mbrookhart commented on a change in pull request #6351:
URL: https://github.com/apache/incubator-tvm/pull/6351#discussion_r488190431
##########
File path: python/tvm/relay/op/strategy/x86.py
##########
@@ -347,12 +348,20 @@ def dense_strategy_cpu(attrs, inputs, out_type, target):
def batch_matmul_strategy_cpu(attrs, inputs, out_type, target):
"""batch_matmul x86 strategy"""
strategy = _op.OpStrategy()
- strategy.add_implementation(
- wrap_compute_batch_matmul(topi.x86.batch_matmul),
- wrap_topi_schedule(topi.x86.schedule_batch_matmul),
- name="batch_matmul.x86",
- plevel=10,
- )
+ if is_dynamic(out_type):
+ strategy.add_implementation(
Review comment:
Hmm, something very similar to this is already in generic.py, what I'm
trying to do here is short-circuit the schedule if we have dynamic shapes. The
x86 schedule, as written, assumes static shapes and breaks during schedule
construction if I give it a dynamic input. Is there a cleaner way to do that
short-circuit in generic.py?
----------------------------------------------------------------
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:
us...@infra.apache.org
