srkreddy1238 opened a new pull request, #13696:
URL: https://github.com/apache/tvm/pull/13696
Various benchmarks enabled for CLML BYOC backend for Adreno GPU.
Networks resnet-18, resnet-34, resnet-50, densenet-121, inception_v3,
mobilenetv1, squeezenet_v1.0, squeezenet_v1.1 are added with FP16 and FP32
dtypes.
Fixes added to handle batch_flatten, dropout to get largest sub graph
possible.
CLML subgraphs runs under OpenCL runtime context, hence CLML execution is
accounted as part of OpenCL profiling.
--
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]
