cbalint13 commented on code in PR #13621:
URL: https://github.com/apache/tvm/pull/13621#discussion_r1056870085
##########
python/tvm/relay/op/strategy/x86.py:
##########
@@ -627,16 +627,16 @@ def batch_matmul_strategy_cpu(attrs, inputs, out_type,
target):
if (
not attrs.transpose_a
and attrs.transpose_b
- and target_has_vnni(mcpu)
+ and target_has_avx512(mcpu)
and inputs[0].dtype == "uint8"
and inputs[1].dtype == "int8"
and inputs[1].shape[-2] % 16 == 0
and inputs[1].shape[-1] % 4 == 0
):
strategy.add_implementation(
- wrap_compute_batch_matmul(topi.x86.batch_matmul_vnni_compute,
need_out_dtype=True),
- wrap_topi_schedule(topi.x86.schedule_batch_matmul_vnni),
- name="batch_matmul_vnni.x86",
Review Comment:
* Don't remove the ```vnni``` one completley
* Instead, maybe a descend strategy would be better:
- if ```has_vnni```
- elif ```has_avx512```
- elif ```has_avx2``` (in a future PR)
- elif ```has_ssse3``` (in a future PR)
* See
[strategy/x86.py](https://github.com/apache/tvm/blob/dd1eb2498a4e2c867a16d7d9ccea010c396e10ae/python/tvm/relay/op/strategy/x86.py#L594-L621),
also descending ```plevel```, in the upcoming [PR#13642
](https://github.com/apache/tvm/pull/13642)
--
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]
