[llvm] 1c0ab34 - [SLP]Add a test for possibly vectorized tiny tree, NFC.

[Alexey Bataev via llvm-commits]

Author: Alexey Bataev
Date: 2021-04-27T13:39:02-07:00
New Revision: 1c0ab3411a7067d301ebf0315736ecf8945cb321

URL: https://github.com/llvm/llvm-project/commit/1c0ab3411a7067d301ebf0315736ecf8945cb321
DIFF: https://github.com/llvm/llvm-project/commit/1c0ab3411a7067d301ebf0315736ecf8945cb321.diff

LOG: [SLP]Add a test for possibly vectorized tiny tree, NFC.

Added: 
    

Modified: 
    llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll

Removed: 
    


################################################################################
diff  --git a/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll b/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll
index be619fdd711b2..65f02770ab853 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -basic-aa -slp-vectorizer -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 | FileCheck %s
+; RUN: opt < %s -basic-aa -slp-vectorizer -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
 
 define void @tiny_tree_fully_vectorizable(double* noalias nocapture %dst, double* noalias nocapture readonly %src, i64 %count) #0 {
 ; CHECK-LABEL: @tiny_tree_fully_vectorizable(
@@ -266,3 +266,46 @@ entry:
   store i32 40, i32* %ptr3, align 4
   ret void
 }
+
+define void @tiny_vector_gather(i32 *%a, i32 *%v1, i32 *%v2) {
+; CHECK-LABEL: @tiny_vector_gather(
+; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[V1:%.*]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[V2:%.*]], align 4
+; CHECK-NEXT:    [[PTR0:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 0
+; CHECK-NEXT:    store i32 [[TMP1]], i32* [[PTR0]], align 16
+; CHECK-NEXT:    [[PTR1:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 1
+; CHECK-NEXT:    store i32 [[TMP2]], i32* [[PTR1]], align 4
+; CHECK-NEXT:    [[PTR2:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 2
+; CHECK-NEXT:    store i32 [[TMP1]], i32* [[PTR2]], align 8
+; CHECK-NEXT:    [[PTR3:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 3
+; CHECK-NEXT:    store i32 [[TMP2]], i32* [[PTR3]], align 4
+; CHECK-NEXT:    [[PTR4:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4
+; CHECK-NEXT:    store i32 [[TMP1]], i32* [[PTR4]], align 16
+; CHECK-NEXT:    [[PTR5:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 5
+; CHECK-NEXT:    store i32 [[TMP2]], i32* [[PTR5]], align 4
+; CHECK-NEXT:    [[PTR6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 6
+; CHECK-NEXT:    store i32 [[TMP1]], i32* [[PTR6]], align 8
+; CHECK-NEXT:    [[PTR7:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 7
+; CHECK-NEXT:    store i32 [[TMP2]], i32* [[PTR7]], align 4
+; CHECK-NEXT:    ret void
+;
+  %1 = load i32, i32* %v1, align 4
+  %2 = load i32, i32* %v2, align 4
+  %ptr0 = getelementptr inbounds i32, i32* %a, i64 0
+  store i32 %1, i32* %ptr0, align 16
+  %ptr1 = getelementptr inbounds i32, i32* %a, i64 1
+  store i32 %2, i32* %ptr1, align 4
+  %ptr2 = getelementptr inbounds i32, i32* %a, i64 2
+  store i32 %1, i32* %ptr2, align 8
+  %ptr3 = getelementptr inbounds i32, i32* %a, i64 3
+  store i32 %2, i32* %ptr3, align 4
+  %ptr4 = getelementptr inbounds i32, i32* %a, i64 4
+  store i32 %1, i32* %ptr4, align 16
+  %ptr5 = getelementptr inbounds i32, i32* %a, i64 5
+  store i32 %2, i32* %ptr5, align 4
+  %ptr6 = getelementptr inbounds i32, i32* %a, i64 6
+  store i32 %1, i32* %ptr6, align 8
+  %ptr7 = getelementptr inbounds i32, i32* %a, i64 7
+  store i32 %2, i32* %ptr7, align 4
+  ret void
+}