From: "Ludovic Courtès" <ludo@gnu.org>
To: 52283@debbugs.gnu.org
Cc: "Ludovic Courtès" <ludo@gnu.org>
Subject: [bug#52283] [PATCH 00/10] Tuning packages for CPU micro-architectures
Date: Sat, 4 Dec 2021 21:34:47 +0100 [thread overview]
Message-ID: <20211204203447.15200-1-ludo@gnu.org> (raw)
Hello Guix!
This patch series is an attempt to allow users to build or
substitute packages for the very CPU they are using, as opposed
to using a generic binary that targets the baseline
architecture—e.g., x86_64 without AVX extensions.
As a reminder, my take on this is that The Right Thing is for
code to select optimized implementations for the host CPU at
load time, using (possibly hand-crafted) “function multi-versioning”:
https://hpc.guix.info/blog/2018/01/pre-built-binaries-vs-performance/
Now, there’s at least one situation where developers don’t do
“the right thing”: C++ header-only libraries. It turns out
header-only libraries with #ifdef’d SIMD code are quite common:
Eigen, xsimd, xtensor, etc. Every user of those libs has to be
compiled with ‘-march=native’ to take advantage of those
SIMD-optimized routines and there’s little hope of seeing those
libraries implement load-time or run-time selection¹.
This patch set implements “package multi-versioning”, where a package
can have different variants users may choose from: baseline, haswell,
skylake, etc. This is implemented as a package transformation option,
‘--tune’. Without any argument, ‘--tune’ grafts tuned package variants
for each package that has the ‘tunable?’ property. For example:
guix shell eigen-benchmarks --tune -- benchBlasGemm 16 16 16 100 100
runs one of the Eigen benchmarks tuned for the host CPU, because
‘eigen-benchmarks’ is marked as “tunable”.
This is achieved not by passing ‘-march=native’, because the daemon
might be running on a separate machine with a different CPU, but by
identifying the ‘-march’ value corresponding to the host CPU and
passing ‘-march’ to the compiler, via a wrapper.
On my skylake laptop, that gives a noticeable difference on the GEMM
benchmark of Eigen and good results on the xtensor benchmarks too,
unsurprisingly. I don’t have figures for higher-level applications,
but it’d be nice to benchmark some of Eigen’s dependents for instance,
as shown by:
guix graph -M2 -t reverse-package eigen | xdot -f fdp -
If you could run such benchmarks, that’d be great! :-)
Things like Fenics may benefit from it.
Nix people chose to introduce separate system types for the various
x86_64 micro-architecture levels: x86_64-linux-v1, x86_64-linux-v2,
etc.² I think this is somewhat wasteful and unpractical though.
It’s also unclear whether those levels, defined in the new x86_64
psABI³, are a viable abstraction: vendors seem to be mixing features
rather than really following the accumulative pattern that those
levels imply.
Thoughts?
Ludo’.
¹ https://listengine.tuxfamily.org/lists.tuxfamily.org/eigen/2021/11/msg00006.html
² https://discourse.nixos.org/t/nix-2-4-released/15822
³ https://gitlab.com/x86-psABIs/x86-64-ABI/-/blob/master/x86-64-ABI/low-level-sys-info.tex
Ludovic Courtès (10):
Add (guix cpu).
transformations: Add '--tune'.
ci: Add extra jobs for tunable packages.
gnu: Add eigen-benchmarks.
gnu: Add xsimd-benchmark.
gnu: Add xtensor-benchmark.
gnu: ceres-solver: Mark as tunable.
gnu: Add ceres-solver-benchmarks.
gnu: libfive: Mark as tunable.
gnu: prusa-slicer: Mark as tunable.
Makefile.am | 1 +
doc/guix.texi | 54 ++++++++++++++
gnu/ci.scm | 43 ++++++++---
gnu/packages/algebra.scm | 79 ++++++++++++++++++++
gnu/packages/cpp.scm | 23 ++++++
gnu/packages/engineering.scm | 10 ++-
gnu/packages/maths.scm | 49 ++++++++++++-
guix/cpu.scm | 137 +++++++++++++++++++++++++++++++++++
guix/transformations.scm | 134 ++++++++++++++++++++++++++++++++++
tests/transformations.scm | 20 +++++
10 files changed, 538 insertions(+), 12 deletions(-)
create mode 100644 guix/cpu.scm
base-commit: 052f56e5a614854636563278ee5a2248b3609d87
prerequisite-patch-id: 7e5c2bb5942496daf01a7f6dfc1b0b5b214f1584
--
2.33.0
next reply other threads:[~2021-12-04 20:36 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-04 20:34 Ludovic Courtès [this message]
2021-12-04 20:49 ` [bug#52283] [PATCH 01/10] Add (guix cpu) Ludovic Courtès
2021-12-04 20:49 ` [bug#52283] [PATCH 02/10] transformations: Add '--tune' Ludovic Courtès
2021-12-06 23:18 ` Thiago Jung Bauermann via Guix-patches via
2021-12-07 8:04 ` Ludovic Courtès
2021-12-07 10:32 ` zimoun
2021-12-07 14:52 ` Ludovic Courtès
2021-12-07 15:52 ` zimoun
2021-12-09 9:19 ` Ludovic Courtès
2021-12-09 10:35 ` zimoun
2021-12-10 8:49 ` Ludovic Courtès
2021-12-04 20:49 ` [bug#52283] [PATCH 03/10] ci: Add extra jobs for tunable packages Ludovic Courtès
2021-12-04 20:49 ` [bug#52283] [PATCH 04/10] gnu: Add eigen-benchmarks Ludovic Courtès
2021-12-04 20:49 ` [bug#52283] [PATCH 05/10] gnu: Add xsimd-benchmark Ludovic Courtès
2021-12-04 20:49 ` [bug#52283] [PATCH 06/10] gnu: Add xtensor-benchmark Ludovic Courtès
2021-12-04 20:49 ` [bug#52283] [PATCH 07/10] gnu: ceres-solver: Mark as tunable Ludovic Courtès
2021-12-04 20:49 ` [bug#52283] [PATCH 08/10] gnu: Add ceres-solver-benchmarks Ludovic Courtès
2021-12-04 20:49 ` [bug#52283] [PATCH 09/10] gnu: libfive: Mark as tunable Ludovic Courtès
2021-12-04 20:49 ` [bug#52283] [PATCH 10/10] gnu: prusa-slicer: " Ludovic Courtès
2021-12-05 8:37 ` [bug#52283] [PATCH 00/10] Tuning packages for CPU micro-architectures Mathieu Othacehe
2021-12-06 10:38 ` Ludovic Courtès
2021-12-06 12:47 ` zimoun
2021-12-07 8:39 ` Mathieu Othacehe
2021-12-07 9:02 ` Ludovic Courtès
2021-12-06 16:48 ` Ludovic Courtès
2021-12-04 21:11 ` Ludovic Courtès
2021-12-07 9:13 ` Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 00/12] " Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 01/12] Add (guix cpu) Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 02/12] gnu: gcc: Add 'compiler-cpu-architectures' property Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 03/12] gnu: clang: " Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 04/12] transformations: Add '--tune' Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 05/12] ci: Add extra jobs for tunable packages Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 06/12] gnu: Add eigen-benchmarks Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 07/12] gnu: Add xsimd-benchmark Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 08/12] gnu: Add xtensor-benchmark Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 09/12] gnu: ceres-solver: Mark as tunable Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 10/12] gnu: Add ceres-solver-benchmarks Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 11/12] gnu: libfive: Mark as tunable Ludovic Courtès
2021-12-16 17:58 ` [bug#52283] [PATCH v2 12/12] gnu: prusa-slicer: " Ludovic Courtès
2022-01-01 14:59 ` bug#52283: [PATCH 00/10] Tuning packages for CPU micro-architectures Ludovic Courtès
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20211204203447.15200-1-ludo@gnu.org \
--to=ludo@gnu.org \
--cc=52283@debbugs.gnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this external index
https://git.savannah.gnu.org/cgit/guix.git
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.