Previously dynamic builds were either using the default SWITCH_RATIO
or one from the higher level architecture; this patch ensures the
dynamic builds can use this parameter as well.
must have misplaced this in ../getrf when I made that change in March 2018 (40160ff)
the only changes since then were
RFC : Add half precision gemm for bfloat16 in OpenBLAS Rajalakshmi Srinivasaraghavan
Rajalakshmi Srinivasaraghavan committed on 14 Apr 2020 as 7ebbb50
Change _STDC_VERSION__ to __STDC_VERSION__
Zhiyong Dang committed on 11 May 2018 as 3716267
This patch adds support for bfloat16 data type matrix multiplication kernel.
For architectures that don't support bfloat16, it is defined as unsigned short
(2 bytes). Default unroll sizes can be changed as per architecture as done for
SGEMM and for now 8 and 4 are used for M and N. Size of ncopy/tcopy can be
changed as per architecture requirement and for now, size 2 is used.
Added shgemm in kernel/power/KERNEL.POWER9 and tested in powerpc64le and
powerpc64. For reference, added a small test compare_sgemm_shgemm.c to compare
sgemm and shgemm output.
This patch does not cover OpenBLAS test, benchmark and lapack tests for shgemm.
Complex type implementation can be discussed and added once this is approved.
The current implementation has locks, but the locks each only
have a critical section of one variable so atomic reads/writes
with barriers can be used to achieve the same behavior.
Like the previous patch, pthread_mutex_lock isn't fair, so in a
tight loop the previous thread that has the lock can keep it
starving another thread, even if that thread is about to write
the data that will stop the current thread from spinning.
On a 64c Arm system this improves performance by 20x on sgesv.goto.
Martin Kroeker
Chris Sidebottom
gxw
Zhang Xianyi
Rajalakshmi Srinivasaraghavan
Rajalakshmi Srinivasaraghavan
Ali Saidi
Xianyi Zhang
Guillaume Horel