[Performance] createSession() slow on release 1.15 and 1.17.1 as compare to 1.14 about onnxruntime HOT 6 OPEN

The easiest thing to do would be to disable all optimizers and compare. This would rule out the optimizers at least.

[For ORT team] As an aside I think it'll be really great if ORT printed which optimizers ran during session initialization. Then one can easily compare between different vers if more optimizers ran for the same model as a data point or which didn't.

Isn't that info already available:

from onnxruntime.

Can you please define "slow" with numbers before and after ?

from onnxruntime.

The easiest thing to do would be to disable all optimizers and compare. This would rule out the optimizers at least.

[For ORT team] As an aside I think it'll be really great if ORT printed which optimizers ran during session initialization. Then one can easily compare between different vers if more optimizers ran for the same model as a data point or which didn't.

from onnxruntime.

Do you want me to run experiment with m_ort->SetSessionGraphOptimizationLevel(m_sessionOptions, ORT_DISABLE_ALL)? and share the performance profile json?

from onnxruntime.

Do you want me to run experiment with m_ort->SetSessionGraphOptimizationLevel(m_sessionOptions, ORT_DISABLE_ALL)? and share the performance profile json?

You can try doing that. You can also try enabling INFO level logs to enable the logs I pasted above to see the diff.

Btw - what is the impact of this ? I know session creation time has nearly doubled, but unless you have a scenario where you need to create many sessions, the impact can't be significant ?

from onnxruntime.

I didn't create this issue, but session creation time is important to us, too. We use onnxruntime for on-the-fly constant folding in Spox and higher-level in-house solutions. We want to push our tooling to a point were we can deliver a similar interactive UX as NumPy and Pandas.

from onnxruntime.