void CodeGenFunction::EmitOMPInnerLoop(const OMPLoopDirective &S,
OMPPrivateScope &LoopScope,
bool SeparateIter) {
auto LoopExit = getJumpDestInCurrentScope("omp.inner.for.end");
auto Cnt = getPGORegionCounter(&S);
// Start the loop with a block that tests the condition.
auto CondBlock = createBasicBlock("omp.inner.for.cond");
EmitBlock(CondBlock);
LoopStack.push(CondBlock);
// If there are any cleanups between here and the loop-exit scope,
// create a block to stage a loop exit along.
auto ExitBlock = LoopExit.getBlock();
if (LoopScope.requiresCleanups())
ExitBlock = createBasicBlock("omp.inner.for.cond.cleanup");
auto LoopBody = createBasicBlock("omp.inner.for.body");
// Emit condition: "IV < LastIteration + 1 [ - 1]"
// ("- 1" when lastprivate clause is present - separate one iteration).
llvm::Value *BoolCondVal = EvaluateExprAsBool(S.getCond(SeparateIter));
Builder.CreateCondBr(BoolCondVal, LoopBody, ExitBlock,
PGO.createLoopWeights(S.getCond(SeparateIter), Cnt));
if (ExitBlock != LoopExit.getBlock()) {
EmitBlock(ExitBlock);
EmitBranchThroughCleanup(LoopExit);
}
EmitBlock(LoopBody);
Cnt.beginRegion(Builder);
// Create a block for the increment.
auto Continue = getJumpDestInCurrentScope("omp.inner.for.inc");
BreakContinueStack.push_back(BreakContinue(LoopExit, Continue));
EmitOMPLoopBody(S);
EmitStopPoint(&S);
// Emit "IV = IV + 1" and a back-edge to the condition block.
EmitBlock(Continue.getBlock());
EmitIgnoredExpr(S.getInc());
BreakContinueStack.pop_back();
EmitBranch(CondBlock);
LoopStack.pop();
// Emit the fall-through block.
EmitBlock(LoopExit.getBlock());
}
void CodeGenFunction::EmitOMPForOuterLoop(OpenMPScheduleClauseKind ScheduleKind,
const OMPLoopDirective &S,
OMPPrivateScope &LoopScope,
llvm::Value *LB, llvm::Value *UB,
llvm::Value *ST, llvm::Value *IL,
llvm::Value *Chunk) {
auto &RT = CGM.getOpenMPRuntime();
assert(!RT.isStaticNonchunked(ScheduleKind, /* Chunked */ Chunk != nullptr) &&
"static non-chunked schedule does not need outer loop");
if (RT.isDynamic(ScheduleKind)) {
ErrorUnsupported(&S, "OpenMP loop with dynamic schedule");
return;
}
// Emit outer loop.
//
// OpenMP [2.7.1, Loop Construct, Description, table 2-1]
// When schedule(static, chunk_size) is specified, iterations are divided into
// chunks of size chunk_size, and the chunks are assigned to the threads in
// the team in a round-robin fashion in the order of the thread number.
//
// while(UB = min(UB, GlobalUB), idx = LB, idx < UB) {
// while (idx <= UB) { BODY; ++idx; } // inner loop
// LB = LB + ST;
// UB = UB + ST;
// }
//
const Expr *IVExpr = S.getIterationVariable();
const unsigned IVSize = getContext().getTypeSize(IVExpr->getType());
const bool IVSigned = IVExpr->getType()->hasSignedIntegerRepresentation();
RT.EmitOMPForInit(*this, S.getLocStart(), ScheduleKind, IVSize, IVSigned, IL,
LB, UB, ST, Chunk);
auto LoopExit = getJumpDestInCurrentScope("omp.dispatch.end");
// Start the loop with a block that tests the condition.
auto CondBlock = createBasicBlock("omp.dispatch.cond");
EmitBlock(CondBlock);
LoopStack.push(CondBlock);
llvm::Value *BoolCondVal = nullptr;
// UB = min(UB, GlobalUB)
EmitIgnoredExpr(S.getEnsureUpperBound());
// IV = LB
EmitIgnoredExpr(S.getInit());
// IV < UB
BoolCondVal = EvaluateExprAsBool(S.getCond(false));
// If there are any cleanups between here and the loop-exit scope,
// create a block to stage a loop exit along.
auto ExitBlock = LoopExit.getBlock();
if (LoopScope.requiresCleanups())
ExitBlock = createBasicBlock("omp.dispatch.cleanup");
auto LoopBody = createBasicBlock("omp.dispatch.body");
Builder.CreateCondBr(BoolCondVal, LoopBody, ExitBlock);
if (ExitBlock != LoopExit.getBlock()) {
EmitBlock(ExitBlock);
EmitBranchThroughCleanup(LoopExit);
}
EmitBlock(LoopBody);
// Create a block for the increment.
auto Continue = getJumpDestInCurrentScope("omp.dispatch.inc");
BreakContinueStack.push_back(BreakContinue(LoopExit, Continue));
EmitOMPInnerLoop(S, LoopScope);
EmitBlock(Continue.getBlock());
BreakContinueStack.pop_back();
// Emit "LB = LB + Stride", "UB = UB + Stride".
EmitIgnoredExpr(S.getNextLowerBound());
EmitIgnoredExpr(S.getNextUpperBound());
EmitBranch(CondBlock);
LoopStack.pop();
// Emit the fall-through block.
EmitBlock(LoopExit.getBlock());
// Tell the runtime we are done.
RT.EmitOMPForFinish(*this, S.getLocStart(), ScheduleKind);
}
