maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[OpenMP][FIX] Disabled optimizations have to be made known 

To avoid simplification with wrong constants we need to make sure we
know that we won't perform specific optimizations based on the users
request. The non-SPMDzation and non-CustomStateMachine flags did only
prevent the final transformation but allowed to value simplification
to go ahead.

Differential Revision: https://reviews.llvm.org/D107862
This commit is contained in:
Johannes Doerfert 2021-08-10 13:24:34 -05:00
parent a8ae41fb51
commit e0c5d83a92
2 changed files with 12 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llvm/lib/Transforms/IPO/OpenMPOpt.cpp
View File

@ -2834,6 +2834,10 @@ struct AAKernelInfoFunction : AAKernelInfo {
// to avoid other parts using the current constant value for simpliication.
auto &OMPInfoCache = static_cast<OMPInformationCache &>(A.getInfoCache());
// If we have disabled SPMD-ization, stop
if (DisableOpenMPOptSPMDization)
SPMDCompatibilityTracker.indicatePessimisticFixpoint();
Function *Fn = getAnchorScope();
if (!OMPInfoCache.Kernels.count(Fn))
return;
@ -2891,6 +2895,9 @@ struct AAKernelInfoFunction : AAKernelInfo {
// in an invalid state, we won't change the value that is in the IR.
if (!isValidState())
return nullptr;
// If we have disabled state machine rewrites, don't make a custom one.
if (DisableOpenMPOptStateMachineRewrite)
return nullptr;
if (AA)
A.recordDependence(*this, *AA, DepClassTy::OPTIONAL);
UsedAssumedInformation = !isAtFixpoint();
@ -2992,10 +2999,6 @@ struct AAKernelInfoFunction : AAKernelInfo {
}
bool changeToSPMDMode(Attributor &A) {
// If we have disabled SPMD-ization, stop
if (DisableOpenMPOptSPMDization)
indicatePessimisticFixpoint();
auto &OMPInfoCache = static_cast<OMPInformationCache &>(A.getInfoCache());
if (!SPMDCompatibilityTracker.isAssumed()) {

5
llvm/test/Transforms/OpenMP/spmdization.ll
View File

@ -138,6 +138,7 @@ define weak void @__omp_offloading_14_a34ca11_sequential_loop_l5() #0 {
; CHECK-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR:%.*]] = alloca i8*, align 8
; CHECK-DISABLED-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-DISABLED-NEXT: [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
; CHECK-DISABLED-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-DISABLED-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 false, i1 false, i1 true)
; CHECK-DISABLED-NEXT: [[THREAD_IS_WORKER:%.*]] = icmp ne i32 [[TMP0]], -1
; CHECK-DISABLED-NEXT: br i1 [[THREAD_IS_WORKER]], label [[WORKER_STATE_MACHINE_BEGIN:%.*]], label [[THREAD_USER_CODE_CHECK:%.*]]
@ -394,6 +395,7 @@ define weak void @__omp_offloading_14_a34ca11_sequential_loop_to_stack_var_l20()
; CHECK-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR:%.*]] = alloca i8*, align 8
; CHECK-DISABLED-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-DISABLED-NEXT: [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
; CHECK-DISABLED-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-DISABLED-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 false, i1 false, i1 true)
; CHECK-DISABLED-NEXT: [[THREAD_IS_WORKER:%.*]] = icmp ne i32 [[TMP0]], -1
; CHECK-DISABLED-NEXT: br i1 [[THREAD_IS_WORKER]], label [[WORKER_STATE_MACHINE_BEGIN:%.*]], label [[THREAD_USER_CODE_CHECK:%.*]]
@ -652,6 +654,7 @@ define weak void @__omp_offloading_14_a34ca11_sequential_loop_to_shared_var_l35(
; CHECK-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR:%.*]] = alloca i8*, align 8
; CHECK-DISABLED-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-DISABLED-NEXT: [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
; CHECK-DISABLED-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-DISABLED-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 false, i1 false, i1 true)
; CHECK-DISABLED-NEXT: [[THREAD_IS_WORKER:%.*]] = icmp ne i32 [[TMP0]], -1
; CHECK-DISABLED-NEXT: br i1 [[THREAD_IS_WORKER]], label [[WORKER_STATE_MACHINE_BEGIN:%.*]], label [[THREAD_USER_CODE_CHECK:%.*]]
@ -932,6 +935,7 @@ define weak void @__omp_offloading_14_a34ca11_sequential_loop_to_shared_var_guar
; CHECK-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR:%.*]] = alloca i8*, align 8
; CHECK-DISABLED-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-DISABLED-NEXT: [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
; CHECK-DISABLED-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-DISABLED-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 false, i1 false, i1 true)
; CHECK-DISABLED-NEXT: [[THREAD_IS_WORKER:%.*]] = icmp ne i32 [[TMP0]], -1
; CHECK-DISABLED-NEXT: br i1 [[THREAD_IS_WORKER]], label [[WORKER_STATE_MACHINE_BEGIN:%.*]], label [[THREAD_USER_CODE_CHECK:%.*]]
@ -1253,6 +1257,7 @@ define weak void @__omp_offloading_14_a34ca11_do_not_spmdize_target_l65() #0 {
; CHECK-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR:%.*]] = alloca i8*, align 8
; CHECK-DISABLED-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-DISABLED-NEXT: [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
; CHECK-DISABLED-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-DISABLED-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 false, i1 false, i1 true)
; CHECK-DISABLED-NEXT: [[THREAD_IS_WORKER:%.*]] = icmp ne i32 [[TMP0]], -1
; CHECK-DISABLED-NEXT: br i1 [[THREAD_IS_WORKER]], label [[WORKER_STATE_MACHINE_BEGIN:%.*]], label [[THREAD_USER_CODE_CHECK:%.*]]