add foss-2022a.eb

Golden_Repo/b/BLIS/BLIS-0.9.0-GCC-11.3.0.eb

+easyblock = 'ConfigureMake'
+
+name = 'BLIS'
+version = '0.9.0'
+
+homepage = 'https://github.com/flame/blis/'
+description = """BLIS is a portable software framework for instantiating high-performance
+BLAS-like dense linear algebra libraries."""
+
+toolchain = {'name': 'GCC', 'version': '11.3.0'}
+
+source_urls = ['https://github.com/flame/blis/archive/']
+sources = ['%(version)s.tar.gz']
+patches = [
+    '%(name)s-%(version)s_disable_power9_kernels.patch',
+    '%(name)s-%(version)s_enable_ppc_autodetect.patch',
+]
+checksums = [
+    '1135f664be7355427b91025075562805cdc6cc730d3173f83533b2c5dcc2f308',  # 0.9.0.tar.gz
+    # BLIS-0.9.0_disable_power9_kernels.patch
+    'ed7a326bc5c5c21c42faefbec2fd7be609d1c7236981b466475edace39307279',
+    # BLIS-0.9.0_enable_ppc_autodetect.patch
+    'f373fb252c0d14036fb631f048091976cceb02abb3e570a97fbaeac2fbb12328',
+]
+builddependencies = [
+    ('Python', '3.10.4', '-bare'),
+    ('Perl', '5.34.1'),
+]
+
+configopts = '--enable-cblas --enable-threading=openmp --enable-shared CC="$CC" auto'
+
+runtest = 'check'
+
+sanity_check_paths = {
+    'files': ['include/blis/cblas.h', 'include/blis/blis.h',
+              'lib/libblis.a', 'lib/libblis.%s' % SHLIB_EXT],
+    'dirs': [],
+}
+
+modextrapaths = {'CPATH': 'include/blis'}
+
+moduleclass = 'numlib'

Golden_Repo/b/BLIS/BLIS-0.9.0_disable_power9_kernels.patch

+There seemingly are bugs in the Power9 kernels.
+Workaround this by using the generic kernels on Power9 introduced by
+https://github.com/flame/blis/commit/ee9ff988c49f16696679d4c6cd3dcfcac7295be7
+See https://github.com/flame/blis/issues/621
+
+diff --git a/build/detect/config/config_detect.c b/build/detect/config/config_detect.c
+index 5e29def..5603163 100644
+--- a/build/detect/config/config_detect.c
++++ b/build/detect/config/config_detect.c
+@@ -70,6 +70,8 @@
+ int main( int argc, char** argv )
+ {
+ 	arch_t id = bli_cpuid_query_id();
++ 	if(id == BLIS_ARCH_POWER9)
++ 		id = BLIS_ARCH_GENERIC;
+ 	char*  s  = bli_arch_string( id );
+ 
+ 	printf( "%s\n", s );

Golden_Repo/b/BLIS/BLIS-0.9.0_enable_ppc_autodetect.patch

+Add autodetection for POWER7, POWER9 & POWER10
+See https://github.com/amd/blis/pull/6
+
+Author: Alexander Grund (TU Dresden)
+diff -ur a/frame/base/bli_cpuid.c b/frame/base/bli_cpuid.c
+--- a/frame/base/bli_cpuid.c	2022-04-01 15:12:06.000000000 +0200
++++ b/frame/base/bli_cpuid.c	2022-07-07 16:15:43.724020000 +0200
+@@ -485,7 +485,7 @@
+ 	return TRUE;
+ }
+ 
+-#elif defined(__aarch64__) || defined(__arm__) || defined(_M_ARM)
++#elif defined(__aarch64__) || defined(__arm__) || defined(_M_ARM) || defined(_ARCH_PPC)
+ 
+ arch_t bli_cpuid_query_id( void )
+ {
+@@ -530,9 +530,14 @@
+ 			return BLIS_ARCH_GENERIC;
+ 		}
+ 	}
+-	else if ( vendor == VENDOR_UNKNOWN )
++	else if ( vendor == VENDOR_IBM )
+ 	{
+-		return BLIS_ARCH_GENERIC;
++		if ( model == MODEL_POWER7)
++			return BLIS_ARCH_POWER7;
++		else if ( model == MODEL_POWER9)
++			return BLIS_ARCH_POWER9;
++		else if ( model == MODEL_POWER10)
++			return BLIS_ARCH_POWER10;
+ 	}
+ 
+ 	return BLIS_ARCH_GENERIC;
+@@ -1203,7 +1208,7 @@
+ 	return VENDOR_ARM;
+ }
+ 
+-#elif defined(__arm__) || defined(_M_ARM)
++#elif defined(__arm__) || defined(_M_ARM) || defined(_ARCH_PPC)
+ 
+ /* 
+    I can't easily find documentation to do this as for aarch64, though
+@@ -1240,6 +1245,20 @@
+ 	char  feat_str[ TEMP_BUFFER_SIZE ];
+ 	char* r_val;
+ 
++#ifdef _ARCH_PPC
++	r_val = find_string_in( "cpu", proc_str, TEMP_BUFFER_SIZE, pci_str );
++	if ( r_val == NULL ) return VENDOR_IBM;
++
++	if ( strstr( proc_str, "POWER7" ) != NULL )
++		*model = MODEL_POWER7;
++	else if ( strstr( proc_str, "POWER9" ) != NULL )
++		*model = MODEL_POWER9;
++	else if ( strstr( proc_str, "POWER10" ) != NULL )
++		*model = MODEL_POWER10;
++
++	return VENDOR_IBM;
++#endif
++
+ 	//printf( "bli_cpuid_query(): beginning search\n" );
+ 
+ 	// Search /proc/cpuinfo for the 'Processor' entry.
+diff -ur a/frame/base/bli_cpuid.h b/frame/base/bli_cpuid.h
+--- a/frame/base/bli_cpuid.h	2022-04-01 15:12:06.000000000 +0200
++++ b/frame/base/bli_cpuid.h	2022-07-07 16:09:22.617023000 +0200
+@@ -161,19 +161,23 @@
+ 	FEATURE_AVX512VL = 0x4000
+ };
+ 
+-#elif defined(__aarch64__) || defined(__arm__) || defined(_M_ARM)
++#elif defined(__aarch64__) || defined(__arm__) || defined(_M_ARM) || defined(_ARCH_PPC)
+ 
+ char* find_string_in( char* target, char* buffer, size_t buf_len, char* filepath );
+ 
+ enum
+ {
+ 	VENDOR_ARM = 0,
++	VENDOR_IBM,
+ 	VENDOR_UNKNOWN
+ };
+ enum
+ {
+ 	MODEL_ARMV7 = 0,
+ 	MODEL_ARMV8,
++	MODEL_POWER7,
++	MODEL_POWER9,
++	MODEL_POWER10,
+ 	MODEL_UNKNOWN
+ };
+ enum

Golden_Repo/f/FFTW.MPI/FFTW.MPI-3.3.10-gompi-2022a.eb

+name = 'FFTW.MPI'
+version = '3.3.10'
+
+homepage = 'https://www.fftw.org'
+description = """FFTW is a C subroutine library for computing the discrete Fourier transform (DFT)
+in one or more dimensions, of arbitrary input size, and of both real and complex data."""
+
+toolchain = {'name': 'gompi', 'version': '2022a'}
+toolchainopts = {'pic': True}
+
+source_urls = [homepage]
+sources = ['fftw-%(version)s.tar.gz']
+checksums = ['56c932549852cddcfafdab3820b0200c7742675be92179e59e6215b340e26467']
+
+dependencies = [('FFTW', '3.3.10')]
+
+runtest = 'check'
+
+moduleclass = 'numlib'

Golden_Repo/f/FFTW/FFTW-3.3.10-GCC-11.3.0.eb

+name = 'FFTW'
+version = '3.3.10'
+
+homepage = 'https://www.fftw.org'
+description = """FFTW is a C subroutine library for computing the discrete Fourier transform (DFT)
+in one or more dimensions, of arbitrary input size, and of both real and complex data."""
+
+toolchain = {'name': 'GCC', 'version': '11.3.0'}
+toolchainopts = {'pic': True}
+
+source_urls = [homepage]
+sources = [SOURCELOWER_TAR_GZ]
+checksums = ['56c932549852cddcfafdab3820b0200c7742675be92179e59e6215b340e26467']
+
+runtest = 'check'
+
+moduleclass = 'numlib'

Golden_Repo/f/FlexiBLAS/FlexiBLAS-3.2.0-GCC-11.3.0.eb

+easyblock = 'Bundle'
+
+name = 'FlexiBLAS'
+version = '3.2.0'
+
+homepage = 'https://gitlab.mpi-magdeburg.mpg.de/software/flexiblas-release'
+description = """FlexiBLAS is a wrapper library that enables the exchange of the BLAS and LAPACK implementation
+used by a program without recompiling or relinking it."""
+
+toolchain = {'name': 'GCC', 'version': '11.3.0'}
+local_extra_flags = "-fstack-protector-strong -fstack-clash-protection"
+toolchainopts = {'pic': True, 'extra_cflags': local_extra_flags, 'extra_fflags': local_extra_flags}
+
+builddependencies = [
+    ('CMake', '3.23.1'),
+    ('Python', '3.10.4', '-bare'),  # required for running the tests
+    ('BLIS', '0.9.0'),
+]
+
+dependencies = [
+    ('BLIS', '0.9.0'),
+    ('OpenBLAS', '0.3.20'),
+    ('imkl', {'arch=*': '2022.1.0', 'arch=aarch64': False}, '', SYSTEM),
+]
+
+# note: first listed backend will be used as default by FlexiBLAS,
+# unless otherwise specified via easyconfig parameter flexiblas_default
+local_backends = ['OpenBLAS', 'BLIS']
+
+# imkl supplies its backend via the imkl module, not as a dependency
+if ARCH == 'x86_64':
+    local_backends = local_backends = ['imkl', 'OpenBLAS', 'BLIS']
+
+default_component_specs = {'start_dir': '%(namelower)s-%(version)s'}
+sanity_check_all_components = True
+
+# Also build and install LAPACKE, which FlexiBLAS does not support yet
+components = [
+    (name, version, {
+        'source_urls': ['https://github.com/mpimd-csc/flexiblas/releases/download/v%(version)s/'],
+        'sources': [SOURCELOWER_TAR_GZ],
+        'checksums': ['a3f4d66a30b6fa6473e492de86d34abc5f9d4e69d4d91ba23618388e8df05904'],
+        'backends': local_backends,
+    }),
+    ('LAPACK', '3.10.1', {
+        'easyblock': 'CMakeMake',
+        'source_urls': ['https://github.com/Reference-LAPACK/lapack/archive/'],
+        'sources': ['v%(version)s.tar.gz'],
+        'checksums': ['cd005cd021f144d7d5f7f33c943942db9f03a28d110d6a3b80d718a295f7f714'],
+        'configopts': ('-DBUILD_SHARED_LIBS=ON -DUSE_OPTIMIZED_BLAS=ON -DLAPACKE=ON '
+                       '-DUSE_OPTIMIZED_LAPACK=ON -DBUILD_DEPRECATED=ON '
+                       '-DCMAKE_INSTALL_INCLUDEDIR=%(installdir)s/include/flexiblas'),
+        'sanity_check_paths': {
+            'files': ['lib/liblapacke.%s' % SHLIB_EXT, 'include/flexiblas/lapacke.h'],
+            'dirs': [],
+        },
+    }),
+]
+
+moduleclass = 'lib'

Golden_Repo/f/foss/foss-2022a.eb

+easyblock = 'Toolchain'
+
+name = 'foss'
+version = '2022a'
+
+homepage = 'https://easybuild.readthedocs.io/en/master/Common-toolchains.html#foss-toolchain'
+description = """GNU Compiler Collection (GCC) based compiler toolchain, including
+ OpenMPI for MPI support, OpenBLAS (BLAS and LAPACK support), FFTW and ScaLAPACK."""
+
+toolchain = SYSTEM
+
+local_gccver = '11.3.0'
+
+# toolchain used to build foss dependencies
+local_comp_mpi_tc = ('gompi', version)
+
+# we need GCC and OpenMPI as explicit dependencies instead of gompi toolchain
+# because of toolchain preparation functions
+dependencies = [
+    ('GCC', local_gccver),
+    ('OpenMPI', '4.1.4', '', ('GCC', local_gccver)),
+    ('FlexiBLAS', '3.2.0', '', ('GCC', local_gccver)),
+    ('FFTW', '3.3.10', '', ('GCC', local_gccver)),
+    ('FFTW.MPI', '3.3.10', '', local_comp_mpi_tc),
+    ('ScaLAPACK', '2.2.0', '-fb', local_comp_mpi_tc),
+]
+
+moduleclass = 'toolchain'

Golden_Repo/g/gompi/gompi-2022a.eb

+easyblock = 'Toolchain'
+
+name = 'gompi'
+version = '2022a'
+
+homepage = '(none)'
+description = """GNU Compiler Collection (GCC) based compiler toolchain,
+ including OpenMPI for MPI support."""
+
+toolchain = SYSTEM
+
+local_gccver = '11.3.0'
+
+# compiler toolchain dependencies
+dependencies = [
+    ('GCC', local_gccver),  # includes both GCC and binutils
+    ('OpenMPI', '4.1.4', '', ('GCC', local_gccver)),
+]
+
+moduleclass = 'toolchain'

Golden_Repo/i/imkl/imkl-2022.1.0.eb

+name = 'imkl'
+version = '2022.1.0'
+
+homepage = 'https://software.intel.com/content/www/us/en/develop/tools/oneapi/components/onemkl.html'
+description = "Intel oneAPI Math Kernel Library"
+
+toolchain = SYSTEM
+
+# see https://software.intel.com/content/www/us/en/develop/articles/oneapi-standalone-components.html
+source_urls = ['https://registrationcenter-download.intel.com/akdlm/irc_nas/18721/']
+sources = ['l_onemkl_p_%(version)s.223_offline.sh']
+checksums = ['4b325a3c4c56e52f4ce6c8fbb55d7684adc16425000afc860464c0f29ea4563e']
+
+interfaces = False
+
+installopts = "--download-cache=%(builddir)s/cache --download-dir=%(builddir)s/download --log-dir=%(builddir)s/log"
+
+moduleclass = 'numlib'

Golden_Repo/o/OpenBLAS/OpenBLAS-0.3.15_workaround-gcc-miscompilation.patch

+Workaround optimizer bug in GCC on POWER9.
+See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100799
+
+Author: Alexander Grund (TU Dresden)
+
+diff --git a/Makefile.power b/Makefile.power
+index 946f5523..96b14dca 100644
+--- a/Makefile.power
++++ b/Makefile.power
+@@ -35,6 +35,7 @@ endif
+ ifneq ($(F_COMPILER), PGI)
+ FCOMMON_OPT += -O2 -frecursive -fno-fast-math
+ ifeq ($(C_COMPILER), GCC)
++FCOMMON_OPT += -fstack-protector-strong
+ ifneq ($(GCCVERSIONGT4), 1)
+ $(warning your compiler is too old to fully support POWER9, getting a newer version of gcc is recommended)
+ FCOMMON_OPT += -mcpu=power8 -mtune=power8 

Golden_Repo/o/OpenBLAS/OpenBLAS-0.3.20-GCC-11.3.0.eb

+name = 'OpenBLAS'
+version = '0.3.20'
+
+homepage = 'http://www.openblas.net/'
+description = "OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version."
+
+toolchain = {'name': 'GCC', 'version': '11.3.0'}
+
+source_urls = [
+    # order matters, trying to download the large.tgz/timing.tgz LAPACK tarballs from GitHub causes trouble
+    'https://www.netlib.org/lapack/timing/',
+    'https://github.com/xianyi/OpenBLAS/archive/',
+]
+sources = ['v%(version)s.tar.gz']
+patches = [
+    ('large.tgz', '.'),
+    ('timing.tgz', '.'),
+    'OpenBLAS-0.3.15_workaround-gcc-miscompilation.patch',
+]
+checksums = [
+    '8495c9affc536253648e942908e88e097f2ec7753ede55aca52e5dead3029e3c',  # v0.3.20.tar.gz
+    'f328d88b7fa97722f271d7d0cfea1c220e0f8e5ed5ff01d8ef1eb51d6f4243a1',  # large.tgz
+    '999c65f8ea8bd4eac7f1c7f3463d4946917afd20a997807300fe35d70122f3af',  # timing.tgz
+    # OpenBLAS-0.3.15_workaround-gcc-miscompilation.patch
+    'e6b326fb8c4a8a6fd07741d9983c37a72c55c9ff9a4f74a80e1352ce5f975971',
+]
+
+# extensive testing can be enabled by uncommenting the line below
+# runtest = 'PATH=.:$PATH lapack-timing'
+
+moduleclass = 'numlib'

Golden_Repo/s/ScaLAPACK/ScaLAPACK-2.2.0-gompi-2022a-fb.eb

+name = 'ScaLAPACK'
+version = '2.2.0'
+versionsuffix = '-fb'
+
+homepage = 'https://www.netlib.org/scalapack/'
+description = """The ScaLAPACK (or Scalable LAPACK) library includes a subset of LAPACK routines
+ redesigned for distributed memory MIMD parallel computers."""
+
+toolchain = {'name': 'gompi', 'version': '2022a'}
+toolchainopts = {'pic': True}
+
+source_urls = [homepage]
+sources = [SOURCELOWER_TGZ]
+patches = ['ScaLAPACK-%(version)s_fix-GCC-10.patch']
+checksums = [
+    '40b9406c20735a9a3009d863318cb8d3e496fb073d201c5463df810e01ab2a57',  # scalapack-2.2.0.tgz
+    'f6bc3c6dee012ba4a696548a2e12b6aae932ce4fd5a142153b338839f52b5906',  # ScaLAPACK-2.2.0_fix-GCC-10.patch
+]
+
+builddependencies = [
+    ('CMake', '3.23.1'),
+]
+
+dependencies = [
+    ('FlexiBLAS', '3.2.0'),
+]
+
+# Config Opts based on AOCL User Guide:
+# https://developer.amd.com/wp-content/resources/AOCL_User%20Guide_2.2.pdf
+
+configopts = '-DBUILD_SHARED_LIBS=ON '
+configopts += '-DBLAS_LIBRARIES="$EBROOTFLEXIBLAS/lib/libflexiblas.%s" ' % SHLIB_EXT
+configopts += '-DLAPACK_LIBRARIES="$EBROOTFLEXIBLAS/lib/libflexiblas.%s" ' % SHLIB_EXT
+configopts += '-DCMAKE_C_COMPILER=mpicc '
+configopts += '-DCMAKE_Fortran_COMPILER=mpif90 '
+configopts += '-DCMAKE_Fortran_FLAGS="-lpthread -fopenmp $DCMAKE_Fortran_FLAGS" '
+
+sanity_check_paths = {
+    'files': ['lib/libscalapack.%s' % SHLIB_EXT, 'lib64/libscalapack.%s' % SHLIB_EXT],
+    'dirs': ["lib", "lib64"],
+}
+
+moduleclass = 'numlib'