ARMv8 builds were a bit mixed up, with ThunderX2 code in ARMv8 mode
(which is not right because TX2 is ARMv8.1) as well as requiring a few
redundancies in the defines, making it harder to maintain and understand
what core has what. A few other minor issues were also fixed.
Tests were made on the following cores: A53, A57, A72, Falkor, ThunderX,
ThunderX2, and XGene.
Tests were: OpenBLAS/test, OpenBLAS/benchmark, BLAS-Tester.
A summary:
* Removed TX2 code from ARMv8 build, to make sure it is compatible with
all ARMv8 cores, not just v8.1. Also, the TX2 code has actually
harmed performance on big cores.
* Commoned up ARMv8 architectures' defines in params.h, to make sure
that all will benefit from ARMv8 settings, in addition to their own.
* Adding a few more cores, using ARMv8's include strategy, to benefit
from compiler optimisations using mtune. Also updated cache
information from the manuals, making sure we set good conservative
values by default. Removed Vulcan, as it's an alias to TX2.
* Auto-detecting most of those cores, but also updating the forced
compilation in getarch.c, to make sure the parameters are the same
whether compiled natively or forced arch.
Benefits:
* ARMv8 build is now guaranteed to work on all ARMv8 cores
* Improved performance for ARMv8 builds on some cores (A72, Falkor,
ThunderX1 and 2: up to 11%) over current develop
* Improved performance for *all* cores comparing to develop branch
before TX2's patch (9% ~ 36%)
* ThunderX1 builds are 14% faster than ARMv8 on TX1, 9% faster than
current develop's branch and 8% faster than deveop before tx2 patches
Issues:
* Regression from current develop branch for A53 (-12%) and A57 (-3%)
with ARMv8 builds, but still faster than before TX2's commit (+15%
and +24% respectively). This can be improved with a simplification of
TX2's code, to be done in future patches. At least the code is
guaranteed to be ARMv8.0 now.
Comments:
* CortexA57 builds are unchanged on A57 hardware from develop's branch,
which makes sense, as it's untouched.
* CortexA72 builds improve over A57 on A72 hardware, even if they're
using the same includes due to new compiler tunning in the makefile.
This patch adds the basic infrastructure for adding the SkylakeX (Intel Skylake server)
target. The SkylakeX target will use the AVX512 (AVX512VL level) instruction set,
which brings 2 basic things:
1) 512 bit wide SIMD (2x width of AVX2)
2) 32 SIMD registers (2x the number on AVX2)
This initial patch only contains a trivial transofrmation of the Haswell SGEMM kernel
to AVX512VL; more will follow later but this patch aims to get the infrastructure
in place for this "later".
Full performance tuning has not been done yet; with more registers and wider SIMD
it's in theory possible to retune the kernels but even without that there's an
interesting enough performance increase (30-40% range) with just this change.
TARGET as specified with make is already return-terminated when getarch reads it. This led to an empty line written to config_last.h that awk in Makefile.install then expanded to a spurious "#define OPENBLAS_" in openblas_config.h (as noted by "kmb" on the mailing list)
Optimizations for APM's xgene-1 (aarch64).
1) general system updates to support armv8 better. Make all did not work, one needed to supply TARGET=ARMV8.
2) sgem 4x4 kernel in assembler using SIMD, and configuration changes to use it.
3) strmm 4x4 kernel in C. Since the sgem kernel does 4x4, the trmm kernel must also do 4xN.
Added Dave Nuechterlein to the contributors list.
Ali Saidi
Xianyi Zhang
Martin Kroeker
AbdelRauf
maomao194313
TiborGY
Renato Golin
Arjan van de Ven
Jerry Zhao
Alex Arslan
Shivraj Patil
Sébastien Villemot
Denis Steckelmacher
Ashwin Sekhar T K
Andrew Pinski
Zhang Xianyi
Howard Su
Jerome Robert
Werner Saar
Lauri Tirkkonen
Ashwin Sekhar T K
Grazvydas Ignotas
Fábio Perez
Hank Anderson
Benedikt Huber
Timothy Gu
Explorer09
Xianyi Zhang