When emitting the storage (or memory copy operations) for constant
initializers, the decision whether to split a constant structure or
array store into a sequence of field stores or to use `memcpy` is
based upon the optimization level and the size of the initializer.
In afe8b93ffd, we extended this by
allowing constants to be split when the array (or struct) type does
not match the type of data the address to the object (constant) is
expected to contain. This may happen when `emitStoresForConstant` is
called by `EmitAutoVarInit`, as the element type of the address gets
shrunk. When this occurs, let the initializer be split into a bunch
of stores only under `-ftrivial-auto-var-init=pattern`.
Fixes: https://github.com/llvm/llvm-project/issues/84178.
115 lines
5.9 KiB
C
115 lines
5.9 KiB
C
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --prefix-filecheck-ir-name _
|
|
// RUN: %clang_cc1 -fopenmp -O1 -x c -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK
|
|
|
|
typedef enum omp_allocator_handle_t {
|
|
omp_null_allocator = 0,
|
|
omp_default_mem_alloc = 1,
|
|
omp_large_cap_mem_alloc = 2,
|
|
omp_const_mem_alloc = 3,
|
|
omp_high_bw_mem_alloc = 4,
|
|
omp_low_lat_mem_alloc = 5,
|
|
omp_cgroup_mem_alloc = 6,
|
|
omp_pteam_mem_alloc = 7,
|
|
omp_thread_mem_alloc = 8,
|
|
KMP_ALLOCATOR_MAX_HANDLE = __UINTPTR_MAX__
|
|
} omp_allocator_handle_t;
|
|
|
|
typedef enum omp_memspace_handle_t {
|
|
omp_default_mem_space = 0,
|
|
omp_large_cap_mem_space = 1,
|
|
omp_const_mem_space = 2,
|
|
omp_high_bw_mem_space = 3,
|
|
omp_low_lat_mem_space = 4,
|
|
llvm_omp_target_host_mem_space = 100,
|
|
llvm_omp_target_shared_mem_space = 101,
|
|
llvm_omp_target_device_mem_space = 102,
|
|
KMP_MEMSPACE_MAX_HANDLE = __UINTPTR_MAX__
|
|
} omp_memspace_handle_t;
|
|
|
|
typedef enum {
|
|
omp_atk_sync_hint = 1,
|
|
omp_atk_alignment = 2,
|
|
omp_atk_access = 3,
|
|
omp_atk_pool_size = 4,
|
|
omp_atk_fallback = 5,
|
|
omp_atk_fb_data = 6,
|
|
omp_atk_pinned = 7,
|
|
omp_atk_partition = 8
|
|
} omp_alloctrait_key_t;
|
|
|
|
typedef __UINTPTR_TYPE__ omp_uintptr_t;
|
|
typedef __SIZE_TYPE__ size_t;
|
|
|
|
typedef struct {
|
|
omp_alloctrait_key_t key;
|
|
omp_uintptr_t value;
|
|
} omp_alloctrait_t;
|
|
|
|
extern omp_allocator_handle_t
|
|
omp_init_allocator(omp_memspace_handle_t memspace, int ntraits,
|
|
const omp_alloctrait_t traits[]);
|
|
|
|
#define N 1024
|
|
|
|
void foo() {
|
|
int *x;
|
|
|
|
omp_memspace_handle_t x_memspace = omp_default_mem_space;
|
|
omp_alloctrait_t x_traits[1] = {omp_atk_alignment, 64};
|
|
omp_allocator_handle_t x_alloc = omp_init_allocator(x_memspace, 1, x_traits);
|
|
|
|
#pragma omp parallel for allocate(x_alloc : x) private(x)
|
|
for (int i = 0; i < N; i++) {
|
|
(void)x;
|
|
}
|
|
}
|
|
// CHECK-LABEL: define {{[^@]+}}@foo
|
|
// CHECK-SAME: () local_unnamed_addr #[[ATTR0:[0-9]+]] {
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[X_TRAITS:%.*]] = alloca [1 x %struct.omp_alloctrait_t], align 16
|
|
// CHECK-NEXT: [[X_ALLOC:%.*]] = alloca i64, align 8
|
|
// CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 16, ptr nonnull [[X_TRAITS]]) #[[ATTR5:[0-9]+]]
|
|
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr noundef nonnull align 16 dereferenceable(16) [[X_TRAITS]], ptr noundef nonnull align 16 dereferenceable(16) @__const.foo.x_traits, i64 16, i1 false)
|
|
// CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 8, ptr nonnull [[X_ALLOC]]) #[[ATTR5]]
|
|
// CHECK-NEXT: [[CALL:%.*]] = call i64 @omp_init_allocator(i64 noundef 0, i32 noundef 1, ptr noundef nonnull [[X_TRAITS]]) #[[ATTR5]]
|
|
// CHECK-NEXT: store i64 [[CALL]], ptr [[X_ALLOC]], align 8, !tbaa [[TBAA3:![0-9]+]]
|
|
// CHECK-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr nonnull @[[GLOB2:[0-9]+]], i32 1, ptr nonnull @foo.omp_outlined, ptr nonnull [[X_ALLOC]])
|
|
// CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 8, ptr nonnull [[X_ALLOC]]) #[[ATTR5]]
|
|
// CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 16, ptr nonnull [[X_TRAITS]]) #[[ATTR5]]
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK-LABEL: define {{[^@]+}}@foo.omp_outlined
|
|
// CHECK-SAME: (ptr noalias nocapture noundef readonly [[DOTGLOBAL_TID_:%.*]], ptr noalias nocapture readnone [[DOTBOUND_TID_:%.*]], ptr nocapture noundef nonnull readonly align 8 dereferenceable(8) [[X_ALLOC:%.*]]) #[[ATTR4:[0-9]+]] {
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 4, ptr nonnull [[DOTOMP_LB]]) #[[ATTR5]]
|
|
// CHECK-NEXT: store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA6:![0-9]+]]
|
|
// CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 4, ptr nonnull [[DOTOMP_UB]]) #[[ATTR5]]
|
|
// CHECK-NEXT: store i32 1023, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA6]]
|
|
// CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 4, ptr nonnull [[DOTOMP_STRIDE]]) #[[ATTR5]]
|
|
// CHECK-NEXT: store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA6]]
|
|
// CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 4, ptr nonnull [[DOTOMP_IS_LAST]]) #[[ATTR5]]
|
|
// CHECK-NEXT: store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA6]]
|
|
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[DOTGLOBAL_TID_]], align 4, !tbaa [[TBAA6]]
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load i64, ptr [[X_ALLOC]], align 8, !tbaa [[TBAA3]]
|
|
// CHECK-NEXT: [[CONV:%.*]] = inttoptr i64 [[TMP1]] to ptr
|
|
// CHECK-NEXT: [[DOTX__VOID_ADDR:%.*]] = tail call ptr @__kmpc_alloc(i32 [[TMP0]], i64 8, ptr [[CONV]])
|
|
// CHECK-NEXT: call void @__kmpc_for_static_init_4(ptr nonnull @[[GLOB1:[0-9]+]], i32 [[TMP0]], i32 34, ptr nonnull [[DOTOMP_IS_LAST]], ptr nonnull [[DOTOMP_LB]], ptr nonnull [[DOTOMP_UB]], ptr nonnull [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4
|
|
// CHECK-NEXT: [[COND:%.*]] = call i32 @llvm.smin.i32(i32 [[TMP2]], i32 1023)
|
|
// CHECK-NEXT: store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA6]]
|
|
// CHECK-NEXT: call void @__kmpc_for_static_fini(ptr nonnull @[[GLOB1]], i32 [[TMP0]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = load i64, ptr [[X_ALLOC]], align 8, !tbaa [[TBAA3]]
|
|
// CHECK-NEXT: [[CONV5:%.*]] = inttoptr i64 [[TMP3]] to ptr
|
|
// CHECK-NEXT: call void @__kmpc_free(i32 [[TMP0]], ptr [[DOTX__VOID_ADDR]], ptr [[CONV5]])
|
|
// CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 4, ptr nonnull [[DOTOMP_IS_LAST]]) #[[ATTR5]]
|
|
// CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 4, ptr nonnull [[DOTOMP_STRIDE]]) #[[ATTR5]]
|
|
// CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 4, ptr nonnull [[DOTOMP_UB]]) #[[ATTR5]]
|
|
// CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 4, ptr nonnull [[DOTOMP_LB]]) #[[ATTR5]]
|
|
// CHECK-NEXT: ret void
|
|
//
|