You may want to remeasure the throughput using the best config. We've observed that AutoTVM measurement might be inaccurate for some reasons. For example, [this recent PR](https://github.com/apache/incubator-tvm/pull/5200) fixed one for Intel, but it must have some others.
--- [Visit Topic](https://discuss.tvm.ai/t/auto-tuned-convolution-achieving-higher-than-v100s-theoretical-peak-single-precision-flops/6325/2) 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/a1a627b9d80ae8442635b9fa7a816d5535086a2dbcbb8372697fd5c58fe29fd5).
