[AMDGPU] Fixed constexpr expansion to handle multiple uses

Recently added convertConstantExprsToInstructions() does not handle
a case when a same ConstantExpr used multiple times in the same
instruction. A first use is replaced and the rest of the uses in the
instruction are replaced as well with the replaceUsesOfWith(). Then
function attempts to replace a constant already destroyed.

So far this interface is only used by the AMDGPU BE.

Differential Revision: https://reviews.llvm.org/D104425

diff --git a/llvm/lib/IR/ReplaceConstant.cpp b/llvm/lib/IR/ReplaceConstant.cpp
index 06dedb2..9382f82 100644 (file)
--- a/llvm/lib/IR/ReplaceConstant.cpp
+++ b/llvm/lib/IR/ReplaceConstant.cpp
@@ -84,6 +84,7 @@ void convertConstantExprsToInstructions(
     Instruction *I,
     std::map<Use *, std::vector<std::vector<ConstantExpr *>>> &CEPaths,
     SmallPtrSetImpl<Instruction *> *Insts) {
+  SmallPtrSet<ConstantExpr *, 8> Visited;
   for (Use &U : I->operands()) {
     // The operand U is either not a constant expression operand or the
     // constant expression paths do not belong to U, ignore U.
@@ -102,7 +103,6 @@ void convertConstantExprsToInstructions(
     // constant expressions along all paths to corresponding instructions.
     auto *II = I;
     auto &Paths = CEPaths[&U];
-    SmallPtrSet<ConstantExpr *, 8> Visited;
     for (auto &Path : Paths) {
       for (auto *CE : Path) {
         if (!Visited.insert(CE).second)

diff --git a/llvm/test/CodeGen/AMDGPU/lower-kernel-lds-constexpr.ll b/llvm/test/CodeGen/AMDGPU/lower-kernel-lds-constexpr.ll
index 99a7c21..402a75f 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/lower-kernel-lds-constexpr.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-kernel-lds-constexpr.ll
@@ -9,6 +9,7 @@
 ; CHECK: %llvm.amdgcn.kernel.k2.lds.t = type { i32 }
 ; CHECK: %llvm.amdgcn.kernel.k3.lds.t = type { [32 x i8] }
 ; CHECK: %llvm.amdgcn.kernel.k4.lds.t = type { [2 x i8] }
+; CHECK: %llvm.amdgcn.kernel.k5.lds.t = type { [505 x i32] }
 
 ; Use constant from different kernels
 ;.
@@ -17,6 +18,7 @@
 ; CHECK: @llvm.amdgcn.kernel.k2.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k2.lds.t undef, align 4
 ; CHECK: @llvm.amdgcn.kernel.k3.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k3.lds.t undef, align 16
 ; CHECK: @llvm.amdgcn.kernel.k4.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k4.lds.t undef, align 2
+; CHECK: @llvm.amdgcn.kernel.k5.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k5.lds.t undef, align 16
 ;.
 define amdgpu_kernel void @k0(i64 %x) {
 ; CHECK-LABEL: @k0(
@@ -97,3 +99,16 @@ define amdgpu_kernel void @k4(i64 %x) {
   store i8 1, i8 addrspace(0)* %ptr, align 1
   ret void
 }
+
+@lds.4 = internal unnamed_addr addrspace(3) global [505 x i32] undef, align 4
+
+; Multiple constexpr use in a same instruction.
+define amdgpu_kernel void @k5() {
+; CHECK-LABEL: @k5(
+; CHECK-NEXT: %1 = addrspacecast [505 x i32] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k5.lds.t, %llvm.amdgcn.kernel.k5.lds.t addrspace(3)* @llvm.amdgcn.kernel.k5.lds, i32 0, i32 0) to [505 x i32]*
+; CHECK-NEXT: %2 = getelementptr inbounds [505 x i32], [505 x i32]* %1, i64 0, i64 0
+; CHECK-NEXT: call void undef(i32* %2, i32* %2)
+;
+  call void undef(i32* getelementptr inbounds ([505 x i32], [505 x i32]* addrspacecast ([505 x i32] addrspace(3)* @lds.4 to [505 x i32]*), i64 0, i64 0), i32* getelementptr inbounds ([505 x i32], [505 x i32]* addrspacecast ([505 x i32] addrspace(3)* @lds.4 to [505 x i32]*), i64 0, i64 0))
+  ret void
+}