================
@@ -811,8 +812,13 @@ LogicalResult
ConvertAllocOpToGpuRuntimeCallPattern::matchAndRewrite(
// descriptor.
Type elementPtrType = this->getElementPtrType(memRefType);
auto stream = adaptor.getAsyncDependencies().front();
+
+ auto isHostShared = rewriter.create<mlir::LLVM::ConstantOp>(
+ loc, llvmInt64Type, rewriter.getI64IntegerAttr(isShared));
+
Value allocatedPtr =
- allocCallBuilder.create(loc, rewriter, {sizeBytes, stream}).getResult();
+ allocCallBuilder.create(loc, rewriter, {sizeBytes, stream, isHostShared})
+ .getResult();
----------------
keryell wrote:
I guess that if the runtime uses actually synchronous allocation behind the
scene and produces an always-ready async token, it works, even if non optimal.
https://github.com/llvm/llvm-project/pull/65539
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
