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

[OpenMP] Use AAHeapToStack/AAHeapToShared analysis in SPMDization 

SPMDization D102307 detects incompatible OpenMP runtime calls to abort converting a target region to SPMD mode. Calls to memory allocation/de-allocation routines kmpc_alloc_shared, kmpc_free_shared are incompatible unless they are removed by AAHeapToStack/AAHeapToShared analysis. This patch extends SPMDization detection to include AAHeapToStack/AAHeapToShared analysis results for enlarging the scope of possible SPMDized regions detected.

Reviewed By: jdoerfert

Differential Revision: https://reviews.llvm.org/D105634
This commit is contained in:
Giorgis Georgakoudis 2021-07-21 18:36:17 -07:00
parent 921c548f11
commit f8c40ed8f8
4 changed files with 598 additions and 84 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/include/llvm/Transforms/IPO/Attributor.h
View File

@ -3557,6 +3557,10 @@ struct AAHeapToStack : public StateWrapper<BooleanState, AbstractAttribute> {
/// Returns true if HeapToStack conversion is assumed to be possible. /// Returns true if HeapToStack conversion is assumed to be possible.
virtual bool isAssumedHeapToStack(const CallBase &CB) const = 0; virtual bool isAssumedHeapToStack(const CallBase &CB) const = 0;
/// Returns true if HeapToStack conversion is assumed and the CB is a
/// callsite to a free operation to be removed.
virtual bool isAssumedHeapToStackRemovedFree(CallBase &CB) const = 0;
/// Create an abstract attribute view for the position \p IRP. /// Create an abstract attribute view for the position \p IRP.
static AAHeapToStack &createForPosition(const IRPosition &IRP, Attributor &A); static AAHeapToStack &createForPosition(const IRPosition &IRP, Attributor &A);

16
llvm/lib/Transforms/IPO/AttributorAttributes.cpp
View File

@ -5714,6 +5714,22 @@ struct AAHeapToStackFunction final : public AAHeapToStack {
return false; return false;
} }
bool isAssumedHeapToStackRemovedFree(CallBase &CB) const override {
if (!isValidState())
return false;
for (auto &It : AllocationInfos) {
AllocationInfo &AI = *It.second;
if (AI.Status == AllocationInfo::INVALID)
continue;
if (AI.PotentialFreeCalls.count(&CB))
return true;
}
return false;
}
ChangeStatus manifest(Attributor &A) override { ChangeStatus manifest(Attributor &A) override {
assert(getState().isValidState() && assert(getState().isValidState() &&
"Attempted to manifest an invalid state!"); "Attempted to manifest an invalid state!");

103
llvm/lib/Transforms/IPO/OpenMPOpt.cpp
View File

@ -2516,6 +2516,13 @@ struct AAHeapToShared : public StateWrapper<BooleanState, AbstractAttribute> {
static AAHeapToShared &createForPosition(const IRPosition &IRP, static AAHeapToShared &createForPosition(const IRPosition &IRP,
Attributor &A); Attributor &A);
/// Returns true if HeapToShared conversion is assumed to be possible.
virtual bool isAssumedHeapToShared(CallBase &CB) const = 0;
/// Returns true if HeapToShared conversion is assumed and the CB is a
/// callsite to a free operation to be removed.
virtual bool isAssumedHeapToSharedRemovedFree(CallBase &CB) const = 0;
/// See AbstractAttribute::getName(). /// See AbstractAttribute::getName().
const std::string getName() const override { return "AAHeapToShared"; } const std::string getName() const override { return "AAHeapToShared"; }
@ -2544,6 +2551,29 @@ struct AAHeapToSharedFunction : public AAHeapToShared {
/// See AbstractAttribute::trackStatistics(). /// See AbstractAttribute::trackStatistics().
void trackStatistics() const override {} void trackStatistics() const override {}
/// This functions finds free calls that will be removed by the
/// HeapToShared transformation.
void findPotentialRemovedFreeCalls(Attributor &A) {
auto &OMPInfoCache = static_cast<OMPInformationCache &>(A.getInfoCache());
auto &FreeRFI = OMPInfoCache.RFIs[OMPRTL___kmpc_free_shared];
PotentialRemovedFreeCalls.clear();
// Update free call users of found malloc calls.
for (CallBase *CB : MallocCalls) {
SmallVector<CallBase *, 4> FreeCalls;
for (auto *U : CB->users()) {
CallBase *C = dyn_cast<CallBase>(U);
if (C && C->getCalledFunction() == FreeRFI.Declaration)
FreeCalls.push_back(C);
}
if (FreeCalls.size() != 1)
continue;
PotentialRemovedFreeCalls.insert(FreeCalls.front());
}
}
void initialize(Attributor &A) override { void initialize(Attributor &A) override {
auto &OMPInfoCache = static_cast<OMPInformationCache &>(A.getInfoCache()); auto &OMPInfoCache = static_cast<OMPInformationCache &>(A.getInfoCache());
auto &RFI = OMPInfoCache.RFIs[OMPRTL___kmpc_alloc_shared]; auto &RFI = OMPInfoCache.RFIs[OMPRTL___kmpc_alloc_shared];
@ -2551,6 +2581,16 @@ struct AAHeapToSharedFunction : public AAHeapToShared {
for (User *U : RFI.Declaration->users()) for (User *U : RFI.Declaration->users())
if (CallBase *CB = dyn_cast<CallBase>(U)) if (CallBase *CB = dyn_cast<CallBase>(U))
MallocCalls.insert(CB); MallocCalls.insert(CB);
findPotentialRemovedFreeCalls(A);
}
bool isAssumedHeapToShared(CallBase &CB) const {
return isValidState() && MallocCalls.count(&CB);
}
bool isAssumedHeapToSharedRemovedFree(CallBase &CB) const {
return isValidState() && PotentialRemovedFreeCalls.count(&CB);
} }
ChangeStatus manifest(Attributor &A) override { ChangeStatus manifest(Attributor &A) override {
@ -2638,6 +2678,8 @@ struct AAHeapToSharedFunction : public AAHeapToShared {
MallocCalls.erase(CB); MallocCalls.erase(CB);
} }
findPotentialRemovedFreeCalls(A);
if (NumMallocCalls != MallocCalls.size()) if (NumMallocCalls != MallocCalls.size())
return ChangeStatus::CHANGED; return ChangeStatus::CHANGED;
@ -2646,6 +2688,8 @@ struct AAHeapToSharedFunction : public AAHeapToShared {
/// Collection of all malloc calls in a function. /// Collection of all malloc calls in a function.
SmallPtrSet<CallBase *, 4> MallocCalls; SmallPtrSet<CallBase *, 4> MallocCalls;
/// Collection of potentially removed free calls in a function.
SmallPtrSet<CallBase *, 4> PotentialRemovedFreeCalls;
}; };
struct AAKernelInfo : public StateWrapper<KernelInfoState, AbstractAttribute> { struct AAKernelInfo : public StateWrapper<KernelInfoState, AbstractAttribute> {
@ -3407,6 +3451,10 @@ struct AAKernelInfoCallSite : AAKernelInfo {
SPMDCompatibilityTracker.insert(&CB); SPMDCompatibilityTracker.insert(&CB);
ReachedUnknownParallelRegions.insert(&CB); ReachedUnknownParallelRegions.insert(&CB);
break; break;
case OMPRTL___kmpc_alloc_shared:
case OMPRTL___kmpc_free_shared:
// Return without setting a fixpoint, to be resolved in updateImpl.
return;
default: default:
// Unknown OpenMP runtime calls cannot be executed in SPMD-mode, // Unknown OpenMP runtime calls cannot be executed in SPMD-mode,
// generally. // generally.
@ -3425,12 +3473,55 @@ struct AAKernelInfoCallSite : AAKernelInfo {
// sense to specialize attributes for call sites arguments instead of // sense to specialize attributes for call sites arguments instead of
// redirecting requests to the callee argument. // redirecting requests to the callee argument.
Function *F = getAssociatedFunction(); Function *F = getAssociatedFunction();
const IRPosition &FnPos = IRPosition::function(*F);
auto &FnAA = A.getAAFor<AAKernelInfo>(*this, FnPos, DepClassTy::REQUIRED); auto &OMPInfoCache = static_cast<OMPInformationCache &>(A.getInfoCache());
if (getState() == FnAA.getState()) const auto &It = OMPInfoCache.RuntimeFunctionIDMap.find(F);
return ChangeStatus::UNCHANGED;
getState() = FnAA.getState(); // If F is not a runtime function, propagate the AAKernelInfo of the callee.
return ChangeStatus::CHANGED; if (It == OMPInfoCache.RuntimeFunctionIDMap.end()) {
const IRPosition &FnPos = IRPosition::function(*F);
auto &FnAA = A.getAAFor<AAKernelInfo>(*this, FnPos, DepClassTy::REQUIRED);
if (getState() == FnAA.getState())
return ChangeStatus::UNCHANGED;
getState() = FnAA.getState();
return ChangeStatus::CHANGED;
}
// F is a runtime function that allocates or frees memory, check
// AAHeapToStack and AAHeapToShared.
KernelInfoState StateBefore = getState();
assert((It->getSecond() == OMPRTL___kmpc_alloc_shared ||
It->getSecond() == OMPRTL___kmpc_free_shared) &&
"Expected a __kmpc_alloc_shared or __kmpc_free_shared runtime call");
CallBase &CB = cast<CallBase>(getAssociatedValue());
auto &HeapToStackAA = A.getAAFor<AAHeapToStack>(
*this, IRPosition::function(*CB.getCaller()), DepClassTy::OPTIONAL);
auto &HeapToSharedAA = A.getAAFor<AAHeapToShared>(
*this, IRPosition::function(*CB.getCaller()), DepClassTy::OPTIONAL);
RuntimeFunction RF = It->getSecond();
switch (RF) {
// If neither HeapToStack nor HeapToShared assume the call is removed,
// assume SPMD incompatibility.
case OMPRTL___kmpc_alloc_shared:
if (!HeapToStackAA.isAssumedHeapToStack(CB) &&
!HeapToSharedAA.isAssumedHeapToShared(CB))
SPMDCompatibilityTracker.insert(&CB);
break;
case OMPRTL___kmpc_free_shared:
if (!HeapToStackAA.isAssumedHeapToStackRemovedFree(CB) &&
!HeapToSharedAA.isAssumedHeapToSharedRemovedFree(CB))
SPMDCompatibilityTracker.insert(&CB);
break;
default:
SPMDCompatibilityTracker.insert(&CB);
}
return StateBefore == getState() ? ChangeStatus::UNCHANGED
: ChangeStatus::CHANGED;
} }
}; };

559
llvm/test/Transforms/OpenMP/spmdization.ll
View File

@ -2,7 +2,7 @@
; RUN: opt -S -passes=openmp-opt < %s | FileCheck %s ; RUN: opt -S -passes=openmp-opt < %s | FileCheck %s
;; void unknown(void); ;; void unknown(void);
;; void spmd_amenable(void) __attribute__((assume("ompx_spmd_amenable"))) ;; void spmd_amenable(void) __attribute__((assume("ompx_spmd_amenable")));
;; ;;
;; void sequential_loop() { ;; void sequential_loop() {
;; #pragma omp target teams ;; #pragma omp target teams
@ -13,7 +13,39 @@
;; unknown(); ;; unknown();
;; } ;; }
;; } ;; }
; spmd_amenable(); ;; spmd_amenable();
;; }
;; }
;;
;; void use(__attribute__((noescape)) int *) __attribute__((assume("ompx_spmd_amenable")));
;;
;; void sequential_loop_to_stack_var() {
;; #pragma omp target teams
;; {
;; int x;
;; use(&x);
;; for (int i = 0; i < 100; ++i) {
;; #pragma omp parallel
;; {
;; unknown();
;; }
;; }
;; spmd_amenable();
;; }
;; }
;;
;; void sequential_loop_to_shared_var() {
;; #pragma omp target teams
;; {
;; int x;
;; for (int i = 0; i < 100; ++i) {
;; #pragma omp parallel
;; {
;; x++;
;; unknown();
;; }
;; }
;; spmd_amenable();
;; } ;; }
;; } ;; }
@ -23,20 +55,22 @@ target triple = "nvptx64"
@0 = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00", align 1 @0 = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00", align 1
@1 = private unnamed_addr constant %struct.ident_t { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* @0, i32 0, i32 0) }, align 8 @1 = private unnamed_addr constant %struct.ident_t { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* @0, i32 0, i32 0) }, align 8
@__omp_offloading_2c_38c77_sequential_loop_l4_exec_mode = weak constant i8 1 @__omp_offloading_14_5896c35_sequential_loop_l5_exec_mode = weak constant i8 1
@llvm.compiler.used = appending global [1 x i8*] [i8* @__omp_offloading_2c_38c77_sequential_loop_l4_exec_mode], section "llvm.metadata" @__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20_exec_mode = weak constant i8 1
@__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35_exec_mode = weak constant i8 1
@llvm.compiler.used = appending global [3 x i8*] [i8* @__omp_offloading_14_5896c35_sequential_loop_l5_exec_mode, i8* @__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20_exec_mode, i8* @__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35_exec_mode], section "llvm.metadata"
; The second argument of __kmpc_target_init and deinit is is set to true to indicate that we can run in SPMD mode.
; The last argument is set to false since full runtime support is not needed in SPMDization.
; We also adjusted the global __omp_offloading_2c_38c77_sequential_loop_l4_exec_mode to have a zero initializer (which indicates SPMD mode to the runtime).
;. ;.
; CHECK: @[[GLOB0:[0-9]+]] = private unnamed_addr constant [23 x i8] c" ; CHECK: @[[GLOB0:[0-9]+]] = private unnamed_addr constant [23 x i8] c"
; CHECK: @[[GLOB1:[0-9]+]] = private unnamed_addr constant [[STRUCT_IDENT_T:%.*]] { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* @[[GLOB0]], i32 0, i32 0) }, align 8 ; CHECK: @[[GLOB1:[0-9]+]] = private unnamed_addr constant [[STRUCT_IDENT_T:%.*]] { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* @[[GLOB0]], i32 0, i32 0) }, align 8
; CHECK: @[[__OMP_OFFLOADING_2C_38C77_SEQUENTIAL_LOOP_L4_EXEC_MODE:[a-zA-Z0-9_$"\\.-]+]] = weak constant i8 2 ; CHECK: @[[__OMP_OFFLOADING_14_5896C35_SEQUENTIAL_LOOP_L5_EXEC_MODE:[a-zA-Z0-9_$"\\.-]+]] = weak constant i8 2
; CHECK: @[[LLVM_COMPILER_USED:[a-zA-Z0-9_$"\\.-]+]] = appending global [1 x i8*] [i8* @__omp_offloading_2c_38c77_sequential_loop_l4_exec_mode], section "llvm.metadata" ; CHECK: @[[__OMP_OFFLOADING_14_5896C35_SEQUENTIAL_LOOP_TO_STACK_VAR_L20_EXEC_MODE:[a-zA-Z0-9_$"\\.-]+]] = weak constant i8 2
; CHECK: @[[__OMP_OFFLOADING_14_5896C35_SEQUENTIAL_LOOP_TO_SHARED_VAR_L35_EXEC_MODE:[a-zA-Z0-9_$"\\.-]+]] = weak constant i8 2
; CHECK: @[[LLVM_COMPILER_USED:[a-zA-Z0-9_$"\\.-]+]] = appending global [3 x i8*] [i8* @__omp_offloading_14_5896c35_sequential_loop_l5_exec_mode, i8* @__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20_exec_mode, i8* @__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35_exec_mode], section "llvm.metadata"
; CHECK: @[[X:[a-zA-Z0-9_$"\\.-]+]] = internal addrspace(3) global [4 x i8] undef, align 32
;. ;.
define weak void @__omp_offloading_2c_38c77_sequential_loop_l4() #0 { define weak void @__omp_offloading_14_5896c35_sequential_loop_l5() #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_offloading_2c_38c77_sequential_loop_l4 ; CHECK-LABEL: define {{[^@]+}}@__omp_offloading_14_5896c35_sequential_loop_l5
; CHECK-SAME: () #[[ATTR0:[0-9]+]] { ; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4 ; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
@ -46,9 +80,9 @@ define weak void @__omp_offloading_2c_38c77_sequential_loop_l4() #0 {
; CHECK-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1 ; CHECK-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
; CHECK-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]] ; CHECK-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
; CHECK: user_code.entry: ; CHECK: user_code.entry:
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR2:[0-9]+]] ; CHECK-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR3:[0-9]+]]
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTTHREADID_TEMP_]], align 4 ; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTTHREADID_TEMP_]], align 4
; CHECK-NEXT: call void @__omp_outlined__(i32* noalias nocapture noundef nonnull readonly align 4 dereferenceable(4) [[DOTTHREADID_TEMP_]], i32* noalias nocapture noundef nonnull readnone align 4 dereferenceable(4) [[DOTZERO_ADDR]]) #[[ATTR2]] ; CHECK-NEXT: call void @__omp_outlined__(i32* noundef nonnull align 4 dereferenceable(4) [[DOTTHREADID_TEMP_]], i32* noundef nonnull align 4 dereferenceable(4) [[DOTZERO_ADDR]]) #[[ATTR3]]
; CHECK-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i1 true, i1 false) ; CHECK-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i1 true, i1 false)
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; CHECK: worker.exit: ; CHECK: worker.exit:
@ -65,7 +99,7 @@ entry:
user_code.entry: ; preds = %entry user_code.entry: ; preds = %entry
%1 = call i32 @__kmpc_global_thread_num(%struct.ident_t* @1) %1 = call i32 @__kmpc_global_thread_num(%struct.ident_t* @1)
store i32 %1, i32* %.threadid_temp., align 4 store i32 %1, i32* %.threadid_temp., align 4
call void @__omp_outlined__(i32* %.threadid_temp., i32* %.zero.addr) #2 call void @__omp_outlined__(i32* %.threadid_temp., i32* %.zero.addr) #3
call void @__kmpc_target_deinit(%struct.ident_t* @1, i1 false, i1 true) call void @__kmpc_target_deinit(%struct.ident_t* @1, i1 false, i1 true)
ret void ret void
@ -75,91 +109,116 @@ worker.exit: ; preds = %entry
declare i32 @__kmpc_target_init(%struct.ident_t*, i1, i1, i1) declare i32 @__kmpc_target_init(%struct.ident_t*, i1, i1, i1)
; Function Attrs: convergent norecurse nounwind
define internal void @__omp_outlined__(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 { define internal void @__omp_outlined__(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__ ; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__
; CHECK-SAME: (i32* noalias nocapture nofree noundef nonnull readonly align 4 dereferenceable(4) [[DOTGLOBAL_TID_:%.*]], i32* noalias nocapture nofree nonnull readnone align 4 dereferenceable(4) [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] { ; CHECK-SAME: (i32* noalias nofree noundef nonnull align 4 dereferenceable(4) [[DOTGLOBAL_TID_:%.*]], i32* noalias nofree noundef nonnull align 4 dereferenceable(4) [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[I:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [0 x i8*], align 8 ; CHECK-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [0 x i8*], align 8
; CHECK-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
; CHECK-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
; CHECK-NEXT: store i32 0, i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND:%.*]] ; CHECK-NEXT: br label [[FOR_COND:%.*]]
; CHECK: for.cond: ; CHECK: for.cond:
; CHECK-NEXT: [[I_0:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ] ; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[I_0]], 100 ; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP0]], 100
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]] ; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body: ; CHECK: for.body:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[DOTGLOBAL_TID_]], align 4 ; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[DOTGLOBAL_TID_]], align 4
; CHECK-NEXT: [[TMP1:%.*]] = bitcast [0 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8** ; CHECK-NEXT: [[TMP2:%.*]] = bitcast [0 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
; CHECK-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* noundef @[[GLOB1]], i32 [[TMP0]], i32 noundef 1, i32 noundef -1, i32 noundef -1, i8* noundef bitcast (void (i32*, i32*)* @__omp_outlined__1 to i8*), i8* noundef bitcast (void (i16, i32)* @__omp_outlined__1_wrapper to i8*), i8** noundef [[TMP1]], i64 noundef 0) ; CHECK-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* noundef @[[GLOB1]], i32 [[TMP1]], i32 noundef 1, i32 noundef -1, i32 noundef -1, i8* noundef bitcast (void (i32*, i32*)* @__omp_outlined__1 to i8*), i8* noundef bitcast (void (i16, i32)* @__omp_outlined__1_wrapper to i8*), i8** noundef [[TMP2]], i64 noundef 0)
; CHECK-NEXT: br label [[FOR_INC]] ; CHECK-NEXT: br label [[FOR_INC:%.*]]
; CHECK: for.inc: ; CHECK: for.inc:
; CHECK-NEXT: [[INC]] = add nsw i32 [[I_0]], 1 ; CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP8:![0-9]+]] ; CHECK-NEXT: [[INC:%.*]] = add nsw i32 [[TMP3]], 1
; CHECK-NEXT: store i32 [[INC]], i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK: for.end: ; CHECK: for.end:
; CHECK-NEXT: call void @spmd_amenable() ; CHECK-NEXT: call void @spmd_amenable() #[[ATTR4:[0-9]+]]
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
entry: entry:
%.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
%i = alloca i32, align 4
%captured_vars_addrs = alloca [0 x i8*], align 8 %captured_vars_addrs = alloca [0 x i8*], align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
store i32 0, i32* %i, align 4
br label %for.cond br label %for.cond
for.cond: ; preds = %for.inc, %entry for.cond: ; preds = %for.inc, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ] %0 = load i32, i32* %i, align 4
%cmp = icmp slt i32 %i.0, 100 %cmp = icmp slt i32 %0, 100
br i1 %cmp, label %for.body, label %for.end br i1 %cmp, label %for.body, label %for.end
for.body: ; preds = %for.cond for.body: ; preds = %for.cond
%0 = load i32, i32* %.global_tid., align 4 %1 = load i32*, i32** %.global_tid..addr, align 8
%1 = bitcast [0 x i8*]* %captured_vars_addrs to i8** %2 = load i32, i32* %1, align 4
call void @__kmpc_parallel_51(%struct.ident_t* @1, i32 %0, i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*)* @__omp_outlined__1 to i8*), i8* bitcast (void (i16, i32)* @__omp_outlined__1_wrapper to i8*), i8** %1, i64 0) %3 = bitcast [0 x i8*]* %captured_vars_addrs to i8**
call void @__kmpc_parallel_51(%struct.ident_t* @1, i32 %2, i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*)* @__omp_outlined__1 to i8*), i8* bitcast (void (i16, i32)* @__omp_outlined__1_wrapper to i8*), i8** %3, i64 0)
br label %for.inc br label %for.inc
for.inc: ; preds = %for.body for.inc: ; preds = %for.body
%inc = add nsw i32 %i.0, 1 %4 = load i32, i32* %i, align 4
br label %for.cond, !llvm.loop !6 %inc = add nsw i32 %4, 1
store i32 %inc, i32* %i, align 4
br label %for.cond, !llvm.loop !9
for.end: ; preds = %for.cond for.end: ; preds = %for.cond
call void @spmd_amenable() call void @spmd_amenable() #4
ret void ret void
} }
; Function Attrs: convergent norecurse nounwind
define internal void @__omp_outlined__1(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 { define internal void @__omp_outlined__1(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__1 ; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__1
; CHECK-SAME: (i32* noalias nocapture nofree readnone [[DOTGLOBAL_TID_:%.*]], i32* noalias nocapture nofree readnone [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] { ; CHECK-SAME: (i32* noalias nofree [[DOTGLOBAL_TID_:%.*]], i32* noalias nofree [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: call void @unknown() #[[ATTR4:[0-9]+]] ; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
; CHECK-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
; CHECK-NEXT: call void @unknown() #[[ATTR5:[0-9]+]]
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
entry: entry:
call void @unknown() #3 %.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
call void @unknown() #5
ret void ret void
} }
; Function Attrs: convergent
declare void @unknown() #1 declare void @unknown() #1
; Function Attrs: convergent norecurse nounwind
define internal void @__omp_outlined__1_wrapper(i16 zeroext %0, i32 %1) #0 { define internal void @__omp_outlined__1_wrapper(i16 zeroext %0, i32 %1) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__1_wrapper ; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__1_wrapper
; CHECK-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR0]] { ; CHECK-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
; CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4 ; CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4 ; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[GLOBAL_ARGS:%.*]] = alloca i8**, align 8 ; CHECK-NEXT: [[GLOBAL_ARGS:%.*]] = alloca i8**, align 8
; CHECK-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4 ; CHECK-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-NEXT: store i16 [[TMP0]], i16* [[DOTADDR]], align 2
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4 ; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
; CHECK-NEXT: call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]]) ; CHECK-NEXT: call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
; CHECK-NEXT: call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]]) #[[ATTR2]] ; CHECK-NEXT: call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]]) #[[ATTR3]]
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
entry: entry:
%.addr = alloca i16, align 2
%.addr1 = alloca i32, align 4 %.addr1 = alloca i32, align 4
%.zero.addr = alloca i32, align 4 %.zero.addr = alloca i32, align 4
%global_args = alloca i8**, align 8 %global_args = alloca i8**, align 8
store i32 0, i32* %.zero.addr, align 4 store i32 0, i32* %.zero.addr, align 4
store i16 %0, i16* %.addr, align 2
store i32 %1, i32* %.addr1, align 4 store i32 %1, i32* %.addr1, align 4
call void @__kmpc_get_shared_variables(i8*** %global_args) call void @__kmpc_get_shared_variables(i8*** %global_args)
call void @__omp_outlined__1(i32* %.addr1, i32* %.zero.addr) #2 call void @__omp_outlined__1(i32* %.addr1, i32* %.zero.addr) #3
ret void ret void
} }
@ -167,49 +226,393 @@ declare void @__kmpc_get_shared_variables(i8***)
declare void @__kmpc_parallel_51(%struct.ident_t*, i32, i32, i32, i32, i8*, i8*, i8**, i64) declare void @__kmpc_parallel_51(%struct.ident_t*, i32, i32, i32, i32, i8*, i8*, i8**, i64)
; Function Attrs: nounwind declare void @spmd_amenable() #2
declare i32 @__kmpc_global_thread_num(%struct.ident_t*) #2
declare i32 @__kmpc_global_thread_num(%struct.ident_t*) #3
declare void @__kmpc_target_deinit(%struct.ident_t*, i1, i1) declare void @__kmpc_target_deinit(%struct.ident_t*, i1, i1)
declare void @spmd_amenable() #4 define weak void @__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20() #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20
; CHECK-SAME: () #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
; CHECK-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 true, i1 false, i1 false)
; CHECK-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
; CHECK-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
; CHECK: user_code.entry:
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR3]]
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTTHREADID_TEMP_]], align 4
; CHECK-NEXT: call void @__omp_outlined__2(i32* noundef nonnull align 4 dereferenceable(4) [[DOTTHREADID_TEMP_]], i32* noundef nonnull align 4 dereferenceable(4) [[DOTZERO_ADDR]]) #[[ATTR3]]
; CHECK-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i1 true, i1 false)
; CHECK-NEXT: ret void
; CHECK: worker.exit:
; CHECK-NEXT: ret void
;
entry:
%.zero.addr = alloca i32, align 4
%.threadid_temp. = alloca i32, align 4
store i32 0, i32* %.zero.addr, align 4
%0 = call i32 @__kmpc_target_init(%struct.ident_t* @1, i1 false, i1 true, i1 true)
%exec_user_code = icmp eq i32 %0, -1
br i1 %exec_user_code, label %user_code.entry, label %worker.exit
attributes #0 = { convergent norecurse nounwind "frame-pointer"="all" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="sm_53" "target-features"="+ptx32,+sm_53" } user_code.entry: ; preds = %entry
attributes #1 = { convergent "frame-pointer"="all" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="sm_53" "target-features"="+ptx32,+sm_53" } %1 = call i32 @__kmpc_global_thread_num(%struct.ident_t* @1)
attributes #2 = { nounwind } store i32 %1, i32* %.threadid_temp., align 4
attributes #3 = { convergent } call void @__omp_outlined__2(i32* %.threadid_temp., i32* %.zero.addr) #3
attributes #4 = { "llvm.assume"="ompx_spmd_amenable" } call void @__kmpc_target_deinit(%struct.ident_t* @1, i1 false, i1 true)
ret void
!omp_offload.info = !{!0} worker.exit: ; preds = %entry
!nvvm.annotations = !{!1} ret void
!llvm.module.flags = !{!2, !3, !4, !8, !9} }
!llvm.ident = !{!5}
!0 = !{i32 0, i32 44, i32 232567, !"sequential_loop", i32 4, i32 0} define internal void @__omp_outlined__2(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 {
!1 = !{void ()* @__omp_offloading_2c_38c77_sequential_loop_l4, !"kernel", i32 1} ; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__2
!2 = !{i32 1, !"wchar_size", i32 4} ; CHECK-SAME: (i32* noalias nofree noundef nonnull align 4 dereferenceable(4) [[DOTGLOBAL_TID_:%.*]], i32* noalias nofree noundef nonnull align 4 dereferenceable(4) [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
!3 = !{i32 7, !"PIC Level", i32 2} ; CHECK-NEXT: entry:
!4 = !{i32 7, !"frame-pointer", i32 2} ; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
!5 = !{!"clang version 13.0.0"} ; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
!6 = distinct !{!6, !7} ; CHECK-NEXT: [[I:%.*]] = alloca i32, align 4
!7 = !{!"llvm.loop.mustprogress"} ; CHECK-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [0 x i8*], align 8
!8 = !{i32 7, !"openmp", i32 50} ; CHECK-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
!9 = !{i32 7, !"openmp-device", i32 50} ; CHECK-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
; CHECK-NEXT: [[TMP0:%.*]] = alloca i8, i64 4, align 1
; CHECK-NEXT: [[X_ON_STACK:%.*]] = bitcast i8* [[TMP0]] to i32*
; CHECK-NEXT: call void @use(i32* nocapture [[X_ON_STACK]]) #[[ATTR4]]
; CHECK-NEXT: store i32 0, i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND:%.*]]
; CHECK: for.cond:
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP1]], 100
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTGLOBAL_TID_]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = bitcast [0 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
; CHECK-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* noundef @[[GLOB1]], i32 [[TMP2]], i32 noundef 1, i32 noundef -1, i32 noundef -1, i8* noundef bitcast (void (i32*, i32*)* @__omp_outlined__3 to i8*), i8* noundef bitcast (void (i16, i32)* @__omp_outlined__3_wrapper to i8*), i8** noundef [[TMP3]], i64 noundef 0)
; CHECK-NEXT: br label [[FOR_INC:%.*]]
; CHECK: for.inc:
; CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: [[INC:%.*]] = add nsw i32 [[TMP4]], 1
; CHECK-NEXT: store i32 [[INC]], i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: call void @spmd_amenable() #[[ATTR4]]
; CHECK-NEXT: ret void
;
entry:
%.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
%i = alloca i32, align 4
%captured_vars_addrs = alloca [0 x i8*], align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
%x = call i8* @__kmpc_alloc_shared(i64 4)
%x_on_stack = bitcast i8* %x to i32*
call void @use(i32* nocapture %x_on_stack) #4
store i32 0, i32* %i, align 4
br label %for.cond
for.cond: ; preds = %for.inc, %entry
%0 = load i32, i32* %i, align 4
%cmp = icmp slt i32 %0, 100
br i1 %cmp, label %for.body, label %for.end
for.body: ; preds = %for.cond
%1 = load i32*, i32** %.global_tid..addr, align 8
%2 = load i32, i32* %1, align 4
%3 = bitcast [0 x i8*]* %captured_vars_addrs to i8**
call void @__kmpc_parallel_51(%struct.ident_t* @1, i32 %2, i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*)* @__omp_outlined__3 to i8*), i8* bitcast (void (i16, i32)* @__omp_outlined__3_wrapper to i8*), i8** %3, i64 0)
br label %for.inc
for.inc: ; preds = %for.body
%4 = load i32, i32* %i, align 4
%inc = add nsw i32 %4, 1
store i32 %inc, i32* %i, align 4
br label %for.cond, !llvm.loop !11
for.end: ; preds = %for.cond
call void @spmd_amenable() #4
call void @__kmpc_free_shared(i8* %x, i64 4)
ret void
}
declare i8* @__kmpc_alloc_shared(i64) #3
declare void @use(i32* nocapture) #2
define internal void @__omp_outlined__3(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__3
; CHECK-SAME: (i32* noalias nofree [[DOTGLOBAL_TID_:%.*]], i32* noalias nofree [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
; CHECK-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
; CHECK-NEXT: call void @unknown() #[[ATTR5]]
; CHECK-NEXT: ret void
;
entry:
%.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
call void @unknown() #5
ret void
}
define internal void @__omp_outlined__3_wrapper(i16 zeroext %0, i32 %1) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__3_wrapper
; CHECK-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
; CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[GLOBAL_ARGS:%.*]] = alloca i8**, align 8
; CHECK-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-NEXT: store i16 [[TMP0]], i16* [[DOTADDR]], align 2
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
; CHECK-NEXT: call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
; CHECK-NEXT: call void @__omp_outlined__3(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]]) #[[ATTR3]]
; CHECK-NEXT: ret void
;
entry:
%.addr = alloca i16, align 2
%.addr1 = alloca i32, align 4
%.zero.addr = alloca i32, align 4
%global_args = alloca i8**, align 8
store i32 0, i32* %.zero.addr, align 4
store i16 %0, i16* %.addr, align 2
store i32 %1, i32* %.addr1, align 4
call void @__kmpc_get_shared_variables(i8*** %global_args)
call void @__omp_outlined__3(i32* %.addr1, i32* %.zero.addr) #3
ret void
}
declare void @__kmpc_free_shared(i8* nocapture, i64) #3
define weak void @__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35() #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35
; CHECK-SAME: () #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
; CHECK-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 true, i1 false, i1 false)
; CHECK-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
; CHECK-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
; CHECK: user_code.entry:
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR3]]
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTTHREADID_TEMP_]], align 4
; CHECK-NEXT: call void @__omp_outlined__4(i32* noundef nonnull align 4 dereferenceable(4) [[DOTTHREADID_TEMP_]], i32* noundef nonnull align 4 dereferenceable(4) [[DOTZERO_ADDR]]) #[[ATTR3]]
; CHECK-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i1 true, i1 false)
; CHECK-NEXT: ret void
; CHECK: worker.exit:
; CHECK-NEXT: ret void
;
entry:
%.zero.addr = alloca i32, align 4
%.threadid_temp. = alloca i32, align 4
store i32 0, i32* %.zero.addr, align 4
%0 = call i32 @__kmpc_target_init(%struct.ident_t* @1, i1 false, i1 true, i1 true)
%exec_user_code = icmp eq i32 %0, -1
br i1 %exec_user_code, label %user_code.entry, label %worker.exit
user_code.entry: ; preds = %entry
%1 = call i32 @__kmpc_global_thread_num(%struct.ident_t* @1)
store i32 %1, i32* %.threadid_temp., align 4
call void @__omp_outlined__4(i32* %.threadid_temp., i32* %.zero.addr) #3
call void @__kmpc_target_deinit(%struct.ident_t* @1, i1 false, i1 true)
ret void
worker.exit: ; preds = %entry
ret void
}
define internal void @__omp_outlined__4(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__4
; CHECK-SAME: (i32* noalias nofree noundef nonnull align 4 dereferenceable(4) [[DOTGLOBAL_TID_:%.*]], i32* noalias nofree noundef nonnull align 4 dereferenceable(4) [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[I:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [1 x i8*], align 8
; CHECK-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
; CHECK-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
; CHECK-NEXT: store i32 0, i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND:%.*]]
; CHECK: for.cond:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP0]], 100
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
; CHECK-NEXT: store i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([4 x i8], [4 x i8] addrspace(3)* @x, i32 0, i32 0) to i8*), i8** [[TMP1]], align 8
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTGLOBAL_TID_]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = bitcast [1 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
; CHECK-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* noundef @[[GLOB1]], i32 [[TMP2]], i32 noundef 1, i32 noundef -1, i32 noundef -1, i8* noundef bitcast (void (i32*, i32*, i32*)* @__omp_outlined__5 to i8*), i8* noundef bitcast (void (i16, i32)* @__omp_outlined__5_wrapper to i8*), i8** noundef [[TMP3]], i64 noundef 1)
; CHECK-NEXT: br label [[FOR_INC:%.*]]
; CHECK: for.inc:
; CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: [[INC:%.*]] = add nsw i32 [[TMP4]], 1
; CHECK-NEXT: store i32 [[INC]], i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: call void @spmd_amenable() #[[ATTR4]]
; CHECK-NEXT: ret void
;
entry:
%.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
%i = alloca i32, align 4
%captured_vars_addrs = alloca [1 x i8*], align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
%x = call i8* @__kmpc_alloc_shared(i64 4)
%x_on_stack = bitcast i8* %x to i32*
store i32 0, i32* %i, align 4
br label %for.cond
for.cond: ; preds = %for.inc, %entry
%0 = load i32, i32* %i, align 4
%cmp = icmp slt i32 %0, 100
br i1 %cmp, label %for.body, label %for.end
for.body: ; preds = %for.cond
%1 = getelementptr inbounds [1 x i8*], [1 x i8*]* %captured_vars_addrs, i64 0, i64 0
%2 = bitcast i32* %x_on_stack to i8*
store i8* %2, i8** %1, align 8
%3 = load i32*, i32** %.global_tid..addr, align 8
%4 = load i32, i32* %3, align 4
%5 = bitcast [1 x i8*]* %captured_vars_addrs to i8**
call void @__kmpc_parallel_51(%struct.ident_t* @1, i32 %4, i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32*)* @__omp_outlined__5 to i8*), i8* bitcast (void (i16, i32)* @__omp_outlined__5_wrapper to i8*), i8** %5, i64 1)
br label %for.inc
for.inc: ; preds = %for.body
%6 = load i32, i32* %i, align 4
%inc = add nsw i32 %6, 1
store i32 %inc, i32* %i, align 4
br label %for.cond, !llvm.loop !12
for.end: ; preds = %for.cond
call void @spmd_amenable() #4
call void @__kmpc_free_shared(i8* %x, i64 4)
ret void
}
define internal void @__omp_outlined__5(i32* noalias %.global_tid., i32* noalias %.bound_tid., i32* nonnull align 4 dereferenceable(4) %x) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__5
; CHECK-SAME: (i32* noalias nofree [[DOTGLOBAL_TID_:%.*]], i32* noalias nofree [[DOTBOUND_TID_:%.*]], i32* nofree nonnull align 4 dereferenceable(4) [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[X_ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
; CHECK-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
; CHECK-NEXT: store i32* [[X]], i32** [[X_ADDR]], align 8
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[X]], align 4
; CHECK-NEXT: [[INC:%.*]] = add nsw i32 [[TMP0]], 1
; CHECK-NEXT: store i32 [[INC]], i32* [[X]], align 4
; CHECK-NEXT: call void @unknown() #[[ATTR5]]
; CHECK-NEXT: ret void
;
entry:
%.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
%x.addr = alloca i32*, align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
store i32* %x, i32** %x.addr, align 8
%0 = load i32*, i32** %x.addr, align 8
%1 = load i32, i32* %0, align 4
%inc = add nsw i32 %1, 1
store i32 %inc, i32* %0, align 4
call void @unknown() #5
ret void
}
define internal void @__omp_outlined__5_wrapper(i16 zeroext %0, i32 %1) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__5_wrapper
; CHECK-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
; CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[GLOBAL_ARGS:%.*]] = alloca i8**, align 8
; CHECK-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-NEXT: store i16 [[TMP0]], i16* [[DOTADDR]], align 2
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
; CHECK-NEXT: call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
; CHECK-NEXT: [[TMP2:%.*]] = load i8**, i8*** [[GLOBAL_ARGS]], align 8
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i8*, i8** [[TMP2]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i8** [[TMP3]] to i32**
; CHECK-NEXT: [[TMP5:%.*]] = load i32*, i32** [[TMP4]], align 8
; CHECK-NEXT: call void @__omp_outlined__5(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]], i32* [[TMP5]]) #[[ATTR3]]
; CHECK-NEXT: ret void
;
entry:
%.addr = alloca i16, align 2
%.addr1 = alloca i32, align 4
%.zero.addr = alloca i32, align 4
%global_args = alloca i8**, align 8
store i32 0, i32* %.zero.addr, align 4
store i16 %0, i16* %.addr, align 2
store i32 %1, i32* %.addr1, align 4
call void @__kmpc_get_shared_variables(i8*** %global_args)
%2 = load i8**, i8*** %global_args, align 8
%3 = getelementptr inbounds i8*, i8** %2, i64 0
%4 = bitcast i8** %3 to i32**
%5 = load i32*, i32** %4, align 8
call void @__omp_outlined__5(i32* %.addr1, i32* %.zero.addr, i32* %5) #3
ret void
}
attributes #0 = { convergent noinline norecurse nounwind "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
attributes #1 = { convergent "frame-pointer"="none" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
attributes #2 = { convergent "frame-pointer"="none" "llvm.assume"="ompx_spmd_amenable" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
attributes #3 = { nounwind }
attributes #4 = { convergent "llvm.assume"="ompx_spmd_amenable" }
attributes #5 = { convergent }
!omp_offload.info = !{!0, !1, !2}
!nvvm.annotations = !{!3, !4, !5}
!llvm.module.flags = !{!6, !7, !8}
!0 = !{i32 0, i32 20, i32 92892213, !"sequential_loop_to_stack_var", i32 20, i32 1}
!1 = !{i32 0, i32 20, i32 92892213, !"sequential_loop", i32 5, i32 0}
!2 = !{i32 0, i32 20, i32 92892213, !"sequential_loop_to_shared_var", i32 35, i32 2}
!3 = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_l5, !"kernel", i32 1}
!4 = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20, !"kernel", i32 1}
!5 = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35, !"kernel", i32 1}
!6 = !{i32 1, !"wchar_size", i32 4}
!7 = !{i32 7, !"openmp", i32 50}
!8 = !{i32 7, !"openmp-device", i32 50}
!9 = distinct !{!9, !10}
!10 = !{!"llvm.loop.mustprogress"}
!11 = distinct !{!11, !10}
!12 = distinct !{!12, !10}
;. ;.
; CHECK: attributes #[[ATTR0]] = { convergent norecurse nounwind "frame-pointer"="all" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="sm_53" "target-features"="+ptx32,+sm_53" } ; CHECK: attributes #[[ATTR0]] = { convergent noinline norecurse nounwind "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
; CHECK: attributes #[[ATTR1:[0-9]+]] = { convergent "frame-pointer"="all" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="sm_53" "target-features"="+ptx32,+sm_53" } ; CHECK: attributes #[[ATTR1:[0-9]+]] = { convergent "frame-pointer"="none" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
; CHECK: attributes #[[ATTR2]] = { nounwind } ; CHECK: attributes #[[ATTR2:[0-9]+]] = { convergent "frame-pointer"="none" "llvm.assume"="ompx_spmd_amenable" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
; CHECK: attributes #[[ATTR3:[0-9]+]] = { "llvm.assume"="ompx_spmd_amenable" } ; CHECK: attributes #[[ATTR3]] = { nounwind }
; CHECK: attributes #[[ATTR4]] = { convergent } ; CHECK: attributes #[[ATTR4]] = { convergent "llvm.assume"="ompx_spmd_amenable" }
; CHECK: attributes #[[ATTR5]] = { convergent }
;. ;.
; CHECK: [[META0:![0-9]+]] = !{i32 0, i32 44, i32 232567, !"sequential_loop", i32 4, i32 0} ; CHECK: [[META0:![0-9]+]] = !{i32 0, i32 20, i32 92892213, !"sequential_loop_to_stack_var", i32 20, i32 1}
; CHECK: [[META1:![0-9]+]] = !{void ()* @__omp_offloading_2c_38c77_sequential_loop_l4, !"kernel", i32 1} ; CHECK: [[META1:![0-9]+]] = !{i32 0, i32 20, i32 92892213, !"sequential_loop", i32 5, i32 0}
; CHECK: [[META2:![0-9]+]] = !{i32 1, !"wchar_size", i32 4} ; CHECK: [[META2:![0-9]+]] = !{i32 0, i32 20, i32 92892213, !"sequential_loop_to_shared_var", i32 35, i32 2}
; CHECK: [[META3:![0-9]+]] = !{i32 7, !"PIC Level", i32 2} ; CHECK: [[META3:![0-9]+]] = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_l5, !"kernel", i32 1}
; CHECK: [[META4:![0-9]+]] = !{i32 7, !"frame-pointer", i32 2} ; CHECK: [[META4:![0-9]+]] = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20, !"kernel", i32 1}
; CHECK: [[META5:![0-9]+]] = !{i32 7, !"openmp", i32 50} ; CHECK: [[META5:![0-9]+]] = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35, !"kernel", i32 1}
; CHECK: [[META6:![0-9]+]] = !{i32 7, !"openmp-device", i32 50} ; CHECK: [[META6:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
; CHECK: [[META7:![0-9]+]] = !{!"clang version 13.0.0"} ; CHECK: [[META7:![0-9]+]] = !{i32 7, !"openmp", i32 50}
; CHECK: [[LOOP8]] = distinct !{!8, !9} ; CHECK: [[META8:![0-9]+]] = !{i32 7, !"openmp-device", i32 50}
; CHECK: [[META9:![0-9]+]] = !{!"llvm.loop.mustprogress"} ; CHECK: [[LOOP9]] = distinct !{!9, !10}
; CHECK: [[META10:![0-9]+]] = !{!"llvm.loop.mustprogress"}
; CHECK: [[LOOP11]] = distinct !{!11, !10}
; CHECK: [[LOOP12]] = distinct !{!12, !10}
;. ;.