Hi!
I just compiled OpenBLAS and it's not passing in 2 tests of the BLAS-Tester
This is the Makefile.rule used to compile OpenBLAS
(my processor is a i5 3330 with 1024MB of L2 cache):
#
# Beginning of user configuration
#
# This library's version
VERSION = 0.3.0.dev
# 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
# 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
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 = 1
# 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
USE_OPENMP = 1
# 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
# automatically detected by the the script.
# NUM_THREADS = 24
# if you don't need to install the static library, please comment it in.
# NO_STATIC = 1
# if you don't need generate the shared library, please comment it in.
# NO_SHARED = 1
# If you don't need CBLAS interface, please comment it in.
# NO_CBLAS = 1
# If you only want CBLAS interface without installing Fortran compiler,
# please comment it in.
# ONLY_CBLAS = 1
# If you don't need LAPACK, please comment it in.
# If you set NO_LAPACK=1, the library automatically sets NO_LAPACKE=1.
# NO_LAPACK = 1
# If you don't need LAPACKE (C Interface to LAPACK), please comment it in.
# NO_LAPACKE = 1
# Build LAPACK Deprecated functions since LAPACK 3.6.0
BUILD_LAPACK_DEPRECATED = 1
# Build RecursiveLAPACK on top of LAPACK
# BUILD_RELAPACK = 1
# If you want to use legacy threaded Level 3 implementation.
# USE_SIMPLE_THREADED_LEVEL3 = 1
# 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
# are not sure(equivalent to "-i8" 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
# If you want to disable CPU/Memory affinity on Linux.
#NO_AFFINITY = 1
# if you are compiling for Linux and you have more than 16 numa nodes or more than 256 cpus
# BIGNUMA = 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 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 = 5
# 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)
# 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 mumber by THREAD_TIMEOUT
# CCOMMON_OPT += -DTHREAD_TIMEOUT=26
# Using special device driver for mapping physically contigous memory
# to the user space. If bigphysarea is enabled, it will use it.
# DEVICEDRIVER_ALLOCATION = 1
# If you need to synchronize FP CSR between threads (for x86/x86_64 only).
# CONSISTENT_FPCSR = 1
# 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
# in small matrix sizes. The default value is 4.
# GEMM_MULTITHREAD_THRESHOLD = 4
# If you need santy check by comparing reference BLAS. It'll be very
# slow (Not implemented yet).
# SANITY_CHECK = 1
# The installation directory.
PREFIX = /c/OpenBLAS-develop/build
# 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
# enable this flag only on 64bit Linux and if you need a thread safe lapack library
# 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=
#
# End of user configuration
#
This is the Makefile.rule used to compile BLAS-Tester:
#
# configuration
#
#
# Default compiler
# Supports gcc & icc.
#
CC = gcc
# CC = icc
FC = gfortran
#
# CPU architecture
#
# For i386 and x86-64 (default)
ARCH = X86
#
# For Loongson CPU
# ARCH = loongson
#
# For SW1600 CPU
# ARCH = sw1600
#
# For ARM
# ARCH = ARM
#
# For ARM 64-bit
# ARCH = ARM64
#
# define BINARY=32 or BINARY=64
#
BINARY=64
# the path to BLAS library
#
TEST_BLAS = /c/OpenBLAS-develop/build/lib/libopenblas.a
# The size of Level 2 Cache (default = 4M)
# 4M=4194304 6M=6291456 8M=8388608 12M=12582912
# 1M=1048576
L2SIZE = 1048576
# The number of threads (default = 1)
#
NUMTHREADS = 4
# Use OPENMP
#
USE_OPENMP = 1
# BLAS interface is compiled by ifort
#
# F_INTERFACE_INTEL = 1
# Use 64-bit int
#
# INTERFACE64 = 1
# Debug the library
#
DEBUG = 1
# Reference Level-3 BLAS is very slow. If you only want test
# the performance, please use this flag.
#
ONLY_PERFORMANCE=1
# Don't test i?amin level 1 BLAS function.
# If you test ATLAS, please use this flag
#
# NO_EXTENSION=1
# To test BLAS invalid reading.
#
#
TEST_INVALID_READ=1
And these are the outputs from xdl3blastst.exe and xzl3blastst.exe, in which I didn't pass:
xdl3blastst.exe
--------------------------------- GEMM ----------------------------------
TST# A B M N K ALPHA LDA LDB BETA LDC TIME MFLOP SpUp TEST
==== = = ==== ==== ==== ===== ==== ==== ===== ==== ===== ===== ==== =====
0 N N 100 100 100 1.0 1000 1000 1.0 1000 0.00 0.0 1.00 -----
0 N N 100 100 100 1.0 1000 1000 1.0 1000 0.00 2000.1 0.00 FAIL
1 N N 200 200 200 1.0 1000 1000 1.0 1000 0.00 0.0 1.00 -----
1 N N 200 200 200 1.0 1000 1000 1.0 1000 0.00 16001.2 0.00 FAIL
2 N N 300 300 300 1.0 1000 1000 1.0 1000 0.00 0.0 1.00 -----
2 N N 300 300 300 1.0 1000 1000 1.0 1000 0.00 26998.7 0.00 FAIL
3 N N 400 400 400 1.0 1000 1000 1.0 1000 0.00 0.0 1.00 -----
3 N N 400 400 400 1.0 1000 1000 1.0 1000 0.00 64004.6 0.00 FAIL
4 N N 500 500 500 1.0 1000 1000 1.0 1000 0.00 0.0 1.00 -----
4 N N 500 500 500 1.0 1000 1000 1.0 1000 0.01 25000.0 0.00 FAIL
5 N N 600 600 600 1.0 1000 1000 1.0 1000 0.00 0.0 1.00 -----
5 N N 600 600 600 1.0 1000 1000 1.0 1000 0.02 28799.8 0.00 FAIL
6 N N 700 700 700 1.0 1000 1000 1.0 1000 0.00 0.0 1.00 -----
6 N N 700 700 700 1.0 1000 1000 1.0 1000 0.02 36101.1 0.00 FAIL
7 N N 800 800 800 1.0 1000 1000 1.0 1000 0.00 0.0 1.00 -----
7 N N 800 800 800 1.0 1000 1000 1.0 1000 0.02 44519.4 0.00 FAIL
8 N N 900 900 900 1.0 1000 1000 1.0 1000 0.00 0.0 1.00 -----
8 N N 900 900 900 1.0 1000 1000 1.0 1000 0.04 40497.8 0.00 FAIL
9 N N 1000 1000 1000 1.0 1000 1000 1.0 1000 0.00 0.0 1.00 -----
9 N N 1000 1000 1000 1.0 1000 1000 1.0 1000 0.04 55552.2 0.00 FAIL
10 tests run, 0 passed
ERROR: resid=16594586171.078035, normD=89.889952, normA=28.793478, normB=29.226439, normC=28.989082, eps=2.220446e-015
resid=16594586171.078035
ERROR: resid=2773246963.051268, normD=218.792316, normA=56.642434, normB=57.305220, normC=54.731481, eps=2.220446e-015
resid=2773246963.051268
ERROR: resid=1094383692.194749, normD=403.595201, normA=81.700942, normB=82.799372, normC=81.839090, eps=2.220446e-015
resid=1094383692.194749
ERROR: resid=534562438.250687, normD=596.196173, normA=108.791732, normB=107.565588, normC=107.305327, eps=2.220446e-015
resid=534562438.250687
ERROR: resid=305866010.093331, normD=816.988601, normA=135.098887, normB=134.129053, normC=132.769989, eps=2.220446e-015
resid=305866010.093331
ERROR: resid=192610482.239102, normD=1069.112441, normA=161.428768, normB=160.691640, normC=160.611920, eps=2.220446e-015
resid=192610482.239102
ERROR: resid=138021619.603977, normD=1367.737912, normA=185.091087, normB=185.631790, normC=185.557983, eps=2.220446e-015
resid=138021619.603977
ERROR: resid=96740043.055165, normD=1660.811029, normA=213.176325, normB=211.591894, normC=214.262286, eps=2.220446e-015
resid=96740043.055165
ERROR: resid=74284120.110187, normD=1991.189904, normA=235.355207, normB=238.370610, normC=239.087816, eps=2.220446e-015
resid=74284120.110187
ERROR: resid=56641560.947299, normD=2339.706092, normA=263.700784, normB=267.147553, normC=264.072542, eps=2.220446e-015
resid=56641560.947299
xzl3blastst.exe
----------------------------------- GEMM ---------------------------------------
TST# A B M N K ALPHA LDA LDB BETA LDC TIME MFLOP SpUp TEST
==== = = ==== ==== ==== ==== ==== ==== ==== ==== ==== ==== ==== ===== ==== =====
0 N N 100 100 100 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 0.0 1.00 -----
0 N N 100 100 100 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 8000.6 0.00 FAIL
1 N N 200 200 200 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 0.0 1.00 -----
1 N N 200 200 200 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 64004.6 0.00 FAIL
2 N N 300 300 300 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 0.0 1.00 -----
2 N N 300 300 300 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 35999.7 0.00 FAIL
3 N N 400 400 400 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 0.0 1.00 -----
3 N N 400 400 400 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 39381.7 0.00 FAIL
4 N N 500 500 500 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 0.0 1.00 -----
4 N N 500 500 500 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 43474.2 0.00 FAIL
5 N N 600 600 600 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 0.0 1.00 -----
5 N N 600 600 600 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 40183.4 0.00 FAIL
6 N N 700 700 700 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 0.0 1.00 -----
6 N N 700 700 700 1.0 0.0 1000 1000 1.0 0.0 1000 0.1 43553.6 0.00 FAIL
7 N N 800 800 800 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 0.0 1.00 -----
7 N N 800 800 800 1.0 0.0 1000 1000 1.0 0.0 1000 0.2 23674.9 0.00 FAIL
8 N N 900 900 900 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 0.0 1.00 -----
8 N N 900 900 900 1.0 0.0 1000 1000 1.0 0.0 1000 0.1 43520.1 0.00 FAIL
9 N N 1000 1000 1000 1.0 0.0 1000 1000 1.0 0.0 1000 0.0 0.0 1.00 -----
9 N N 1000 1000 1000 1.0 0.0 1000 1000 1.0 0.0 1000 0.2 43475.9 0.00 FAIL
10 tests run, 0 passed
ERROR: resid=5808263227.808679, normD=216.237078, normA=55.385994, normB=54.860139, normC=55.180648, eps=2.220446e-015
resid=5808263227.808679
ERROR: resid=1074809828.113166, normD=601.797181, normA=106.491473, normB=109.570072, normC=108.054166, eps=2.220446e-015
resid=1074809828.113166
ERROR: resid=396457559.182390, normD=1083.087382, normA=161.254057, normB=159.568429, normC=159.385091, eps=2.220446e-015
resid=396457559.182390
ERROR: resid=199769392.057709, normD=1661.614599, normA=211.307150, normB=210.324956, normC=210.715331, eps=2.220446e-015
resid=199769392.057709
ERROR: resid=111071418.163279, normD=2253.468650, normA=264.344989, normB=264.029114, normC=261.827991, eps=2.220446e-015
resid=111071418.163279
ERROR: resid=71719253.247765, normD=3004.049181, normA=315.190676, normB=316.395238, normC=315.265541, eps=2.220446e-015
resid=71719253.247765
ERROR: resid=48877783.458658, normD=3768.493740, normA=367.077460, normB=365.469404, normC=369.750940, eps=2.220446e-015
resid=48877783.458658
ERROR: resid=35328098.327874, normD=4572.585438, normA=419.474251, normB=417.001526, normC=416.551214, eps=2.220446e-015
resid=35328098.327874
ERROR: resid=26326291.949775, normD=5440.816380, normA=468.969008, normB=471.419747, normC=467.777930, eps=2.220446e-015
resid=26326291.949775
ERROR: resid=20419316.036365, normD=6425.550719, normA=520.205707, normB=521.716708, normC=522.178614, eps=2.220446e-015
resid=20419316.036365