summaryrefslogtreecommitdiff
path: root/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/Transforms/LoopVectorize/ARM/interleaved_cost.ll')
-rw-r--r--test/Transforms/LoopVectorize/ARM/interleaved_cost.ll164
1 files changed, 136 insertions, 28 deletions
diff --git a/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll b/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll
index de3626b57d831..29adec049f674 100644
--- a/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll
+++ b/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll
@@ -1,39 +1,147 @@
-; RUN: opt -S -debug-only=loop-vectorize -loop-vectorize -instcombine < %s 2>&1 | FileCheck %s
+; RUN: opt -loop-vectorize -force-vector-width=2 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_2
+; RUN: opt -loop-vectorize -force-vector-width=4 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_4
+; RUN: opt -loop-vectorize -force-vector-width=8 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_8
+; RUN: opt -loop-vectorize -force-vector-width=16 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_16
; REQUIRES: asserts
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "armv8--linux-gnueabihf"
-@AB = common global [1024 x i8] zeroinitializer, align 4
-@CD = common global [1024 x i8] zeroinitializer, align 4
+%i8.2 = type {i8, i8}
+define void @i8_factor_2(%i8.2* %data, i64 %n) {
+entry:
+ br label %for.body
+
+; VF_8-LABEL: Checking a loop in "i8_factor_2"
+; VF_8: Found an estimated cost of 2 for VF 8 For instruction: %tmp2 = load i8, i8* %tmp0, align 1
+; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i8, i8* %tmp1, align 1
+; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp0, align 1
+; VF_8-NEXT: Found an estimated cost of 2 for VF 8 For instruction: store i8 0, i8* %tmp1, align 1
+; VF_16-LABEL: Checking a loop in "i8_factor_2"
+; VF_16: Found an estimated cost of 2 for VF 16 For instruction: %tmp2 = load i8, i8* %tmp0, align 1
+; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i8, i8* %tmp1, align 1
+; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp0, align 1
+; VF_16-NEXT: Found an estimated cost of 2 for VF 16 For instruction: store i8 0, i8* %tmp1, align 1
+for.body:
+ %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
+ %tmp0 = getelementptr inbounds %i8.2, %i8.2* %data, i64 %i, i32 0
+ %tmp1 = getelementptr inbounds %i8.2, %i8.2* %data, i64 %i, i32 1
+ %tmp2 = load i8, i8* %tmp0, align 1
+ %tmp3 = load i8, i8* %tmp1, align 1
+ store i8 0, i8* %tmp0, align 1
+ store i8 0, i8* %tmp1, align 1
+ %i.next = add nuw nsw i64 %i, 1
+ %cond = icmp slt i64 %i.next, %n
+ br i1 %cond, label %for.body, label %for.end
+
+for.end:
+ ret void
+}
-define void @test_byte_interleaved_cost(i8 %C, i8 %D) {
+%i16.2 = type {i16, i16}
+define void @i16_factor_2(%i16.2* %data, i64 %n) {
entry:
br label %for.body
-; 8xi8 and 16xi8 are valid i8 vector types, so the cost of the interleaved
-; access group is 2.
-
-; CHECK: LV: Found an estimated cost of 2 for VF 8 For instruction: %tmp = load i8, i8* %arrayidx0, align 4
-; CHECK: LV: Found an estimated cost of 2 for VF 16 For instruction: %tmp = load i8, i8* %arrayidx0, align 4
-
-for.body: ; preds = %for.body, %entry
- %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
- %arrayidx0 = getelementptr inbounds [1024 x i8], [1024 x i8]* @AB, i64 0, i64 %indvars.iv
- %tmp = load i8, i8* %arrayidx0, align 4
- %tmp1 = or i64 %indvars.iv, 1
- %arrayidx1 = getelementptr inbounds [1024 x i8], [1024 x i8]* @AB, i64 0, i64 %tmp1
- %tmp2 = load i8, i8* %arrayidx1, align 4
- %add = add nsw i8 %tmp, %C
- %mul = mul nsw i8 %tmp2, %D
- %arrayidx2 = getelementptr inbounds [1024 x i8], [1024 x i8]* @CD, i64 0, i64 %indvars.iv
- store i8 %add, i8* %arrayidx2, align 4
- %arrayidx3 = getelementptr inbounds [1024 x i8], [1024 x i8]* @CD, i64 0, i64 %tmp1
- store i8 %mul, i8* %arrayidx3, align 4
- %indvars.iv.next = add nuw nsw i64 %indvars.iv, 2
- %cmp = icmp slt i64 %indvars.iv.next, 1024
- br i1 %cmp, label %for.body, label %for.end
-
-for.end: ; preds = %for.body
+; VF_4-LABEL: Checking a loop in "i16_factor_2"
+; VF_4: Found an estimated cost of 2 for VF 4 For instruction: %tmp2 = load i16, i16* %tmp0, align 2
+; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp1, align 2
+; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp0, align 2
+; VF_4-NEXT: Found an estimated cost of 2 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2
+; VF_8-LABEL: Checking a loop in "i16_factor_2"
+; VF_8: Found an estimated cost of 2 for VF 8 For instruction: %tmp2 = load i16, i16* %tmp0, align 2
+; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i16, i16* %tmp1, align 2
+; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp0, align 2
+; VF_8-NEXT: Found an estimated cost of 2 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2
+; VF_16-LABEL: Checking a loop in "i16_factor_2"
+; VF_16: Found an estimated cost of 4 for VF 16 For instruction: %tmp2 = load i16, i16* %tmp0, align 2
+; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i16, i16* %tmp1, align 2
+; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp0, align 2
+; VF_16-NEXT: Found an estimated cost of 4 for VF 16 For instruction: store i16 0, i16* %tmp1, align 2
+for.body:
+ %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
+ %tmp0 = getelementptr inbounds %i16.2, %i16.2* %data, i64 %i, i32 0
+ %tmp1 = getelementptr inbounds %i16.2, %i16.2* %data, i64 %i, i32 1
+ %tmp2 = load i16, i16* %tmp0, align 2
+ %tmp3 = load i16, i16* %tmp1, align 2
+ store i16 0, i16* %tmp0, align 2
+ store i16 0, i16* %tmp1, align 2
+ %i.next = add nuw nsw i64 %i, 1
+ %cond = icmp slt i64 %i.next, %n
+ br i1 %cond, label %for.body, label %for.end
+
+for.end:
+ ret void
+}
+
+%i32.2 = type {i32, i32}
+define void @i32_factor_2(%i32.2* %data, i64 %n) {
+entry:
+ br label %for.body
+
+; VF_2-LABEL: Checking a loop in "i32_factor_2"
+; VF_2: Found an estimated cost of 2 for VF 2 For instruction: %tmp2 = load i32, i32* %tmp0, align 4
+; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp1, align 4
+; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4
+; VF_2-NEXT: Found an estimated cost of 2 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4
+; VF_4-LABEL: Checking a loop in "i32_factor_2"
+; VF_4: Found an estimated cost of 2 for VF 4 For instruction: %tmp2 = load i32, i32* %tmp0, align 4
+; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i32, i32* %tmp1, align 4
+; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp0, align 4
+; VF_4-NEXT: Found an estimated cost of 2 for VF 4 For instruction: store i32 0, i32* %tmp1, align 4
+; VF_8-LABEL: Checking a loop in "i32_factor_2"
+; VF_8: Found an estimated cost of 4 for VF 8 For instruction: %tmp2 = load i32, i32* %tmp0, align 4
+; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i32, i32* %tmp1, align 4
+; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp0, align 4
+; VF_8-NEXT: Found an estimated cost of 4 for VF 8 For instruction: store i32 0, i32* %tmp1, align 4
+; VF_16-LABEL: Checking a loop in "i32_factor_2"
+; VF_16: Found an estimated cost of 8 for VF 16 For instruction: %tmp2 = load i32, i32* %tmp0, align 4
+; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i32, i32* %tmp1, align 4
+; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp0, align 4
+; VF_16-NEXT: Found an estimated cost of 8 for VF 16 For instruction: store i32 0, i32* %tmp1, align 4
+for.body:
+ %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
+ %tmp0 = getelementptr inbounds %i32.2, %i32.2* %data, i64 %i, i32 0
+ %tmp1 = getelementptr inbounds %i32.2, %i32.2* %data, i64 %i, i32 1
+ %tmp2 = load i32, i32* %tmp0, align 4
+ %tmp3 = load i32, i32* %tmp1, align 4
+ store i32 0, i32* %tmp0, align 4
+ store i32 0, i32* %tmp1, align 4
+ %i.next = add nuw nsw i64 %i, 1
+ %cond = icmp slt i64 %i.next, %n
+ br i1 %cond, label %for.body, label %for.end
+
+for.end:
+ ret void
+}
+
+%half.2 = type {half, half}
+define void @half_factor_2(%half.2* %data, i64 %n) {
+entry:
+ br label %for.body
+
+; VF_4-LABEL: Checking a loop in "half_factor_2"
+; VF_4: Found an estimated cost of 40 for VF 4 For instruction: %tmp2 = load half, half* %tmp0, align 2
+; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load half, half* %tmp1, align 2
+; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store half 0xH0000, half* %tmp0, align 2
+; VF_4-NEXT: Found an estimated cost of 32 for VF 4 For instruction: store half 0xH0000, half* %tmp1, align 2
+; VF_8-LABEL: Checking a loop in "half_factor_2"
+; VF_8: Found an estimated cost of 80 for VF 8 For instruction: %tmp2 = load half, half* %tmp0, align 2
+; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load half, half* %tmp1, align 2
+; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store half 0xH0000, half* %tmp0, align 2
+; VF_8-NEXT: Found an estimated cost of 64 for VF 8 For instruction: store half 0xH0000, half* %tmp1, align 2
+for.body:
+ %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
+ %tmp0 = getelementptr inbounds %half.2, %half.2* %data, i64 %i, i32 0
+ %tmp1 = getelementptr inbounds %half.2, %half.2* %data, i64 %i, i32 1
+ %tmp2 = load half, half* %tmp0, align 2
+ %tmp3 = load half, half* %tmp1, align 2
+ store half 0., half* %tmp0, align 2
+ store half 0., half* %tmp1, align 2
+ %i.next = add nuw nsw i64 %i, 1
+ %cond = icmp slt i64 %i.next, %n
+ br i1 %cond, label %for.body, label %for.end
+
+for.end:
ret void
}
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-02 10:20:51 +0000