csullivan commented on a change in pull request #8823:
URL: https://github.com/apache/tvm/pull/8823#discussion_r696264693
##########
File path: python/tvm/target/target.py
##########
@@ -413,79 +413,118 @@ def bifrost(model="unknown", options=None):
return Target(" ".join(["opencl"] + opts))
-def hexagon(cpu_ver="v66", sim_args=None, llvm_args=None, hvx=128):
+def hexagon(cpu_ver="v66", **kwargs):
"""Returns a Hexagon target.
Parameters
----------
- cpu_ver : str
+ cpu_ver : str (default: "v66")
Review comment:
My take is that the need for the user to provide the often very detailed
`mcpu` option is the usability burden IMO.
In some SDKs the ability exists to query sufficient information to construct
the mcpu option equivalent, and I'd love to see TVM be better able to use this
information to produce optimal codegen automatically. Though I'm still not sure
if that will be possible or helpful hexagon, just wanted to raise the
discussion with @kparzysz-quic if he sees hexagon specific merit for the
effort.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
