Emil Ohlsson authored Jan 29, 2025 and Anton Bondarenko committed Jan 29, 2025

Update all version indications

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

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

Jens Elofsson authored Jan 28, 2025 and Jakub Sujak committed Jan 28, 2025

Remove fp32 and fp16 scale datatypes from
- kai_rhs_pack_kxn_qsi4c32p_qsu4c32s1s0
- kai_rhs_pack_nxk_qsi4c32p_qsu4c32s1s0

since they aren't being used and just creates more maintenance work.

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

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

Version 6.5 does not support conlyopts for cc_library and C only
options need to be handled in a different way

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

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

Michael Kozlov authored Jan 28, 2025 and Felix Johnny Thomasmathibalan committed Jan 28, 2025

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

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

Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Approved-by: Jakub Sujak <jakub.sujak@arm.com>

All licenses in the LICENSES directory apply equally to the distribution of KleidiAI.

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

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

Anitha Raj authored Jan 27, 2025 and Jakub Sujak committed Jan 27, 2025

In kai_matmul_clamp_f32_qai8dxp1vlx8_qsi4cxp4vlx8_1vlx4vl_sme2_mopa:
 * Fix the offset calculation
 * Fix pointer increments in the matmul

Add new shapes to unit tests, to test n > 64

Resolves: #KLEIDIAI-405, #COMPMID-7918

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: Emil Ohlsson <emil.ohlsson@arm.com>
Approved-by: Jakub Sujak <jakub.sujak@arm.com>

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

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

Anitha Raj authored Jan 27, 2025 and Emil Ohlsson committed Jan 27, 2025

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

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

Downstream projects might not build with same toolchain, which might
trigger warnings. Instead of treating these warnings as errors, using
this patch they are only warnings.

Also, add `-Werror` to the build flags to our testing pipeline, because
we do not want to accidentally introduce new warnings by mistake

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

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

Mention recent fixes for compiler warnings produced by enabling the `-Wcast-qual -Wmissing-prototypes -Wstrict-prototypes -Woverlength-strings` compiler options.

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

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

- Enable "-Wmissing-prototypes" compiler warning flag in the CMake and Bazel build scripts to catch missing prototypes. Additionally, enable "-Wstrict-prototypes" option.

- Expose missing prototypes in the public API.

- Resolve conflicting prototypes by aligning the definition to the declaration.

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

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

Translation of a 1x1 Convolution into a GEMM use case
is shown along with breaking the output matrix calculation
into smaller blocks as per the underlying microkernel used.

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

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

Overlength strings are unavoidable with inline assembly blocks. Disable the diagnostic inline to not flag this warning up to -Wall -Wextra builds.

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

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

It's important that type casts do not remove type qualifiers such as const.

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

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

Remove compiler options that had unnecessarily disabled certain compilation warnings.

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

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

Gian Marco Iodice authored Jan 20, 2025 and Felix Johnny Thomasmathibalan committed Jan 20, 2025

Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>

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

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

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

Gian Marco Iodice authored Jan 16, 2025 and Emil Ohlsson committed Jan 16, 2025

- Previously, we were dividing m_idx/n_idx by m_step/n_step. However, since m_step/n_step can be different from mr/nr, we should divide by mr/nr instead

Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>

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

Reviewed-by: Anitha Raj <anitha.raj@arm.com>
Reviewed-by: Emil Ohlsson <emil.ohlsson@arm.com>
Approved-by: Emil Ohlsson <emil.ohlsson@arm.com>

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

* Read the CPU system registers provided by the operating system
  to detect CPU features.

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

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

Gian Marco Iodice authored Jan 13, 2025 and Viet-Hoa Do committed Jan 13, 2025

- Add clamp to int8_min and int8_max to avoid saturation of the result

Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>

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

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

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

Describe changes since 1.1.0

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

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

Emil Ohlsson authored Jan 10, 2025 and Felix Johnny Thomasmathibalan committed Jan 10, 2025

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

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

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

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

This reverts commit 048daeb9.

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

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

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

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

Suhail M authored Jan 07, 2025 and Felix Johnny Thomasmathibalan committed Jan 07, 2025

- Adds support for BF16 SME2 GEMM Operations
- Adds Packing kernels for BF16 SME2
- Adds tests for BF16 SME2 GEMM Kernels

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

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

Pass the right CPU feature check for unit test.

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

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

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

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

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

Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Approved-by: Jens Elofsson <jens.elofsson@arm.com>

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

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

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

Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Approved-by: Jakub Sujak <jakub.sujak@arm.com>

* Bump revision of REUSE pre-commit hook to latest.

* Lint only committed files for the correct copyright and license. This prevents the pre-commit hook from failing checks on new files in the source tree that are not intended to be committed.

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

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

Suhail M authored Jan 02, 2025 and Felix Johnny Thomasmathibalan committed Jan 02, 2025

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

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

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

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

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

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

Anitha Raj authored Dec 24, 2024 and Jakub Sujak committed Dec 24, 2024

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

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

Emil Ohlsson authored Dec 24, 2024 and Jakub Sujak committed Dec 24, 2024

Restructure int8 testing to run each kernel in isolation based only on
reference data

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

Reviewed-by: Emil Ohlsson <emil.ohlsson@arm.com>
Approved-by: Felix Johnny Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com>

Michael Kozlov authored Dec 24, 2024 and Jakub Sujak committed Dec 24, 2024

- Add unit tests for new microkernels

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

Reviewed-by: Anitha Raj <anitha.raj@arm.com>
Reviewed-by: Anton Bondarenko <anton.bondarenko@arm.com>
Approved-by: Jakub Sujak <jakub.sujak@arm.com>