================
@@ -1102,12 +1102,64 @@ struct DeferredStore {
};
} // namespace
+/// Check whether allocations for the given operation might potentially have to
+/// be done in device shared memory. That means we're compiling for a
offloading
+/// target, the operation is an `omp::TargetOp` or nested inside of one and
that
+/// target region represents a Generic (non-SPMD) kernel.
+///
+/// This represents a necessary but not sufficient set of conditions to use
+/// device shared memory in place of regular allocas. Depending on the
variable,
+/// its uses or the associated OpenMP construct might also need to be taken
into
+/// account.
+static bool
+mightAllocInDeviceSharedMemory(Operation &op,
+ const llvm::OpenMPIRBuilder &ompBuilder) {
+ if (!ompBuilder.Config.isTargetDevice())
+ return false;
+
+ auto targetOp = dyn_cast<omp::TargetOp>(op);
+ if (!targetOp)
+ targetOp = op.getParentOfType<omp::TargetOp>();
+
+ return targetOp &&
+ !bitEnumContainsAny(
+ targetOp.getKernelExecFlags(targetOp.getInnermostCapturedOmpOp()),
+ omp::TargetRegionFlags::spmd);
+}
+
+/// Check whether the entry block argument representing the private copy of a
+/// variable in an OpenMP construct must be allocated in device shared memory,
+/// based on what the uses of that copy are.
+///
+/// This must only be called if a previous call to
+/// \c mightAllocInDeviceSharedMemory has already returned \c true for the
+/// operation that owns the specified block argument.
+static bool mustAllocPrivateVarInDeviceSharedMemory(BlockArgument value) {
+ Operation *parentOp = value.getOwner()->getParentOp();
+ auto targetOp = dyn_cast<omp::TargetOp>(parentOp);
+ if (!targetOp)
+ targetOp = parentOp->getParentOfType<omp::TargetOp>();
+ assert(targetOp && "expected a parent omp.target operation");
+
+ for (auto *user : value.getUsers()) {
+ if (auto parallelOp = dyn_cast<omp::ParallelOp>(user)) {
+ if (llvm::is_contained(parallelOp.getReductionVars(), value))
+ return true;
+ } else if (auto parallelOp = user->getParentOfType<omp::ParallelOp>()) {
+ if (targetOp->isProperAncestor(parallelOp))
----------------
bhandarkar-pranav wrote:
There seems to be a hole in my understanding of this. At this point in the
code, we know that `value` iis a `BlockArgument`. We know that it has an an
ancestor, `targetOp` that is an `omp::TargetOp`. Should't all the users of a
`BlockArgument` be such that they are dominated by the `BlockArgument`.
Therefore `targetOp` should trivially be an ancestor of all users, no? All this
is to say that the use of a `BlockArgument` inside a `omp::ParallelOp` should
be enough and this ancestor check is superfluous. Unless, of course, I am
missing something that is obvious.
https://github.com/llvm/llvm-project/pull/150924
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
