search

openxla / xla

A machine learning compiler for GPUs, CPUs, and ML accelerators
Apache License 2.0
2.55k stars 394 forks source link

[GPU] Remove DRAM size from model_str in device description. #14881

Closed sergachev closed 1 month ago

sergachev commented 1 month ago

Exact DRAM size can slightly vary for the same GPU model so it shouldn't be used in model identification. The removed part of gpu_compiler_test_autotune_db.textproto illustrates that.

dimitar-asenov commented 1 month ago

I just saw this PR. We're aware of the problem and I'm actually working on a different solution that also excludes the RAM, but also makes other changes to the cache string. It should be ready today.

dimitar-asenov commented 1 month ago

FYI: the alternative PR is ready, but we need to wait until Thursday to submit it. Conceptually, it's very similar to this one.

sergachev commented 1 month ago

Then what's the reason to prefer it?

dimitar-asenov commented 1 month ago

Here is the current version of the other PR: https://github.com/openxla/xla/pull/14954

Then what's the reason to prefer it?

The other PR doesn't change the model_str in cuda executor. It touches only the autotuning key and does a cleanup related to deviceless autotuning keys. It also does changes that are needed internally (and not visible on GitHub). At the point I became aware of your PR we already had the internal one nearly done. It's now fully ready but we have to wait for an extra internal approval until tomorrow.