You are viewing a plain text version of this content. The canonical link for it is here.
Posted to discuss-archive@tvm.apache.org by Anabeana via TVM Discuss <no...@discuss.tvm.ai> on 2020/06/10 10:29:07 UTC
[TVM Discuss] [Questions] Quick start tutorial gives " Cannot find
config for target=cuda -model=unknown, workload=('conv2d_nchw.cuda'"
Hi,
I am also facing same warning issue while running ***resnet-50*** on **'GeForce GTX 1070'** with *--model=1080ti*, and taking **4.58ms** for [inferencing](https://github.com/apache/incubator-tvm/blob/master/apps/benchmark/gpu_imagenet_bench.py) which is nearly twice than actual expected value(w.r.t benchmark on 1080ti). Do I need to fine-tune those workloads for hardware? or is there any pre-tuned cache available for 1070?
Please help me on this.
---
[Visit Topic](https://discuss.tvm.ai/t/quick-start-tutorial-gives-cannot-find-config-for-target-cuda-model-unknown-workload-conv2d-nchw-cuda/5874/3) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/5d9e2dd6e8e7b0d0639f65c8dd69b6796d83979577c874f6c85fffdaa262993c).
[TVM Discuss] [Questions] Quick start tutorial gives " Cannot find
config for target=cuda -model=unknown, workload=('conv2d_nchw.cuda'"
Posted by Anabeana via TVM Discuss <no...@discuss.tvm.ai>.
Thank you. Looking forward to.
---
[Visit Topic](https://discuss.tvm.ai/t/quick-start-tutorial-gives-cannot-find-config-for-target-cuda-model-unknown-workload-conv2d-nchw-cuda/5874/8) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/9df3b499020609d041b27c28d6844ae4b11b5a6038ec5a30a39683d3b1905a8e).
[TVM Discuss] [Questions] Quick start tutorial gives " Cannot find
config for target=cuda -model=unknown, workload=('conv2d_nchw.cuda'"
Posted by ckh via TVM Discuss <no...@discuss.tvm.ai>.
I've just referenced the [benchmarks](https://github.com/apache/incubator-tvm/blob/master/apps/benchmark/gpu_imagenet_bench.py), but the 2080ti doesn't seem to be there.
Maybe the 2080ti also needs to be tuned.
---
[Visit Topic](https://discuss.tvm.ai/t/quick-start-tutorial-gives-cannot-find-config-for-target-cuda-model-unknown-workload-conv2d-nchw-cuda/5874/7) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/055b900ae1e43a40768022dd8dcb45f74f05b9fa93f0672459c80b5e672287ca).
[TVM Discuss] [Questions] Quick start tutorial gives " Cannot find
config for target=cuda -model=unknown, workload=('conv2d_nchw.cuda'"
Posted by Anabeana via TVM Discuss <no...@discuss.tvm.ai>.
I tried to do the same test on another machine 'RTX 2080ti', getting similar warning issue. I couldn't find pre-tuned log file for 2080ti in the [log repo](https://github.com/uwsampl/tophub).
- Is this updated or I am looking in wrong link?
- Is there an option to clear log-cache, and run benchmarking freshly, or is it not necessary?
Thanks in advance.
---
[Visit Topic](https://discuss.tvm.ai/t/quick-start-tutorial-gives-cannot-find-config-for-target-cuda-model-unknown-workload-conv2d-nchw-cuda/5874/6) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/d5923d01555bb2c59ce051c724ad380c0d072ddc782540e7fa8eb0726c10ba11).
[TVM Discuss] [Questions] Quick start tutorial gives " Cannot find
config for target=cuda -model=unknown, workload=('conv2d_nchw.cuda'"
Posted by Anabeana via TVM Discuss <no...@discuss.tvm.ai>.
Thank you so much, for your immediate input. Let me try tuning in my local machine.
---
[Visit Topic](https://discuss.tvm.ai/t/quick-start-tutorial-gives-cannot-find-config-for-target-cuda-model-unknown-workload-conv2d-nchw-cuda/5874/5) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/94c2aa70915c9facdd55801024743919f25a898fc05659299019c6f6f157d2b3).
[TVM Discuss] [Questions] Quick start tutorial gives " Cannot find
config for target=cuda -model=unknown, workload=('conv2d_nchw.cuda'"
Posted by ckh via TVM Discuss <no...@discuss.tvm.ai>.
I am not sure, but titan, 2080ti, 1080ti have tuned configuration in TVM.
So if you want to get the optimal performance for the 1070ti, tuning seems to be the right choice.
also There is a simple tuning template provided in the TVM tutorial, so use it to tune it.
---
[Visit Topic](https://discuss.tvm.ai/t/quick-start-tutorial-gives-cannot-find-config-for-target-cuda-model-unknown-workload-conv2d-nchw-cuda/5874/4) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/bd5ef9c25f2f75b4951b1b023c0015ece1bf6057f78a2a459b83db5ccdad2b5d).