[llvm] 3ee1882 - Add another test which breaks the load insert point

[via llvm-commits]

Author: bipmis
Date: 2022-11-03T12:28:24Z
New Revision: 3ee1882299f9f7d62c10093fa968f0b16669df0c

URL: https://github.com/llvm/llvm-project/commit/3ee1882299f9f7d62c10093fa968f0b16669df0c
DIFF: https://github.com/llvm/llvm-project/commit/3ee1882299f9f7d62c10093fa968f0b16669df0c.diff

LOG: Add another test which breaks the load insert point

Added: 
    

Modified: 
    llvm/test/Transforms/AggressiveInstCombine/AArch64/or-load.ll
    llvm/test/Transforms/AggressiveInstCombine/X86/or-load.ll

Removed: 
    


################################################################################
diff  --git a/llvm/test/Transforms/AggressiveInstCombine/AArch64/or-load.ll b/llvm/test/Transforms/AggressiveInstCombine/AArch64/or-load.ll
index 822af07c7fada..24febe4ed8fbc 100644
--- a/llvm/test/Transforms/AggressiveInstCombine/AArch64/or-load.ll
+++ b/llvm/test/Transforms/AggressiveInstCombine/AArch64/or-load.ll
@@ -1820,3 +1820,55 @@ define i32 @loadCombine_4consecutive_badinsert(ptr %p) {
   %o3 = or i32 %o2, %s4
   ret i32 %o3
 }
+
+define i32 @loadCombine_4consecutive_badinsert2(ptr %p) {
+; LE-LABEL: @loadCombine_4consecutive_badinsert2(
+; LE-NEXT:    [[P3:%.*]] = getelementptr i8, ptr [[P:%.*]], i32 3
+; LE-NEXT:    store i8 0, ptr [[P3]], align 1
+; LE-NEXT:    [[L1:%.*]] = load i32, ptr [[P]], align 1
+; LE-NEXT:    ret i32 [[L1]]
+;
+; BE-LABEL: @loadCombine_4consecutive_badinsert2(
+; BE-NEXT:    [[P1:%.*]] = getelementptr i8, ptr [[P:%.*]], i32 1
+; BE-NEXT:    [[P2:%.*]] = getelementptr i8, ptr [[P]], i32 2
+; BE-NEXT:    [[P3:%.*]] = getelementptr i8, ptr [[P]], i32 3
+; BE-NEXT:    [[L2:%.*]] = load i8, ptr [[P1]], align 1
+; BE-NEXT:    store i8 0, ptr [[P3]], align 1
+; BE-NEXT:    [[L3:%.*]] = load i8, ptr [[P2]], align 1
+; BE-NEXT:    [[L4:%.*]] = load i8, ptr [[P3]], align 1
+; BE-NEXT:    [[L1:%.*]] = load i8, ptr [[P]], align 1
+; BE-NEXT:    [[E1:%.*]] = zext i8 [[L1]] to i32
+; BE-NEXT:    [[E2:%.*]] = zext i8 [[L2]] to i32
+; BE-NEXT:    [[E3:%.*]] = zext i8 [[L3]] to i32
+; BE-NEXT:    [[E4:%.*]] = zext i8 [[L4]] to i32
+; BE-NEXT:    [[S2:%.*]] = shl i32 [[E2]], 8
+; BE-NEXT:    [[S3:%.*]] = shl i32 [[E3]], 16
+; BE-NEXT:    [[S4:%.*]] = shl i32 [[E4]], 24
+; BE-NEXT:    [[O1:%.*]] = or i32 [[E1]], [[S2]]
+; BE-NEXT:    [[O2:%.*]] = or i32 [[O1]], [[S3]]
+; BE-NEXT:    [[O3:%.*]] = or i32 [[O2]], [[S4]]
+; BE-NEXT:    ret i32 [[O3]]
+;
+  %p1 = getelementptr i8, ptr %p, i32 1
+  %p2 = getelementptr i8, ptr %p, i32 2
+  %p3 = getelementptr i8, ptr %p, i32 3
+  %l2 = load i8, ptr %p1
+  store i8 0, ptr %p3, align 1
+  %l3 = load i8, ptr %p2
+  %l4 = load i8, ptr %p3
+  %l1 = load i8, ptr %p
+
+  %e1 = zext i8 %l1 to i32
+  %e2 = zext i8 %l2 to i32
+  %e3 = zext i8 %l3 to i32
+  %e4 = zext i8 %l4 to i32
+
+  %s2 = shl i32 %e2, 8
+  %s3 = shl i32 %e3, 16
+  %s4 = shl i32 %e4, 24
+
+  %o1 = or i32 %e1, %s2
+  %o2 = or i32 %o1, %s3
+  %o3 = or i32 %o2, %s4
+  ret i32 %o3
+}

diff  --git a/llvm/test/Transforms/AggressiveInstCombine/X86/or-load.ll b/llvm/test/Transforms/AggressiveInstCombine/X86/or-load.ll
index b043bb75313c5..7eb3fc31ba6d6 100644
--- a/llvm/test/Transforms/AggressiveInstCombine/X86/or-load.ll
+++ b/llvm/test/Transforms/AggressiveInstCombine/X86/or-load.ll
@@ -1940,3 +1940,55 @@ define i32 @loadCombine_4consecutive_badinsert(ptr %p) {
   %o3 = or i32 %o2, %s4
   ret i32 %o3
 }
+
+define i32 @loadCombine_4consecutive_badinsert2(ptr %p) {
+; LE-LABEL: @loadCombine_4consecutive_badinsert2(
+; LE-NEXT:    [[P3:%.*]] = getelementptr i8, ptr [[P:%.*]], i32 3
+; LE-NEXT:    store i8 0, ptr [[P3]], align 1
+; LE-NEXT:    [[L1:%.*]] = load i32, ptr [[P]], align 1
+; LE-NEXT:    ret i32 [[L1]]
+;
+; BE-LABEL: @loadCombine_4consecutive_badinsert2(
+; BE-NEXT:    [[P1:%.*]] = getelementptr i8, ptr [[P:%.*]], i32 1
+; BE-NEXT:    [[P2:%.*]] = getelementptr i8, ptr [[P]], i32 2
+; BE-NEXT:    [[P3:%.*]] = getelementptr i8, ptr [[P]], i32 3
+; BE-NEXT:    [[L2:%.*]] = load i8, ptr [[P1]], align 1
+; BE-NEXT:    store i8 0, ptr [[P3]], align 1
+; BE-NEXT:    [[L3:%.*]] = load i8, ptr [[P2]], align 1
+; BE-NEXT:    [[L4:%.*]] = load i8, ptr [[P3]], align 1
+; BE-NEXT:    [[L1:%.*]] = load i8, ptr [[P]], align 1
+; BE-NEXT:    [[E1:%.*]] = zext i8 [[L1]] to i32
+; BE-NEXT:    [[E2:%.*]] = zext i8 [[L2]] to i32
+; BE-NEXT:    [[E3:%.*]] = zext i8 [[L3]] to i32
+; BE-NEXT:    [[E4:%.*]] = zext i8 [[L4]] to i32
+; BE-NEXT:    [[S2:%.*]] = shl i32 [[E2]], 8
+; BE-NEXT:    [[S3:%.*]] = shl i32 [[E3]], 16
+; BE-NEXT:    [[S4:%.*]] = shl i32 [[E4]], 24
+; BE-NEXT:    [[O1:%.*]] = or i32 [[E1]], [[S2]]
+; BE-NEXT:    [[O2:%.*]] = or i32 [[O1]], [[S3]]
+; BE-NEXT:    [[O3:%.*]] = or i32 [[O2]], [[S4]]
+; BE-NEXT:    ret i32 [[O3]]
+;
+  %p1 = getelementptr i8, ptr %p, i32 1
+  %p2 = getelementptr i8, ptr %p, i32 2
+  %p3 = getelementptr i8, ptr %p, i32 3
+  %l2 = load i8, ptr %p1
+  store i8 0, ptr %p3, align 1
+  %l3 = load i8, ptr %p2
+  %l4 = load i8, ptr %p3
+  %l1 = load i8, ptr %p
+
+  %e1 = zext i8 %l1 to i32
+  %e2 = zext i8 %l2 to i32
+  %e3 = zext i8 %l3 to i32
+  %e4 = zext i8 %l4 to i32
+
+  %s2 = shl i32 %e2, 8
+  %s3 = shl i32 %e3, 16
+  %s4 = shl i32 %e4, 24
+
+  %o1 = or i32 %e1, %s2
+  %o2 = or i32 %o1, %s3
+  %o3 = or i32 %o2, %s4
+  ret i32 %o3
+}