[llvm] [SLP][NFC]Add a test with the missed vectorization opportunity, NFC (PR #216790)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Aug 17 10:43:30 PDT 2026
llvmorg-github-actions[bot] wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: Alexey Bataev (alexey-bataev)
<details>
<summary>Changes</summary>
---
Full diff: https://github.com/llvm/llvm-project/pull/216790.diff
1 Files Affected:
- (added) llvm/test/Transforms/SLPVectorizer/AArch64/abs-mul-buildvector-in-loop.ll (+110)
``````````diff
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/abs-mul-buildvector-in-loop.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/abs-mul-buildvector-in-loop.ll
new file mode 100644
index 0000000000000..ef80d9e6bcfd9
--- /dev/null
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/abs-mul-buildvector-in-loop.ll
@@ -0,0 +1,110 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -S --passes=slp-vectorizer -mtriple=aarch64-linux-gnu -mcpu=cortex-a57 < %s | FileCheck %s
+
+ at lut = external constant [0 x i8]
+
+define void @test(ptr noalias %src, ptr noalias %descriptor, i32 %N) {
+; CHECK-LABEL: define void @test(
+; CHECK-SAME: ptr noalias [[SRC:%.*]], ptr noalias [[DESCRIPTOR:%.*]], i32 [[N:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: [[ENTRY:.*]]:
+; CHECK-NEXT: [[CMP32:%.*]] = icmp sgt i32 [[N]], 0
+; CHECK-NEXT: br i1 [[CMP32]], label %[[FOR_BODY:.*]], label %[[FOR_COND_CLEANUP:.*]]
+; CHECK: [[FOR_COND_CLEANUP]]:
+; CHECK-NEXT: ret void
+; CHECK: [[FOR_BODY]]:
+; CHECK-NEXT: [[SRC_ADDR_035:%.*]] = phi ptr [ [[ARRAYIDX:%.*]], %[[FOR_BODY]] ], [ [[SRC]], %[[ENTRY]] ]
+; CHECK-NEXT: [[P_034:%.*]] = phi ptr [ [[INCDEC_PTR10:%.*]], %[[FOR_BODY]] ], [ @lut, %[[ENTRY]] ]
+; CHECK-NEXT: [[I_033:%.*]] = phi i32 [ [[INC:%.*]], %[[FOR_BODY]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: [[ARRAYIDX]] = getelementptr inbounds nuw i8, ptr [[SRC_ADDR_035]], i64 1
+; CHECK-NEXT: [[TMP0:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-NEXT: [[CONV:%.*]] = zext i8 [[TMP0]] to i32
+; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[SRC_ADDR_035]], i64 -1
+; CHECK-NEXT: [[TMP1:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT: [[CONV2:%.*]] = zext i8 [[TMP1]] to i32
+; CHECK-NEXT: [[SUB:%.*]] = sub nsw i32 [[CONV]], [[CONV2]]
+; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds nuw i8, ptr [[SRC_ADDR_035]], i64 17
+; CHECK-NEXT: [[TMP2:%.*]] = load i8, ptr [[ARRAYIDX3]], align 1
+; CHECK-NEXT: [[CONV4:%.*]] = zext i8 [[TMP2]] to i32
+; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i8, ptr [[SRC_ADDR_035]], i64 -17
+; CHECK-NEXT: [[TMP3:%.*]] = load i8, ptr [[ARRAYIDX5]], align 1
+; CHECK-NEXT: [[CONV6:%.*]] = zext i8 [[TMP3]] to i32
+; CHECK-NEXT: [[SUB7:%.*]] = sub nsw i32 [[CONV4]], [[CONV6]]
+; CHECK-NEXT: [[TMP4:%.*]] = load i8, ptr [[P_034]], align 1
+; CHECK-NEXT: [[CONV9:%.*]] = zext i8 [[TMP4]] to i32
+; CHECK-NEXT: [[INCDEC_PTR10]] = getelementptr inbounds nuw i8, ptr [[P_034]], i64 2
+; CHECK-NEXT: [[BIN:%.*]] = getelementptr inbounds nuw i8, ptr [[P_034]], i64 1
+; CHECK-NEXT: [[TMP5:%.*]] = load i8, ptr [[BIN]], align 1
+; CHECK-NEXT: [[IDX_EXT:%.*]] = zext i8 [[TMP5]] to i64
+; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds nuw [4 x i8], ptr [[DESCRIPTOR]], i64 [[IDX_EXT]]
+; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[SUB]], [[CONV9]]
+; CHECK-NEXT: [[MUL12:%.*]] = mul nsw i32 [[SUB7]], [[CONV9]]
+; CHECK-NEXT: [[TMP6:%.*]] = tail call i32 @llvm.abs.i32(i32 [[MUL]], i1 true)
+; CHECK-NEXT: [[TMP7:%.*]] = tail call i32 @llvm.abs.i32(i32 [[MUL12]], i1 true)
+; CHECK-NEXT: [[TMP8:%.*]] = load <4 x i32>, ptr [[ADD_PTR]], align 4
+; CHECK-NEXT: [[TMP9:%.*]] = insertelement <4 x i32> poison, i32 [[MUL]], i64 0
+; CHECK-NEXT: [[TMP10:%.*]] = insertelement <4 x i32> [[TMP9]], i32 [[MUL12]], i64 1
+; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i32> [[TMP10]], i32 [[TMP6]], i64 2
+; CHECK-NEXT: [[TMP12:%.*]] = insertelement <4 x i32> [[TMP11]], i32 [[TMP7]], i64 3
+; CHECK-NEXT: [[TMP13:%.*]] = add nsw <4 x i32> [[TMP8]], [[TMP12]]
+; CHECK-NEXT: store <4 x i32> [[TMP13]], ptr [[ADD_PTR]], align 4
+; CHECK-NEXT: [[INC]] = add nuw nsw i32 [[I_033]], 1
+; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i32 [[INC]], [[N]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_COND_CLEANUP]], label %[[FOR_BODY]]
+;
+entry:
+ %cmp32 = icmp sgt i32 %N, 0
+ br i1 %cmp32, label %for.body, label %for.cond.cleanup
+
+for.cond.cleanup:
+ ret void
+
+for.body:
+ %src.addr.035 = phi ptr [ %arrayidx, %for.body ], [ %src, %entry ]
+ %p.034 = phi ptr [ %incdec.ptr10, %for.body ], [ @lut, %entry ]
+ %i.033 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
+ %arrayidx = getelementptr inbounds nuw i8, ptr %src.addr.035, i64 1
+ %0 = load i8, ptr %arrayidx, align 1
+ %conv = zext i8 %0 to i32
+ %arrayidx1 = getelementptr inbounds i8, ptr %src.addr.035, i64 -1
+ %1 = load i8, ptr %arrayidx1, align 1
+ %conv2 = zext i8 %1 to i32
+ %sub = sub nsw i32 %conv, %conv2
+ %arrayidx3 = getelementptr inbounds nuw i8, ptr %src.addr.035, i64 17
+ %2 = load i8, ptr %arrayidx3, align 1
+ %conv4 = zext i8 %2 to i32
+ %arrayidx5 = getelementptr inbounds i8, ptr %src.addr.035, i64 -17
+ %3 = load i8, ptr %arrayidx5, align 1
+ %conv6 = zext i8 %3 to i32
+ %sub7 = sub nsw i32 %conv4, %conv6
+ %4 = load i8, ptr %p.034, align 1
+ %conv9 = zext i8 %4 to i32
+ %incdec.ptr10 = getelementptr inbounds nuw i8, ptr %p.034, i64 2
+ %bin = getelementptr inbounds nuw i8, ptr %p.034, i64 1
+ %5 = load i8, ptr %bin, align 1
+ %idx.ext = zext i8 %5 to i64
+ %add.ptr = getelementptr inbounds nuw [4 x i8], ptr %descriptor, i64 %idx.ext
+ %mul = mul nsw i32 %sub, %conv9
+ %mul12 = mul nsw i32 %sub7, %conv9
+ %6 = load i32, ptr %add.ptr, align 4
+ %add = add nsw i32 %6, %mul
+ store i32 %add, ptr %add.ptr, align 4
+ %arrayidx14 = getelementptr inbounds nuw i8, ptr %add.ptr, i64 4
+ %7 = load i32, ptr %arrayidx14, align 4
+ %add15 = add nsw i32 %7, %mul12
+ store i32 %add15, ptr %arrayidx14, align 4
+ %8 = tail call i32 @llvm.abs.i32(i32 %mul, i1 true)
+ %arrayidx16 = getelementptr inbounds nuw i8, ptr %add.ptr, i64 8
+ %9 = load i32, ptr %arrayidx16, align 4
+ %add17 = add nsw i32 %9, %8
+ store i32 %add17, ptr %arrayidx16, align 4
+ %10 = tail call i32 @llvm.abs.i32(i32 %mul12, i1 true)
+ %arrayidx18 = getelementptr inbounds nuw i8, ptr %add.ptr, i64 12
+ %11 = load i32, ptr %arrayidx18, align 4
+ %add19 = add nsw i32 %11, %10
+ store i32 %add19, ptr %arrayidx18, align 4
+ %inc = add nuw nsw i32 %i.033, 1
+ %exitcond.not = icmp eq i32 %inc, %N
+ br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+}
+
+declare i32 @llvm.abs.i32(i32, i1 immarg)
``````````
</details>
https://github.com/llvm/llvm-project/pull/216790
More information about the llvm-commits
mailing list