[Apache TVM Discuss] [Questions] Low TVM performance with Galaxy S20+(CPU)

2021-04-14 Thread Eye via Apache TVM Discuss
Maybe cpu is at low energy mode ? ``` ## arm linux ## ➜ ~ cat /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor performance performance performance performance ➜ ~ Connection to 192.168.31.79 closed. ## rk3399 Android ➜ Playground adb shell * daemon not running; st

[Apache TVM Discuss] [Questions] Vitis-AI Integration: How to use both DPU cores?

2021-03-05 Thread Eye via Apache TVM Discuss
Here is my guss: [ How to optimize GEMM on CPU --- Parallel](https://tvm.apache.org/docs/tutorials/optimize/opt_gemm.html). Follow above link you will find out how TVM optimize computation by **`Parallel`**. Maybe use two cores is same way. --- [Visit Topic](https://discuss.tvm.apac

[Apache TVM Discuss] [Questions] Auto-tune finished, but Build error occurs for my own onnx model

2020-11-18 Thread Eye via Apache TVM Discuss
try with `opt_level=2`, in my case this work. don't known which optimise pass fault --- [Visit Topic](https://discuss.tvm.apache.org/t/auto-tune-finished-but-build-error-occurs-for-my-own-onnx-model/6409/3) to respond. You are receiving this because you enabled mailing list mode. To un

[Apache TVM Discuss] [Questions] Why stop quantize after first ``nn.global_avg_pool2d``

2020-10-20 Thread Eye via Apache TVM Discuss
@register_annotate_function("nn.global_avg_pool2d") def global_avg_pool2d_rewrite(ref_call, new_args, ctx): """Rewrite function for global_avg_pool2d for stopping quantize""" if quantize_context().check_to_skip(ref_call): return None expr, x_kind = _g