## Changes
### Split-K support in `gemm_quant_kernel.hpp`
- **`SplitKBatchOffset`**: Added `aq_group_offset` and
`aq_k_split_offset` fields (mirroring the existing `bq_*` fields for B)
to track each split-K batch's position within the AQ scale tensor. For
`ABQuantGrouped`, both offsets are computed from `k_id * KRead` divided
by `AQuantGroupSize::kK`.
- **`MakeAQBlockWindow`**: Added an `aq_group_offset` parameter
(defaulting to 0 for non-split-K paths) so the AQ tensor view's K-group
dimension reflects only the remaining K-groups from the split-K offset,
consistent with how `MakeBQBlockWindow` handles the BQ tensor.
- **`RunGemm`**: Threads the `aq_k_split_offset` through to
`MakeAQBlockWindow` when in split-K mode.
### Constraints in `IsSupportedArgument()`
Four constraints gate split-K (`k_batch > 1`) for ABQuantGrouped:
1. **Mode check** — split-K is only allowed for `BQuantGrouped` (no
preshuffle) or `ABQuantGrouped` (no `APreshuffleQuant`). Any other quant
mode with `k_batch > 1` returns `false`.
2. **B quant group alignment** — `KRead` (per-batch K slice) must be
divisible by `BQuantGroupSize::kK`. Each batch must operate on complete
B quantization groups; a partial group would require splitting a scale
value across batches.
3. **A quant group alignment** (new, ABQuantGrouped only) — `KRead` must
also be divisible by `AQuantGroupSize::kK` for the same reason applied
to the AQ scale tensor.
4. **Minimum 2 K-tile iterations per batch** (new) — The
software-pipelined GEMM kernels (CompV3 family) prefetch one tile ahead,
so they require `per_batch_num_loop = KRead / KPerBlock >= 2`. When
`KRead == KPerBlock` (i.e. each batch is exactly one tile), the prefetch
reads into the next batch's memory region and produces incorrect
results. Configurations where `K == k_batch * KPerBlock` are therefore
rejected.
### Example update (`run_gemm_quant_example.inc`)
Updated the comment above the `IsSupportedArgument` call to document
that split-K is now supported for both `BQuantGrouped` (no preshuffle)
and `ABQuantGrouped` (no `APreshuffleQuant`).
## Unit Tests
Two new test files covering decode and prefill tile shapes across a
range of `k_batch` values (2–8), data types (FP8, BF8), and quantization
group sizes (1×1×128 and 1×128×128 for B):
- `test_gemm_quant_abquant_splitk_decode.cpp` — uses the decode tile
shape (M=16, N=64, K_tile=256)
- `test_gemm_quant_abquant_splitk_prefill.cpp` — uses the prefill tile
shape (M=128, N=128, K_tile=128)
Each test calls `run_test_with_validation` which runs the kernel and
checks correctness against a CPU reference. Configurations excluded from
tests are annotated with comments explaining which constraint they
violate (typically the `per_batch_num_loop >= 2` requirement).
## Prerequisites
This PR depends on #4429, which must be merged before this can be
merged.
---------
Co-authored-by: Erwin Terpstra <erwin.terpstra@streamhpc.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
## Proposed changes
Summary:
- Modified implementation for grouped_gemm_fixed_nk_bias
- FP16 WMMA examples
- WMMA instances
- Profiler for grouped_gemm_fixed_nk_bias
- Add WMMA instances to existing tests
**This PR depends on PR https://github.com/ROCm/rocm-libraries/pull/4299
and should be merged after it.
Only the last 6 commits are in the scope of this PR.**
## Checklist
Please put an `x` into the boxes that apply. You can also fill these out
after creating the PR. If you're not sure, please don't hesitate to ask.
- [x] I have added tests relevant to the introduced functionality, and
the unit tests are passing locally
- [x] I have added the test to REGRESSION_TESTS list defined at the top
of CMakeLists.txt in tests/CMakeLists.txt, **IF** the test takes more
than 30 seconds to run.
- [x] I have added inline documentation which enables the maintainers
with understanding the motivation
- [x] I have removed the stale documentation which is no longer relevant
after this pull request
- [ ] (If this change is user-facing) I have added release notes which
provide the end users with a brief summary of the improvement from this
pull request
- [x] I have run `clang-format` on all changed files
- [ ] Any dependent changes have been merged
## Discussion
If this is a relatively large or complex change, feel free to start a
discussion by explaining why you chose the solution you did and what
alternatives you considered
## Submission Checklist
- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
## Motivation
Improvements for CK Tile convolution builder run function and atol/rtol
calculations.
## Technical Details
- Add preprocessing function for wrw when k_batch is larger than 1 for
builder run function
- Divide num acums by number of groups to get real number of accums
## Test Plan
CI wrw tests
## Test Result
pending
## Submission Checklist
- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
AICK-783
## Motivation
This is causing a failing PR for Windows:
https://github.com/ROCm/TheRock/pull/3382
```
[composable_kernel configure] -- Jenga kernel files to be generated: B:\build\ml-libs\composable_kernel\build\example\ck_tile\50_sparse_attn\fmha_jenga_fwd_d128_fp16_batch_b128x128x32x128x32x128_r4x1x1_r4x1x1_w32x32x16_w32x32x16_qr_async_vr_psddv_nlogits_nbias_nmask_nskip_nsquant_ntrload.cpp;B:\build\ml-libs\composable_kernel\build\example\ck_tile\50_sparse_attn\fmha_jenga_fwd_d128_fp16_batch_b128x128x32x128x32x128_r4x1x1_r4x1x1_w32x32x16_w32x32x16_qr_async_vr_psskddv_nlogits_nbias_nmask_nskip_nsquant_ntrload.cpp;B:\build\ml-libs\composable_kernel\build\example\ck_tile\50_sparse_attn\fmha_jenga_fwd_d128_fp16_batch_b128x128x32x128x32x128_r4x1x1_r4x1x1_w32x32x16_w32x32x16_qr_async_vr_psddv_nlogits_nbias_mask_nskip_nsquant_ntrload.cpp;B:\build\ml-libs\composable_kernel\build\example\ck_tile\50_sparse_attn\fmha_jenga_fwd_d128_fp16_batch_b128x128x32x128x32x128_r4x1x1_r4x1x1_w32x32x16_w32x32x16_qr_async_vr_psskddv_nlogits_nbias_mask_nskip_nsquant_ntrload.cpp;B:\build\ml-libs\composable_kernel\build\example\ck_tile\50_sparse_attn\fmha_jenga_fwd_d128_bf16_batch_b128x128x32x128x32x128_r4x1x1_r4x1x1_w32x32x16_w32x32x16_qr_async_vr_psddv_nlogits_nbias_nmask_nskip_nsquant_ntrload.cpp;B:\build\ml-libs\composable_kernel\build\example\ck_tile\50_sparse_attn\fmha_jenga_fwd_d128_bf16_batch_b128x128x32x128x32x128_r4x1x1_r4x1x1_w32x32x16_w32x32x16_qr_async_vr_psskddv_nlogits_nbias_nmask_nskip_nsquant_ntrload.cpp;B:\build\ml-libs\composable_kernel\build\example\ck_tile\50_sparse_attn\fmha_jenga_fwd_d128_bf16_batch_b128x128x32x128x32x128_r4x1x1_r4x1x1_w32x32x16_w32x32x16_qr_async_vr_psddv_nlogits_nbias_mask_nskip_nsquant_ntrload.cpp;B:\build\ml-libs\composable_kernel\build\example\ck_tile\50_sparse_attn\fmha_jenga_fwd_d128_bf16_batch_b128x128x32x128x32x128_r4x1x1_r4x1x1_w32x32x16_w32x32x16_qr_async_vr_psskddv_nlogits_nbias_mask_nskip_nsquant_ntrload.cpp;B:\build\ml-libs\composable_kernel\build\example\ck_tile\50_sparse_attn\fmha_jenga_fwd_api.cpp
[composable_kernel configure] CMake Error at example/ck_tile/50_sparse_attn/CMakeLists.txt:61 (add_library):
[composable_kernel configure] Syntax error in cmake code when parsing string
[composable_kernel configure]
[composable_kernel configure] B:\build\ml-libs\composable_kernel\build\example\ck_tile\50_sparse_attn\fmha_jenga_fwd_d128_fp16_batch_b128x128x32x128x32x128_r4x1x1_r4x1x1_w32x32x16_w32x32x16_qr_async_vr_psddv_nlogits_nbias_nmask_nskip_nsquant_ntrload.cpp
[composable_kernel configure]
[composable_kernel configure] Invalid character escape '\b'.
```
## Technical Details
The file:
[fmha_fwd_appendkv.py](https://github.com/ROCm/rocm-libraries/compare/users/brockhargreaves-amd/ck/fix-windows-cmake-path-problem?expand=1#diff-bef22bf9ba21eb93c725493ecc7edcb6f2a8f0a9a173dcfca6bda7a9f4eced78)
writes a bunch of paths to a text file which is later parsed by cmake.
When passing a pathlib.Path to str(), str() converts to a native path,
in this case / to \\ on Windows which confuses cmake. In this case we
need to write paths with forward slashes and then pass those onward to
cmake.
## Test Plan
1. Ensure this doesn't impact existing CI.
2. Ensure compilation of Windows pass locally.
## Test Result
1. Passes existing CI
2. This fixes the compilation error locally.
## Submission Checklist
- [ x ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
## Motivation
Full build on Windows is currently broken due to compiler errors, this
PR should help fix that. This is also holding up the following PR in the
TheRock: https://github.com/ROCm/TheRock/pull/3382
## Technical Details
1. I don't see a good reason to be nesting a windows include inside the
ck_tile namespace. It was causing compiler errors too: Windows.h comes
with min and max, which was conflicting with ck_tile::min and
ck_tile::max, so I moved it out. I also defined NOMINMAX to prevent this
inclusion in the future.
2. The TRUE/FALSE macros are already used by Windows.h, which causes an
error. So I've opted for True/False. You can see this pattern in other
rocm-libraries.
3. The M_PI macro isn't available, at least in the WIN32_LEAN_AND_MEAN
context, from \<cmath\> on Windows. We'll be able to use
std::numbers::v_pi\<float\> when we have C++20 support.
4. There was a missing \<chrono\> include.
## Test Plan
Test locally and make sure this doesn't impact existing CI.
## Test Result
Compiles locally and passes existing ci.
## Submission Checklist
- [ x ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
## Motivation
Add support for grouped gemm multi ABD fixed NK. MR
## Technical Details
Changes from the reverted PR:
- Device struct for grouped gemm with multiple ABD and fixed NK
(DeviceGroupedGemm_Wmma_Multi_ABD_Fixed_NK).
- Wmma versions of existing example codes: 59_grouped_gemm_multi_ABD
- Unit tests for both new wmma implementation and the reference xdl code
(previously missing)
- Note: Some Xdl instances were commented out because of unit test
failures. As mentioned apparently for xdl this feature was missing tests
so our assumption is either there is an implemenetation bug or these
instances were not set up correctly. Has the potential for a follow-up
issue.
- Generic ck profiler interface with the purpose of calling unit tests.
- Gemm instances with specific elementwise operations for gemm bias gelu
calculations.
- Added class for grouped gemm multi ABD reference calculations.
Fix epilogue selection in device implementation that caused unit test
failures
## Test Plan
Covered by added unit tests
## Test Result
CI successfully passing
## Submission Checklist
- [ ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
---------
Co-authored-by: Zoltán Lakatos <zoltan.lakatos@streamhpc.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
## Proposed changes
Supported types combinations using BQuant=e8m0:
- A=bf16
- B=bf16,bf8,fp4
Summary:
- remove usage of `pk_fp4_raw_t`: consistent with other implementations
and avoid taking into account of the packed size explicitly. In general,
the raw type should not be used because CK Tile internally takes care of
the PackedSize, so using the raw type adds unnecessary complexity to the
implementation
- handle microscaling by checking for `e8m0` type for BQuant (previous
implementation was inconsistent)
- add support for scaling instructions in `DequantPack8`
- mx pipeline:
- extend existing pipeline to support different B types
- add support to scale and cast before writing to LDS or after reading
from LDS (this can be defined in the `Problem` by the user)
- block gemm:
- mx pipeline is now using block gemm BQuant
- block gemm BQuant can now load from LDS and apply scale and then call
block gemm universal operator. This adds new functionalities and remove
code duplication
- warp gemm:
- add case to support 128bit ds_read/write for both A and B when A=16bit
and B=8bit
- add examples and tests: note that some tests for bf16/fp4 already
existed but were removed during previous tests refactoring. I added them
again and other relevant tests for new types combinations
## Checklist
Please put an `x` into the boxes that apply. You can also fill these out
after creating the PR. If you're not sure, please don't hesitate to ask.
- [ ] I have added tests relevant to the introduced functionality, and
the unit tests are passing locally
- [ ] I have added the test to REGRESSION_TESTS list defined at the top
of CMakeLists.txt in tests/CMakeLists.txt, **IF** the test takes more
than 30 seconds to run.
- [ ] I have added inline documentation which enables the maintainers
with understanding the motivation
- [ ] I have removed the stale documentation which is no longer relevant
after this pull request
- [ ] (If this change is user-facing) I have added release notes which
provide the end users with a brief summary of the improvement from this
pull request
- [ ] I have run `clang-format` on all changed files
- [ ] Any dependent changes have been merged
## Discussion
If this is a relatively large or complex change, feel free to start a
discussion by explaining why you chose the solution you did and what
alternatives you considered
---
🔁 Imported from
[ROCm/composable_kernel#3689](https://github.com/ROCm/composable_kernel/pull/3689)
🧑💻 Originally authored by @EnricoDeg
---------
Co-authored-by: Enrico Degregori <enrico@streamhpc.com>
Co-authored-by: systems-assistant[bot] <systems-assistant[bot]@users.noreply.github.com>
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
Co-authored-by: Enrico Degregori <73224202+EnricoDeg@users.noreply.github.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
## Motivation
Currently, Stream-K has 3 reduction options: 1) atomics, 2) The
reduction described in the Stream-K paper, and 3) a tree reduction. The
reduction strategy described in the original Stream-K paper has the
starting workgroup of each tile sequentially accumulating partial
results of other contributing workgroups in the tile, which requires a
linear number of steps. Hence, for clarity, this works updates the
naming of the `StreamKReductionStrategy` enum members to better describe
the existing reduction strategy options.
## Technical Details
Prior to this change, the enum is as follows:
```cpp
enum StreamKReductionStrategy : uint32_t
{
Atomic = 0u,
Reduction = 1u,
TreeReduction = 2u
};
```
But, the distinction between `Reduction` and `TreeReduction` is not very
clear and has some redundancy.
Hence, the updated enum is as follows:
```cpp
enum StreamKReductionStrategy : uint32_t
{
Atomic = 0u,
Linear = 1u,
Tree = 2u
};
```
All references to `StreamKReductionStrategy` were updated to reflect
this change.
## Test Plan
No new functionality was added, so no new tests were added; I just
validated existing tests and examples.
## Test Result
All tests passed locally.
## Submission Checklist
- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
## Motivation
Add support of gfx11 architectures (RDNA3) to FMHA.
## Technical Details
Distributions (matrix elements to lane registers mapping) of gfx11 WMMA
are completely different from distributions of gfx9 MFMA and gfx12 WMMA.
There are two cases in FMHA where this difference matters:
* usage of results (matrix C) of one GEMM as input (matrix A) of another
GEMM.
* random number generation for dropout (implementation for gfx9 MFMA,
gfx12 WMMA and host validation produce the same results).
Both cases are solved by a special remapping implemented using
`__builtin_amdgcn_permlanex16` and `__builtin_amdgcn_perm`.
Additional changes:
* FMHA tests are now build and run only for those types for which
instances exist (gfx11 supports only fp16 and bf16).
* Two fixes for uninitialized values (`mask.sink` and
`do_fp8_static_quant`): they may contain garbage resulting in incorrect
dispatching logic, sometimes tests report that there are no instance
available for current parameters.
* Small fix to remove expcnt(0) from s_waitcnt instruction on gfx11 when
they are not requested (i.e. every time), likely has no effect on
performance but makes disassembly a bit clearer.
## Test Plan
```
ninja test_ck_tile_fmha
bin/test_ck_tile_fmha_fwd_fp16
bin/test_ck_tile_fmha_fwd_bf16
bin/test_ck_tile_fmha_bwd_fp16
bin/test_ck_tile_fmha_bwd_bf16
```
## Test Result
All tests must pass (some tests may be skipped).
## Submission Checklist
- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Reverts ROCm/rocm-libraries#4638
unfortunately, this PR interfered with the PR#4299 and caused build
errors for gfx11:
In file included from
/rocm-libraries/projects/composablekernel/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_wmma_fixed_nk_bf16_bf16_bf16_mk_kn_mn_instance.cpp:7:
In file included from
/rocm-libraries/projects/composablekernel/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_wmma_fixed_nk_instance.hpp:11:
/rocm-libraries/projects/composablekernel/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_wmma_fixed_nk.hpp:553:21:
error: no matching function for call to 'CheckValidity'
553 | if(!GridwiseGemm::CheckValidity(
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~
1. Add GetEstimateVgprCount to estimate the VGPR usage in
GridwiseGemm_wmma_cshuffle_v3
2. Add IsValidCompilationParameter to disable kernel which use too many
vgprs.
- Currently, the threashold is AvailableVgprCount * 1.25
3. Modify examples to avoid test is disabled on gfx11
It is port from internal repo
PR[#192](https://github.com/ROCm/composable_kernel/issues/192)
## Motivation
<!-- Explain the purpose of this PR and the goals it aims to achieve.
-->
## 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: illsilin_amdeng <Illia.Silin@amd.com>
## Proposed changes
This PR adds an RDNA4 implementation of the device_grouped_gemm_fixed_nk
instance library using for WMMA.
The implementation is based on the existing
DeviceGroupedGemm_Xdl_Fixed_NK design and reuses the same high-level
structure, but replaces the XDL kernel with a WMMA-based one. It uses
the GridwiseGemm_wmma_cshuffle_v3 kernel.
At this stage, the focus is functional correctness and compatibility,
not performance tuning.
## Technical Details
- Device struct for grouped gemm fixed NK
- Example code for the WMMA version
- Unit tests for both new wmma implementation and the reference XDL code
(previously missing)
- Generic ck profiler interface with the purpose of calling unit tests.
## Checklist
Please put an into the boxes that apply. You can also fill these out
after creating the PR. If you're not sure, please don't hesitate to ask.
- [x] I have added tests relevant to the introduced functionality, and
the unit tests are passing locally
- [x] I have added the test to REGRESSION_TESTS list defined at the top
of CMakeLists.txt in tests/CMakeLists.txt, **IF** the test takes more
than 30 seconds to run.
- [ ] I have added inline documentation which enables the maintainers
with understanding the motivation
- [ ] I have removed the stale documentation which is no longer relevant
after this pull request
- [x] (If this change is user-facing) I have added release notes which
provide the end users with a brief summary of the improvement from this
pull request
- [x] I have run on all changed files
- [x] Any dependent changes have been merged
## Discussion
If this is a relatively large or complex change, feel free to start a
discussion by explaining why you chose the solution you did and what
alternatives you considered
---
🔁 Imported from
[ROCm/composable_kernel#3668](https://github.com/ROCm/composable_kernel/pull/3668)
🧑💻 Originally authored by @bidlekm
---------
Co-authored-by: Marton Bidlek <marton.bidlek@streamhpc.com>
Co-authored-by: Erwin Terpstra <erwin.terpstra@streamhpc.com>
Co-authored-by: bidlekm <bidlekmarton@gmail.com>
Co-authored-by: assistant-librarian[bot] <assistant-librarian[bot]@users.noreply.github.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
## Motivation
This PR has 4 patches:
1. Fix the CI error of grouped gemm.
2. Fix the incompatibility of old linux version.
3. Fix the potential errors of flatmm.
4. Address the previous comments of abquant eight warps pipeline
solution.
---------
Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
This pull request introduces several improvements and fixes related to
quantized grouped GEMM (General Matrix Multiply) pipelines and their
supporting utilities.
# The numerical issue
## Steps to reproduce
```bash
Run
./bin/tile_example_gemm_weight_preshuffle -prec=fp8
./bin/tile_example_gemm_weight_preshuffle -prec=int4
```
# Solution
The main changes address type correctness, improve data layout and
shuffling logic, and expand test coverage to better validate different
GEMM configurations.
**Key changes include:**
### Data layout and shuffling logic
* Refactored the logic in `shuffle_b_permuteN` to use `constexpr`
variables for `KLane` and `ItemsPerAccess`, simplifying tile view
construction and correcting the permutation order for improved
efficiency and correctness (`tensor_shuffle_utils.hpp`).
* Fixed the calculation of `KLaneBytes` in weight preshuffle pipeline
policies to account for internal data type conversion (e.g., from
`pk_int4_t` to `fp8`), ensuring accurate memory access and alignment in
quantized GEMM policies (`wp_pipeline_agmem_bgmem_creg_base_policy.hpp`,
`gemm_wp_abquant_pipeline_ag_bg_cr_base_policy.hpp`).
[[1]](diffhunk://#diff-93f16cd76e6e24404777e682a5ac8e039913ddd6a438c7efd61fdda42276e4efL274-R275)
[[2]](diffhunk://#diff-9c3d0fc3c014feed435bfd93ba1f8f9fb3e054dcc322deada3addf70bee5a58cL100-R105)
### Test infrastructure enhancements
* Unit tests did not catch this issue since there were no tests for fp8.
Added new configuration structs (`config_mn_16x16`, `config_mn_32x32`)
to support additional GEMM tile shapes and updated tests to run with
these configurations for broader coverage
(`test_gemm_pipeline_util.hpp`).
[[1]](diffhunk://#diff-5a5962b2c4aa7f6a87d1d6201ad383135e30df13b42654e997d870d57420d5b8R86-R103)
[[2]](diffhunk://#diff-5a5962b2c4aa7f6a87d1d6201ad383135e30df13b42654e997d870d57420d5b8L255-R269)
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
## Proposed changes
Implement BQuantPreshuffle option for the ABQuant PreshuffleB pipeline.
## Checklist
Please put an `x` into the boxes that apply. You can also fill these out
after creating the PR. If you're not sure, please don't hesitate to ask.
- [X] I have added tests relevant to the introduced functionality, and
the unit tests are passing locally
- [X] I have added the test to REGRESSION_TESTS list defined at the top
of CMakeLists.txt in tests/CMakeLists.txt, **IF** the test takes more
than 30 seconds to run.
- [X] I have added inline documentation which enables the maintainers
with understanding the motivation
- [X] I have removed the stale documentation which is no longer relevant
after this pull request
- [ ] (If this change is user-facing) I have added release notes which
provide the end users with a brief summary of the improvement from this
pull request
- [X] I have run `clang-format` on all changed files
- [X] Any dependent changes have been merged
---
🔁 Imported from
[ROCm/composable_kernel#3687](https://github.com/ROCm/composable_kernel/pull/3687)
🧑💻 Originally authored by @ErwinTerpstra
---------
Co-authored-by: Erwin Terpstra <erwin.terpstra@streamhpc.com>
Co-authored-by: systems-assistant[bot] <systems-assistant[bot]@users.noreply.github.com>
## Motivation
This PR updates CK_TILE blockscale GEMM-quant kernels and launch helpers
to compile across multiple GPU architectures by introducing compile-time
availability gating and a new attribute tag mechanism for kernel
symbol/attribute specialization.
## Technical Details
- Add an architecture-guarded `kIsAvailable` flag to the gfx950 pipeline
and propagate availability handling into `QuantGemmKernel`.
- Extend `make_kernel`/`kentry` to accept an `Attr` tag enabling
per-kernel compile-time attributes (e.g., `no-packed-fp32-ops`) and
unique symbols.
- Update the blockscale GEMM quant example to pass kernel attributes and
adjust gfx950 gating.
## Test Plan
- CI
- Local test: `cmake .. --preset dev -DGPU_TARGETS='gfx942;gfx950'
-GNinja && ninja tile_example_gemm_quant`
- Local test with ROCm/aiter#1954
## Test Result
<!-- Briefly summarize test outcomes. -->
## Submission Checklist
- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
## Proposed changes
This PR enables group mode (variable-length attention) kernel generation
for PyTorch's CK SDPA backend.
## Checklist
Please put an `x` into the boxes that apply. You can also fill these out
after creating the PR. If you're not sure, please don't hesitate to ask.
- [X] I have added tests relevant to the introduced functionality, and
the unit tests are passing locally
- [ ] I have added the test to REGRESSION_TESTS list defined at the top
of CMakeLists.txt in tests/CMakeLists.txt, **IF** the test takes more
than 30 seconds to run.
- [ ] I have added inline documentation which enables the maintainers
with understanding the motivation
- [ ] I have removed the stale documentation which is no longer relevant
after this pull request
- [ ] (If this change is user-facing) I have added release notes which
provide the end users with a brief summary of the improvement from this
pull request
- [X] I have run `clang-format` on all changed files
- [ ] Any dependent changes have been merged
## Discussion
The change is minimal (single line deletion) but enables a significant
feature: variable-length attention support for ROCm users via PyTorch's
torch.nn.attention.varlen API.
---
🔁 Imported from
[ROCm/composable_kernel#3553](https://github.com/ROCm/composable_kernel/pull/3553)
🧑💻 Originally authored by @chinmaydk99
Co-authored-by: Chinmay_Kuchinad <ChinmayDattanand.Kuchinad@amd.com>
## Proposed changes
gemm blockscale eightwarps support
## Checklist
Please put an `x` into the boxes that apply. You can also fill these out
after creating the PR. If you're not sure, please don't hesitate to ask.
- [ ] I have added tests relevant to the introduced functionality, and
the unit tests are passing locally
- [ ] I have added the test to REGRESSION_TESTS list defined at the top
of CMakeLists.txt in tests/CMakeLists.txt, **IF** the test takes more
than 30 seconds to run.
- [ ] I have added inline documentation which enables the maintainers
with understanding the motivation
- [ ] I have removed the stale documentation which is no longer relevant
after this pull request
- [ ] (If this change is user-facing) I have added release notes which
provide the end users with a brief summary of the improvement from this
pull request
- [x] I have run `clang-format` on all changed files
- [x] Any dependent changes have been merged
## Discussion
If this is a relatively large or complex change, feel free to start a
discussion by explaining why you chose the solution you did and what
alternatives you considered
---
🔁 Imported from
[ROCm/composable_kernel#3650](https://github.com/ROCm/composable_kernel/pull/3650)
🧑💻 Originally authored by @kensclin
---------
Co-authored-by: KenSCLin <lshyhchy@amd.com>
Co-authored-by: Ding, Yi <yi.ding@amd.com>
Co-authored-by: systems-assistant[bot] <systems-assistant[bot]@users.noreply.github.com>
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
Added support for conv v6 pipeline in ck tile's convolution forward
kernel. CK Tile v6 pipeline is the equivalent to old ck's V5 pipeline
and should be faster than other pipelines for some cases. This PR also
adds tests inside profiler that's currently inside experimental
directory, so now we should be able to detect regressions easier.
---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: subhajitdchow <sduttach@amd.com>
Implement per-page K/V quantization for paged attention:
- Add KV_BLOCKSCALE enum to BlockAttentionQuantScaleEnum
- Use exp2 shift trick to eliminate explicit P scaling overhead
- Prefetch physical pages offset for KV cache, overlaps with
computations
## Proposed changes
Please describe the motivation behind the pull request, whether it
enables a new feature or fixes a bug. If there are associated pull
requests or issues, please link them to the pull request.
## Checklist
Please put an `x` into the boxes that apply. You can also fill these out
after creating the PR. If you're not sure, please don't hesitate to ask.
- [ ] I have added tests relevant to the introduced functionality, and
the unit tests are passing locally
- [ ] I have added the test to REGRESSION_TESTS list defined at the top
of CMakeLists.txt in tests/CMakeLists.txt, **IF** the test takes more
than 30 seconds to run.
- [ ] I have added inline documentation which enables the maintainers
with understanding the motivation
- [ ] I have removed the stale documentation which is no longer relevant
after this pull request
- [ ] (If this change is user-facing) I have added release notes which
provide the end users with a brief summary of the improvement from this
pull request
- [ ] I have run `clang-format` on all changed files
- [ ] Any dependent changes have been merged
## Discussion
If this is a relatively large or complex change, feel free to start a
discussion by explaining why you chose the solution you did and what
alternatives you considered
---
🔁 Imported from
[ROCm/composable_kernel#3696](https://github.com/ROCm/composable_kernel/pull/3696)
🧑💻 Originally authored by @Jeff-Huang
---------
Co-authored-by: Jeff Huang <chiachi.huang@amd.com>
Co-authored-by: Illia Silin <Illia.Silin@amd.com>
* [Compiler] Addressing new compiler warnings
Clang enables new lifetime warnings in production and we see build
errors due to this with the staging compiler.
The attributes added in this PR are suggested by the compiler. However,
I'm not very familiar with the code base, so the changes may be
incorrect.
* Update some more instances
* Adds file-level ignores via clang diagnostic pragma
The number of instances was large, so I decided to use file-level scope
to disable the warning via pragma clang diagnostic ignored.
It also showed this warning coming from the gtest dependency. For that,
I did add the respective command line flag to the CMake variables. I
don't know if this is acceptable or not.
* This adds the remaining instances
For a build on gfx90a.
* fix clang format
* Adding couple more instances from gfx1200 build
* Fixed another few instances
---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
[ROCm/composable_kernel commit: 069500464d]
* Adding remaining flavors for grouped conv fwd
As titled. Following variants are added:
- grouped_conv2d_fwd_dynamic_op
- grouped_conv3d_fwd_dynamic_op
- grouped_conv3d_fwd_bilinear
- grouped_conv3d_fwd_convscale
- grouped_conv3d_fwd_convinvscale
- grouped_conv3d_fwd_convscale_add
- grouped_conv3d_fwd_convscale_relu
- grouped_conv3d_fwd_scale
- grouped_conv3d_fwd_combconvscale
- grouped_conv3d_fwd_scaleadd_scaleadd_relu
* Fix incomplete parsing of types from source names in add_instance_library() cmakelists function so we don't build f8 on RDNA3.
* Do not build f8 / bf8 only flavor tests on RDNA3
* Make sure we have proper generic instances for all instance lists related to the post-ces extra flavors, with scalarPerVector = 1. Then disable all but one generic instance per instance list to reduce compile time.
* Post rebase fix: Template parameters for Grouped Conv Fwd Device Impl got tweaked upstream.
* adding int8 and fp16 overloads to the elementwise operations
* fixed copilot nits
* Addressing review comments:
- removed unnecessary examples for dynamic op
- removed unnecessary conv specalizations for all the flavors
- removed spurious bilinear and scale source files
* clang-format
* reduced no of tests
---------
Co-authored-by: Wojciech Laskowski <wojciech.laskowski@streamhpc.com>
[ROCm/composable_kernel commit: 2377a62837]
* chore: split block scale example instances in more separate files to speed up compile times
* wip: fp4 scaffolding for abquant
* feat: add fp4 decoding-while-loading to abquant pipeline
* feat: add support for fp4 CPU verification in abquant
* chore: add time tracking to reference calculation
* feat: add a4w4 test for blockscale gemm
* feat: optimize reference calculation by preconverting values to AccType
* feat: add fp4 to fp8 look-up table
* fix: reference to wrong ComputeDataType field in QuantProblem
* feat: type utilities for determining MFMA compute types
* feat: packed fp4 for abquant weight preshuffle
* feat: add separate tests for a4w4 base case, padding and preshuffleB
* fix: fp4 conversion on gfx950 attempting to use non-supported method
* fix: test case was using quant group sizes which don't work on gfx950 due to larger mfma tile size
* chore: add fp4 preshuffleb mode to block scale example
* chore: sanity check for packed types being 1 byte
* chore: clarify tensor dimension indices with constants
* chore: replace traits check with specialized check for packed types
* style: some minor refactoring and cleanup
* fix: correct conversion table for FNUZ fp8
* chore: add fp4 instances to main abquant instances again
* chore: use same initialization branch for int4 and fp4
* chore: add missing initialization for fp4 in block scale gemm example
---------
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
[ROCm/composable_kernel commit: 6a6177a246]
* Add multi AB support to wave transfer
* Improviments to multi ABD examples
* Add instances and use intrawave v1 instead of interwave
* Apply changes to other transfers
* Wave transfer: add support for multiple internal vgpr buffers
* Fix compilation error gfx11
[ROCm/composable_kernel commit: f16d9100e4]
* initial commit
* preshuffleQuant support for ABQuant
* fix mxfp4 to use correct QuantGroupSize
* addressing review comments and seperated Preshufflequant for A and B
* updated grouped gemm example for updated traits definition
* fix for CI failure
* updated grouped_gemm_abquant test for updated traits definition
* updated grouped_gemm_abquant test for updated traits definition
[ROCm/composable_kernel commit: 9b168082b7]
* Add padding support with transpose
Also move check before writing storing is_src_valid during reading
* Add/modify instances to use wave transfer for gemm universal
Condition is changed so now the vectorsize of vmem reading and lds
writing must be equal to 8 in order to use the wave transfer
* Fix clang format
* Modify example
* Fix bwd data
* Add restriction for wave transfer with padding and transpose
Add test case which shows this limitation
* Fix validity checks 8 bit types
* Add validity check gemm_bias_add_reduce
* Add validity check grouped gemm tile loop
* Fix validity checks new flavours
* Minor fixes
* Fix clang format
[ROCm/composable_kernel commit: 2e49b6b2f7]
* WIP: host level interwave pipeline compiles
* WIP: interwave implementation computes correct GEMM result when no aquant
* WIP: quantization works for subset of problem shapes
* WIP: quantization works for subset of problem shapes
* WIP: interwave memory pipeline passes local test
* feat: Add interwave pipeline implementation for memory pipline in aquant
* test: add unit test for aquant memory pipeline
* WIP: host level interwave pipeline compiles
* WIP: interwave implementation computes correct GEMM result when no aquant
* WIP: quantization works for subset of problem shapes
* WIP: quantization works for subset of problem shapes
* WIP: interwave memory pipeline passes local test
* feat: Add interwave pipeline implementation for memory pipline in aquant
* fix: compilation error on gfx950
* chore: remove debug statements from the code
* test: resolve merge conflict
* test: remove non rcr unit tests from test suite
[ROCm/composable_kernel commit: b8751e505d]
* add block scale parameters to kernel
* add block scale to kernel
* add smoke test
* format
* Revert "format"
This reverts commit 356c3c9706.
* only format my code
* format py
* fix auto not allowd in function prototype
* change instance tttt to ttff
* fix structured binding issue
* change s_acc elementwise op
* async pipeline add block scale
* add quantation P using shift exp2
* precompute (m - shift) once per row
* change blk scale seqstrt ptr name
* fix some name
* fix for deduction guide
* fix some comments
* add P scale to qr_ksvs_pipeline
* add comment to idx_identity
* change the method of calculating descale block index
* unify naming style: use block_scale_ as name prefix
* unify naming style
* update the CHANGELOG.md
* Add FP8 block scale quantization support for FMHA forward kernel
---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
[ROCm/composable_kernel commit: dd0b4294af]
* wip: test suite for batched gemm multiple d gemm multiple d, working on gridwise implenentation
* wip: many fixes in implementation of batched gemm gemm multiple d
* wip: batched gemm gemm multiple d gridwise op compiling, not working yet
* fix: incorrect d0 grid indexing in batched gemm gemm multipled
* feat: add instances for batched gemm add relu gemm add
* chore: configure instance with low vector transfer size for odd sizes
* chore: add some more validation to device batched gemm gemm multiple d, and removed template parameter that didn't really make sense
* fix: upate device_batched_gemm_gemm_wmma to work with new gridwise changes
* fix: disable odd size tests on XDL archs
* chore: removed temporary logging
* chore: update some references to C tensor to E tensor
* Tentative fix for example template params
* Tentative fix for non-multi-D batched gemm gemm device impl.
* Tentative fix for xdl example template params
* Tentative fix for profiler build on gfx90a
* chore: improve device batched gemm gemm multi D comment to include all ops and dimensions
* chore: explicitly call ck::make_tuple to prevent issues when std::make_tuple would apply
* fix: make the gemm1 data types match what happens in the device op
* feat: add d0s/d1s datatypes and layouts to the device op type string
* chore: change element-wise op so addition happens in fp32
* chore: add static asserts for gemm0/gemm1 calculated wave sizes
* chore: also updated other element-wise ops to use fp32 calculations
* chore: log number of supported instances
* chore: update instance comment
* chore: disable kernel timing in example by default
* fix: gemm1 wave size calculation
* fix: make sure batched gemm multiple d gemm multiple d profiler performs correct type conversions
* chore: remove increased tolerance in batched gemm gemm multiple d example
* chore: add comment explaining that verification fails for certain input values
* chore: clarify instance comment
---------
Co-authored-by: kiefer <kiefer.van.teutem@streamhpc.com>
[ROCm/composable_kernel commit: d5ae81b292]
Add signal-based synchronization for persistent GEMM kernels where
input data becomes available incrementally. Uses modulo wraparound
(like PyTorch's AsyncMM) for chunk index calculation:
chunk_idx = ((tile_idx + tile_idx_pivot) / tiles_per_chunk) % num_chunks
Key components:
- PersistentAsyncInputScheduler struct with tiles_per_chunk_m,
chunk_signals, tile_idx_pivot_m, and num_chunks fields
- wait_eq_wave method using __builtin_amdgcn_s_sleep for power efficiency
- IsSupportedArgument validation for scheduler parameters
- Example demonstrating async input scheduling with simulated producer
- GTest unit tests covering all layout combinations
[ROCm/composable_kernel commit: 91b4102a59]
* Add support to fp16 + compute fp16 and bf16 + compute bf16 contractions
Enables hipTensor to access the WMMA HW functionalities
for these combinations of datatype on gfx11 and gfx12.
* Fix change to contraction scale tests
* Fix clang-format
[ROCm/composable_kernel commit: 7d8bca7ddc]
* feat: test setup for batched contraction (aka batched gemm multiple d e permute)
* wip: device struct for WMMA batched contraction multiple d based on new gridwise op
* feat: working batched contraction on RDNA, non-naive tensor descriptors for gridwise_gemm_wmma_cshuffle_v3, test setup for odd cases
* fix: failure to resolve template parameters when calling new function overload
* fix: passing reference type as parameter instead of underlying types
* fix: merge error caused duplicate definitions
* fix: make sure constness of template and parameters types match
* fix: don't compile batched contraction test on unsupported architectures
* feat: add example for new wmma implementation, and consolidate example code between platforms
* style: return inline instead of with branch
* chore: add extra assert on vector memory access sizes
* chore: clean up some unused variables
* fix: correct tail number calculation, added small cases and extra instances to the test
* fix: properly support wave transfer by generating correct grid descriptors dependent on the transfer method
[ROCm/composable_kernel commit: fe40a5d139]
