[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
diff --git a/clang/lib/Sema/SemaOpenMP.cpp b/clang/lib/Sema/SemaOpenMP.cpp
index 97647c3..d2c08ca 100644
--- a/clang/lib/Sema/SemaOpenMP.cpp
+++ b/clang/lib/Sema/SemaOpenMP.cpp
@@ -1675,11 +1675,37 @@
break;
}
case OMPD_taskloop: {
+ QualType KmpInt32Ty =
+ Context.getIntTypeForBitwidth(/*DestWidth=*/32, /*Signed=*/1);
+ QualType KmpUInt64Ty =
+ Context.getIntTypeForBitwidth(/*DestWidth=*/64, /*Signed=*/0);
+ QualType KmpInt64Ty =
+ Context.getIntTypeForBitwidth(/*DestWidth=*/64, /*Signed=*/1);
+ QualType Args[] = {Context.VoidPtrTy.withConst().withRestrict()};
+ FunctionProtoType::ExtProtoInfo EPI;
+ EPI.Variadic = true;
+ QualType CopyFnType = Context.getFunctionType(Context.VoidTy, Args, EPI);
Sema::CapturedParamNameType Params[] = {
+ std::make_pair(".global_tid.", KmpInt32Ty),
+ std::make_pair(".part_id.", Context.getPointerType(KmpInt32Ty)),
+ std::make_pair(".privates.",
+ Context.VoidPtrTy.withConst().withRestrict()),
+ std::make_pair(
+ ".copy_fn.",
+ Context.getPointerType(CopyFnType).withConst().withRestrict()),
+ std::make_pair(".task_t.", Context.VoidPtrTy.withConst()),
+ std::make_pair(".lb.", KmpUInt64Ty),
+ std::make_pair(".ub.", KmpUInt64Ty), std::make_pair(".st.", KmpInt64Ty),
+ std::make_pair(".liter.", KmpInt32Ty),
std::make_pair(StringRef(), QualType()) // __context with shared vars
};
ActOnCapturedRegionStart(DSAStack->getConstructLoc(), CurScope, CR_OpenMP,
Params);
+ // Mark this captured region as inlined, because we don't use outlined
+ // function directly.
+ getCurCapturedRegion()->TheCapturedDecl->addAttr(
+ AlwaysInlineAttr::CreateImplicit(
+ Context, AlwaysInlineAttr::Keyword_forceinline, SourceRange()));
break;
}
case OMPD_taskloop_simd: {
@@ -4614,6 +4640,15 @@
LastIteration32.get()->getType()->hasSignedIntegerRepresentation(),
LastIteration64.get(), SemaRef)))
LastIteration = LastIteration32;
+ QualType VType = LastIteration.get()->getType();
+ QualType RealVType = VType;
+ QualType StrideVType = VType;
+ if (isOpenMPTaskLoopDirective(DKind)) {
+ VType =
+ SemaRef.Context.getIntTypeForBitwidth(/*DestWidth=*/64, /*Signed=*/0);
+ StrideVType =
+ SemaRef.Context.getIntTypeForBitwidth(/*DestWidth=*/64, /*Signed=*/1);
+ }
if (!LastIteration.isUsable())
return 0;
@@ -4649,7 +4684,6 @@
SourceLocation InitLoc = IterSpaces[0].InitSrcRange.getBegin();
- QualType VType = LastIteration.get()->getType();
// Build variables passed into runtime, nesessary for worksharing directives.
ExprResult LB, UB, IL, ST, EUB;
if (isOpenMPWorksharingDirective(DKind) || isOpenMPTaskLoopDirective(DKind) ||
@@ -4678,8 +4712,9 @@
/*DirectInit*/ false, /*TypeMayContainAuto*/ false);
// Stride variable returned by runtime (we initialize it to 1 by default).
- VarDecl *STDecl = buildVarDecl(SemaRef, InitLoc, VType, ".omp.stride");
- ST = buildDeclRefExpr(SemaRef, STDecl, VType, InitLoc);
+ VarDecl *STDecl =
+ buildVarDecl(SemaRef, InitLoc, StrideVType, ".omp.stride");
+ ST = buildDeclRefExpr(SemaRef, STDecl, StrideVType, InitLoc);
SemaRef.AddInitializerToDecl(
STDecl, SemaRef.ActOnIntegerConstant(InitLoc, 1).get(),
/*DirectInit*/ false, /*TypeMayContainAuto*/ false);
@@ -4699,8 +4734,8 @@
ExprResult IV;
ExprResult Init;
{
- VarDecl *IVDecl = buildVarDecl(SemaRef, InitLoc, VType, ".omp.iv");
- IV = buildDeclRefExpr(SemaRef, IVDecl, VType, InitLoc);
+ VarDecl *IVDecl = buildVarDecl(SemaRef, InitLoc, RealVType, ".omp.iv");
+ IV = buildDeclRefExpr(SemaRef, IVDecl, RealVType, InitLoc);
Expr *RHS = (isOpenMPWorksharingDirective(DKind) ||
isOpenMPTaskLoopDirective(DKind) ||
isOpenMPDistributeDirective(DKind))