Yes, if you really want to improve, you need to analyze deeper. Like what kind
of instruction effects lower performance then you should try to avoid it (Like
using tensorize). I think your current performance is good enough now.
---
[Visit
Topic](https://discuss.tvm.ai/t/how-to-further-im
CPI rate is a little high. One reason is maybe we generate too many redundancy
instructions. So tensorize GEMM core part maybe is one solution. As you have
performed better than oneDNN, you could compute the efficiency of CPU (like
60%, 70% or ...), if you have reached like 98% efficiency, yo
For Intel x86 target, firstly, we should read the doc :
https://tvm.apache.org/docs/tutorials/optimize/opt_gemm.html, which covers
important aspects of tvm schedule primitives and its effect. Secondly,
recommend to reading
https://tvm.apache.org/docs/tutorials/autotvm/tune_simple_template.htm
In the topi, we could get the target information during schedule using
`tvm.target.Target.current()`. But we don't have `target_host` information as
far as I know.
But seems that you could do in `def _build_for_device` (we could add pass
inside it like other passes). However, you should doub
I think it is the correct way to handle it. This is the same as the doc:
https://docs.tvm.ai/tutorials/dev/low_level_custom_pass.html
---
[Visit Topic](https://discuss.tvm.ai/t/remove-an-attribute-from-ir/6526/3) to
respond.
You are receiving this because you enabled mailing list mode.
I think if we could implement it in C++, we could boost auto tvm tuning speed.
---
[Visit Topic](https://discuss.tvm.ai/t/can-you-do-auto-tuning-in-c/6362/3) to
respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://d
Quantized tf model has complex logic need to handle, which has some special ops
like FakeQuant. I think we could support it in the future, because currently
TFLite has helped us to handle this and we only need to parse quantized TFLite
model. TF , TOCO, TFLite is one complete path for supporti
We are working in progress. @janimesh has implemented some stuff.
---
[Visit
Topic](https://discuss.tvm.ai/t/can-not-compile-quantized-tflite-model-with-int32-bias/2891/5)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
