Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Formatting the CPU arch #602

Merged
merged 15 commits into from
Nov 25, 2024
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions build_requirements.txt
Original file line number Diff line number Diff line change
Expand Up @@ -4,3 +4,5 @@ myst-parser==0.18.0
sphinx-copybutton==0.5.0
sphinx-design==0.5.0
m2r2==0.3.2
linuxdoc==20240924
standard-imghdr==3.13.0
3 changes: 2 additions & 1 deletion docs/source/conf.py
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,8 @@
"sphinx.ext.intersphinx",
"sphinx_copybutton",
"sphinx_design",
"cppkokkos"]
"cppkokkos",
"linuxdoc.rstFlatTable"]

# Add any paths that contain templates here, relative to this directory.
templates_path = ['_templates']
Expand Down
179 changes: 95 additions & 84 deletions docs/source/keywords.rst
Original file line number Diff line number Diff line change
Expand Up @@ -347,91 +347,102 @@ Architectures
CPU architectures
-----------------

.. list-table::
:widths: 25 65 10
:header-rows: 1
:align: left

* -
- Description/info
- Default

* * ``Kokkos_ARCH_NATIVE``
* Optimize for the local CPU architecture
* ``OFF``

* * ``Kokkos_ARCH_A64FX``
* Optimize for ARMv8.2 with SVE Support
* ``OFF``

* * ``Kokkos_ARCH_AMDAVX``
* Optimize for AMDAVX architecture
* ``OFF``

* * ``Kokkos_ARCH_ARMV80``
* Optimize for ARMV80 architecture
* ``OFF``

* * ``Kokkos_ARCH_ARMV81``
* Optimize for ARMV81 architecture
* ``OFF``

* * ``Kokkos_ARCH_ARMV8_THUNDERX``
* Optimize for ARMV8_THUNDERX architecture
* ``OFF``

* * ``Kokkos_ARCH_ARMV8_THUNDERX2``
* Optimize for the ARMV8_THUNDERX2 architecture
* ``OFF``

* * ``Kokkos_ARCH_BDW``
* Optimize for BDW architecture
* ``OFF``

* * ``Kokkos_ARCH_HSW``
* Optimize for HSW architecture
* ``OFF``

* * ``Kokkos_ARCH_KNC``
* Optimize for KNC architecture
* ``OFF``

* * ``Kokkos_ARCH_KNL``
* Optimize for KNL architecture
* ``OFF``

* * ``Kokkos_ARCH_POWER8``
* Optimize for POWER8 architecture
* ``OFF``

* * ``Kokkos_ARCH_POWER9``
* Optimize for POWER9 architecture
* ``OFF``

* * ``Kokkos_ARCH_SKX``
* Optimize for SKX architecture
* ``OFF``

* * ``Kokkos_ARCH_SNB``
* Optimize for SNB architecture
* ``OFF``

* * ``Kokkos_ARCH_SPR``
* Optimize for Sapphire Rapids architecture
* ``OFF``

* * ``Kokkos_ARCH_ZEN``
* Optimize for Zen architecture
* ``OFF``

* * ``Kokkos_ARCH_ZEN2``
* Optimize for Zen2 architecture
* ``OFF``

* * ``Kokkos_ARCH_ZEN3``
* Optimize for Zen3 architecture
* ``OFF``
Kokkos does not automatically add compiler flags to optimize for a specific CPU architecture.
When compiling on the machine that the code also runs on, the easiest way to get the CPU code optimized is using ``Kokkos_ARCH_NATIVE=ON`` when configuring.
In case of compiling for another machine, the CPU architecture can be manually specified. For the available architectures see the following list.

.. flat-table:: CPU architectures
:header-rows: 1
:stub-columns: 0
:widths: 20 20 40 20

* - Cmake keyword
- Architecture/Instruction set
- Examples
- Vendor

* - ``Kokkos_ARCH_ZEN3``
- Zen 3/amd64
- Epyc 7713 @ ORNL Frontier
- :rspan:`3`
AMD

* - ``Kokkos_ARCH_ZEN2``
- Zen 2/amd64
- Epyc 7742 @ NOAA

* - ``Kokkos_ARCH_ZEN``
- Zen/amd64
- Epyc @ ANL Selene

* - ``Kokkos_ARCH_AMDAVX``
- Bullozer/amd64
-

* - ``Kokkos_ARCH_A64FX``
- ARMv8.2/A64
- A64FX @ Fugaku
- :rspan:`4`
ARM

* - ``Kokkos_ARCH_ARMV8_THUNDERX2``
- ARMv8/A64
- ThunderX2 @ SNL Astra
ThunderX2 @ CEA BullSequana

* - ``Kokkos_ARCH_ARMV81``
- ARMv8.1/A64,A32
-

* - ``Kokkos_ARCH_ARMV8_THUNDERX``
- ARMv8/A64
-

* - ``Kokkos_ARCH_ARMV80``
- ARMv8.0/A64,A32
-

* - ``Kokkos_ARCH_POWER8``
- Power8/Power ISA
-
- :rspan:`1`
IBM

* - ``Kokkos_ARCH_POWER9``
- Power9/Power ISA
- POWER9 @ ORNL Summit
POWER9 @ LLNL Sierra

* - ``Kokkos_ARCH_SNB``
- Sandy Bridge/x86-64
-
- :rspan:`6`
Intel

* - ``Kokkos_ARCH_KNC``
- knc/x86-64
-

* - ``Kokkos_ARCH_KNL``
- knl/x86-64
- 31S1P @ Tianhe-2

* - ``Kokkos_ARCH_HSW``
- Haswell/x86-64
- 2680v3 @ NASA Pleiades

* - ``Kokkos_ARCH_BDW``
- Braodwell/x86-64
- 2680v4 @ NASA Pleiades

* - ``Kokkos_ARCH_SKX``
- Skylake/x86-64
- 6130 @ OSU Pete

* - ``Kokkos_ARCH_SPR``
- Sapphire Rapids/x86-64
- Xeon 9470C @ ANL Aurora
Xeon @ LANL Crossroads

GPU Architectures
-----------------
Expand Down
Loading