floraachy
/
OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Reword/expand comments in Makefile.rule 

Lots of small changes in the wording of the comments, plus an expansion of the NUM_THREADS and NO_AFFINITY sections.
This commit is contained in:
TiborGY 2019-01-27 15:33:00 +01:00 committed by GitHub
parent 89b60dab8a
commit 0f24b39ebf
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 29 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
Makefile.rule
View File

@ -48,6 +48,8 @@ VERSION = 0.3.6.dev
# HOSTCC = gcc # HOSTCC = gcc
# If you need 32bit binary, define BINARY=32, otherwise define BINARY=64 # 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 # BINARY=64
# About threaded BLAS. It will be automatically detected if you don't # About threaded BLAS. It will be automatically detected if you don't
@ -57,7 +59,7 @@ VERSION = 0.3.6.dev
# USE_THREAD = 0 # USE_THREAD = 0
# If you're going to use this library with OpenMP, please comment it in. # If you're going to use this library with OpenMP, please comment it in.
# This flag is always set for POWER8. Don't modify the flag # This flag is always set for POWER8. Don't set USE_OPENMP = 0 if you're targeting POWER8.
# USE_OPENMP = 1 # USE_OPENMP = 1
# The OpenMP scheduler to use - by default this is "static" and you # The OpenMP scheduler to use - by default this is "static" and you
@ -68,36 +70,39 @@ VERSION = 0.3.6.dev
# allow you to select the scheduler from the environment variable OMP_SCHEDULE # allow you to select the scheduler from the environment variable OMP_SCHEDULE
# CCOMMON_OPT += -DOMP_SCHED=dynamic # CCOMMON_OPT += -DOMP_SCHED=dynamic
# You can define maximum number of threads. Basically it should be # You can define the maximum number of threads. Basically it should be less
# less than actual number of cores. If you don't specify one, it's # than or equal to the number of CPU threads. If you don't specify one, it's
# automatically detected by the the script. # automatically detected by the the script.
# 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.
# NUM_THREADS = 24 # NUM_THREADS = 24
# If you have enabled USE_OPENMP and your application would call # If you have enabled USE_OPENMP and your application would call
# OpenBLAS's calculation API from multi threads, please comment it in. # OpenBLAS's calculation API from multiple threads, please comment this in.
# This flag defines how many instances of OpenBLAS's calculation API can # This flag defines how many instances of OpenBLAS's calculation API can actually
# actually run in parallel. If more threads call OpenBLAS's calculation API, # 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. # they need to wait for the preceding API calls to finish or risk data corruption.
# NUM_PARALLEL = 2 # NUM_PARALLEL = 2
# if you don't need to install the static library, please comment it in. # If you don't need to generate the static library, please comment this in.
# NO_STATIC = 1 # NO_STATIC = 1
# if you don't need generate the shared library, please comment it in. # If you don't need to generate the shared library, please comment this in.
# NO_SHARED = 1 # NO_SHARED = 1
# If you don't need CBLAS interface, please comment it in. # If you don't need the CBLAS interface, please comment this in.
# NO_CBLAS = 1 # NO_CBLAS = 1
# If you only want CBLAS interface without installing Fortran compiler, # If you only want the CBLAS interface without installing a Fortran compiler,
# please comment it in. # please comment this in.
# ONLY_CBLAS = 1 # ONLY_CBLAS = 1
# If you don't need LAPACK, please comment it in. # If you don't need LAPACK, please comment this in.
# If you set NO_LAPACK=1, the library automatically sets NO_LAPACKE=1. # If you set NO_LAPACK=1, the build system automatically sets NO_LAPACKE=1.
# NO_LAPACK = 1 # NO_LAPACK = 1
# If you don't need LAPACKE (C Interface to LAPACK), please comment it in. # If you don't need LAPACKE (C Interface to LAPACK), please comment this in.
# NO_LAPACKE = 1 # NO_LAPACKE = 1
# Build LAPACK Deprecated functions since LAPACK 3.6.0 # Build LAPACK Deprecated functions since LAPACK 3.6.0
@ -106,7 +111,7 @@ BUILD_LAPACK_DEPRECATED = 1
# Build RecursiveLAPACK on top of LAPACK # Build RecursiveLAPACK on top of LAPACK
# BUILD_RELAPACK = 1 # BUILD_RELAPACK = 1
# If you want to use legacy threaded Level 3 implementation. # If you want to use the legacy threaded Level 3 implementation.
# USE_SIMPLE_THREADED_LEVEL3 = 1 # USE_SIMPLE_THREADED_LEVEL3 = 1
# If you want to use the new, still somewhat experimental code that uses # If you want to use the new, still somewhat experimental code that uses
@ -116,8 +121,8 @@ BUILD_LAPACK_DEPRECATED = 1
# USE_TLS = 1 # USE_TLS = 1
# If you want to drive whole 64bit region by BLAS. Not all Fortran # If you want to drive whole 64bit region by BLAS. Not all Fortran
# compiler supports this. It's safe to keep comment it out if you # compilers support this. It's safe to keep this commented out if you
# are not sure(equivalent to "-i8" option). # are not sure. (This is equivalent to the "-i8" ifort option).
# INTERFACE64 = 1 # INTERFACE64 = 1
# Unfortunately most of kernel won't give us high quality buffer. # Unfortunately most of kernel won't give us high quality buffer.
@ -125,10 +130,15 @@ BUILD_LAPACK_DEPRECATED = 1
# but it will consume time. If you don't like it, you can disable one. # but it will consume time. If you don't like it, you can disable one.
NO_WARMUP = 1 NO_WARMUP = 1
# If you want to disable CPU/Memory affinity on Linux. # 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.
# For this reason, affinity handling is disabled by default. Can be safely enabled if nothing
# else modifies affinity settings.
NO_AFFINITY = 1 NO_AFFINITY = 1
# if you are compiling for Linux and you have more than 16 numa nodes or more than 256 cpus # If you are compiling for Linux and you have more than 16 numa nodes or more than 256 cpus
# BIGNUMA = 1 # BIGNUMA = 1
# Don't use AVX kernel on Sandy Bridge. It is compatible with old compilers # Don't use AVX kernel on Sandy Bridge. It is compatible with old compilers