[MLIR][NVVM] Add support for shared::cta destination (llvm#168056)

This patch adds support for shared::cta as destination space in
the TMA non-tensor copy Op (from global to shared::cta).

* Appropriate verifier checks are added.
* Unit tests are added to verify the lowering.

The related intrinsic changes were merged through PR llvm#167508.

Signed-off-by: Durgadoss R <[email protected]>

Author: durga4github

mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp

@@ -252,6 +252,7 @@ LogicalResult CpAsyncBulkGlobalToSharedClusterOp::verify() {
 <<<<<<< HEAD
 <<<<<<< HEAD
 <<<<<<< HEAD
+<<<<<<< HEAD
 static LogicalResult verifyMBarrierArriveLikeOp(Operation *op, Value addr,
                                                 NVVM::MemScopeKind scope,
                                                 Value retVal = nullptr) {
@@ -291,6 +292,8 @@ LogicalResult MBarrierCompleteTxOp::verify() {
 >>>>>>> 95aa70cf209a ([MLIR][NVVM] Add support for shared::cta destination (#168056))
 =======
 >>>>>>> 95aa70cf209a ([MLIR][NVVM] Add support for shared::cta destination (#168056))
+=======
+>>>>>>> 95aa70cf209a ([MLIR][NVVM] Add support for shared::cta destination (#168056))
 LogicalResult ConvertFloatToTF32Op::verify() {
   using RndMode = NVVM::FPRoundingMode;
   switch (getRnd()) {