[GFX1250][MX GEMM] Unified FLATMM GroupedGemm Implementation
for MX Data Types (#8325)
## Motivation
Design and test a unified FLATMM GroupedGemm interface so that it
supports all MX FP8, FP6, and FP4 data types on both the gfx950 and
gfx1250 architectures and works seamlessly across these platforms.
## Technical Details
Implementation exposes Grouped Gemm interface for MX FLATMM and MX TDM
FLATMM pipelines.
## Test Plan
Add the following tests:
- ck_tile/grouped_gemm_mx/test_grouped_gemm_mx_flatmm_non_tdm.cpp
- ck_tile/grouped_gemm_mx/test_grouped_gemm_mx_flatmm_tdm.cpp
- ck_tile/flatmm/test_mx_flatmm_persistent.cpp
Verify on the gfx950 and gfx1250 architectures.
## Test Result
All tests pass. Verified on A0 hardware with rocm-7.14.0a20260517
## Submission Checklist
- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
[CK_TILE][GFX1250] Enable MX GEMM FLATMM with ASYNC
## Motivation
Enables MX GEMM FLATMM pipeline on gfx1250. The pipeline uses an async
load instruction for tensor A, which complements the existing MX GEMM
FLATMM pipeline with TDM load. At this time, only FLATMM MX pipelines
are enabled on gfx1250.
## Technical Details
The existing gfx950 implementation was extended to support gfx1250
architecture. All three MX FP data types are supported across the two
ASICs.
It should be noted that while the TDM pipeline uses an emulated
32x32x128 warp-tile instruction, the present submission relies on the
built-in 16x16x128 instruction, called 4 times per warp.
## Test Plan
Existing `test/ck_tile/flatmm` tests were extended to cover new gfx1250
functionality.
To help facilitate the testing in development,
`example/ck_tile/18_flatmm/script/smoke_test_mx.sh` script was
introduced to verify various combinations of supported data types and
pipeline versions.
## Test Result
The present submission is expected to work on both gfx950 and gfx1250
hardware for all reasonable sizes and all MX FP8/FP6/FP4 data types.
## Submission Checklist
- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
- [x] Relies on #6978 and should only be merged after the changes are
merged to the `develop`.
[CK] suppress compiler warnings while building pytorch. (#7760)
## Motivation
Recently added compiler flags that are required to suppress false
warnings by latest staging compiler are not recognized by older compiler
versions and are triggering an avalanche of warnings. Previous attempt
to suppress them by using -Wno-unknown-warning-option flag didn't help,
because that flag wasn't recognized either and just added more warnings.
I've verified that current approach by checking the clang version
actually works as intended and makes the warnings go away.
## Technical Details
<!-- Explain the changes along with any relevant GitHub links. -->
## Test Plan
<!-- Explain any relevant testing done to verify this PR. -->
## Test Result
<!-- Briefly summarize test outcomes. -->
## Submission Checklist
- [ ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
[CK] upgrade CI to rocm7.13 as default compiler (#7612)
## Motivation
Upgrade the default docker and compiler version in CI to rocm7.13.
In order to pass all the checks I had to also clean up a lot of
non-ascii characters in the source code comments and modify a couple of
tests that were affected by a new compiler logic.
## Technical Details
<!-- Explain the changes along with any relevant GitHub links. -->
## Test Plan
<!-- Explain any relevant testing done to verify this PR. -->
## Test Result
<!-- Briefly summarize test outcomes. -->
## Submission Checklist
- [ ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
---------
Co-authored-by: Aviral Goel <aviral.goel@amd.com>
[CK] add composable kernel support on gfx1250 (#6978)
## Motivation
Add composable kernel support on gfx1250.
## Technical Details
<!-- Explain the changes along with any relevant GitHub links. -->
## Test Plan
<!-- Explain any relevant testing done to verify this PR. -->
## Test Result
<!-- Briefly summarize test outcomes. -->
## Submission Checklist
- [ ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
---------
Co-authored-by: Qun Lin <qlin@amd.com>
Co-authored-by: jialuo12_amdeng <jia.luo@amd.com>
Co-authored-by: Andriy Roshchenko <andriy.roshchenko@amd.com>
Co-authored-by: hsivasun_amdeng <haresh.sivasuntharampillai@amd.com>
[CK] Suppress new staging compiler errors (#7384)
## Motivation
This should make new builds with staging compiler pass.
## Technical Details
<!-- Explain the changes along with any relevant GitHub links. -->
## Test Plan
<!-- Explain any relevant testing done to verify this PR. -->
## Test Result
<!-- Briefly summarize test outcomes. -->
## Submission Checklist
- [ ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
ck_tile: add gtest unit tests for MX flatmm (gfx950) (#5082)
## Summary
- Add correctness unit tests for the MX-format flatmm kernel
(`example/ck_tile/18_flatmm/mxgemm`) under `test/ck_tile/flatmm/`
- Tests cover all five dtype combinations: FP4×FP4, FP8×FP8, FP6×FP6,
FP8×FP4, FP4×FP8
- Tests cover all four kernel dispatch paths (the `has_hot_loop` ×
`tail_num` product):
- `has_hot_loop=false, tail=ODD` (K=256, num_loop=1)
- `has_hot_loop=false, tail=EVEN` (K=512, num_loop=2)
- `has_hot_loop=true, tail=ODD` (K=768, num_loop=3)
- `has_hot_loop=true, tail=EVEN` (K=1024, num_loop=4)
- Remove unsupported `-split_k` CLI option from
`tile_example_mx_flatmm`; the pre-shuffled B layout is incompatible with
K-splitting and the option silently produced wrong results
## Changes
**New files (`test/ck_tile/flatmm/`):**
- `CMakeLists.txt` — builds 40 kernel instances as a shared OBJECT
library, links into 5 per-dtype test executables; forwards
`-DCK_TILE_USE_OCP_FP8` when `CK_USE_OCP_FP8` is ON
- `test_mx_flatmm_base.hpp` — base test fixture with
`run_test_with_validation(M, N, K, kbatch=1)`
- `test_mx_flatmm_fixtures.hpp` — concrete `TestMXFlatmm` typed test
class and type aliases
- `test_mx_flatmm_fp{4fp4,8fp8,6fp6,8fp4,4fp8}.cpp` — per-dtype
`TYPED_TEST_SUITE` files
**Modified files:**
- `example/ck_tile/18_flatmm/mxgemm/mx_flatmm_arch_traits.hpp` — moved
`preShuffleWeight` here (was in `mx_flatmm.cpp`) so it is includeable by
both the example and the tests
- `example/ck_tile/18_flatmm/mxgemm/mx_flatmm.cpp` / `run_mx_flatmm.inc`
— removed `-split_k` CLI arg, hardcoded `k_batch=1`, fixed `k_split`
formula, updated call sites after `preShuffleWeight` move
- `test/ck_tile/CMakeLists.txt` — added `add_subdirectory(flatmm)`
---------
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
