icemelon9 commented on a change in pull request #5324:
[Runtime][Relay][Cleanup] Clean up for memory pass to enable heterogenous
execution support.
URL: https://github.com/apache/incubator-tvm/pull/5324#discussion_r408496446
##########
File path: include/tvm/relay/attrs/memory.h
##########
@@ -27,10 +27,37 @@
#include <tvm/ir/attrs.h>
#include <tvm/relay/expr.h>
#include <string>
+#include <vector>
namespace tvm {
namespace relay {
+std::vector<TensorType> FlattenTupleType(const Type& type);
+std::vector<Expr> FromTupleType(const Type& type, const Expr& expr);
+Expr ToTupleType(const Type& t, const Array<Expr>& exprs);
+
+/*!
+ * \brief Options for allocating storage.
+ */
+struct AllocStorageAttrs : public tvm::AttrsNode<AllocStorageAttrs> {
+ DataType dtype;
+ int device_id;
+ int device_type;
+
+ TVM_DECLARE_ATTRS(AllocStorageAttrs, "relay.attrs.AllocStorageAttrs") {
+ TVM_ATTR_FIELD(dtype)
+ .describe(
+ "The dtype of the tensor to allocate.")
+ .set_default(DataType::Float(32, 1));
+ TVM_ATTR_FIELD(device_id)
Review comment:
After a discussion with Jared, we agreed that we can keep the device id for
future proof to support multiple devices. And the device type can be still
useful in the attributes for certain analysis. So we decide to go with S0, and
keep the current design.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
