| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
| |
Bug: https://bugs.gentoo.org/936099
Signed-off-by: Sv. Lockal <lockalsash@gmail.com>
Signed-off-by: Sam James <sam@gentoo.org>
|
|
|
|
|
|
|
|
|
| |
Update the references, since the original reference does not
contain MI300. The "see also" blog is also removed because it hasn't been
updated for 2 years.
Signed-off-by: Yiyang Wu <xgreenlandforwyy@gmail.com>
Signed-off-by: Benda Xu <heroxbd@gentoo.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Initially, rocm.eclass append xnack[1,2] feature flag to gfx9 GPUs,
since ROCm upstream does this in many of their math libraries, e.g.
rocBLAS [3]. The list includes gfx90a:xnack+, indicating xnack is usable
for MI200 series, thus rocm.eclass append :xnack+ to gfx90a.
But it turns out xnack- is also common for MI200 series, restricting to
xnack+ produces incompatible GPU kernel with xnack- mode.
Also, community also explores using xnack on other gfx9 GPU [4,5], which
is previously restricted to xnack- in rocm.eclass.
By not appending xnack feature flag, GPU kernels are compiled to "xnack
any" mode, which can be run in either mode, potentially scarifying some
performance [6,7], with no direct evidence. rocFFT reports no
performance penalty[8].
For the reason above, do not append xnack feature flag to AMDGPU_TARGETS,
which is compatible with GPUs operate in both xnack mode.
[1] https://wiki.gentoo.org/wiki/ROCm#XNACK_target_feature
[2] https://rocm.docs.amd.com/en/latest/conceptual/gpu-memory.html#xnack
[3] https://github.com/ROCm/rocBLAS/blob/release/rocm-rel-5.0/CMakeLists.txt#L201
[4] https://niconiconi.neocities.org/tech-notes/xnack-on-amd-gpus/
[5] https://arxiv.org/abs/2401.02680
[6] https://llvm.org/docs/AMDGPUUsage.html#target-features
[7] https://docs.olcf.ornl.gov/systems/crusher_quick_start_guide.html#compiling-hip-kernels-for-specific-xnack-modes
[8] https://github.com/ROCm/rocFFT/commit/cd2689360ba3b3579d044d8925838ff307b4b4cf
Signed-off-by: Yiyang Wu <xgreenlandforwyy@gmail.com>
Signed-off-by: Benda Xu <heroxbd@gentoo.org>
Closes: https://github.com/gentoo/gentoo/pull/36254
|
|
|
|
|
|
|
|
|
|
|
| |
Low level ebuilds such as dev-util/hip and
dev-libs/rocm-opencl-runtime unconditionally supports all the AMDGPU
cards. They do not need to define amdgpu_targets_* USE-flags. But
their src_test() call check_amdgpu() to confirm an AMDGPU is
available.
Reference: https://marc.info/?l=gentoo-dev&m=170045497732286
Signed-off-by: Benda Xu <heroxbd@gentoo.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
ROCm libraries with version <5 are cleaned up, remove version 4 support
for rocm.eclass.
RDNA3 has initial support in ROCm libraries starting from 5.4 releases.
Enable gfx110* amdgpu_targets in rocm.eclass and add corresponding
description.
Closes: https://bugs.gentoo.org/891499
Closes: https://github.com/gentoo/gentoo/pull/29320
Signed-off-by: Yiyang Wu <xgreenlandforwyy@gmail.com>
Signed-off-by: Benda Xu <heroxbd@gentoo.org>
|
|
|
|
| |
Signed-off-by: David Seifert <soap@gentoo.org>
|
|
This eclass provides utilities for ROCm libraries in
https://github.com/ROCmSoftwarePlatform, e.g. rocBLAS, rocFFT.
It contains a USE_EXPAND, amdgpu_targets_*, which handles the GPU
architecture to compile, and keep targets coherent among dependencies.
Packages that depend on ROCm libraries, like cupy, can also make use of
this eclass, mainly specify GPU architecture and it's corresponding
dependencies via USE_EXPAND.
Closes: https://github.com/gentoo/gentoo/pull/26784
Closes: https://bugs.gentoo.org/810619
Bug: https://bugs.gentoo.org/817440
Reference: https://archives.gentoo.org/gentoo-dev/message/49b17ca059187a4b5d983a9500507158
Signed-off-by: Yiyang Wu <xgreenlandforwyy@gmail.com>
Signed-off-by: Benda Xu <heroxbd@gentoo.org>
|