Add _int_mm primitive that binds cuBLAS int8@int8 -> int32 matmul and that translates to Triton based mm templates under max autotune. This is a very useful first step towards better supporting quantization on the GPU. This is a not a user facing API, but an internal primitive.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/94339
Approved by: https://github.com/ngimel, https://github.com/jansel
Temporary Fix for #95312
In triton, 1 warp computes 16x16 tile of output, so for 32x32 block we only need 4 warps. 8 warps IMA, which is a bug, but it's not a good config anyway.
Triton main is supposed to have better behavior for these pathological, but we are not on main yet.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/95339
Approved by: https://github.com/ezyang, https://github.com/Chillee
Summary:
this diff adds logic to handle a global autotuning cache, stored in json format at config.global_cache_path.
what is changing from `DiskCache`:
* `DiskCache` is renamed to `PersistentCache`
* the local cache is now stored as a single file in json format, located at `/tmp/torchinductor_{$USER}/local_cache`. the file contains a dictionary structure like `local_cache[name][inputs][choice]` where `name` is the type of operation, like `addmm`, `inputs` is the repr of the inputs, and `choice` is the hash of a `ChoiceCaller`. the stored value is the benchmark time for that `ChoiceCaller`.
* a global cache is added, initially stored at `fbcode/caffe2/torch/_inductor/global_cache`, with almost identical format as the local cache. since the global cache exists over different machines, there is an additional `dinfo` field, such that `global_cache[dinfo] = local_cache` (at least structure wise, there is no guarantee that the global cache and local cache share the same values). `dinfo` is just a repr of the cuda device properties.
* the autotuner will prioritize the global cache, and return values from there first, before looking in the local cache
* the autotuner will look in both the global cache and the local cache even when `max_autotune=False`, but will still only generate values if `max_autotune=True`.
* the autotuner will log global cache hits and misses to a scuba table (inductor_autotuning_cache) which will be used to update the global cache at regular intervals
Test Plan: D43285472
Differential Revision: D42785435
Pull Request resolved: https://github.com/pytorch/pytorch/pull/94922
Approved by: https://github.com/jansel
