derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
121 lines
6.7 KiB
C
121 lines
6.7 KiB
C
// RUN: %clang_cc1 -emit-llvm -triple arm64-- -fexperimental-max-bitint-width=1024 -o - %s -O0 | FileCheck %s --check-prefix=CHECK-O0
|
|
// RUN: %clang_cc1 -emit-llvm -disable-llvm-optzns -fexperimental-max-bitint-width=1024 -triple arm64-- -o - %s -O3 | FileCheck %s --check-prefix=CHECK-O3
|
|
|
|
struct large {
|
|
void* pointers[8];
|
|
};
|
|
|
|
void pass_large(struct large);
|
|
void pass_large_BitInt(_BitInt(129));
|
|
|
|
// For arm64, we don't use byval to pass structs and _BitInt(>128) type, but instead we create
|
|
// temporary allocas.
|
|
//
|
|
// Make sure we generate the appropriate lifetime markers for the temporary
|
|
// allocas so that the optimizer can re-use stack slots if possible.
|
|
void example(void) {
|
|
struct large l = {0};
|
|
pass_large(l);
|
|
pass_large(l);
|
|
}
|
|
// CHECK-O0-LABEL: define{{.*}} void @example(
|
|
// The alloca for the struct on the stack.
|
|
// CHECK-O0: %[[l:[0-9A-Za-z-]+]] = alloca %struct.large, align 8
|
|
// The alloca for the temporary stack space that we use to pass the argument.
|
|
// CHECK-O0-NEXT: %[[byvaltemp:[0-9A-Za-z-]+]] = alloca %struct.large, align 8
|
|
// Another one to pass the argument to the second function call.
|
|
// CHECK-O0-NEXT: %[[byvaltemp1:[0-9A-Za-z-]+]] = alloca %struct.large, align 8
|
|
// First, memset `l` to 0.
|
|
// CHECK-O0-NEXT: call void @llvm.memset.p0.i64(ptr align 8 %[[l]], i8 0, i64 64, i1 false)
|
|
// Then, memcpy `l` to the temporary stack space.
|
|
// CHECK-O0-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 8 %[[byvaltemp]], ptr align 8 %[[l]], i64 64, i1 false)
|
|
// Finally, call using a pointer to the temporary stack space.
|
|
// CHECK-O0-NEXT: call void @pass_large(ptr noundef dead_on_return %[[byvaltemp]])
|
|
// Now, do the same for the second call, using the second temporary alloca.
|
|
// CHECK-O0-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 8 %[[byvaltemp1]], ptr align 8 %[[l]], i64 64, i1 false)
|
|
// CHECK-O0-NEXT: call void @pass_large(ptr noundef dead_on_return %[[byvaltemp1]])
|
|
// CHECK-O0-NEXT: ret void
|
|
//
|
|
// At O3, we should have lifetime markers to help the optimizer re-use the temporary allocas.
|
|
//
|
|
// CHECK-O3-LABEL: define{{.*}} void @example(
|
|
// The alloca for the struct on the stack.
|
|
// CHECK-O3: %[[l:[0-9A-Za-z-]+]] = alloca %struct.large, align 8
|
|
// The alloca for the temporary stack space that we use to pass the argument.
|
|
// CHECK-O3-NEXT: %[[byvaltemp:[0-9A-Za-z-]+]] = alloca %struct.large, align 8
|
|
// Another one to pass the argument to the second function call.
|
|
// CHECK-O3-NEXT: %[[byvaltemp1:[0-9A-Za-z-]+]] = alloca %struct.large, align 8
|
|
//
|
|
// Mark the start of the lifetime for `l`
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.start.p0(ptr %[[l]])
|
|
//
|
|
// First, memset `l` to 0.
|
|
// CHECK-O3-NEXT: call void @llvm.memset.p0.i64(ptr align 8 %[[l]], i8 0, i64 64, i1 false)
|
|
//
|
|
// Lifetime of the first temporary starts here and ends right after the call.
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.start.p0(ptr %[[byvaltemp]])
|
|
//
|
|
// Then, memcpy `l` to the temporary stack space.
|
|
// CHECK-O3-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 8 %[[byvaltemp]], ptr align 8 %[[l]], i64 64, i1 false)
|
|
// Finally, call using a pointer to the temporary stack space.
|
|
// CHECK-O3-NEXT: call void @pass_large(ptr noundef dead_on_return %[[byvaltemp]])
|
|
//
|
|
// The lifetime of the temporary used to pass a pointer to the struct ends here.
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.end.p0(ptr %[[byvaltemp]])
|
|
//
|
|
// Now, do the same for the second call, using the second temporary alloca.
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.start.p0(ptr %[[byvaltemp1]])
|
|
// CHECK-O3-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 8 %[[byvaltemp1]], ptr align 8 %[[l]], i64 64, i1 false)
|
|
// CHECK-O3-NEXT: call void @pass_large(ptr noundef dead_on_return %[[byvaltemp1]])
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.end.p0(ptr %[[byvaltemp1]])
|
|
//
|
|
// Mark the end of the lifetime of `l`.
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.end.p0(ptr %l)
|
|
// CHECK-O3-NEXT: ret void
|
|
|
|
void example_BitInt(void) {
|
|
_BitInt(129) l = {0};
|
|
pass_large_BitInt(l);
|
|
pass_large_BitInt(l);
|
|
}
|
|
// CHECK-O0-LABEL: define dso_local void @example_BitInt(
|
|
// CHECK-O0-NEXT: entry:
|
|
// CHECK-O0-NEXT: [[L:%.*]] = alloca i256, align 16
|
|
// CHECK-O0-NEXT: [[INDIRECT_ARG_TEMP:%.*]] = alloca i256, align 16
|
|
// CHECK-O0-NEXT: [[INDIRECT_ARG_TEMP1:%.*]] = alloca i256, align 16
|
|
// CHECK-O0-NEXT: store i256 0, ptr [[L]], align 16
|
|
// CHECK-O0-NEXT: [[TMP0:%.*]] = load i256, ptr [[L]], align 16
|
|
// CHECK-O0-NEXT: [[LOADEDV:%.*]] = trunc i256 [[TMP0]] to i129
|
|
// CHECK-O0-NEXT: [[STOREDV:%.*]] = sext i129 [[LOADEDV]] to i256
|
|
// CHECK-O0-NEXT: store i256 [[STOREDV]], ptr [[INDIRECT_ARG_TEMP]], align 16
|
|
// CHECK-O0-NEXT: call void @pass_large_BitInt(ptr noundef dead_on_return [[INDIRECT_ARG_TEMP]])
|
|
// CHECK-O0-NEXT: [[TMP1:%.*]] = load i256, ptr [[L]], align 16
|
|
// CHECK-O0-NEXT: [[LOADEDV1:%.*]] = trunc i256 [[TMP1]] to i129
|
|
// CHECK-O0-NEXT: [[STOREDV1:%.*]] = sext i129 [[LOADEDV1]] to i256
|
|
// CHECK-O0-NEXT: store i256 [[STOREDV1]], ptr [[INDIRECT_ARG_TEMP1]], align 16
|
|
// CHECK-O0-NEXT: call void @pass_large_BitInt(ptr noundef dead_on_return [[INDIRECT_ARG_TEMP1]])
|
|
// CHECK-O0-NEXT: ret void
|
|
//
|
|
// CHECK-O3-LABEL: define dso_local void @example_BitInt(
|
|
// CHECK-O3-NEXT: entry:
|
|
// CHECK-O3-NEXT: [[L:%.*]] = alloca i256, align 16
|
|
// CHECK-O3-NEXT: [[INDIRECT_ARG_TEMP:%.*]] = alloca i256, align 16
|
|
// CHECK-O3-NEXT: [[INDIRECT_ARG_TEMP1:%.*]] = alloca i256, align 16
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.start.p0(ptr [[L]])
|
|
// CHECK-O3-NEXT: store i256 0, ptr [[L]], align 16, !tbaa [[TBAA6:![0-9]+]]
|
|
// CHECK-O3-NEXT: [[TMP0:%.*]] = load i256, ptr [[L]], align 16, !tbaa [[TBAA6]]
|
|
// CHECK-O3-NEXT: [[LOADEDV:%.*]] = trunc i256 [[TMP0]] to i129
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.start.p0(ptr [[INDIRECT_ARG_TEMP]])
|
|
// CHECK-O3-NEXT: [[STOREDV:%.*]] = sext i129 [[LOADEDV]] to i256
|
|
// CHECK-O3-NEXT: store i256 [[STOREDV]], ptr [[INDIRECT_ARG_TEMP]], align 16, !tbaa [[TBAA6]]
|
|
// CHECK-O3-NEXT: call void @pass_large_BitInt(ptr noundef dead_on_return [[INDIRECT_ARG_TEMP]])
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.end.p0(ptr [[INDIRECT_ARG_TEMP]])
|
|
// CHECK-O3-NEXT: [[TMP1:%.*]] = load i256, ptr [[L]], align 16, !tbaa [[TBAA6]]
|
|
// CHECK-O3-NEXT: [[LOADEDV1:%.*]] = trunc i256 [[TMP1]] to i129
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.start.p0(ptr [[INDIRECT_ARG_TEMP1]])
|
|
// CHECK-O3-NEXT: [[STOREDV1:%.*]] = sext i129 [[LOADEDV1]] to i256
|
|
// CHECK-O3-NEXT: store i256 [[STOREDV1]], ptr [[INDIRECT_ARG_TEMP1]], align 16, !tbaa [[TBAA6]]
|
|
// CHECK-O3-NEXT: call void @pass_large_BitInt(ptr noundef dead_on_return [[INDIRECT_ARG_TEMP1]])
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.end.p0(ptr [[INDIRECT_ARG_TEMP1]])
|
|
// CHECK-O3-NEXT: call void @llvm.lifetime.end.p0(ptr [[L]])
|