[FRONTEND][BACKEND] Added trans instruction; made flash attention bwd pass work (#943)

lib/Analysis/Alias.cpp

@@ -26,7 +26,7 @@ ChangeResult SharedMemoryAliasAnalysis::visitOperation(
     // These ops may allocate a new shared memory buffer.
     auto result = op->getResult(0);
     // FIXME(Keren): extract and insert are always alias for now
-    if (isa<tensor::ExtractSliceOp>(op)) {
+    if (isa<tensor::ExtractSliceOp, triton::TransOp>(op)) {
       // extract_slice %src
       aliasInfo = AliasInfo(operands[0]->getValue());
       pessimistic = false;

lib/Analysis/Utility.cpp

@@ -105,7 +105,7 @@ bool maybeSharedAllocationOp(Operation *op) {
 }
 
 bool maybeAliasOp(Operation *op) {
-  return isa<tensor::ExtractSliceOp>(op) ||
+  return isa<tensor::ExtractSliceOp>(op) || isa<triton::TransOp>(op) ||
          isa<triton::gpu::InsertSliceAsyncOp>(op) ||
          isa<tensor::InsertSliceOp>(op);
 }