[clang] cece0a1 - Revert "[ConstantFold] Drop gep of gep fold entirely (#95126)"
Nikita Popov via cfe-commits
cfe-commits at lists.llvm.org
Wed Jun 12 02:52:27 PDT 2024
Author: Nikita Popov
Date: 2024-06-12T11:52:12+02:00
New Revision: cece0a105b29dcbb9d88d0aa264c4745c07a8456
URL: https://github.com/llvm/llvm-project/commit/cece0a105b29dcbb9d88d0aa264c4745c07a8456
DIFF: https://github.com/llvm/llvm-project/commit/cece0a105b29dcbb9d88d0aa264c4745c07a8456.diff
LOG: Revert "[ConstantFold] Drop gep of gep fold entirely (#95126)"
This reverts commit 3b3b839c66dc49674fd6646650525a2173030690.
This broke the flang+openmp+offload buildbot, as reported in
https://github.com/llvm/llvm-project/pull/95126#issuecomment-2162424019.
Added:
Modified:
clang/test/CodeGenCUDA/managed-var.cu
clang/test/CodeGenCXX/2011-12-19-init-list-ctor.cpp
clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist-pr12086.cpp
clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp
clang/test/CodeGenCXX/ms-inline-asm-fields.cpp
clang/test/OpenMP/threadprivate_codegen.cpp
llvm/include/llvm/IR/ConstantFold.h
llvm/lib/Analysis/InstructionSimplify.cpp
llvm/lib/IR/ConstantFold.cpp
llvm/lib/IR/Constants.cpp
Removed:
################################################################################
diff --git a/clang/test/CodeGenCUDA/managed-var.cu b/clang/test/CodeGenCUDA/managed-var.cu
index 07e1a1e692c75..5206acc62fe00 100644
--- a/clang/test/CodeGenCUDA/managed-var.cu
+++ b/clang/test/CodeGenCUDA/managed-var.cu
@@ -127,10 +127,9 @@ __device__ __host__ float load2() {
// HOST-LABEL: define {{.*}}@_Z5load3v()
// HOST: %ld.managed = load ptr, ptr @v2, align 16
-// HOST: %0 = getelementptr inbounds [100 x %struct.vec], ptr %ld.managed, i64 0, i64 1
-// HOST: %1 = getelementptr inbounds %struct.vec, ptr %0, i32 0, i32 1
-// HOST: %2 = load float, ptr %1, align 4
-// HOST: ret float %2
+// HOST: %0 = getelementptr inbounds [100 x %struct.vec], ptr %ld.managed, i64 0, i64 1, i32 1
+// HOST: %1 = load float, ptr %0, align 4
+// HOST: ret float %1
float load3() {
return v2[1].y;
}
@@ -140,11 +139,10 @@ float load3() {
// HOST: %0 = getelementptr inbounds [100 x %struct.vec], ptr %ld.managed, i64 0, i64 1
// HOST: %1 = ptrtoint ptr %0 to i64
// HOST: %ld.managed1 = load ptr, ptr @v2, align 16
-// HOST: %2 = getelementptr inbounds [100 x %struct.vec], ptr %ld.managed1, i64 0, i64 1
-// HOST: %3 = getelementptr inbounds %struct.vec, ptr %2, i32 0, i32 1
-// HOST: %4 = ptrtoint ptr %3 to i64
-// HOST: %5 = sub i64 %4, %1
-// HOST: %sub.ptr.div = sdiv exact i64 %5, 4
+// HOST: %2 = getelementptr inbounds [100 x %struct.vec], ptr %ld.managed1, i64 0, i64 1, i32 1
+// HOST: %3 = ptrtoint ptr %2 to i64
+// HOST: %4 = sub i64 %3, %1
+// HOST: %sub.ptr.div = sdiv exact i64 %4, 4
// HOST: %conv = sitofp i64 %sub.ptr.div to float
// HOST: ret float %conv
float addr_taken2() {
diff --git a/clang/test/CodeGenCXX/2011-12-19-init-list-ctor.cpp b/clang/test/CodeGenCXX/2011-12-19-init-list-ctor.cpp
index 14557829268ef..4033adc8f0390 100644
--- a/clang/test/CodeGenCXX/2011-12-19-init-list-ctor.cpp
+++ b/clang/test/CodeGenCXX/2011-12-19-init-list-ctor.cpp
@@ -21,6 +21,6 @@ struct S {
// CHECK: store i32 0, ptr @arr
// CHECK: call void @_ZN1AC1EPKc(ptr {{[^,]*}} getelementptr inbounds (%struct.S, ptr @arr, i32 0, i32 1), ptr noundef @.str)
// CHECK: store i32 1, ptr getelementptr inbounds (%struct.S, ptr @arr, i64 1)
-// CHECK: call void @_ZN1AC1EPKc(ptr {{[^,]*}} getelementptr inbounds (%struct.S, ptr getelementptr inbounds (%struct.S, ptr @arr, i64 1), i32 0, i32 1), ptr noundef @.str.1)
+// CHECK: call void @_ZN1AC1EPKc(ptr {{[^,]*}} getelementptr inbounds (%struct.S, ptr @arr, i64 1, i32 1), ptr noundef @.str.1)
// CHECK: store i32 2, ptr getelementptr inbounds (%struct.S, ptr @arr, i64 2)
-// CHECK: call void @_ZN1AC1EPKc(ptr {{[^,]*}} getelementptr inbounds (%struct.S, ptr getelementptr inbounds (%struct.S, ptr @arr, i64 2), i32 0, i32 1), ptr noundef @.str.2)
+// CHECK: call void @_ZN1AC1EPKc(ptr {{[^,]*}} getelementptr inbounds (%struct.S, ptr @arr, i64 2, i32 1), ptr noundef @.str.2)
diff --git a/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist-pr12086.cpp b/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist-pr12086.cpp
index caa92f47a93c2..6fbe4c7fd17a7 100644
--- a/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist-pr12086.cpp
+++ b/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist-pr12086.cpp
@@ -79,12 +79,12 @@ std::initializer_list<std::initializer_list<int>> nested = {
// CHECK-DYNAMIC-BL: store i32 {{.*}}, ptr getelementptr inbounds (i32, ptr @_ZGR6nested1_, i64 1)
// CHECK-DYNAMIC-BL: store ptr @_ZGR6nested1_,
// CHECK-DYNAMIC-BL: ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 1), align 8
-// CHECK-DYNAMIC-BL: store i64 2, ptr getelementptr inbounds ({{.*}}, ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 1), i32 0, i32 1), align 8
+// CHECK-DYNAMIC-BL: store i64 2, ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 1, i32 1), align 8
// CHECK-DYNAMIC-BL: store i32 5, ptr @_ZGR6nested2_
// CHECK-DYNAMIC-BL: store i32 {{.*}}, ptr getelementptr inbounds (i32, ptr @_ZGR6nested2_, i64 1)
// CHECK-DYNAMIC-BL: store ptr @_ZGR6nested2_,
// CHECK-DYNAMIC-BL: ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 2), align 8
-// CHECK-DYNAMIC-BL: store i64 2, ptr getelementptr inbounds ({{.*}}, ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 2), i32 0, i32 1), align 8
+// CHECK-DYNAMIC-BL: store i64 2, ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 2, i32 1), align 8
// CHECK-DYNAMIC-BL: store ptr @_ZGR6nested_,
// CHECK-DYNAMIC-BL: ptr @nested, align 8
// CHECK-DYNAMIC-BL: store i64 3, ptr getelementptr inbounds ({{.*}}, ptr @nested, i32 0, i32 1), align 8
@@ -119,13 +119,13 @@ std::initializer_list<std::initializer_list<int>> nested = {
// CHECK-DYNAMIC-BE: store ptr @_ZGR6nested1_,
// CHECK-DYNAMIC-BE: ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 1), align 8
// CHECK-DYNAMIC-BE: store ptr getelementptr inbounds ([2 x i32], ptr @_ZGR6nested1_, i64 0, i64 2),
-// CHECK-DYNAMIC-BE: ptr getelementptr inbounds ({{.*}}, ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 1), i32 0, i32 1), align 8
+// CHECK-DYNAMIC-BE: ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 1, i32 1), align 8
// CHECK-DYNAMIC-BE: store i32 5, ptr @_ZGR6nested2_
// CHECK-DYNAMIC-BE: store i32 {{.*}}, ptr getelementptr inbounds (i32, ptr @_ZGR6nested2_, i64 1)
// CHECK-DYNAMIC-BE: store ptr @_ZGR6nested2_,
// CHECK-DYNAMIC-BE: ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 2), align 8
// CHECK-DYNAMIC-BE: store ptr getelementptr inbounds ([2 x i32], ptr @_ZGR6nested2_, i64 0, i64 2),
-// CHECK-DYNAMIC-BE: ptr getelementptr inbounds ({{.*}}, ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 2), i32 0, i32 1), align 8
+// CHECK-DYNAMIC-BE: ptr getelementptr inbounds ({{.*}}, ptr @_ZGR6nested_, i64 2, i32 1), align 8
// CHECK-DYNAMIC-BE: store ptr @_ZGR6nested_,
// CHECK-DYNAMIC-BE: ptr @nested, align 8
// CHECK-DYNAMIC-BE: store ptr getelementptr inbounds ([3 x {{.*}}], ptr @_ZGR6nested_, i64 0, i64 3),
diff --git a/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp b/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp
index ef05f0334cd75..3d0cf968bfd54 100644
--- a/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp
+++ b/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp
@@ -365,12 +365,12 @@ namespace partly_constant {
//
// Second init list.
// CHECK: store ptr {{.*}}@[[PARTLY_CONSTANT_SECOND]]{{.*}}, ptr getelementptr inbounds ({{.*}}, ptr {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 1)
- // CHECK: store i64 2, ptr getelementptr inbounds ({{.*}}, ptr getelementptr inbounds ({{.*}}, ptr {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 1), i32 0, i32 1)
+ // CHECK: store i64 2, ptr getelementptr inbounds ({{.*}}, ptr {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 1, i32 1)
//
// Third init list.
// CHECK-NOT: @[[PARTLY_CONSTANT_THIRD]],
// CHECK: store ptr {{.*}}@[[PARTLY_CONSTANT_THIRD]]{{.*}}, ptr getelementptr inbounds ({{.*}}, ptr {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 2)
- // CHECK: store i64 4, ptr getelementptr inbounds ({{.*}}, ptr getelementptr inbounds ({{.*}}, ptr {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 2), i32 0, i32 1)
+ // CHECK: store i64 4, ptr getelementptr inbounds ({{.*}}, ptr {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 2, i32 1)
// CHECK-NOT: @[[PARTLY_CONSTANT_THIRD]],
//
// Outer init list.
diff --git a/clang/test/CodeGenCXX/ms-inline-asm-fields.cpp b/clang/test/CodeGenCXX/ms-inline-asm-fields.cpp
index e3441d0b4614e..403e9c8427760 100644
--- a/clang/test/CodeGenCXX/ms-inline-asm-fields.cpp
+++ b/clang/test/CodeGenCXX/ms-inline-asm-fields.cpp
@@ -24,7 +24,7 @@ extern "C" int test_param_field(A p) {
extern "C" int test_namespace_global() {
// CHECK: define{{.*}} i32 @test_namespace_global()
-// CHECK: call i32 asm sideeffect inteldialect "mov eax, $1", "{{.*}}"(ptr elementtype(i32) getelementptr inbounds (%"struct.A::B", ptr getelementptr inbounds (%struct.A, ptr @_ZN4asdf8a_globalE, i32 0, i32 2), i32 0, i32 1))
+// CHECK: call i32 asm sideeffect inteldialect "mov eax, $1", "{{.*}}"(ptr elementtype(i32) getelementptr inbounds (%struct.A, ptr @_ZN4asdf8a_globalE, i32 0, i32 2, i32 1))
// CHECK: ret i32
__asm mov eax, asdf::a_global.a3.b2
}
diff --git a/clang/test/OpenMP/threadprivate_codegen.cpp b/clang/test/OpenMP/threadprivate_codegen.cpp
index 7a6269954d39e..2ee328008cc4b 100644
--- a/clang/test/OpenMP/threadprivate_codegen.cpp
+++ b/clang/test/OpenMP/threadprivate_codegen.cpp
@@ -2586,7 +2586,7 @@ int foobar() {
// SIMD1-NEXT: [[TMP12:%.*]] = load i32, ptr [[RES]], align 4
// SIMD1-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP12]], [[TMP11]]
// SIMD1-NEXT: store i32 [[ADD3]], ptr [[RES]], align 4
-// SIMD1-NEXT: [[TMP13:%.*]] = load i32, ptr getelementptr inbounds ([3 x %struct.S1], ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1), i64 0, i64 1), align 4
+// SIMD1-NEXT: [[TMP13:%.*]] = load i32, ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1, i64 1), align 4
// SIMD1-NEXT: [[TMP14:%.*]] = load i32, ptr [[RES]], align 4
// SIMD1-NEXT: [[ADD4:%.*]] = add nsw i32 [[TMP14]], [[TMP13]]
// SIMD1-NEXT: store i32 [[ADD4]], ptr [[RES]], align 4
@@ -2663,7 +2663,7 @@ int foobar() {
// SIMD1-NEXT: [[TMP6:%.*]] = load i32, ptr [[RES]], align 4
// SIMD1-NEXT: [[ADD2:%.*]] = add nsw i32 [[TMP6]], [[TMP5]]
// SIMD1-NEXT: store i32 [[ADD2]], ptr [[RES]], align 4
-// SIMD1-NEXT: [[TMP7:%.*]] = load i32, ptr getelementptr inbounds ([3 x %struct.S1], ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1), i64 0, i64 1), align 4
+// SIMD1-NEXT: [[TMP7:%.*]] = load i32, ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1, i64 1), align 4
// SIMD1-NEXT: [[TMP8:%.*]] = load i32, ptr [[RES]], align 4
// SIMD1-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP8]], [[TMP7]]
// SIMD1-NEXT: store i32 [[ADD3]], ptr [[RES]], align 4
@@ -3052,7 +3052,7 @@ int foobar() {
// SIMD2-NEXT: [[TMP12:%.*]] = load i32, ptr [[RES]], align 4, !dbg [[DBG187:![0-9]+]]
// SIMD2-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP12]], [[TMP11]], !dbg [[DBG187]]
// SIMD2-NEXT: store i32 [[ADD3]], ptr [[RES]], align 4, !dbg [[DBG187]]
-// SIMD2-NEXT: [[TMP13:%.*]] = load i32, ptr getelementptr inbounds ([3 x %struct.S1], ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1), i64 0, i64 1), align 4, !dbg [[DBG188:![0-9]+]]
+// SIMD2-NEXT: [[TMP13:%.*]] = load i32, ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1, i64 1), align 4, !dbg [[DBG188:![0-9]+]]
// SIMD2-NEXT: [[TMP14:%.*]] = load i32, ptr [[RES]], align 4, !dbg [[DBG189:![0-9]+]]
// SIMD2-NEXT: [[ADD4:%.*]] = add nsw i32 [[TMP14]], [[TMP13]], !dbg [[DBG189]]
// SIMD2-NEXT: store i32 [[ADD4]], ptr [[RES]], align 4, !dbg [[DBG189]]
@@ -3133,7 +3133,7 @@ int foobar() {
// SIMD2-NEXT: [[TMP6:%.*]] = load i32, ptr [[RES]], align 4, !dbg [[DBG222:![0-9]+]]
// SIMD2-NEXT: [[ADD2:%.*]] = add nsw i32 [[TMP6]], [[TMP5]], !dbg [[DBG222]]
// SIMD2-NEXT: store i32 [[ADD2]], ptr [[RES]], align 4, !dbg [[DBG222]]
-// SIMD2-NEXT: [[TMP7:%.*]] = load i32, ptr getelementptr inbounds ([3 x %struct.S1], ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1), i64 0, i64 1), align 4, !dbg [[DBG223:![0-9]+]]
+// SIMD2-NEXT: [[TMP7:%.*]] = load i32, ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1, i64 1), align 4, !dbg [[DBG223:![0-9]+]]
// SIMD2-NEXT: [[TMP8:%.*]] = load i32, ptr [[RES]], align 4, !dbg [[DBG224:![0-9]+]]
// SIMD2-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP8]], [[TMP7]], !dbg [[DBG224]]
// SIMD2-NEXT: store i32 [[ADD3]], ptr [[RES]], align 4, !dbg [[DBG224]]
@@ -5707,7 +5707,7 @@ int foobar() {
// SIMD3-NEXT: [[TMP12:%.*]] = load i32, ptr [[RES]], align 4
// SIMD3-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP12]], [[TMP11]]
// SIMD3-NEXT: store i32 [[ADD3]], ptr [[RES]], align 4
-// SIMD3-NEXT: [[TMP13:%.*]] = load i32, ptr getelementptr inbounds ([3 x %struct.S1], ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1), i64 0, i64 1), align 4
+// SIMD3-NEXT: [[TMP13:%.*]] = load i32, ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1, i64 1), align 4
// SIMD3-NEXT: [[TMP14:%.*]] = load i32, ptr [[RES]], align 4
// SIMD3-NEXT: [[ADD4:%.*]] = add nsw i32 [[TMP14]], [[TMP13]]
// SIMD3-NEXT: store i32 [[ADD4]], ptr [[RES]], align 4
@@ -5784,7 +5784,7 @@ int foobar() {
// SIMD3-NEXT: [[TMP6:%.*]] = load i32, ptr [[RES]], align 4
// SIMD3-NEXT: [[ADD2:%.*]] = add nsw i32 [[TMP6]], [[TMP5]]
// SIMD3-NEXT: store i32 [[ADD2]], ptr [[RES]], align 4
-// SIMD3-NEXT: [[TMP7:%.*]] = load i32, ptr getelementptr inbounds ([3 x %struct.S1], ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1), i64 0, i64 1), align 4
+// SIMD3-NEXT: [[TMP7:%.*]] = load i32, ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1, i64 1), align 4
// SIMD3-NEXT: [[TMP8:%.*]] = load i32, ptr [[RES]], align 4
// SIMD3-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP8]], [[TMP7]]
// SIMD3-NEXT: store i32 [[ADD3]], ptr [[RES]], align 4
@@ -6173,7 +6173,7 @@ int foobar() {
// SIMD4-NEXT: [[TMP12:%.*]] = load i32, ptr [[RES]], align 4, !dbg [[DBG187:![0-9]+]]
// SIMD4-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP12]], [[TMP11]], !dbg [[DBG187]]
// SIMD4-NEXT: store i32 [[ADD3]], ptr [[RES]], align 4, !dbg [[DBG187]]
-// SIMD4-NEXT: [[TMP13:%.*]] = load i32, ptr getelementptr inbounds ([3 x %struct.S1], ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1), i64 0, i64 1), align 4, !dbg [[DBG188:![0-9]+]]
+// SIMD4-NEXT: [[TMP13:%.*]] = load i32, ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1, i64 1), align 4, !dbg [[DBG188:![0-9]+]]
// SIMD4-NEXT: [[TMP14:%.*]] = load i32, ptr [[RES]], align 4, !dbg [[DBG189:![0-9]+]]
// SIMD4-NEXT: [[ADD4:%.*]] = add nsw i32 [[TMP14]], [[TMP13]], !dbg [[DBG189]]
// SIMD4-NEXT: store i32 [[ADD4]], ptr [[RES]], align 4, !dbg [[DBG189]]
@@ -6254,7 +6254,7 @@ int foobar() {
// SIMD4-NEXT: [[TMP6:%.*]] = load i32, ptr [[RES]], align 4, !dbg [[DBG222:![0-9]+]]
// SIMD4-NEXT: [[ADD2:%.*]] = add nsw i32 [[TMP6]], [[TMP5]], !dbg [[DBG222]]
// SIMD4-NEXT: store i32 [[ADD2]], ptr [[RES]], align 4, !dbg [[DBG222]]
-// SIMD4-NEXT: [[TMP7:%.*]] = load i32, ptr getelementptr inbounds ([3 x %struct.S1], ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1), i64 0, i64 1), align 4, !dbg [[DBG223:![0-9]+]]
+// SIMD4-NEXT: [[TMP7:%.*]] = load i32, ptr getelementptr inbounds ([2 x [3 x %struct.S1]], ptr @arr_x, i64 0, i64 1, i64 1), align 4, !dbg [[DBG223:![0-9]+]]
// SIMD4-NEXT: [[TMP8:%.*]] = load i32, ptr [[RES]], align 4, !dbg [[DBG224:![0-9]+]]
// SIMD4-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP8]], [[TMP7]], !dbg [[DBG224]]
// SIMD4-NEXT: store i32 [[ADD3]], ptr [[RES]], align 4, !dbg [[DBG224]]
diff --git a/llvm/include/llvm/IR/ConstantFold.h b/llvm/include/llvm/IR/ConstantFold.h
index 42043d365b2d3..9b3c8a0e5a632 100644
--- a/llvm/include/llvm/IR/ConstantFold.h
+++ b/llvm/include/llvm/IR/ConstantFold.h
@@ -52,7 +52,7 @@ namespace llvm {
Constant *V2);
Constant *ConstantFoldCompareInstruction(CmpInst::Predicate Predicate,
Constant *C1, Constant *C2);
- Constant *ConstantFoldGetElementPtr(Type *Ty, Constant *C,
+ Constant *ConstantFoldGetElementPtr(Type *Ty, Constant *C, bool InBounds,
std::optional<ConstantRange> InRange,
ArrayRef<Value *> Idxs);
} // End llvm namespace
diff --git a/llvm/lib/Analysis/InstructionSimplify.cpp b/llvm/lib/Analysis/InstructionSimplify.cpp
index 00895860ca49b..8b2aa6b9f18b0 100644
--- a/llvm/lib/Analysis/InstructionSimplify.cpp
+++ b/llvm/lib/Analysis/InstructionSimplify.cpp
@@ -5068,8 +5068,9 @@ static Value *simplifyGEPInst(Type *SrcTy, Value *Ptr,
return nullptr;
if (!ConstantExpr::isSupportedGetElementPtr(SrcTy))
- return ConstantFoldGetElementPtr(SrcTy, cast<Constant>(Ptr), std::nullopt,
- Indices);
+ // TODO(gep_nowrap): Pass on the whole GEPNoWrapFlags.
+ return ConstantFoldGetElementPtr(SrcTy, cast<Constant>(Ptr),
+ NW.isInBounds(), std::nullopt, Indices);
auto *CE =
ConstantExpr::getGetElementPtr(SrcTy, cast<Constant>(Ptr), Indices, NW);
diff --git a/llvm/lib/IR/ConstantFold.cpp b/llvm/lib/IR/ConstantFold.cpp
index 34bcf36ec212c..77a833610a3a9 100644
--- a/llvm/lib/IR/ConstantFold.cpp
+++ b/llvm/lib/IR/ConstantFold.cpp
@@ -1404,7 +1404,35 @@ Constant *llvm::ConstantFoldCompareInstruction(CmpInst::Predicate Predicate,
return nullptr;
}
+// Combine Indices - If the source pointer to this getelementptr instruction
+// is a getelementptr instruction, combine the indices of the two
+// getelementptr instructions into a single instruction.
+static Constant *foldGEPOfGEP(GEPOperator *GEP, Type *PointeeTy, bool InBounds,
+ ArrayRef<Value *> Idxs) {
+ if (PointeeTy != GEP->getResultElementType())
+ return nullptr;
+
+ // Leave inrange handling to DL-aware constant folding.
+ if (GEP->getInRange())
+ return nullptr;
+
+ // Only handle simple case with leading zero index. We cannot perform an
+ // actual addition as we don't know the correct index type size to use.
+ Constant *Idx0 = cast<Constant>(Idxs[0]);
+ if (!Idx0->isNullValue())
+ return nullptr;
+
+ SmallVector<Value*, 16> NewIndices;
+ NewIndices.reserve(Idxs.size() + GEP->getNumIndices());
+ NewIndices.append(GEP->idx_begin(), GEP->idx_end());
+ NewIndices.append(Idxs.begin() + 1, Idxs.end());
+ return ConstantExpr::getGetElementPtr(
+ GEP->getSourceElementType(), cast<Constant>(GEP->getPointerOperand()),
+ NewIndices, InBounds && GEP->isInBounds());
+}
+
Constant *llvm::ConstantFoldGetElementPtr(Type *PointeeTy, Constant *C,
+ bool InBounds,
std::optional<ConstantRange> InRange,
ArrayRef<Value *> Idxs) {
if (Idxs.empty()) return C;
@@ -1434,5 +1462,10 @@ Constant *llvm::ConstantFoldGetElementPtr(Type *PointeeTy, Constant *C,
cast<VectorType>(GEPTy)->getElementCount(), C)
: C;
+ if (ConstantExpr *CE = dyn_cast<ConstantExpr>(C))
+ if (auto *GEP = dyn_cast<GEPOperator>(CE))
+ if (Constant *C = foldGEPOfGEP(GEP, PointeeTy, InBounds, Idxs))
+ return C;
+
return nullptr;
}
diff --git a/llvm/lib/IR/Constants.cpp b/llvm/lib/IR/Constants.cpp
index d07907372f0e4..a76be441875a1 100644
--- a/llvm/lib/IR/Constants.cpp
+++ b/llvm/lib/IR/Constants.cpp
@@ -2438,7 +2438,8 @@ Constant *ConstantExpr::getGetElementPtr(Type *Ty, Constant *C,
assert(Ty && "Must specify element type");
assert(isSupportedGetElementPtr(Ty) && "Element type is unsupported!");
- if (Constant *FC = ConstantFoldGetElementPtr(Ty, C, InRange, Idxs))
+ if (Constant *FC =
+ ConstantFoldGetElementPtr(Ty, C, NW.isInBounds(), InRange, Idxs))
return FC; // Fold a few common cases.
assert(GetElementPtrInst::getIndexedType(Ty, Idxs) && "GEP indices invalid!");
More information about the cfe-commits
mailing list