This allows Julia to set a default number of threads (usually `1`) to be
used when no other thread counts are specified [0], to short-circuit the
default OpenBLAS thread initialization routine that spins up a different
number of threads than Julia would otherwise choose.
The reason to add a new environment variable is that we want to be able
to configure OpenBLAS to avoid performing its initial memory
allocation/thread startup, as that can consume significant amounts of
memory, but we still want to be sensitive to legacy codebases that set
things like `OMP_NUM_THREADS` or `GOTOBLAS_NUM_THREADS`. Creating a new
environment variable that is openblas-specific and is not already
publicly used to control the overall number of threads of programs like
Julia seems to be the best way forward.
[0] https://github.com/JuliaLang/julia/pull/46844
Some compilers (namely LLVM) are not happy with clobbering
registers in inline assembly.
Use $at as temporary register and explicitly use noat
hint.
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
This fixes compilation in the following case:
$(MAKE) USE_OPENMP=1 USE_THREAD=1 NO_LAPACK=0 DYNAMIC_ARCH=1 \
DYNAMIC_LIST="HASWELL SKYLAKEX ATOM COOPERLAKE SAPPHIRERAPIDS ZEN"
Add pointers to the definition of the hardware capability flags in glibc
and describe how they relate to the levels CPU_Z13 and CPU_Z14 for
optimized kernels.
To aid identifying available hardware capabilities and in debugging
potential build issues, dump their value in dynamic_arch_init() when
OPENBLAS_VERBOSE is set to 2 or higher.
Signed-off-by: Marius Hillenbrand <mhillen@linux.ibm.com>
On s390x, the run-time detection for DYNAMIC_ARCH and the compile-time
choice in cpuid_zarch use different methods for identifying the
supported CPU features. To make cpuid_zarch future-proof and both easier
to maintain, switch cpuid_zarch to the same mechanism as DYNAMIC_ZARCH
(i.e., derive the supported CPU features from hwcap flags) and share
code between both (in a new header cpuid_zarch.h).
Signed-off-by: Marius Hillenbrand <mhillen@linux.ibm.com>
Martin Kroeker
Honglin Zhu
Elliot Saba
Kai T. Ohlhus
Jiaxun Yang
gxw
Adam Niederer
JonasZhou
Sunita Nadampalli
Rafael Cardoso Fernandes Sousa
Marius Hillenbrand
Wangyang Guo