Jens Elofsson authored Feb 18, 2025 and Jakub Sujak committed Feb 18, 2025

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

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

Update all version indicators to 1.4.0.

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

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

Jens Elofsson authored Feb 18, 2025 and Felix Johnny Thomasmathibalan committed Feb 18, 2025

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

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

lhs stride is removed from
kai_run_matmul_clamp_qai8_qai8_qsi8cxp2vlx4sb_1x16vl_sme2_dot

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

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

Michael Kozlov authored Feb 17, 2025 and Felix Johnny Thomasmathibalan committed Feb 17, 2025

- Add new assembly ukernel optimized with FEAT_DOTPROD for matrix multiplication with 1x8 block size.
- Update build script.
- Add to unit test.

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

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

Emil Ohlsson authored Feb 17, 2025 and Jakub Sujak committed Feb 17, 2025

Add support for GEMV like kernel for producing QAI8 from QAI8 LHS and
QSI8CXP packed RHS.

Update unit tests to include support for new kernel

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

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

Anton Bondarenko authored Feb 17, 2025 and Felix Johnny Thomasmathibalan committed Feb 17, 2025

When adding negative tests a potential crash from positive
one got masked. Enforce exit from a test script for positive
test crash.

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

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

Anton Bondarenko authored Feb 17, 2025 and Felix Johnny Thomasmathibalan committed Feb 17, 2025

Add negative test for CPU features to make sure actual binaries
using non-supported instructions would crash with illegal instruction
signal.

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

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

Anton Bondarenko authored Feb 13, 2025 and Felix Johnny Thomasmathibalan committed Feb 13, 2025

Testing with bare minimum of CPU features allows to verify
that optional features are properly guarded with feature checks.

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

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

Number of parallel jobs suitable for current CI runner configuration
not always could be retrieved by standard system utilities. The value
need to be hardcoded to avoid unexpected memory usage and could be
aligned with current CI resources and configuration.

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

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

Michael Kozlov authored Feb 12, 2025 and Emil Ohlsson committed Feb 12, 2025

- Update build script
- Add to unit test

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

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

Michael Kozlov authored Feb 11, 2025 and Anton Bondarenko committed Feb 11, 2025

To test a potential ukernel use case and to test offset helper functions.

Resolves: #COMPMID-7887

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: Anton Bondarenko <anton.bondarenko@arm.com>

Anitha Raj authored Feb 11, 2025 and Anton Bondarenko committed Feb 11, 2025

Resolves: #KLEIDIAI-485, #COMPMID-8024

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

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

Multi-platform images simplifies usage as there is no need to
use dedicated tag for different platform. But a special care need
to be taken when building the image. Current version expect native,
or emulated, support from builder.

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

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

Gian Marco Iodice authored Feb 06, 2025 and Felix Johnny Thomasmathibalan committed Feb 06, 2025

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

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

Communicate build requirements to targets linking to KleidiAI by
adding the absolute path rather than relative path in the header
 search path.

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

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

- Remove designated initializers in matmul_clamp_f32_qai8dxp_qsi4c32p_test
- Fix number format in testcase instantiation
- Enable matmul_clamp_f32_qai8dxp_qsi4c32p_test for all platforms

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

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

Michael Kozlov authored Feb 06, 2025 and Jakub Sujak committed Feb 06, 2025

- Update build script
- Add to unit test

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

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

Jens Elofsson authored Feb 04, 2025 and Felix Johnny Thomasmathibalan committed Feb 04, 2025

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

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

- r27C is necessary for MTE Builds

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

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

Suhail M authored Jan 31, 2025 and Felix Johnny Thomasmathibalan committed Jan 31, 2025

- Added demonstration of klediai integration as external dependency 

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

Anton Bondarenko authored Jan 30, 2025 and Felix Johnny Thomasmathibalan committed Jan 30, 2025

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

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

Jens Elofsson authored Jan 30, 2025 and Felix Johnny Thomasmathibalan committed Jan 30, 2025

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

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

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>