================
@@ -4899,6 +4899,234 @@ void
CGOpenMPRuntime::emitSingleReductionCombiner(CodeGenFunction &CGF,
}
}
+void CGOpenMPRuntime::emitPrivateReduction(
+ CodeGenFunction &CGF, SourceLocation Loc, ArrayRef<const Expr *> Privates,
+ ArrayRef<const Expr *> LHSExprs, ArrayRef<const Expr *> RHSExprs,
+ ArrayRef<const Expr *> ReductionOps) {
+ if (LHSExprs.empty() || Privates.empty() || ReductionOps.empty())
+ return;
+
+ if (LHSExprs.size() != Privates.size() ||
+ LHSExprs.size() != ReductionOps.size())
+ return;
+
+ // Create a shared global variable (__shared_reduction_var) to accumulate
the
+ // final result.
+ //
+ // Call __kmpc_barrier to synchronize threads before initialization.
+ //
+ // The master thread (thread_id == 0) initializes __shared_reduction_var
+ // with the identity value or initializer.
+ //
+ // Call __kmpc_barrier to synchronize before combining.
+ // For each i:
+ // - Thread enters critical section.
+ // - Reads its private value from LHSExprs[i].
+ // - Updates __shared_reduction_var[i] =
RedOp_i(__shared_reduction_var[i],
+ // LHSExprs[i]).
+ // - Exits critical section.
+ //
+ // Call __kmpc_barrier after combining.
----------------
chandraghale wrote:
Agreed. Handling simple cases with atomics for performance is a good idea.I
would like to address this in a follow-up patch. Currently, synchronization
generated here is independent of the `nowait` clause.
https://github.com/llvm/llvm-project/pull/134709
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
