sci-libs / composable-kernel

High Performance Composable Kernel for AMD GPUs

Official package sites : https://github.com/ROCm/composable_kernel ·

v7.2.0 :: 0/7.2 :: gentoo

Modified
License
MIT
Keywords
~amd64
USE flags
debug profiler test

v7.1.0 :: 0/7.1 :: gentoo

Modified
License
MIT
Keywords
~amd64
USE flags
debug profiler test

v7.0.2 :: 0/7.0 :: gentoo

Modified
License
MIT
Keywords
~amd64
USE flags
debug profiler test

v6.4.3 :: 0/6.4 :: gentoo

Modified
License
MIT
Keywords
~amd64
USE flags
debug profiler test

v6.3.0 :: 0/6.3 :: gentoo

Modified
License
MIT
Keywords
~amd64
USE flags
debug profiler test

General

debug
Enable extra debug codepaths, like asserts and extra output. If you want to get meaningful backtraces see https://wiki.gentoo.org/wiki/Project:Quality_Assurance/Backtraces
profiler
Build and install the Composable Kernal profiler (ckProfiler)
test
Enable dependencies and/or preparations necessary to run tests (usually controlled by FEATURES=test but can be toggled independently)

amdgpu_targets

gfx1010
RDNA GPU, codename navi10, including Radeon RX 5700XT/5700/5700M/5700B/5700XTB/5600XT/5600/5600M, Radeon Pro 5700XT/5700, Radeon Pro W5700X/W5700
gfx1011
RDNA GPU, codename navi12, including Radeon Pro 5600M/V520
gfx1012
RDNA GPU, codename navi14, including Radeon RX 5500XT/5500/5500M/5500XTB/5300/5300M, Radeon Pro 5500XT/5500M/5300/5300M, Radeon Pro W5500X/W5500/W5500M/W5300M
gfx1030
RDNA2 GPU, codename navi21/sienna cichlid, including Radeon RX 6950XT/6900XT/6800XT/6800, Radeon Pro W6800/V620
gfx1031
RDNA2 GPU, codename navi22/navy flounder, including Radeon RX 6750XT/6700XT/6800M/6700M
gfx1100
RDNA3 GPU, codename navi31/plum bonito, including Radeon RX 7900 XTX/XT/GRE, AMD Radeon Pro W7900/W7800
gfx1101
RDNA3 GPU, codename navi32, including Radeon RX 7700XT/7800XT, AMD Radeon PRO W7700/V710
gfx1101
RDNA3 GPU, codename navi32, including Radeon RX 7700XT/7800XT, AMD Radeon PRO W7700/V710
gfx1102
RDNA3 GPU, codename navi33, including Radeon RX 7400/7600/7600M/7600M XT/7700S/7600S, AMD Radeon PRO W7600/W7500
gfx1103
RDNA3 APU, codename navi3x, including Radeon 700M/780M
gfx1150
RDNA 3.5 APU (Strix Point), including Radeon 890M
gfx1151
RDNA 3.5 APU (Strix Halo), including Radeon 8060S
gfx1200
RDNA4 GPU, codename navi44, including Radeon RX 9060XT/9060XT LP
gfx1201
RDNA4 GPU, codename navi48, including Radeon RX 9070/9070XT/9070GRE and Radeon AI PRO R9600D/R9700
gfx803
Fiji GPU, codename fiji, including Radeon R9 Nano/Fury/FuryX, Radeon Pro Duo, FirePro S9300x2, Radeon Instinct MI8
gfx900
Vega GPU, codename vega10, including Radeon Vega Frontier Edition, Radeon RX Vega 56/64, Radeon RX Vega 64 Liquid, Radeon Pro Vega 48/56/64/64X, Radeon Pro WX 8200/9100, Radeon Pro V320/V340/SSG, Radeon Instinct MI25
gfx906
Vega GPU, codename vega20, including Radeon (Pro) VII, Radeon Instinct MI50/MI60
gfx906
Vega GPU, codename vega20, including Radeon (Pro) VII, Radeon Instinct MI50/MI60
gfx908
CDNA Accelerator, codename arcturus, including AMD Instinct MI100 Accelerator
gfx90a
CDNA2 Accelerator, codename aldebaran, including AMD Instinct MI200 series Accelerators
gfx940
CDNA3 Accelerator, codename aqua_vangaram, MI300A rev 0
gfx941
CDNA3 Accelerator, codename aqua_vangaram, MI300X rev 0
gfx942
CDNA3 Accelerator, codename aqua_vangaram, MI300A and MI300X rev >=1
gfx950
CDNA4 Accelerator, including AMD Instinct MI350X and MI355X

python_targets

python3_12
Build with Python 3.12
python3_13
Build with Python 3.13
python3_14
Build with Python 3.14

dev-lang / python : An interpreted, interactive, object-oriented programming language

dev-util / hip : C++ Heterogeneous-Compute Interface for Portability

dev-lang / python : An interpreted, interactive, object-oriented programming language

dev-util / hip : C++ Heterogeneous-Compute Interface for Portability

media-libs / oidn : Intel Open Image Denoise library

sci-libs / miopen : AMD's Machine Intelligence Library

932188
sci-libs/rccl and sci-libs/composable-kernel does not respect amdgpu_flags
977408
sci-libs/composable-kernel-7.2.0: failed to link bin/ckProfiler
Repository mirror & CI · gentoo
Merge updates from master
Andreas Sturmlechner · gentoo
sci-libs/composable-kernel: Use cmake_comment_add_subdirectory
Signed-off-by: Andreas Sturmlechner <asturm@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Sv. Lockal · gentoo
sci-libs/composable-kernel: add 7.2.0
A word of caution: where 7.1.0 previously took 42 minutes to build, 7.2.0 takes 68 minutes to build (all just a single target on fast CPU). Follow https://github.com/ROCm/rocm-libraries/issues/4229 for updates. Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Part-of: https://github.com/gentoo/gentoo/pull/45826 Signed-off-by: Sam James <sam@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Sv. Lockal · gentoo
sci-libs/composable-kernel: read expand-isa patch for 7.1.0
Closes: https://bugs.gentoo.org/965887 Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Part-of: https://github.com/gentoo/gentoo/pull/44725 Signed-off-by: Sam James <sam@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Patrick Lauer · gentoo
sci-libs/composable-kernel: add 7.1.0
Signed-off-by: Patrick Lauer <patrick@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Sv. Lockal · gentoo
sci-libs/composable-kernel: use rocm_add_sandbox in configure phase
During configuration we don't care if AMD device is present (contrarily to test phase). New function rocm_add_sandbox does not die when AMD device is missing. Closes: https://bugs.gentoo.org/965198 Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Part-of: https://github.com/gentoo/gentoo/pull/44355 Closes: https://github.com/gentoo/gentoo/pull/44355 Signed-off-by: Sam James <sam@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Repository mirror & CI · gentoo
Merge updates from master
Sv. Lockal · gentoo
sci-libs/composable-kernel: add 7.0.2
Bug: https://bugs.gentoo.org/964799 Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Part-of: https://github.com/gentoo/gentoo/pull/44165 Signed-off-by: Sam James <sam@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Andreas Sturmlechner · gentoo
sci-libs/*: Re-add ROCm 5.7.1 packages for now
It was not supposed to be dropped just yet. Signed-off-by: Andreas Sturmlechner <asturm@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Andreas Sturmlechner · gentoo
sci-libs/composable-kernel: drop 5.7.1-r1
Signed-off-by: Andreas Sturmlechner <asturm@gentoo.org>
Andreas Sturmlechner · gentoo
sci-libs/composable-kernel: drop 5.7.1-r1
Signed-off-by: Andreas Sturmlechner <asturm@gentoo.org>
Andreas Sturmlechner · gentoo
sci-libs/composable-kernel: drop 6.4.1
Signed-off-by: Andreas Sturmlechner <asturm@gentoo.org>
Andreas Sturmlechner · gentoo
sci-libs/composable-kernel: drop 6.1.1
Signed-off-by: Andreas Sturmlechner <asturm@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Sv. Lockal · gentoo
sci-libs/composable-kernel: use available memory for MAKEOPTS hint
"free" might me filled with cached data and not suitable for calculation. Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Part-of: https://github.com/gentoo/gentoo/pull/43406 Signed-off-by: Sam James <sam@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Patrick Lauer · gentoo
sci-libs/composable-kernel: add 6.4.3
Signed-off-by: Patrick Lauer <patrick@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Repository mirror & CI · gentoo
Merge updates from master
Sv. Lockal · gentoo
sci-libs/composable-kernel: add 6.4.1
Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Part-of: https://github.com/gentoo/gentoo/pull/42554 Signed-off-by: Sam James <sam@gentoo.org>
Sv. Lockal · gentoo
sci-libs/composable-kernel: fix compilation with AMDGPU_TARGETS="gfx1012"
This adds few patches from https://github.com/ROCm/composable_kernel/issues/775#issuecomment-2726315348 that allow to compile with RDNA1 GPUs. Also it limits the number of threads (jobs) expecting ~2Gb RAM usage per thread (as suggested in composable_kernel README). Closes: https://bugs.gentoo.org/947583 Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Part-of: https://github.com/gentoo/gentoo/pull/41240 Closes: https://github.com/gentoo/gentoo/pull/41240 Signed-off-by: Sam James <sam@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Sv. Lockal · gentoo
sci-libs/composable-kernel: add 6.3.0
Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Signed-off-by: Sam James <sam@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Sv. Lockal · gentoo
sci-libs/composable-kernel: strip unsupported flags for potentially switched compiler
Additionally: fix compilation with libc++ Bug: https://bugs.gentoo.org/936099 Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Signed-off-by: Sam James <sam@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Sv. Lockal · gentoo
sci-libs/composable-kernel: add 6.1.1
Changes: * add patch for Clang 17 compatibility (official build uses Clang 18) * add patch for "Could NOT find Git (missing: GIT_EXECUTABLE)" * drop dev-libs/half dependency in all versions (not used) * rename ROCmSoftwarePlatform -> ROCm in URLs Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Signed-off-by: Sam James <sam@gentoo.org>
Repository mirror & CI · gentoo
Merge updates from master
Sv. Lockal · gentoo
sci-libs/composable-kernel: new package, add 5.7.1-r1
Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Signed-off-by: Sam James <sam@gentoo.org>