aboutsummaryrefslogtreecommitdiffstats
path: root/test/Transforms/LoopVectorize/AArch64
diff options
context:
space:
mode:
Diffstat (limited to 'test/Transforms/LoopVectorize/AArch64')
-rw-r--r--test/Transforms/LoopVectorize/AArch64/aarch64-unroll.ll10
-rw-r--r--test/Transforms/LoopVectorize/AArch64/arbitrary-induction-step.ll44
-rw-r--r--test/Transforms/LoopVectorize/AArch64/arm64-unroll.ll10
-rw-r--r--test/Transforms/LoopVectorize/AArch64/gather-cost.ll28
-rw-r--r--test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll8
5 files changed, 50 insertions, 50 deletions
diff --git a/test/Transforms/LoopVectorize/AArch64/aarch64-unroll.ll b/test/Transforms/LoopVectorize/AArch64/aarch64-unroll.ll
index 9962c3d..a689f44 100644
--- a/test/Transforms/LoopVectorize/AArch64/aarch64-unroll.ll
+++ b/test/Transforms/LoopVectorize/AArch64/aarch64-unroll.ll
@@ -22,12 +22,12 @@ for.body.preheader: ; preds = %entry
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
- %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
- %0 = load i32* %arrayidx, align 4
- %arrayidx2 = getelementptr inbounds i32* %b, i64 %indvars.iv
- %1 = load i32* %arrayidx2, align 4
+ %arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
+ %0 = load i32, i32* %arrayidx, align 4
+ %arrayidx2 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
+ %1 = load i32, i32* %arrayidx2, align 4
%add = add nsw i32 %1, %0
- %arrayidx4 = getelementptr inbounds i32* %c, i64 %indvars.iv
+ %arrayidx4 = getelementptr inbounds i32, i32* %c, i64 %indvars.iv
store i32 %add, i32* %arrayidx4, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
diff --git a/test/Transforms/LoopVectorize/AArch64/arbitrary-induction-step.ll b/test/Transforms/LoopVectorize/AArch64/arbitrary-induction-step.ll
index 95734bf..4cd703f 100644
--- a/test/Transforms/LoopVectorize/AArch64/arbitrary-induction-step.ll
+++ b/test/Transforms/LoopVectorize/AArch64/arbitrary-induction-step.ll
@@ -11,8 +11,8 @@ target triple = "aarch64--linux-gnueabi"
; }
; CHECK-LABEL: @ind_plus2(
-; CHECK: load <4 x i32>*
-; CHECK: load <4 x i32>*
+; CHECK: load <4 x i32>, <4 x i32>*
+; CHECK: load <4 x i32>, <4 x i32>*
; CHECK: mul nsw <4 x i32>
; CHECK: mul nsw <4 x i32>
; CHECK: add nsw <4 x i32>
@@ -21,7 +21,7 @@ target triple = "aarch64--linux-gnueabi"
; CHECK: icmp eq i64 %index.next, 512
; FORCE-VEC-LABEL: @ind_plus2(
-; FORCE-VEC: %wide.load = load <2 x i32>*
+; FORCE-VEC: %wide.load = load <2 x i32>, <2 x i32>*
; FORCE-VEC: mul nsw <2 x i32>
; FORCE-VEC: add nsw <2 x i32>
; FORCE-VEC: %index.next = add i64 %index, 2
@@ -34,8 +34,8 @@ for.body: ; preds = %entry, %for.body
%A.addr = phi i32* [ %A, %entry ], [ %inc.ptr, %for.body ]
%i = phi i32 [ 0, %entry ], [ %add1, %for.body ]
%sum = phi i32 [ 0, %entry ], [ %add, %for.body ]
- %inc.ptr = getelementptr inbounds i32* %A.addr, i64 1
- %0 = load i32* %A.addr, align 4
+ %inc.ptr = getelementptr inbounds i32, i32* %A.addr, i64 1
+ %0 = load i32, i32* %A.addr, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%add1 = add nsw i32 %i, 2
@@ -55,8 +55,8 @@ for.end: ; preds = %for.body
; }
; CHECK-LABEL: @ind_minus2(
-; CHECK: load <4 x i32>*
-; CHECK: load <4 x i32>*
+; CHECK: load <4 x i32>, <4 x i32>*
+; CHECK: load <4 x i32>, <4 x i32>*
; CHECK: mul nsw <4 x i32>
; CHECK: mul nsw <4 x i32>
; CHECK: add nsw <4 x i32>
@@ -65,7 +65,7 @@ for.end: ; preds = %for.body
; CHECK: icmp eq i64 %index.next, 512
; FORCE-VEC-LABEL: @ind_minus2(
-; FORCE-VEC: %wide.load = load <2 x i32>*
+; FORCE-VEC: %wide.load = load <2 x i32>, <2 x i32>*
; FORCE-VEC: mul nsw <2 x i32>
; FORCE-VEC: add nsw <2 x i32>
; FORCE-VEC: %index.next = add i64 %index, 2
@@ -78,8 +78,8 @@ for.body: ; preds = %entry, %for.body
%A.addr = phi i32* [ %A, %entry ], [ %inc.ptr, %for.body ]
%i = phi i32 [ 1024, %entry ], [ %sub, %for.body ]
%sum = phi i32 [ 0, %entry ], [ %add, %for.body ]
- %inc.ptr = getelementptr inbounds i32* %A.addr, i64 1
- %0 = load i32* %A.addr, align 4
+ %inc.ptr = getelementptr inbounds i32, i32* %A.addr, i64 1
+ %0 = load i32, i32* %A.addr, align 4
%mul = mul nsw i32 %0, %i
%add = add nsw i32 %mul, %sum
%sub = add nsw i32 %i, -2
@@ -102,10 +102,10 @@ for.end: ; preds = %for.body
; }
; CHECK-LABEL: @ptr_ind_plus2(
-; CHECK: load i32*
-; CHECK: load i32*
-; CHECK: load i32*
-; CHECK: load i32*
+; CHECK: load i32, i32*
+; CHECK: load i32, i32*
+; CHECK: load i32, i32*
+; CHECK: load i32, i32*
; CHECK: mul nsw i32
; CHECK: mul nsw i32
; CHECK: add nsw i32
@@ -114,13 +114,13 @@ for.end: ; preds = %for.body
; CHECK: %21 = icmp eq i64 %index.next, 1024
; FORCE-VEC-LABEL: @ptr_ind_plus2(
-; FORCE-VEC: load i32*
+; FORCE-VEC: load i32, i32*
; FORCE-VEC: insertelement <2 x i32>
-; FORCE-VEC: load i32*
+; FORCE-VEC: load i32, i32*
; FORCE-VEC: insertelement <2 x i32>
-; FORCE-VEC: load i32*
+; FORCE-VEC: load i32, i32*
; FORCE-VEC: insertelement <2 x i32>
-; FORCE-VEC: load i32*
+; FORCE-VEC: load i32, i32*
; FORCE-VEC: insertelement <2 x i32>
; FORCE-VEC: mul nsw <2 x i32>
; FORCE-VEC: add nsw <2 x i32>
@@ -134,10 +134,10 @@ for.body: ; preds = %for.body, %entry
%A.addr = phi i32* [ %A, %entry ], [ %inc.ptr1, %for.body ]
%sum = phi i32 [ 0, %entry ], [ %add, %for.body ]
%i = phi i32 [ 0, %entry ], [ %inc, %for.body ]
- %inc.ptr = getelementptr inbounds i32* %A.addr, i64 1
- %0 = load i32* %A.addr, align 4
- %inc.ptr1 = getelementptr inbounds i32* %A.addr, i64 2
- %1 = load i32* %inc.ptr, align 4
+ %inc.ptr = getelementptr inbounds i32, i32* %A.addr, i64 1
+ %0 = load i32, i32* %A.addr, align 4
+ %inc.ptr1 = getelementptr inbounds i32, i32* %A.addr, i64 2
+ %1 = load i32, i32* %inc.ptr, align 4
%mul = mul nsw i32 %1, %0
%add = add nsw i32 %mul, %sum
%inc = add nsw i32 %i, 1
diff --git a/test/Transforms/LoopVectorize/AArch64/arm64-unroll.ll b/test/Transforms/LoopVectorize/AArch64/arm64-unroll.ll
index f8eb3ed..395b468 100644
--- a/test/Transforms/LoopVectorize/AArch64/arm64-unroll.ll
+++ b/test/Transforms/LoopVectorize/AArch64/arm64-unroll.ll
@@ -22,12 +22,12 @@ for.body.preheader: ; preds = %entry
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
- %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
- %0 = load i32* %arrayidx, align 4
- %arrayidx2 = getelementptr inbounds i32* %b, i64 %indvars.iv
- %1 = load i32* %arrayidx2, align 4
+ %arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
+ %0 = load i32, i32* %arrayidx, align 4
+ %arrayidx2 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
+ %1 = load i32, i32* %arrayidx2, align 4
%add = add nsw i32 %1, %0
- %arrayidx4 = getelementptr inbounds i32* %c, i64 %indvars.iv
+ %arrayidx4 = getelementptr inbounds i32, i32* %c, i64 %indvars.iv
store i32 %add, i32* %arrayidx4, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
diff --git a/test/Transforms/LoopVectorize/AArch64/gather-cost.ll b/test/Transforms/LoopVectorize/AArch64/gather-cost.ll
index bb28538..46b8ef1 100644
--- a/test/Transforms/LoopVectorize/AArch64/gather-cost.ll
+++ b/test/Transforms/LoopVectorize/AArch64/gather-cost.ll
@@ -30,32 +30,32 @@ for.body:
%b.054 = phi float [ 0.000000e+00, %for.body.lr.ph ], [ %add30, %for.body ]
%add = add i64 %v.055, %offset
%mul = mul i64 %add, 3
- %arrayidx = getelementptr inbounds [1536 x float]* @src_data, i64 0, i64 %mul
- %0 = load float* %arrayidx, align 4
- %arrayidx2 = getelementptr inbounds [512 x float]* @kernel, i64 0, i64 %v.055
- %1 = load float* %arrayidx2, align 4
+ %arrayidx = getelementptr inbounds [1536 x float], [1536 x float]* @src_data, i64 0, i64 %mul
+ %0 = load float, float* %arrayidx, align 4
+ %arrayidx2 = getelementptr inbounds [512 x float], [512 x float]* @kernel, i64 0, i64 %v.055
+ %1 = load float, float* %arrayidx2, align 4
%mul3 = fmul fast float %0, %1
- %arrayidx4 = getelementptr inbounds [512 x float]* @kernel2, i64 0, i64 %v.055
- %2 = load float* %arrayidx4, align 4
+ %arrayidx4 = getelementptr inbounds [512 x float], [512 x float]* @kernel2, i64 0, i64 %v.055
+ %2 = load float, float* %arrayidx4, align 4
%mul5 = fmul fast float %mul3, %2
- %arrayidx6 = getelementptr inbounds [512 x float]* @kernel3, i64 0, i64 %v.055
- %3 = load float* %arrayidx6, align 4
+ %arrayidx6 = getelementptr inbounds [512 x float], [512 x float]* @kernel3, i64 0, i64 %v.055
+ %3 = load float, float* %arrayidx6, align 4
%mul7 = fmul fast float %mul5, %3
- %arrayidx8 = getelementptr inbounds [512 x float]* @kernel4, i64 0, i64 %v.055
- %4 = load float* %arrayidx8, align 4
+ %arrayidx8 = getelementptr inbounds [512 x float], [512 x float]* @kernel4, i64 0, i64 %v.055
+ %4 = load float, float* %arrayidx8, align 4
%mul9 = fmul fast float %mul7, %4
%add10 = fadd fast float %r.057, %mul9
%arrayidx.sum = add i64 %mul, 1
- %arrayidx11 = getelementptr inbounds [1536 x float]* @src_data, i64 0, i64 %arrayidx.sum
- %5 = load float* %arrayidx11, align 4
+ %arrayidx11 = getelementptr inbounds [1536 x float], [1536 x float]* @src_data, i64 0, i64 %arrayidx.sum
+ %5 = load float, float* %arrayidx11, align 4
%mul13 = fmul fast float %1, %5
%mul15 = fmul fast float %2, %mul13
%mul17 = fmul fast float %3, %mul15
%mul19 = fmul fast float %4, %mul17
%add20 = fadd fast float %g.056, %mul19
%arrayidx.sum52 = add i64 %mul, 2
- %arrayidx21 = getelementptr inbounds [1536 x float]* @src_data, i64 0, i64 %arrayidx.sum52
- %6 = load float* %arrayidx21, align 4
+ %arrayidx21 = getelementptr inbounds [1536 x float], [1536 x float]* @src_data, i64 0, i64 %arrayidx.sum52
+ %6 = load float, float* %arrayidx21, align 4
%mul23 = fmul fast float %1, %6
%mul25 = fmul fast float %2, %mul23
%mul27 = fmul fast float %3, %mul25
diff --git a/test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll b/test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll
index a01d543..f3c6548 100644
--- a/test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll
+++ b/test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll
@@ -7,7 +7,7 @@ target triple = "aarch64--linux-gnu"
@Foo = common global %struct.anon zeroinitializer, align 4
; CHECK-LABEL: @foo(
-; CHECK: load <4 x i32>*
+; CHECK: load <4 x i32>, <4 x i32>*
; CHECK: sdiv <4 x i32>
; CHECK: store <4 x i32>
@@ -17,10 +17,10 @@ entry:
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
- %arrayidx = getelementptr inbounds %struct.anon* @Foo, i64 0, i32 2, i64 %indvars.iv
- %0 = load i32* %arrayidx, align 4
+ %arrayidx = getelementptr inbounds %struct.anon, %struct.anon* @Foo, i64 0, i32 2, i64 %indvars.iv
+ %0 = load i32, i32* %arrayidx, align 4
%div = sdiv i32 %0, 2
- %arrayidx2 = getelementptr inbounds %struct.anon* @Foo, i64 0, i32 0, i64 %indvars.iv
+ %arrayidx2 = getelementptr inbounds %struct.anon, %struct.anon* @Foo, i64 0, i32 0, i64 %indvars.iv
store i32 %div, i32* %arrayidx2, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 100