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

Allow choosing the OpenMP scheduler and add range hint for GEMM_MULTITHREAD_THRESHOLD

This commit is contained in:
Martin Kroeker 2018-06-15 00:00:13 +02:00 committed by GitHub
parent b218e1a3c5
commit b6b4b3cfc3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
Makefile.rule
View File

@ -60,6 +60,14 @@ VERSION = 0.3.1.dev
# This flag is always set for POWER8. Don't modify the flag # This flag is always set for POWER8. Don't modify the flag
# USE_OPENMP = 1 # 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 maximum number of threads. Basically it should be # You can define maximum number of threads. Basically it should be
# less than actual number of cores. If you don't specify one, it's # less than actual number of cores. If you don't specify one, it's
# automatically detected by the the script. # automatically detected by the the script.
@ -157,7 +165,8 @@ NO_AFFINITY = 1
# If any gemm arguement m, n or k is less or equal this threshold, gemm will be execute # If any gemm arguement m, n or k is less or equal this threshold, gemm will be execute
# with single thread. You can use this flag to avoid the overhead of multi-threading # with single thread. You can use this flag to avoid the overhead of multi-threading
# in small matrix sizes. The default value is 4. # 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 # GEMM_MULTITHREAD_THRESHOLD = 4
# If you need santy check by comparing reference BLAS. It'll be very # If you need santy check by comparing reference BLAS. It'll be very
@ -181,7 +190,7 @@ NO_AFFINITY = 1
COMMON_PROF = -pg COMMON_PROF = -pg
# Build Debug version # Build Debug version
# DEBUG = 1 DEBUG = 1
# Set maximum stack allocation. # Set maximum stack allocation.
# The default value is 2048. 0 disable stack allocation a may reduce GER and GEMV # The default value is 2048. 0 disable stack allocation a may reduce GER and GEMV