Alexander Efimov 605a90c58e [MFMA] Support tile size 4x4 version 1 (#413) ...

This PR enables 4x4 tile size in MFMA based dot operations.

Supported tiled dot is (4x64) x (64x4) -> (4x4) in MFMA layout.
However, actual dot operation should have at least 64 output elements, this is a limitation of other layouts appearing during result processing (i.e. blocked layout can not handle tensors smaller than wavesize).

For example, following dots are supported: (4x64) x (64x16) -> (4x16), (16x64) x (64x4) -> (16x4) or (8x64) x (64x8) -> (8x8)
Following dots are not supporter: (4x128) x (128x4) -> (4x4), (4x64) x (64x8) -> (4x8)

This is a first version of dot using mfma 4x4 instructions, with redundancy and reductions.

2023-12-12 18:23:55 +01:00

..

hopper

[BACKEND] turn on MMA V3 by default on Hopper (#2414)

2023-09-28 22:45:28 -07:00

language

[MFMA] Support tile size 4x4 version 1 (#413)

2023-12-12 18:23:55 +01:00

operators

resolve some merge conflicts

2023-11-06 23:13:10 +00:00

runtime

Merge commit 'ac9fa68d18c777e421bd3f6fb1ddcfd60b6fda33' into ifu-rebase-again

2023-11-06 23:10:10 +00:00

tools

[FRONTEND] Accommodate new triton IR format (#2294)

2023-09-14 09:03:23 -07:00