OpenBLAS/Makefile.rule

#
#  Beginning of user configuration
#

# This library's version
VERSION = 0.3.29.dev

# If you set this prefix, the library name will be lib$(LIBNAMESUFFIX)openblas.a
# and lib$(LIBNAMESUFFIX)openblas.so, with a matching soname in the shared library
# 
# LIBNAMEPREFIX = scipy

# If you set the suffix, the library name will be libopenblas_$(LIBNAMESUFFIX).a
# and libopenblas_$(LIBNAMESUFFIX).so. Meanwhile, the soname in shared library
# is libopenblas_$(LIBNAMESUFFIX).so.0.
# LIBNAMESUFFIX = omp

# You can specify the target architecture, otherwise it's
# automatically detected.
# TARGET = PENRYN

# If you want to support multiple architecture in one binary
# DYNAMIC_ARCH = 1

# If you want the full list of x86_64 architectures supported in DYNAMIC_ARCH
# mode (including individual optimizied codes for PENRYN, DUNNINGTON, OPTERON,
# OPTERON_SSE3, ATOM and NANO rather than fallbacks to older architectures)
# DYNAMIC_OLDER = 1

# C compiler including binary type(32bit / 64bit). Default is gcc.
# Don't use Intel Compiler or PGI, it won't generate right codes as I expect.
# CC = gcc

# Fortran compiler. Default is g77.
# FC = gfortran

# Even you can specify cross compiler. Meanwhile, please set HOSTCC.

# cross compiler for Windows
# CC = x86_64-w64-mingw32-gcc
# FC = x86_64-w64-mingw32-gfortran

# cross compiler for 32bit ARM
# CC = arm-linux-gnueabihf-gcc
# FC = arm-linux-gnueabihf-gfortran

# cross compiler for 64bit ARM
# CC = aarch64-linux-gnu-gcc
# FC = aarch64-linux-gnu-gfortran


# If you use the cross compiler, please set this host compiler.
# HOSTCC = gcc

# If you need 32bit binary, define BINARY=32, otherwise define BINARY=64
# Please note that AVX is not available on 32-bit.
# Setting BINARY=32 disables AVX/AVX2/AVX-512.
# BINARY=64

# About threaded BLAS. It will be automatically detected if you don't
# specify it.
# For force setting for single threaded, specify USE_THREAD = 0
# For force setting for multi  threaded, specify USE_THREAD = 1
# USE_THREAD = 0

# If you want to build a single-threaded OpenBLAS, but expect to call this
# from several concurrent threads in some other program, comment this in for
# thread safety. (This is done automatically for USE_THREAD=1 , and should not
# be necessary when USE_OPENMP=1)
# USE_LOCKING = 1

# If you're going to use this library with OpenMP, please comment it in.
# This flag is always set for POWER8. Don't set USE_OPENMP = 0 if you're targeting POWER8.
# USE_OPENMP = 1

# The OpenMP scheduler to use - by default this is "static" and you
# will normally not want to change this unless you know that your main
# workload will involve tasks that have highly unbalanced running times
# for individual threads. Changing away from "static" may also adversely
# affect memory access locality in NUMA systems. Setting to "runtime" will
# allow you to select the scheduler from the environment variable OMP_SCHEDULE
# CCOMMON_OPT += -DOMP_SCHED=dynamic

# You can define the maximum number of threads. Basically it should be less
# than or equal to the number of CPU threads. If you don't specify one, it's
# automatically detected by the build system.
# If SMT (aka. HT) is enabled on the system, it may or may not be beneficial to 
# restrict NUM_THREADS to the number of physical cores. By default, the automatic 
# detection includes logical CPUs, thus allowing the use of SMT.
# Users may opt at runtime to use less than NUM_THREADS threads.
#
# Note for package maintainers: you can build OpenBLAS with a large NUM_THREADS
# value (eg. 32-256) if you expect your users to use that many threads. Due to the way
# some internal structures are allocated, using a large NUM_THREADS value has a RAM
# footprint penalty, even if users reduce the actual number of threads at runtime.
# NUM_THREADS = 24

# If you have enabled USE_OPENMP and your application would call
# OpenBLAS's calculation API from multiple threads, please comment this in.
# This flag defines how many instances of OpenBLAS's calculation API can actually
# run in parallel. If more than NUM_PARALLEL threads call OpenBLAS's calculation API,
# they need to wait for the preceding API calls to finish or risk data corruption.
# NUM_PARALLEL = 2

# When multithreading, OpenBLAS needs to use a memory buffer for communicating
# and collating results for individual subranges of the original matrix. Since
# the original GotoBLAS of the early 2000s, the default size of this buffer has
# been set at a value of 32<<20 (which is 32MB) on x86_64 , twice that on PPC.
# If you expect to handle large problem sizes (beyond about 30000x30000) uncomment
# this line and adjust the (32<<n) factor if necessary. Usually an insufficient value
# manifests itself as a crash in the relevant scal kernel (sscal_k, dscal_k etc) 
# BUFFERSIZE = 25

# If you don't need to install the static library, please comment this in.
# NO_STATIC = 1

# If you don't need to generate the shared library, please comment this in.
# NO_SHARED = 1

# If you don't need the CBLAS interface, please comment this in.
# NO_CBLAS = 1

# If you only want the CBLAS interface without installing a Fortran compiler,
# please comment this in.
# ONLY_CBLAS = 1

# If you don't need LAPACK, please comment this in.
# If you set NO_LAPACK=1, the build system automatically sets NO_LAPACKE=1.
# NO_LAPACK = 1

# If you don't need LAPACKE (C Interface to LAPACK), please comment this in.
# NO_LAPACKE = 1

# Build LAPACK Deprecated functions since LAPACK 3.6.0
BUILD_LAPACK_DEPRECATED = 1

# The variable type assumed for the length of character arguments when passing
# data between Fortran LAPACK and C BLAS (defaults to "size_t", but older GCC
# versions used "int"). Mismatches will not cause runtime failures but may result
# in build warnings or errors when building with link-time optimization (LTO)
# LAPACK_STRLEN=int

# Build RecursiveLAPACK on top of LAPACK
# BUILD_RELAPACK = 1
# Have RecursiveLAPACK actually replace standard LAPACK routines instead of 
# just adding its equivalents with a RELAPACK_ prefix
# RELAPACK_REPLACE = 1

# If you want to use the legacy threaded Level 3 implementation.
# USE_SIMPLE_THREADED_LEVEL3 = 1

# If you want to use the new, still somewhat experimental code that uses
# thread-local storage instead of a central memory buffer in memory.c
# Note that if your system uses GLIBC, it needs to have at least glibc 2.21
# for this to work.
# USE_TLS = 1

# If you want to drive whole 64bit region by BLAS. Not all Fortran
# compilers support this. It's safe to keep this commented out if you
# are not sure. (This is equivalent to the "-i8" ifort option).
# INTERFACE64 = 1

# Unfortunately most of kernel won't give us high quality buffer.
# BLAS tries to find the best region before entering main function,
# but it will consume time. If you don't like it, you can disable one.
NO_WARMUP = 1

# Comment this in if you want to disable OpenBLAS's CPU/Memory affinity handling.
# This feature is only implemented on Linux, and is always disabled on other platforms.
# Enabling affinity handling may improve performance, especially on NUMA systems, but 
# it may conflict with certain applications that also try to manage affinity.
# This conflict can result in threads of the application calling OpenBLAS ending up locked
# to the same core(s) as OpenBLAS, possibly binding all threads to a single core.
# For this reason, affinity handling is disabled by default. Can be safely enabled if nothing
# else modifies affinity settings.
# Note: enabling affinity has been known to cause problems with NumPy and R
NO_AFFINITY = 1

# If you are compiling for Linux and you have more than 16 numa nodes or more than 256 cpus
# BIGNUMA = 1

# If you are compiling for an embedded system ("bare metal") like Cortex M series
# Note that you will have to provide implementations of malloc() and free() in this case
# EMBEDDED = 1

# Don't use AVX kernel on Sandy Bridge. It is compatible with old compilers
# and OS. However, the performance is low.
# NO_AVX = 1

# Don't use Haswell optimizations if binutils is too old (e.g. RHEL6)
# NO_AVX2 = 1

# Don't use SkylakeX optimizations if binutils or compiler are too old (the build
# system will try to determine this automatically)
# NO_AVX512 = 1

# Don't use parallel make.
# NO_PARALLEL_MAKE = 1

# Force number of make jobs. The default is the number of logical CPU of the host.
# This is particularly useful when using distcc.
# A negative value will disable adding a -j flag to make, allowing to use a parent
# make -j value. This is useful to call OpenBLAS make from an other project
# makefile
# MAKE_NB_JOBS = 2

# If you would like to know minute performance report of GotoBLAS.
# FUNCTION_PROFILE = 1

# Support for IEEE quad precision(it's *real* REAL*16)( under testing)
# This option should not be used - it is a holdover from unfinished code present
# in the original GotoBLAS2 library that may be usable as a starting point but
# is not even expected to compile in its present form.
# QUAD_PRECISION = 1

# Theads are still working for a while after finishing BLAS operation
# to reduce thread activate/deactivate overhead. You can determine
# time out to improve performance. This number should be from 4 to 30
# which corresponds to (1 << n) cycles. For example, if you set to 26,
# thread will be running for (1 << 26) cycles(about 25ms on 3.0GHz
# system). Also you can control this number by THREAD_TIMEOUT
# CCOMMON_OPT	+= -DTHREAD_TIMEOUT=26

# Using special device driver for mapping physically contiguous memory
# to the user space. If bigphysarea is enabled, it will use it.
# DEVICEDRIVER_ALLOCATION = 1

# Use large page allocation (called hugepage support in Linux context)
# for the thread buffers (with access by shared memory operations)
# HUGETLB_ALLOCATION = 1

# Use large page allocation called hugepages in Linux) based on mmap accessing
# a memory-backed pseudofile (requires hugetlbfs to be mounted in the system,
# the example below has it mounted on /hugepages. OpenBLAS will create the backing
# file as gotoblas.processid in that path)
# HUGETLBFILE_ALLOCATION = /hugepages

# If you need to synchronize FP CSR between threads (for x86/x86_64 and aarch64 only).
# CONSISTENT_FPCSR = 1

# If any gemm argument m, n or k is less or equal this threshold, gemm will be execute
# with single thread. (Actually in recent versions this is a factor proportional to the
# number of floating point operations necessary for the given problem size, no longer
# an individual dimension). You can use this setting to avoid the overhead of multi-
# threading in small matrix sizes. The default value is 4, but values as high as 50 have 
# been reported to be optimal for certain workloads (50 is the recommended value for Julia).
# GEMM_MULTITHREAD_THRESHOLD = 4

# If you need sanity check by comparing results to reference BLAS. It'll be very
# slow (Not implemented yet).
# SANITY_CHECK = 1

# The installation directory.
# PREFIX = /opt/OpenBLAS

# Common Optimization Flag;
# The default -O2 is enough.
# Flags for POWER8 are defined in Makefile.power. Don't modify COMMON_OPT
# COMMON_OPT = -O2

# gfortran option for LAPACK to improve thread-safety
# It is enabled by default in Makefile.system for gfortran
# Flags for POWER8 are defined in Makefile.power. Don't modify FCOMMON_OPT
# FCOMMON_OPT = -frecursive

# Profiling flags
COMMON_PROF = -pg

# Build Debug version
# DEBUG = 1

# Set maximum stack allocation.
# The default value is 2048. 0 disable stack allocation a may reduce GER and GEMV
# performance. For details, https://github.com/xianyi/OpenBLAS/pull/482
#
# MAX_STACK_ALLOC = 0

# Add a prefix or suffix to all exported symbol names in the shared library.
# Avoid conflicts with other BLAS libraries, especially when using
# 64 bit integer interfaces in OpenBLAS.
# For details, https://github.com/xianyi/OpenBLAS/pull/459
#
# The same prefix and suffix are also added to the library name,
# i.e. you get lib$(SYMBOLPREFIX)openblas$(SYMBOLSUFFIX) rather than libopenblas
#
# SYMBOLPREFIX=
# SYMBOLSUFFIX=

# Run a C++ based thread safety tester after the build is done.
# This is mostly intended as a developer feature to spot regressions, but users and
# package maintainers can enable this if they have doubts about the thread safety of
# the library, given the configuration in this file.
# By default, the thread safety tester launches 52 concurrent calculations at the same
# time.
#
# Please note that the test uses ~1300 MiB of RAM for the DGEMM test.
#
# The test requires CBLAS to be built, a C++11 capable compiler and the presence of
# an OpenMP implementation. If you are cross-compiling this test will probably not
# work at all.
#
# CPP_THREAD_SAFETY_TEST = 1
#
# use this to run only the less memory-hungry GEMV test
# CPP_THREAD_SAFETY_GEMV = 1


# If you want to enable the experimental BFLOAT16 support
# BUILD_BFLOAT16 = 1


# Set the thread number threshold beyond which the job array for the threaded level3 BLAS
# will be allocated on the heap rather than the stack. (This array alone requires 
# NUM_THREADS*NUM_THREADS*128 bytes of memory so should not pose a problem at low cpu
# counts, but obviously it is not the only item that ends up on the stack.
# The default value of 32 ensures that the overall requirement is compatible
# with the default 1MB stacksize imposed by having the Java VM loaded without use
# of its -Xss parameter.
# The value of 160 formerly used from about version 0.2.7 until 0.3.10 is easily compatible
# with the common Linux stacksize of 8MB but will cause crashes with unwary use of the java
# VM e.g. in Octave or with the java-based libhdfs in numpy or scipy code
# BLAS3_MEM_ALLOC_THRESHOLD = 160



# By default the library contains BLAS functions (and LAPACK if selected) for all input types.
# To build a smaller library supporting e.g. only single precision real (SGEMM etc.) or only
# the functions for complex numbers, uncomment the desired type(s) below
# BUILD_SINGLE = 1
# BUILD_DOUBLE = 1
# BUILD_COMPLEX = 1
# BUILD_COMPLEX16 = 1
#
#  End of user configuration
#