[llvm] 2d9759c - [GlobalOpt] Fix the load types when OptimizeGlobalAddressOfMalloc
Shimin Cui via llvm-commits
llvm-commits at lists.llvm.org
Tue Aug 3 16:23:40 PDT 2021
Author: Shimin Cui
Date: 2021-08-03T19:22:53-04:00
New Revision: 2d9759c7902c5cbc9a7e3ab623321d5578d51687
URL: https://github.com/llvm/llvm-project/commit/2d9759c7902c5cbc9a7e3ab623321d5578d51687
DIFF: https://github.com/llvm/llvm-project/commit/2d9759c7902c5cbc9a7e3ab623321d5578d51687.diff
LOG: [GlobalOpt] Fix the load types when OptimizeGlobalAddressOfMalloc
Currently, in OptimizeGlobalAddressOfMalloc, the transformation for global loads assumes that they have the same Type. With the support of ConstantExpr (https://reviews.llvm.org/D106589), this may not be true any more (as seen in the test case), and we miss the code to handle this, This is to fix that.
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D107397
Added:
llvm/test/Transforms/GlobalOpt/2021-08-03-StoreOnceLoadMultiCasts.ll
Modified:
llvm/lib/Transforms/IPO/GlobalOpt.cpp
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/IPO/GlobalOpt.cpp b/llvm/lib/Transforms/IPO/GlobalOpt.cpp
index 94cd56f1e8e3..5904277fa6a6 100644
--- a/llvm/lib/Transforms/IPO/GlobalOpt.cpp
+++ b/llvm/lib/Transforms/IPO/GlobalOpt.cpp
@@ -967,9 +967,8 @@ OptimizeGlobalAddressOfMalloc(GlobalVariable *GV, CallInst *CI, Type *AllocTy,
}
}
- Constant *RepValue = NewGV;
- if (NewGV->getType() != GV->getValueType())
- RepValue = ConstantExpr::getBitCast(RepValue, GV->getValueType());
+ SmallPtrSet<Constant *, 1> RepValues;
+ RepValues.insert(NewGV);
// If there is a comparison against null, we will insert a global bool to
// keep track of whether the global was initialized yet or not.
@@ -1001,7 +1000,9 @@ OptimizeGlobalAddressOfMalloc(GlobalVariable *GV, CallInst *CI, Type *AllocTy,
Use &LoadUse = *LI->use_begin();
ICmpInst *ICI = dyn_cast<ICmpInst>(LoadUse.getUser());
if (!ICI) {
- LoadUse = RepValue;
+ auto *CE = ConstantExpr::getBitCast(NewGV, LI->getType());
+ RepValues.insert(CE);
+ LoadUse.set(CE);
continue;
}
@@ -1047,9 +1048,8 @@ OptimizeGlobalAddressOfMalloc(GlobalVariable *GV, CallInst *CI, Type *AllocTy,
// To further other optimizations, loop over all users of NewGV and try to
// constant prop them. This will promote GEP instructions with constant
// indices into GEP constant-exprs, which will allow global-opt to hack on it.
- ConstantPropUsersOf(NewGV, DL, TLI);
- if (RepValue != NewGV)
- ConstantPropUsersOf(RepValue, DL, TLI);
+ for (auto *CE : RepValues)
+ ConstantPropUsersOf(CE, DL, TLI);
return NewGV;
}
diff --git a/llvm/test/Transforms/GlobalOpt/2021-08-03-StoreOnceLoadMultiCasts.ll b/llvm/test/Transforms/GlobalOpt/2021-08-03-StoreOnceLoadMultiCasts.ll
new file mode 100644
index 000000000000..bac59f64acd1
--- /dev/null
+++ b/llvm/test/Transforms/GlobalOpt/2021-08-03-StoreOnceLoadMultiCasts.ll
@@ -0,0 +1,44 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -globalopt -S < %s | FileCheck %s
+; RUN: opt -passes=globalopt -S < %s | FileCheck %s
+
+ at g = internal global i32* null, align 8
+
+define signext i32 @f() local_unnamed_addr {
+; CHECK-LABEL: @f(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: call void @f1()
+; CHECK-NEXT: store i32 1, i32* @g.body, align 4
+; CHECK-NEXT: call void @f1()
+; CHECK-NEXT: store i8 2, i8* bitcast (i32* @g.body to i8*), align 4
+; CHECK-NEXT: ret i32 1
+;
+entry:
+ %call = call i8* @malloc(i64 4)
+ %b = bitcast i8* %call to i32*
+ store i32* %b, i32** @g, align 8
+ call void @f1()
+ %0 = load i32*, i32** @g, align 8
+ store i32 1, i32* %0, align 4
+ call void @f1()
+ %1 = load i8*, i8** bitcast (i32** @g to i8**), align 8
+ store i8 2, i8* %1, align 4
+ ret i32 1
+}
+
+define signext i32 @main() {
+; CHECK-LABEL: @main(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[CALL:%.*]] = call signext i32 @f()
+; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* @g.body, align 4
+; CHECK-NEXT: ret i32 [[TMP0]]
+;
+entry:
+ %call = call signext i32 @f()
+ %0 = load i32*, i32** @g, align 8
+ %1 = load i32, i32* %0, align 4
+ ret i32 %1
+}
+
+declare noalias align 16 i8* @malloc(i64)
+declare void @f1()
More information about the llvm-commits
mailing list