shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/clang/test/OpenMP/target_map_deref_array_codegen.cpp
Jennifer Yu 0f2f378425 Add map info for dereference pointer. 
This is to fix run time problem when use:

int **a;
map((*a)[:3]), (*a)[1] or map(**a).

current we skip generate map info for dereference pointer:
&(*a), &(*a)[0], 3*sizeof(int), TARGET_PARAM | TO | FROM

One way to fix runtime problem is to generate map info for dereference
pointer.

map((*a)[:3]):
&(*a), &(*a), sizeof(pointer),  TARGET_PARAM | TO | FROM
&(*a), &(*a)[0], 3*sizeof(int),  PTR_AND_OBJ | TO | FROM

map(**a):
&(*a), &(*a), sizeof(pointer),  TARGET_PARAM | TO | FROM
&(*a), &(**a), sizeof(int),  PTR_AND_OBJ | TO | FROM

The change in CGOpenMPRuntime.cpp add that.

The change in SemaOpenMP is to fix variable of dereference pointer to array
captured by reference.  That is wrong. That cause run time to fail.

The rule is:
If variable is identified in a map clause it is always captured by
reference except if it is a pointer that is dereferenced somehow.

Differential Revision: https://reviews.llvm.org/D145093
2023-03-08 17:43:43 -08:00

316 lines
23 KiB
C++
Raw Blame History

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
extern void *malloc (int __size) throw () __attribute__ ((__malloc__));
void foo(int **t1d)
{
*t1d = (int *) malloc(3 * sizeof(int));
for (int j=0; j < 3; j++)
(*t1d)[j] = 1;
#pragma omp target map(to: (*t1d)[0:3])
(*t1d)[2] = 2;
#pragma omp target map(tofrom : (**t1d))
(*t1d)[0] = 3;
int a = 0, b = 0;
#pragma omp target map(tofrom : (*(*(t1d+a)+b)))
*(*(t1d+a)+b) = 4;
}
#endif
// CHECK: @.offload_maptypes = private unnamed_addr constant [2 x i64] [i64 33, i64 17]
// CHECK: @.offload_maptypes.2 = private unnamed_addr constant [2 x i64] [i64 35, i64 19]
// CHECK: @.offload_maptypes.4 = private unnamed_addr constant [4 x i64] [i64 35, i64 19, i64 800, i64 800]
// CHECK-LABEL: define {{[^@]+}}@_Z3fooPPi
// CHECK-SAME: (ptr noundef [[T1D:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[T1D_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[J:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [2 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [2 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [2 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_BASEPTRS2:%.*]] = alloca [2 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_PTRS3:%.*]] = alloca [2 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_MAPPERS4:%.*]] = alloca [2 x ptr], align 8
// CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[A_CASTED:%.*]] = alloca i64, align 8
// CHECK-NEXT: [[B_CASTED:%.*]] = alloca i64, align 8
// CHECK-NEXT: [[DOTOFFLOAD_BASEPTRS12:%.*]] = alloca [4 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_PTRS13:%.*]] = alloca [4 x ptr], align 8
// CHECK-NEXT: [[DOTOFFLOAD_MAPPERS14:%.*]] = alloca [4 x ptr], align 8
// CHECK-NEXT: store ptr [[T1D]], ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[CALL:%.*]] = call noalias noundef ptr @_Z6malloci(i32 noundef signext 12) #[[ATTR3:[0-9]+]]
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: store ptr [[CALL]], ptr [[TMP0]], align 8
// CHECK-NEXT: store i32 0, ptr [[J]], align 4
// CHECK-NEXT: br label [[FOR_COND:%.*]]
// CHECK: for.cond:
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[J]], align 4
// CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP1]], 3
// CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
// CHECK: for.body:
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TMP2]], align 8
// CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr [[J]], align 4
// CHECK-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP4]] to i64
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[TMP3]], i64 [[IDXPROM]]
// CHECK-NEXT: store i32 1, ptr [[ARRAYIDX]], align 4
// CHECK-NEXT: br label [[FOR_INC:%.*]]
// CHECK: for.inc:
// CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[J]], align 4
// CHECK-NEXT: [[INC:%.*]] = add nsw i32 [[TMP5]], 1
// CHECK-NEXT: store i32 [[INC]], ptr [[J]], align 4
// CHECK-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP6:![0-9]+]]
// CHECK: for.end:
// CHECK-NEXT: [[TMP6:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP7:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP8:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP9:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP10:%.*]] = load ptr, ptr [[TMP9]], align 8
// CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[TMP10]], i64 0
// CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK-NEXT: store ptr [[TMP7]], ptr [[TMP11]], align 8
// CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK-NEXT: store ptr [[TMP8]], ptr [[TMP12]], align 8
// CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
// CHECK-NEXT: store ptr null, ptr [[TMP13]], align 8
// CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK-NEXT: store ptr [[TMP8]], ptr [[TMP14]], align 8
// CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK-NEXT: store ptr [[ARRAYIDX1]], ptr [[TMP15]], align 8
// CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
// CHECK-NEXT: store ptr null, ptr [[TMP16]], align 8
// CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK-NEXT: [[KERNEL_ARGS:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS:%.*]], align 8
// CHECK-NEXT: [[TMP19:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 0
// CHECK-NEXT: store i32 2, ptr [[TMP19]], align 4
// CHECK-NEXT: [[TMP20:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 1
// CHECK-NEXT: store i32 2, ptr [[TMP20]], align 4
// CHECK-NEXT: [[TMP21:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 2
// CHECK-NEXT: store ptr [[TMP17]], ptr [[TMP21]], align 8
// CHECK-NEXT: [[TMP22:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 3
// CHECK-NEXT: store ptr [[TMP18]], ptr [[TMP22]], align 8
// CHECK-NEXT: [[TMP23:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 4
// CHECK-NEXT: store ptr @.offload_sizes, ptr [[TMP23]], align 8
// CHECK-NEXT: [[TMP24:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 5
// CHECK-NEXT: store ptr @.offload_maptypes, ptr [[TMP24]], align 8
// CHECK-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 6
// CHECK-NEXT: store ptr null, ptr [[TMP25]], align 8
// CHECK-NEXT: [[TMP26:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 7
// CHECK-NEXT: store ptr null, ptr [[TMP26]], align 8
// CHECK-NEXT: [[TMP27:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 8
// CHECK-NEXT: store i64 0, ptr [[TMP27]], align 8
// CHECK-NEXT: [[TMP28:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 9
// CHECK-NEXT: store i64 0, ptr [[TMP28]], align 8
// CHECK-NEXT: [[TMP29:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 10
// CHECK-NEXT: store [3 x i32] [i32 -1, i32 0, i32 0], ptr [[TMP29]], align 4
// CHECK-NEXT: [[TMP30:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 11
// CHECK-NEXT: store [3 x i32] zeroinitializer, ptr [[TMP30]], align 4
// CHECK-NEXT: [[TMP31:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS]], i32 0, i32 12
// CHECK-NEXT: store i32 0, ptr [[TMP31]], align 4
// CHECK-NEXT: [[TMP32:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1:[0-9]+]], i64 -1, i32 -1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooPPi_l17.region_id, ptr [[KERNEL_ARGS]])
// CHECK-NEXT: [[TMP33:%.*]] = icmp ne i32 [[TMP32]], 0
// CHECK-NEXT: br i1 [[TMP33]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK: omp_offload.failed:
// CHECK-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooPPi_l17(ptr [[TMP6]]) #[[ATTR3]]
// CHECK-NEXT: br label [[OMP_OFFLOAD_CONT]]
// CHECK: omp_offload.cont:
// CHECK-NEXT: [[TMP34:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP35:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP36:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP37:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP38:%.*]] = load ptr, ptr [[TMP37]], align 8
// CHECK-NEXT: [[TMP39:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS2]], i32 0, i32 0
// CHECK-NEXT: store ptr [[TMP35]], ptr [[TMP39]], align 8
// CHECK-NEXT: [[TMP40:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS3]], i32 0, i32 0
// CHECK-NEXT: store ptr [[TMP36]], ptr [[TMP40]], align 8
// CHECK-NEXT: [[TMP41:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS4]], i64 0, i64 0
// CHECK-NEXT: store ptr null, ptr [[TMP41]], align 8
// CHECK-NEXT: [[TMP42:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS2]], i32 0, i32 1
// CHECK-NEXT: store ptr [[TMP36]], ptr [[TMP42]], align 8
// CHECK-NEXT: [[TMP43:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS3]], i32 0, i32 1
// CHECK-NEXT: store ptr [[TMP38]], ptr [[TMP43]], align 8
// CHECK-NEXT: [[TMP44:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_MAPPERS4]], i64 0, i64 1
// CHECK-NEXT: store ptr null, ptr [[TMP44]], align 8
// CHECK-NEXT: [[TMP45:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_BASEPTRS2]], i32 0, i32 0
// CHECK-NEXT: [[TMP46:%.*]] = getelementptr inbounds [2 x ptr], ptr [[DOTOFFLOAD_PTRS3]], i32 0, i32 0
// CHECK-NEXT: [[KERNEL_ARGS5:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS]], align 8
// CHECK-NEXT: [[TMP47:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 0
// CHECK-NEXT: store i32 2, ptr [[TMP47]], align 4
// CHECK-NEXT: [[TMP48:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 1
// CHECK-NEXT: store i32 2, ptr [[TMP48]], align 4
// CHECK-NEXT: [[TMP49:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 2
// CHECK-NEXT: store ptr [[TMP45]], ptr [[TMP49]], align 8
// CHECK-NEXT: [[TMP50:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 3
// CHECK-NEXT: store ptr [[TMP46]], ptr [[TMP50]], align 8
// CHECK-NEXT: [[TMP51:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 4
// CHECK-NEXT: store ptr @.offload_sizes.1, ptr [[TMP51]], align 8
// CHECK-NEXT: [[TMP52:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 5
// CHECK-NEXT: store ptr @.offload_maptypes.2, ptr [[TMP52]], align 8
// CHECK-NEXT: [[TMP53:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 6
// CHECK-NEXT: store ptr null, ptr [[TMP53]], align 8
// CHECK-NEXT: [[TMP54:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 7
// CHECK-NEXT: store ptr null, ptr [[TMP54]], align 8
// CHECK-NEXT: [[TMP55:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 8
// CHECK-NEXT: store i64 0, ptr [[TMP55]], align 8
// CHECK-NEXT: [[TMP56:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 9
// CHECK-NEXT: store i64 0, ptr [[TMP56]], align 8
// CHECK-NEXT: [[TMP57:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 10
// CHECK-NEXT: store [3 x i32] [i32 -1, i32 0, i32 0], ptr [[TMP57]], align 4
// CHECK-NEXT: [[TMP58:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 11
// CHECK-NEXT: store [3 x i32] zeroinitializer, ptr [[TMP58]], align 4
// CHECK-NEXT: [[TMP59:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS5]], i32 0, i32 12
// CHECK-NEXT: store i32 0, ptr [[TMP59]], align 4
// CHECK-NEXT: [[TMP60:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 -1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooPPi_l19.region_id, ptr [[KERNEL_ARGS5]])
// CHECK-NEXT: [[TMP61:%.*]] = icmp ne i32 [[TMP60]], 0
// CHECK-NEXT: br i1 [[TMP61]], label [[OMP_OFFLOAD_FAILED6:%.*]], label [[OMP_OFFLOAD_CONT7:%.*]]
// CHECK: omp_offload.failed6:
// CHECK-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooPPi_l19(ptr [[TMP34]]) #[[ATTR3]]
// CHECK-NEXT: br label [[OMP_OFFLOAD_CONT7]]
// CHECK: omp_offload.cont7:
// CHECK-NEXT: store i32 0, ptr [[A]], align 4
// CHECK-NEXT: store i32 0, ptr [[B]], align 4
// CHECK-NEXT: [[TMP62:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP63:%.*]] = load i32, ptr [[A]], align 4
// CHECK-NEXT: store i32 [[TMP63]], ptr [[A_CASTED]], align 4
// CHECK-NEXT: [[TMP64:%.*]] = load i64, ptr [[A_CASTED]], align 8
// CHECK-NEXT: [[TMP65:%.*]] = load i32, ptr [[B]], align 4
// CHECK-NEXT: store i32 [[TMP65]], ptr [[B_CASTED]], align 4
// CHECK-NEXT: [[TMP66:%.*]] = load i64, ptr [[B_CASTED]], align 8
// CHECK-NEXT: [[TMP67:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP68:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP69:%.*]] = load i32, ptr [[A]], align 4
// CHECK-NEXT: [[IDX_EXT:%.*]] = sext i32 [[TMP69]] to i64
// CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds ptr, ptr [[TMP68]], i64 [[IDX_EXT]]
// CHECK-NEXT: [[TMP70:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP71:%.*]] = load i32, ptr [[A]], align 4
// CHECK-NEXT: [[IDX_EXT8:%.*]] = sext i32 [[TMP71]] to i64
// CHECK-NEXT: [[ADD_PTR9:%.*]] = getelementptr inbounds ptr, ptr [[TMP70]], i64 [[IDX_EXT8]]
// CHECK-NEXT: [[TMP72:%.*]] = load ptr, ptr [[ADD_PTR9]], align 8
// CHECK-NEXT: [[TMP73:%.*]] = load i32, ptr [[B]], align 4
// CHECK-NEXT: [[IDX_EXT10:%.*]] = sext i32 [[TMP73]] to i64
// CHECK-NEXT: [[ADD_PTR11:%.*]] = getelementptr inbounds i32, ptr [[TMP72]], i64 [[IDX_EXT10]]
// CHECK-NEXT: [[TMP74:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS12]], i32 0, i32 0
// CHECK-NEXT: store ptr [[TMP67]], ptr [[TMP74]], align 8
// CHECK-NEXT: [[TMP75:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS13]], i32 0, i32 0
// CHECK-NEXT: store ptr [[ADD_PTR]], ptr [[TMP75]], align 8
// CHECK-NEXT: [[TMP76:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS14]], i64 0, i64 0
// CHECK-NEXT: store ptr null, ptr [[TMP76]], align 8
// CHECK-NEXT: [[TMP77:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS12]], i32 0, i32 1
// CHECK-NEXT: store ptr [[ADD_PTR]], ptr [[TMP77]], align 8
// CHECK-NEXT: [[TMP78:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS13]], i32 0, i32 1
// CHECK-NEXT: store ptr [[ADD_PTR11]], ptr [[TMP78]], align 8
// CHECK-NEXT: [[TMP79:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS14]], i64 0, i64 1
// CHECK-NEXT: store ptr null, ptr [[TMP79]], align 8
// CHECK-NEXT: [[TMP80:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS12]], i32 0, i32 2
// CHECK-NEXT: store i64 [[TMP64]], ptr [[TMP80]], align 8
// CHECK-NEXT: [[TMP81:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS13]], i32 0, i32 2
// CHECK-NEXT: store i64 [[TMP64]], ptr [[TMP81]], align 8
// CHECK-NEXT: [[TMP82:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS14]], i64 0, i64 2
// CHECK-NEXT: store ptr null, ptr [[TMP82]], align 8
// CHECK-NEXT: [[TMP83:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS12]], i32 0, i32 3
// CHECK-NEXT: store i64 [[TMP66]], ptr [[TMP83]], align 8
// CHECK-NEXT: [[TMP84:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS13]], i32 0, i32 3
// CHECK-NEXT: store i64 [[TMP66]], ptr [[TMP84]], align 8
// CHECK-NEXT: [[TMP85:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_MAPPERS14]], i64 0, i64 3
// CHECK-NEXT: store ptr null, ptr [[TMP85]], align 8
// CHECK-NEXT: [[TMP86:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_BASEPTRS12]], i32 0, i32 0
// CHECK-NEXT: [[TMP87:%.*]] = getelementptr inbounds [4 x ptr], ptr [[DOTOFFLOAD_PTRS13]], i32 0, i32 0
// CHECK-NEXT: [[KERNEL_ARGS15:%.*]] = alloca [[STRUCT___TGT_KERNEL_ARGUMENTS]], align 8
// CHECK-NEXT: [[TMP88:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 0
// CHECK-NEXT: store i32 2, ptr [[TMP88]], align 4
// CHECK-NEXT: [[TMP89:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 1
// CHECK-NEXT: store i32 4, ptr [[TMP89]], align 4
// CHECK-NEXT: [[TMP90:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 2
// CHECK-NEXT: store ptr [[TMP86]], ptr [[TMP90]], align 8
// CHECK-NEXT: [[TMP91:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 3
// CHECK-NEXT: store ptr [[TMP87]], ptr [[TMP91]], align 8
// CHECK-NEXT: [[TMP92:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 4
// CHECK-NEXT: store ptr @.offload_sizes.3, ptr [[TMP92]], align 8
// CHECK-NEXT: [[TMP93:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 5
// CHECK-NEXT: store ptr @.offload_maptypes.4, ptr [[TMP93]], align 8
// CHECK-NEXT: [[TMP94:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 6
// CHECK-NEXT: store ptr null, ptr [[TMP94]], align 8
// CHECK-NEXT: [[TMP95:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 7
// CHECK-NEXT: store ptr null, ptr [[TMP95]], align 8
// CHECK-NEXT: [[TMP96:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 8
// CHECK-NEXT: store i64 0, ptr [[TMP96]], align 8
// CHECK-NEXT: [[TMP97:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 9
// CHECK-NEXT: store i64 0, ptr [[TMP97]], align 8
// CHECK-NEXT: [[TMP98:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 10
// CHECK-NEXT: store [3 x i32] [i32 -1, i32 0, i32 0], ptr [[TMP98]], align 4
// CHECK-NEXT: [[TMP99:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 11
// CHECK-NEXT: store [3 x i32] zeroinitializer, ptr [[TMP99]], align 4
// CHECK-NEXT: [[TMP100:%.*]] = getelementptr inbounds [[STRUCT___TGT_KERNEL_ARGUMENTS]], ptr [[KERNEL_ARGS15]], i32 0, i32 12
// CHECK-NEXT: store i32 0, ptr [[TMP100]], align 4
// CHECK-NEXT: [[TMP101:%.*]] = call i32 @__tgt_target_kernel(ptr @[[GLOB1]], i64 -1, i32 -1, i32 0, ptr @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooPPi_l22.region_id, ptr [[KERNEL_ARGS15]])
// CHECK-NEXT: [[TMP102:%.*]] = icmp ne i32 [[TMP101]], 0
// CHECK-NEXT: br i1 [[TMP102]], label [[OMP_OFFLOAD_FAILED16:%.*]], label [[OMP_OFFLOAD_CONT17:%.*]]
// CHECK: omp_offload.failed16:
// CHECK-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooPPi_l22(ptr [[TMP62]], i64 [[TMP64]], i64 [[TMP66]]) #[[ATTR3]]
// CHECK-NEXT: br label [[OMP_OFFLOAD_CONT17]]
// CHECK: omp_offload.cont17:
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooPPi_l17
// CHECK-SAME: (ptr noundef [[T1D:%.*]]) #[[ATTR2:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[T1D_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[T1D]], ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[TMP0]], align 8
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 2
// CHECK-NEXT: store i32 2, ptr [[ARRAYIDX]], align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooPPi_l19
// CHECK-SAME: (ptr noundef [[T1D:%.*]]) #[[ATTR2]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[T1D_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[T1D]], ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[TMP0]], align 8
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 0
// CHECK-NEXT: store i32 3, ptr [[ARRAYIDX]], align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooPPi_l22
// CHECK-SAME: (ptr noundef [[T1D:%.*]], i64 noundef [[A:%.*]], i64 noundef [[B:%.*]]) #[[ATTR2]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[T1D_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i64, align 8
// CHECK-NEXT: store ptr [[T1D]], ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: store i64 [[A]], ptr [[A_ADDR]], align 8
// CHECK-NEXT: store i64 [[B]], ptr [[B_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[T1D_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[IDX_EXT:%.*]] = sext i32 [[TMP1]] to i64
// CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds ptr, ptr [[TMP0]], i64 [[IDX_EXT]]
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[ADD_PTR]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[IDX_EXT1:%.*]] = sext i32 [[TMP3]] to i64
// CHECK-NEXT: [[ADD_PTR2:%.*]] = getelementptr inbounds i32, ptr [[TMP2]], i64 [[IDX_EXT1]]
// CHECK-NEXT: store i32 4, ptr [[ADD_PTR2]], align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
// CHECK-SAME: () #[[ATTR4:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: call void @__tgt_register_requires(i64 1)
// CHECK-NEXT: ret void
//
Reference in New Issue View Git Blame Copy Permalink