %add.ptr
+ br i1 %cmp.i, label %_ZSt10accumulateIPiiET0_T_S2_S1_.exit, label %for.body.i
+
+_ZSt10accumulateIPiiET0_T_S2_S1_.exit: ; preds = %for.body.i, %entry
+ %__init.addr.0.lcssa.i = phi i32 [ 0, %entry ], [ %add.i, %for.body.i ]
+ ret i32 %__init.addr.0.lcssa.i
+}
+
+; This test checks that we don't vectorize loops that are marked with the "already vectorized" metadata.
+; CHECK: _Z4foo2Pii
+; CHECK-NOT: <4 x i32>
+; CHECK: llvm.vectorizer.already_vectorized
+; CHECK: ret
+define i32 @_Z4foo2Pii(i32* %A, i32 %n) #0 {
+entry:
+ %idx.ext = sext i32 %n to i64
+ %add.ptr = getelementptr inbounds i32* %A, i64 %idx.ext
+ %cmp3.i = icmp eq i32 %n, 0
+ br i1 %cmp3.i, label %_ZSt10accumulateIPiiET0_T_S2_S1_.exit, label %for.body.i
+
+for.body.i: ; preds = %entry, %for.body.i
+ %__init.addr.05.i = phi i32 [ %add.i, %for.body.i ], [ 0, %entry ]
+ %__first.addr.04.i = phi i32* [ %incdec.ptr.i, %for.body.i ], [ %A, %entry ]
+ %0 = load i32* %__first.addr.04.i, align 4, !tbaa !0
+ %add.i = add nsw i32 %0, %__init.addr.05.i
+ %incdec.ptr.i = getelementptr inbounds i32* %__first.addr.04.i, i64 1
+ %cmp.i = icmp eq i32* %incdec.ptr.i, %add.ptr
+ br i1 %cmp.i, label %_ZSt10accumulateIPiiET0_T_S2_S1_.exit, label %for.body.i, !llvm.vectorizer.already_vectorized !3
+
+_ZSt10accumulateIPiiET0_T_S2_S1_.exit: ; preds = %for.body.i, %entry
+ %__init.addr.0.lcssa.i = phi i32 [ 0, %entry ], [ %add.i, %for.body.i ]
+ ret i32 %__init.addr.0.lcssa.i
+}
+
+attributes #0 = { nounwind readonly ssp uwtable "fp-contract-model"="standard" "no-frame-pointer-elim" "no-frame-pointer-elim-non-leaf" "realign-stack" "relocation-model"="pic" "ssp-buffers-size"="8" }
+
+!0 = metadata !{metadata !"int", metadata !1}
+!1 = metadata !{metadata !"omnipotent char", metadata !2}
+!2 = metadata !{metadata !"Simple C/C++ TBAA"}
+!3 = metadata !{}
+
generated by cgit v1.1 at 2025-08-16 07:13:16 +0000