sunjiweiswift opened a new pull request #8539:
URL: https://github.com/apache/tvm/pull/8539
tvm/python/tvm/relay/op/strategy/x86.py
147-159
judge_winograd_auto_scheduler = False
if len(kernel.shape) == 4:
kernel_h, kernel_w, _, co = get_const_tuple(kernel.shape)
judge_winograd_auto_scheduler = (
"float" in data.dtype
and "float" in kernel.dtype
and kernel_h == 3
and kernel_w == 3
and stride_h == 1
and stride_w == 1
and dilation_h == 1
and dilation_w == 1
and 64 < co < 512
# The last condition of co is based on our profiling of
resnet workloads
# on skylake avx512 machines. We found winograd is
faster than direct
# only when co is within this range
)
"co" need large than 64
outc defaults is 32
can not enter winograd
--
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]
