maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/OpenMP/taskloop_codegen.cpp

205 lines
12 KiB
C++
Raw Normal View History

[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -x c++ -emit-llvm %s -o - -femit-all-decls | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - -femit-all-decls | FileCheck %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp-simd -x c++ -emit-llvm %s -o - -femit-all-decls | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - -femit-all-decls | FileCheck --check-prefix SIMD-ONLY0 %s
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
// CHECK-LABEL: @main
int main(int argc, char **argv) {
[OPENMP] General code improvements. llvm-svn: 330140
2018-04-17 01:59:34 +08:00
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* [[DEFLOC:@.+]])
// CHECK: call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[DEFLOC]], i32 [[GTID]],
// CHECK: call i32 @__kmpc_omp_task(%struct.ident_t* [[DEFLOC]], i32 [[GTID]],
[OPENMP] Fix PR34916: Crash on mixing taskloop|tasks directives. If both taskloop and task directives are used at the same time in one program, we may ran into the situation when the particular type for task directive is reused for taskloop directives. Patch fixes this problem. llvm-svn: 315464
2017-10-11 23:29:40 +08:00
#pragma omp task
;
[OPENMP] General code improvements. llvm-svn: 330140
2018-04-17 01:59:34 +08:00
// CHECK: call void @__kmpc_taskgroup(%struct.ident_t* [[DEFLOC]], i32 [[GTID]])
// CHECK: [[TASKV:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i32 33, i64 80, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, [[TDP_TY:%.+]]*)* [[TASK1:@.+]] to i32 (i32, i8*)*))
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[TASK:%.+]] = bitcast i8* [[TASKV]] to [[TDP_TY]]*
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds [[TDP_TY]], [[TDP_TY]]* [[TASK]], i32 0, i32 0
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 5
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 0, i64* [[DOWN]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 6
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 9, i64* [[UP]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 7
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 1, i64* [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
[OPENMP] General code improvements. llvm-svn: 330140
2018-04-17 01:59:34 +08:00
// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 0, i64 0, i8* null)
// CHECK: call void @__kmpc_end_taskgroup(%struct.ident_t* [[DEFLOC]], i32 [[GTID]])
[OPENMP 4.0] Fixed codegen for destructors in task-based directives. If private variables require destructors call at the deletion of the task, additional flag in task flags must be set. Patch fixes this problem. llvm-svn: 269039
2016-05-10 18:36:51 +08:00
#pragma omp taskloop priority(argc)
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
for (int i = 0; i < 10; ++i)
;
[OPENMP] General code improvements. llvm-svn: 330140
2018-04-17 01:59:34 +08:00
// CHECK: [[TASKV:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i32 1, i64 80, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, [[TDP_TY:%.+]]*)* [[TASK2:@.+]] to i32 (i32, i8*)*))
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[TASK:%.+]] = bitcast i8* [[TASKV]] to [[TDP_TY]]*
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds [[TDP_TY]], [[TDP_TY]]* [[TASK]], i32 0, i32 0
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 5
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 0, i64* [[DOWN]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 6
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 9, i64* [[UP]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 7
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 1, i64* [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
[OPENMP 4.5] Codegen for 'grainsize/num_tasks' clauses of 'taskloop' directive. OpenMP 4.5 defines 'taskloop' directive and 2 additional clauses 'grainsize' and 'num_tasks' for this directive. Patch adds codegen for these clauses. These clauses are generated as arguments of the '__kmpc_taskloop' libcall and are encoded the following way: void __kmpc_taskloop(ident_t *loc, int gtid, kmp_task_t *task, int if_val, kmp_uint64 *lb, kmp_uint64 *ub, kmp_int64 st, int nogroup, int sched, kmp_uint64 grainsize, void *task_dup); If 'grainsize' is specified, 'sched' argument must be set to '1' and 'grainsize' argument must be set to the value of the 'grainsize' clause. If 'num_tasks' is specified, 'sched' argument must be set to '2' and 'grainsize' argument must be set to the value of the 'num_tasks' clause. It is possible because these 2 clauses are mutually exclusive and can't be used at the same time on the same directive. If none of these clauses is specified, 'sched' argument must be set to '0'. llvm-svn: 267862
2016-04-28 17:15:06 +08:00
// CHECK: [[GRAINSIZE:%.+]] = zext i32 %{{.+}} to i64
[OPENMP] General code improvements. llvm-svn: 330140
2018-04-17 01:59:34 +08:00
// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 1, i64 [[GRAINSIZE]], i8* null)
[OPENMP 4.5] Codegen for 'grainsize/num_tasks' clauses of 'taskloop' directive. OpenMP 4.5 defines 'taskloop' directive and 2 additional clauses 'grainsize' and 'num_tasks' for this directive. Patch adds codegen for these clauses. These clauses are generated as arguments of the '__kmpc_taskloop' libcall and are encoded the following way: void __kmpc_taskloop(ident_t *loc, int gtid, kmp_task_t *task, int if_val, kmp_uint64 *lb, kmp_uint64 *ub, kmp_int64 st, int nogroup, int sched, kmp_uint64 grainsize, void *task_dup); If 'grainsize' is specified, 'sched' argument must be set to '1' and 'grainsize' argument must be set to the value of the 'grainsize' clause. If 'num_tasks' is specified, 'sched' argument must be set to '2' and 'grainsize' argument must be set to the value of the 'num_tasks' clause. It is possible because these 2 clauses are mutually exclusive and can't be used at the same time on the same directive. If none of these clauses is specified, 'sched' argument must be set to '0'. llvm-svn: 267862
2016-04-28 17:15:06 +08:00
#pragma omp taskloop nogroup grainsize(argc)
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
for (int i = 0; i < 10; ++i)
;
[OPENMP] General code improvements. llvm-svn: 330140
2018-04-17 01:59:34 +08:00
// CHECK: call void @__kmpc_taskgroup(%struct.ident_t* [[DEFLOC]], i32 [[GTID]])
// CHECK: [[TASKV:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i32 1, i64 80, i64 24, i32 (i32, i8*)* bitcast (i32 (i32, [[TDP_TY:%.+]]*)* [[TASK3:@.+]] to i32 (i32, i8*)*))
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[TASK:%.+]] = bitcast i8* [[TASKV]] to [[TDP_TY]]*
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds [[TDP_TY]], [[TDP_TY]]* [[TASK]], i32 0, i32 0
// CHECK: [[IF:%.+]] = icmp ne i32 %{{.+}}, 0
// CHECK: [[IF_INT:%.+]] = sext i1 [[IF]] to i32
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 5
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 0, i64* [[DOWN]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 6
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 %{{.+}}, i64* [[UP]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 7
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 1, i64* [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
[OPENMP] General code improvements. llvm-svn: 330140
2018-04-17 01:59:34 +08:00
// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 [[IF_INT]], i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 2, i64 4, i8* null)
// CHECK: call void @__kmpc_end_taskgroup(%struct.ident_t* [[DEFLOC]], i32 [[GTID]])
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
int i;
[OPENMP 4.5] Codegen for 'grainsize/num_tasks' clauses of 'taskloop' directive. OpenMP 4.5 defines 'taskloop' directive and 2 additional clauses 'grainsize' and 'num_tasks' for this directive. Patch adds codegen for these clauses. These clauses are generated as arguments of the '__kmpc_taskloop' libcall and are encoded the following way: void __kmpc_taskloop(ident_t *loc, int gtid, kmp_task_t *task, int if_val, kmp_uint64 *lb, kmp_uint64 *ub, kmp_int64 st, int nogroup, int sched, kmp_uint64 grainsize, void *task_dup); If 'grainsize' is specified, 'sched' argument must be set to '1' and 'grainsize' argument must be set to the value of the 'grainsize' clause. If 'num_tasks' is specified, 'sched' argument must be set to '2' and 'grainsize' argument must be set to the value of the 'num_tasks' clause. It is possible because these 2 clauses are mutually exclusive and can't be used at the same time on the same directive. If none of these clauses is specified, 'sched' argument must be set to '0'. llvm-svn: 267862
2016-04-28 17:15:06 +08:00
#pragma omp taskloop if(argc) shared(argc, argv) collapse(2) num_tasks(4)
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
for (i = 0; i < argc; ++i)
for (int j = argc; j < argv[argc][argc]; ++j)
;
}
// CHECK: define internal i32 [[TASK1]](
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* %{{.+}}, i32 0, i32 5
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[DOWN_VAL:%.+]] = load i64, i64* [[DOWN]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 6
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[UP_VAL:%.+]] = load i64, i64* [[UP]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 7
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[LITER:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 8
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[LITER_VAL:%.+]] = load i32, i32* [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], i64* [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], i64* [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], i64* [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], i32* [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, i64* [[LB]],
// CHECK: [[LB_I32:%.+]] = trunc i64 [[LB_VAL]] to i32
// CHECK: store i32 [[LB_I32]], i32* [[CNT:%.+]],
// CHECK: br label
// CHECK: [[VAL:%.+]] = load i32, i32* [[CNT]],
// CHECK: [[VAL_I64:%.+]] = sext i32 [[VAL]] to i64
// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]],
// CHECK: [[CMP:%.+]] = icmp ule i64 [[VAL_I64]], [[UB_VAL]]
// CHECK: br i1 [[CMP]], label %{{.+}}, label %{{.+}}
// CHECK: load i32, i32* %
// CHECK: store i32 %
// CHECK: load i32, i32* %
// CHECK: add nsw i32 %{{.+}}, 1
// CHECK: store i32 %{{.+}}, i32* %
// CHECK: br label %
// CHECK: ret i32 0
// CHECK: define internal i32 [[TASK2]](
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* %{{.+}}, i32 0, i32 5
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[DOWN_VAL:%.+]] = load i64, i64* [[DOWN]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 6
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[UP_VAL:%.+]] = load i64, i64* [[UP]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 7
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[LITER:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 8
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[LITER_VAL:%.+]] = load i32, i32* [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], i64* [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], i64* [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], i64* [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], i32* [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, i64* [[LB]],
// CHECK: [[LB_I32:%.+]] = trunc i64 [[LB_VAL]] to i32
// CHECK: store i32 [[LB_I32]], i32* [[CNT:%.+]],
// CHECK: br label
// CHECK: [[VAL:%.+]] = load i32, i32* [[CNT]],
// CHECK: [[VAL_I64:%.+]] = sext i32 [[VAL]] to i64
// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]],
// CHECK: [[CMP:%.+]] = icmp ule i64 [[VAL_I64]], [[UB_VAL]]
// CHECK: br i1 [[CMP]], label %{{.+}}, label %{{.+}}
// CHECK: load i32, i32* %
// CHECK: store i32 %
// CHECK: load i32, i32* %
// CHECK: add nsw i32 %{{.+}}, 1
// CHECK: store i32 %{{.+}}, i32* %
// CHECK: br label %
// CHECK: ret i32 0
// CHECK: define internal i32 [[TASK3]](
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* %{{.+}}, i32 0, i32 5
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[DOWN_VAL:%.+]] = load i64, i64* [[DOWN]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 6
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[UP_VAL:%.+]] = load i64, i64* [[UP]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 7
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[LITER:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 8
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[LITER_VAL:%.+]] = load i32, i32* [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], i64* [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], i64* [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], i64* [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], i32* [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, i64* [[LB]],
// CHECK: store i64 [[LB_VAL]], i64* [[CNT:%.+]],
// CHECK: br label
// CHECK: ret i32 0
// CHECK-LABEL: @_ZN1SC2Ei
struct S {
int a;
S(int c) {
[OPENMP] General code improvements. llvm-svn: 330140
2018-04-17 01:59:34 +08:00
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* [[DEFLOC:@.+]])
// CHECK: [[TASKV:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i32 1, i64 80, i64 16, i32 (i32, i8*)* bitcast (i32 (i32, [[TDP_TY:%.+]]*)* [[TASK4:@.+]] to i32 (i32, i8*)*))
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[TASK:%.+]] = bitcast i8* [[TASKV]] to [[TDP_TY]]*
// CHECK: [[TASK_DATA:%.+]] = getelementptr inbounds [[TDP_TY]], [[TDP_TY]]* [[TASK]], i32 0, i32 0
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 5
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 0, i64* [[DOWN]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 6
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 %{{.+}}, i64* [[UP]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 7
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: store i64 1, i64* [[ST]],
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
[OPENMP 4.5] Codegen for 'grainsize/num_tasks' clauses of 'taskloop' directive. OpenMP 4.5 defines 'taskloop' directive and 2 additional clauses 'grainsize' and 'num_tasks' for this directive. Patch adds codegen for these clauses. These clauses are generated as arguments of the '__kmpc_taskloop' libcall and are encoded the following way: void __kmpc_taskloop(ident_t *loc, int gtid, kmp_task_t *task, int if_val, kmp_uint64 *lb, kmp_uint64 *ub, kmp_int64 st, int nogroup, int sched, kmp_uint64 grainsize, void *task_dup); If 'grainsize' is specified, 'sched' argument must be set to '1' and 'grainsize' argument must be set to the value of the 'grainsize' clause. If 'num_tasks' is specified, 'sched' argument must be set to '2' and 'grainsize' argument must be set to the value of the 'num_tasks' clause. It is possible because these 2 clauses are mutually exclusive and can't be used at the same time on the same directive. If none of these clauses is specified, 'sched' argument must be set to '0'. llvm-svn: 267862
2016-04-28 17:15:06 +08:00
// CHECK: [[NUM_TASKS:%.+]] = zext i32 %{{.+}} to i64
[OPENMP] General code improvements. llvm-svn: 330140
2018-04-17 01:59:34 +08:00
// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 2, i64 [[NUM_TASKS]], i8* null)
[OPENMP 4.5] Codegen for 'grainsize/num_tasks' clauses of 'taskloop' directive. OpenMP 4.5 defines 'taskloop' directive and 2 additional clauses 'grainsize' and 'num_tasks' for this directive. Patch adds codegen for these clauses. These clauses are generated as arguments of the '__kmpc_taskloop' libcall and are encoded the following way: void __kmpc_taskloop(ident_t *loc, int gtid, kmp_task_t *task, int if_val, kmp_uint64 *lb, kmp_uint64 *ub, kmp_int64 st, int nogroup, int sched, kmp_uint64 grainsize, void *task_dup); If 'grainsize' is specified, 'sched' argument must be set to '1' and 'grainsize' argument must be set to the value of the 'grainsize' clause. If 'num_tasks' is specified, 'sched' argument must be set to '2' and 'grainsize' argument must be set to the value of the 'num_tasks' clause. It is possible because these 2 clauses are mutually exclusive and can't be used at the same time on the same directive. If none of these clauses is specified, 'sched' argument must be set to '0'. llvm-svn: 267862
2016-04-28 17:15:06 +08:00
#pragma omp taskloop shared(c) num_tasks(a)
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
for (a = 0; a < c; ++a)
;
}
} s(1);
// CHECK: define internal i32 [[TASK4]](
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[DOWN:%.+]] = getelementptr inbounds [[TD_TY:%.+]], [[TD_TY]]* %{{.+}}, i32 0, i32 5
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[DOWN_VAL:%.+]] = load i64, i64* [[DOWN]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[UP:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 6
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[UP_VAL:%.+]] = load i64, i64* [[UP]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 7
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[LITER:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* %{{.+}}, i32 0, i32 8
[OPENMP 4.5] Codegen for 'taskloop' directive. The taskloop construct specifies that the iterations of one or more associated loops will be executed in parallel using OpenMP tasks. The iterations are distributed across tasks created by the construct and scheduled to be executed. The next code will be generated for the taskloop directive: #pragma omp taskloop num_tasks(N) lastprivate(j) for( i=0; i<N*GRAIN*STRIDE-1; i+=STRIDE ) { int th = omp_get_thread_num(); #pragma omp atomic counter++; #pragma omp atomic th_counter[th]++; j = i; } Generated code: task = __kmpc_omp_task_alloc(NULL,gtid,1,sizeof(struct task),sizeof(struct shar),&task_entry); psh = task->shareds; psh->pth_counter = &th_counter; psh->pcounter = &counter; psh->pj = &j; task->lb = 0; task->ub = N*GRAIN*STRIDE-2; task->st = STRIDE; __kmpc_taskloop( NULL, // location gtid, // gtid task, // task structure 1, // if clause value &task->lb, // lower bound &task->ub, // upper bound STRIDE, // loop increment 0, // 1 if nogroup specified 2, // schedule type: 0-none, 1-grainsize, 2-num_tasks N, // schedule value (ignored for type 0) (void*)&__task_dup_entry // tasks duplication routine ); llvm-svn: 267395
2016-04-25 20:22:29 +08:00
// CHECK: [[LITER_VAL:%.+]] = load i32, i32* [[LITER]],
// CHECK: store i64 [[DOWN_VAL]], i64* [[LB:%[^,]+]],
// CHECK: store i64 [[UP_VAL]], i64* [[UB:%[^,]+]],
// CHECK: store i64 [[ST_VAL]], i64* [[ST:%[^,]+]],
// CHECK: store i32 [[LITER_VAL]], i32* [[LITER:%[^,]+]],
// CHECK: [[LB_VAL:%.+]] = load i64, i64* [[LB]],
// CHECK: [[LB_I32:%.+]] = trunc i64 [[LB_VAL]] to i32
// CHECK: store i32 [[LB_I32]], i32* [[CNT:%.+]],
// CHECK: br label
// CHECK: [[VAL:%.+]] = load i32, i32* [[CNT]],
// CHECK: [[VAL_I64:%.+]] = sext i32 [[VAL]] to i64
// CHECK: [[UB_VAL:%.+]] = load i64, i64* [[UB]],
// CHECK: [[CMP:%.+]] = icmp ule i64 [[VAL_I64]], [[UB_VAL]]
// CHECK: br i1 [[CMP]], label %{{.+}}, label %{{.+}}
// CHECK: load i32, i32* %
// CHECK: store i32 %
// CHECK: load i32, i32* %
// CHECK: add nsw i32 %{{.+}}, 1
// CHECK: store i32 %{{.+}}, i32* %
// CHECK: br label %
// CHECK: ret i32 0
#endif