Update all version indicators to 1.8.0.

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>

Matthew Bentham authored Apr 24, 2025 and Anton Bondarenko committed Apr 24, 2025

Related to #9 - allows some tests to run when the CPU doesn't have bfloat16 support, by reducing need for bfloat16 support in the test framework.

Use of bfcvt in the test framework is replaced by simple truncation - this will effectively
round towards 0.

Add a few tests for negative numbers in the test framework BFloat16 code, and allow running the
unit tests for the framework code on CPUs without bfloat16 hardware support.

Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>

Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Approved-by: Anton Bondarenko <anton.bondarenko@arm.com>

Suhail M authored Apr 24, 2025 and Jakub Sujak committed Apr 24, 2025

- Adds packing and matmul kernels for FP32 SME Indirect GEMM
- Adds tests for Indirect Gemm with FP32 inputs/outputs.

Signed-off-by: Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com>

Reviewed-by: Anton Bondarenko <anton.bondarenko@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-by: Mohammed Suhail Munshi <mohammedsuhail.munshi@arm.com>
Reviewed-by: Emil Ohlsson <emil.ohlsson@arm.com>
Approved-by: Emil Ohlsson <emil.ohlsson@arm.com>

Jens Elofsson authored Apr 24, 2025 and Jakub Sujak committed Apr 24, 2025

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Anton Bondarenko <anton.bondarenko@arm.com>
Approved-by: Jakub Sujak <jakub.sujak@arm.com>

This change bundles some cleanup done while doing FP16 IGEMM work. The
main change is the reduced output from the comparison function, which
instead of printing each differing value on a new line instead bundles
them on a per matrix row, with some block description. Also, the output
is only printed if there is a mismatch

Signed-off-by: Emil Ohlsson <emil.ohlsson@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>

The QAI8 interface doesn't match the interface of the actual kernel.
This change changes the interface to align with the kernel, and then
enforces the interface alignment using unit testing.

Signed-off-by: Emil Ohlsson <emil.ohlsson@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>
Approved-by: Anton Bondarenko <anton.bondarenko@arm.com>

This change introduces three new kernels
* `kai_lhs_imatmul_pack_x16p2vlx2_x16p_sme`
* `kai_rhs_imatmul_pack_kxn_x16p2vlx2b_x16_x16_sme`
* `kai_imatmul_clamp_f16_f16p2vlx2_f16p2vlx2_2vlx2vl_sme2_mopa`

These are used for indirect matmul, for 16-bit floating point data.

This change also adds unit testing for the FP16 imatmul kernels. The
code is written in a type agnostic manner, as to easily allow testing
for other data types with very low effort. This required the addition of
non-templated `read`/`write` functions, as to allow runtime-generic
access.

Signed-off-by: Emil Ohlsson <emil.ohlsson@arm.com>

Reviewed-by: Anton Bondarenko <anton.bondarenko@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-by: Emil Ohlsson <emil.ohlsson@arm.com>
Approved-by: Anton Bondarenko <anton.bondarenko@arm.com>

There are few cleanups for QAI8 that were discovered while doing FP16
work. This change bundles these cleanups

Signed-off-by: Emil Ohlsson <emil.ohlsson@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>

This change moves the QAI8 static initializations to lazy, C++17
compliant, initializations. This change also makes use of kernel
interfaces, as to make sure they're exercised

Signed-off-by: Emil Ohlsson <emil.ohlsson@arm.com>

Approved-by: Jens Elofsson <jens.elofsson@arm.com>

* Our SME kernels are compiled with auto-vectorization disabled,
  but the linker is unable to respect this flag, which can
  cause miscompilation and result in illegal instruction.

Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>

Approved-by: Emil Ohlsson <emil.ohlsson@arm.com>

Evie Wright authored Apr 15, 2025 and Jakub Sujak committed Apr 15, 2025

Signed-off-by: Evie Wright <evie.wright@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>

Update all version indicators to 1.7.0.

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Emil Ohlsson <emil.ohlsson@arm.com>

The get_lhs_offset function pointer type
in f32_bf16p_bf16p is fixed to read get_lhs_packed_offset
as the LHS is packed as well.

Signed-off-by: Felix Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>

Anitha Raj authored Apr 11, 2025 and Viet-Hoa Do committed Apr 11, 2025

Micro-kernels to compute the matrix multiplication of dynamically quantized asymmetric signed 8-bit integer with per-channel quantization (QAI8DX) LHS matrix and quantized symmetric 4-bit signed integer with per-channel quantization (QSI4CX) RHS matrix and the accumulation of the result into a half-precision (F16):

Matrix multiplication (MxN) Micro-kernels of QAI8DX LHS and QSI4CX RHS with F16 output, optimized for FEAT_I8MM and FEAT_DotProd. 
Matrix multiplication (1xN) Micro-kernels of QAI8DX LHS and QSI4CX RHS with F16 output, optimized for FEAT_DotProd.

Signed-off-by: Anitha Raj <anitha.raj@arm.com>

Signed-off-by: Evie Wright <evie.wright@arm.com>

Approved-by: Viet-Hoa Do <viet-hoa.do@arm.com>

Static initialization has no guaranteed order, which may cause test
listing to be initialized before the list of kernels.

This fixes unit tests
- matmul_clamp_f32_bf16p_bf16p_test
- matmul_clamp_f16_bf16p_bf16p_test

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Anton Bondarenko <anton.bondarenko@arm.com>

* Writing to one union member and reading the other union member
  is considered undefined behavior, therefore we need to avoid it.

Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>

Approved-by: Emil Ohlsson <emil.ohlsson@arm.com>

Anitha Raj authored Apr 09, 2025 and Anton Bondarenko committed Apr 09, 2025

Micro-kernels to compute the matrix multiplication of dynamically quantized symmetric signed 8-bit integer with per-block quantization (QSI8D32) LHS matrix and quantized asymmetric 4-bit signed integer with per-block quantization (QAI4C32) RHS matrix and the accumulation of the result into a single-precision (F32) and half-precision (F16) output:

- Matrix multiplication (MxN) Micro-kernels of QSI8D32 LHS and QAI4C32 RHS with F32 output, optimized for FEAT_I8MM.
- Matrix multiplication (1xN) Micro-kernels of QSI8D32 LHS and QAI4C32 RHS with F32 output, optimized for FEAT_DotProd.
- Matrix multiplication (MxN) Micro-kernels of QSI8D32 LHS and QAI4C32 RHS with F16 output, optimized for FEAT_I8MM.
- Matrix multiplication (1xN) Micro-kernels of QSI8D32 LHS and QAI4C32 RHS with F16 output, optimized for FEAT_DotProd.

Signed-off-by: Anitha Raj <anitha.raj@arm.com>

Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Reviewed-by: Anitha Raj <anitha.raj@arm.com>
Reviewed-by: Anton Bondarenko <anton.bondarenko@arm.com>
Approved-by: Anton Bondarenko <anton.bondarenko@arm.com>

This change introduces three new kernels:

* kai_imatmul_clamp_qai8_qai8p2vlx4_qsi8cxpsb2vlx4_2vlx2vl_sme2_mopa
* kai_lhs_imatmul_pack_x8p2vlx4_x8p_sme
* kai_rhs_imatmul_pack_kxn_qsi8cxp2vlx4sb_qs8cx_f32_i32_sme

These kernels are used for _indirect matmul_. The big difference between
these kernels and matmul kernels is that the LHS packing kernel takes an
indirection buffer where each pointer refers to a chunk in K dimension.
The pointers are laid out in a packed manner, where instead of being in
row major order, a column of `get_m_step` chunk pointers are placed
linearly in indirection buffer.

In addition to the kernels themselves, the
`matmul_clamp_qai8_qai8p_qsi8cxp_test.cpp` is extended to perform
testing of these new kernels. The testing flow for these new kernels is
a bit different, in that the packing kernels themselves are not directly
tested, instead only end-to-end flow is tested.

Signed-off-by: Emil Ohlsson <emil.ohlsson@arm.com>
Signed-off-by: Felix Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com>
Signed-off-by: Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com>

Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Reviewed-by: Anton Bondarenko <anton.bondarenko@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-by: Emil Ohlsson <emil.ohlsson@arm.com>
Approved-by: Jakub Sujak <jakub.sujak@arm.com>

There is an issue where the order of static initializations has no
guaranteed order, which can cause test listing to be initialized before
list of kernels. This can be solved by lazily initialize kernel lists on
first use.

This patch applies this fix for `matmul_test.cpp`

Signed-off-by: Emil Ohlsson <emil.ohlsson@arm.com>

Approved-by: Anton Bondarenko <anton.bondarenko@arm.com>

- Remove designated initializers for matmul_clamp_f32_qai8dxp_qsi4cxp_test
to comply with C++17 standard.

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Viet-Hoa Do <viet-hoa.do@arm.com>

* FP16 and BF16 classes are implemented in assembly so the rest
  of the test framework doesn't need to be compiled with FP16
  and BF16 support anymore. It allows the test to be run
  on system with base architecture.
* Remove unnecessary feature guard in kernel header file.
  The user of our API must not need to compile their code
  with BF16 support.

Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>

Removes designated initializers from
- matmul_test.cpp
- matmul_clamp_f16_bf16p_bf16p_test.cpp
- matmul_clamp_f32_bf16p_bf16p_test.cpp

Following changes are made to the test framework:
- Added default value to data_type in DataFormats constructor
- Initialize members of struct MatMulMethod
- Add '-Wpedantic' as a build flag to the affected unit tests

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Reviewed-by: Anton Bondarenko <anton.bondarenko@arm.com>
Reviewed-by: Emil Ohlsson <emil.ohlsson@arm.com>
Approved-by: Emil Ohlsson <emil.ohlsson@arm.com>

Although `hw.optional.AdvSIMD` is the replacement for `hw.optional.neon`, this parameter is not always present in different versions of
the OS. This may lead to the test suite crashing or tests being erroneously skipped.

Instead, we check if the machine supports `hw.optional.arm64` and, if
true, we can assume Advanced SIMD support is always present.

Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>

Approved-by: Viet-Hoa Do <viet-hoa.do@arm.com>

Update all version indicators to 1.6.0.

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>

Dan Johansson authored Mar 26, 2025 and Emil Ohlsson committed Mar 26, 2025

Optimizes this RHS packing by vectorizing the XOR operation. This is done
for segment lenghts of 4 or 8 bytes. The unoptimized path is used for
any other segment length.

Signed-off-by: Dan Johansson <dan.johansson@arm.com>

Approved-by: Emil Ohlsson <emil.ohlsson@arm.com>

* The flag is set incorrectly that disables activation function
  in the GEMV asssembly kernel.
* Test is updated to drive the clamping parameters properly.
  - The clamping parameter is set to reduce 20% the dynamic range
    of the output.

Resolves: KLEIDIAI-545

Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>

* Alias the KleidiAI target for consistent linking to KleidiAI with `KleidiAI::kleidiai`.
* Add install instructions for the KleidiAI library target and its public headers.
* Export the KleidiAI target so that projects may use the imported target with `find_package()`.

Usage:

Install KleidiAI:
```
cmake -S . -B build
cmake --build build
cmake --install build
```

Once installed, KleidiAI can be imported and linked to using `find_package()`.

```
find_package(KleidiAI CONFIG REQUIRED)
target_link_libraries(my_framework PRIVATE KleidiAI::kleidiai)
```

Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>

Approved-by: Viet-Hoa Do <viet-hoa.do@arm.com>

Jens Elofsson authored Mar 12, 2025 and Emil Ohlsson committed Mar 12, 2025

Update all version indicators to 1.5.0.

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Felix Johnny Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com>

Anitha Raj authored Mar 12, 2025 and Emil Ohlsson committed Mar 12, 2025

Fix for reading LHS scale values from in kai_matmul_clamp_f32_qsi8d32p1vlx4_qsi4c32p4vlx4_1vlx4vl_sme2_mopa

Fix the out-of-bounds read while loading the scale values from LHS packed matrix in \`kai_matmul_clamp_f32_qsi8d32p1vlx4_qsi4c32p4vlx4_1vlx4vl_sme2_mopa\` by updating the predicate

Resolves: KLEIDIAI-507

Signed-off-by: Anitha Raj <anitha.raj@arm.com>

Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Reviewed-by: Emil Ohlsson <emil.ohlsson@arm.com>
Approved-by: Emil Ohlsson <emil.ohlsson@arm.com>

Anton Bondarenko authored Mar 11, 2025 and Felix Johnny Thomasmathibalan committed Mar 11, 2025

Build system robustness improved by several methods:
* Mark standard 'build' folder as ignored. This helps
when doing different builds from a same folder
* Combine source files for assembler kernels in same
targets
* Add sorting for new kernel lists
* Relax clean step in CI for faster builds

Signed-off-by: Anton Bondarenko <anton.bondarenko@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Emil Ohlsson <emil.ohlsson@arm.com>

Analyzing skip test w/o a proper report message is hard.
Providing more details helps with that.

Signed-off-by: Anton Bondarenko <anton.bondarenko@arm.com>

Approved-by: Jakub Sujak <jakub.sujak@arm.com>

A couple of cleanups were done while adding support for QAI8 GEMV, these
have been moved out to this patch
* Sorts file lists in `CMakeLists.txt`
* Add additional test shapes
* Minor readability tweaks

Signed-off-by: Emil Ohlsson <emil.ohlsson@arm.com>

Approved-by: Anton Bondarenko <anton.bondarenko@arm.com>

This flag have been removed from CMakeLists.txt, but accidentally left
in kai_defs.bzl.

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Anton Bondarenko <anton.bondarenko@arm.com>

Change type of rhs_zero_point to uint8_t to match the data type in the
kai_rhs_pack_qs4cxs1s0_param-struct.

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Anton Bondarenko <anton.bondarenko@arm.com>

The argument to std::mt19937:s constructor is uint32_t, but the supplied
value (the variable "seed") was uint64_t. This has been changed to uint32_t.

Signed-off-by: Jens Elofsson <jens.elofsson@arm.com>

Approved-by: Anton Bondarenko <anton.bondarenko@arm.com>

Jakub Sujak authored Feb 24, 2025 and Felix Johnny Thomasmathibalan committed Feb 24, 2025

* Refactor the benchmark tool to create a generic abstraction that
allows for running matrix multiplication micro-kernels with different
interfaces.

* Extend benchmark support to all matrix multiplication micro-kernels in
 the library.

Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>

Approved-by: Felix Johnny Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com>

Jakub Sujak authored Feb 24, 2025 and Felix Johnny Thomasmathibalan committed Feb 24, 2025

This flag is a stylistic option in GCC and does not add to security
hardening.

Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>

Approved-by: Felix Johnny Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com>

Michael Kozlov authored Feb 20, 2025 and Felix Johnny Thomasmathibalan committed Feb 20, 2025

- Add new assembly ukernel optimized with FEAT_I8MM for matrix multiplication with 4x8 block size.
- Update build script.
- Add to unit test.

Signed-off-by: Michael Kozlov <michael.kozlov@arm.com>

Approved-by: Felix Johnny Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com>