add support in init script for using 'archdetect' alternative to archspec (only if $EESSI_USE_ARCHDETECT is set to '1')

.github/workflows/tests_archdetect.yml

@@ -0,0 +1,33 @@
+# documentation: https://help.github.com/en/articles/workflow-syntax-for-github-actions
+name: Tests for eessi_archdetect.sh
+on: [push, pull_request]
+jobs:
+  build:
+    runs-on: ubuntu-20.04
+    strategy:
+      matrix:
+        proc_cpuinfo:
+          - x86_64/intel/haswell/archspec-linux-E5-2680-v3
+          - x86_64/intel/skylake_avx512/archspec-linux-6132
+          - x86_64/amd/zen2/Azure-CentOS7-7V12
+          - x86_64/amd/zen3/Azure-CentOS7-7V73X
+          - ppc64le/power9le/unknown-power9le
+          - aarch64/arm/neoverse-n1/Azure-Ubuntu20-Altra
+          - aarch64/arm/neoverse-n1/AWS-awslinux-graviton2
+          - aarch64/arm/neoverse-v1/AWS-awslinux-graviton3
+      fail-fast: false
+    steps:
+    - uses: actions/checkout@v2
+
+    - name: test eessi_archdetect.sh
+      run: |
+          export EESSI_MACHINE_TYPE=${{matrix.proc_cpuinfo}}
+          export EESSI_MACHINE_TYPE=${EESSI_MACHINE_TYPE%%/*}
+          export EESSI_PROC_CPUINFO=./tests/archdetect/${{matrix.proc_cpuinfo}}.cpuinfo
+          CPU_ARCH=$(./init/eessi_archdetect.sh cpupath)
+          if [[ $CPU_ARCH == "$( cat ./tests/archdetect/${{matrix.proc_cpuinfo}}.output )" ]]; then
+              echo "Test for ${{matrix.proc_cpuinfo}} PASSED: $CPU_ARCH" >&2
+          else
+              echo "Test for ${{matrix.proc_cpuinfo}} FAILED: $CPU_ARCH" >&2
+              exit 1
+          fi

init/arch_specs/eessi_arch_arm.spec

@@ -0,0 +1,6 @@
+# ARM CPU architecture specifications
+# Software path in EESSI 	| Vendor ID 	| List of defining CPU features
+"aarch64/arm/neoverse-n1"	"ARM"		"asimd"		# Ampere Altra
+"aarch64/arm/neoverse-n1"	""		"asimd"		# AWS Graviton2
+"aarch64/arm/neoverse-v1"	"ARM"		"asimd svei8mm" 
+"aarch64/arm/neoverse-v1"	""		"asimd svei8mm"	# AWS Graviton3

init/arch_specs/eessi_arch_ppc.spec

@@ -0,0 +1,3 @@
+# POWER CPU architecture specifications
+# Software path in EESSI 	| Vendor ID 	| List of defining CPU features
+"ppc64le/power9le"		""		"POWER9"	# IBM Power9

init/arch_specs/eessi_arch_x86.spec

@@ -0,0 +1,6 @@
+# x86_64 CPU architecture specifications
+# Software path in EESSI 	| Vendor ID 	| List of defining CPU features
+"x86_64/intel/haswell"		"GenuineIntel"	"avx2 fma" 		# Intel Haswell, Broadwell
+"x86_64/intel/skylake_avx512"	"GenuineIntel"	"avx2 fma avx512f avx512bw avx512cd avx512dq avx512vl"	# Intel Skylake, Cascade Lake
+"x86_64/amd/zen2"		"AuthenticAMD"	"avx2 fma"		# AMD Rome
+"x86_64/amd/zen3"		"AuthenticAMD"	"avx2 fma vaes"		# AMD Milan, Milan-X

init/eessi_archdetect.sh

@@ -0,0 +1,143 @@
+#!/usr/bin/env bash
+VERSION="1.0.0"
+
+# Logging
+LOG_LEVEL="INFO"
+
+timestamp () {
+    date "+%Y-%m-%d %H:%M:%S"
+}
+
+log () {
+    # Simple logger function
+    declare -A levels=([DEBUG]=0 [INFO]=1 [WARN]=2 [ERROR]=3)
+    msg_type="${1:-INFO}"
+    msg_body="${2:-'null'}"
+
+    [ ${levels[$msg_type]} ] || log "ERROR" "Unknown log level $msg_type"
+
+    # ignore messages below log level
+    [ ${levels[$msg_type]} -lt ${levels[$LOG_LEVEL]} ] && return 0
+    # print log message to standard error
+    echo "$(timestamp) [$msg_type] $msg_body" >&2
+    # exit after any error message
+    [ $msg_type == "ERROR" ] && exit 1
+}
+
+# Supported CPU specifications
+update_arch_specs(){
+    # Add contents of given spec file into an array
+    # 1: name of array with CPU arch specs
+    # 2: spec file with the additional specs
+
+    [ -z "$1" ] && echo "[ERROR] update_arch_specs: missing array in argument list" >&2 && exit 1
+    local -n arch_specs=$1
+
+    [ ! -f "$2" ] && echo "[ERROR] update_arch_specs: spec file not found: $2" >&2 && exit 1
+    local spec_file="$2"
+    while read spec_line; do
+       # format spec line as an array and append it to array with all CPU arch specs
+       arch_specs+=("(${spec_line})")
+    # remove comments from spec file
+    done < <(sed -E 's/(^|[\s\t])#.*$//g;/^\s*$/d' "$spec_file")
+}
+
+# CPU specification of host system
+get_cpuinfo(){
+    # Return the value from cpuinfo for the matching key
+    # 1: string with key pattern
+
+    [ -z "$1" ] && log "ERROR" "get_cpuinfo: missing key pattern in argument list"
+    cpuinfo_pattern="^${1}\s*:\s*"
+
+    # case insensitive match of key pattern and delete key pattern from result
+    grep -i "$cpuinfo_pattern" ${EESSI_PROC_CPUINFO:-/proc/cpuinfo} | tail -n 1 | sed "s/$cpuinfo_pattern//i"
+}
+
+check_allinfirst(){
+    # Return true if all given arguments after the first are found in the first one
+    # 1: reference string of space separated values
+    # 2,3..: each additional argument is a single value to be found in the reference string
+
+    [ -z "$1" ] && log "ERROR" "check_allinfirst: missing argument with reference string"
+    reference="$1"
+    shift
+
+    for candidate in "$@"; do
+        [[ " $reference " == *" $candidate "* ]] || return 1
+    done
+    return 0
+}
+
+cpupath(){
+    # Identify the best matching CPU architecture from a list of supported specifications for the host CPU
+    # Return the path to the installation files in EESSI of the best matching architecture
+    local cpu_arch_spec=()
+
+    # Identify the host CPU architecture
+    local machine_type=${EESSI_MACHINE_TYPE:-$(uname -m)}
+    log "DEBUG" "cpupath: Host CPU architecture identified as '$machine_type'"
+
+    # Populate list of supported specs for this architecture
+    case $machine_type in
+        "x86_64") local spec_file="eessi_arch_x86.spec";;
+        "aarch64") local spec_file="eessi_arch_arm.spec";;
+        "ppc64le") local spec_file="eessi_arch_ppc.spec";;
+        *) log "ERROR" "cpupath: Unsupported CPU architecture $machine_type"
+    esac
+    # spec files are located in a subfolder with this script
+    local base_dir=$(dirname $(realpath $0))
+    update_arch_specs cpu_arch_spec "$base_dir/arch_specs/${spec_file}"
+
+    # Identify the host CPU vendor
+    local cpu_vendor_tag="vendor[ _]id"
+    local cpu_vendor=$(get_cpuinfo "$cpu_vendor_tag")
+    log "DEBUG" "cpupath: CPU vendor of host system: '$cpu_vendor'"
+
+    # Identify the host CPU flags or features
+    local cpu_flag_tag='flags'
+    # cpuinfo systems print different line identifiers, eg features, instead of flags
+    [ "${cpu_vendor}" == "ARM" ] && cpu_flag_tag='flags'
+    [ "${machine_type}" == "aarch64" ] && [ "${cpu_vendor}x" == "x" ] && cpu_flag_tag='features'
+    [ "${machine_type}" == "ppc64le" ] && cpu_flag_tag='cpu'
+
+    local cpu_flags=$(get_cpuinfo "$cpu_flag_tag")
+    log "DEBUG" "cpupath: CPU flags of host system: '$cpu_flags'"
+
+    # Default to generic CPU
+    local best_arch_match="generic"
+
+    # Iterate over the supported CPU specifications to find the best match for host CPU
+    # Order of the specifications matters, the last one to match will be selected
+    for arch in "${cpu_arch_spec[@]}"; do
+        eval "arch_spec=$arch"
+        if [ "${cpu_vendor}x" == "${arch_spec[1]}x" ]; then
+            # each flag in this CPU specification must be found in the list of flags of the host
+            check_allinfirst "${cpu_flags[*]}" ${arch_spec[2]} && best_arch_match=${arch_spec[0]} && \
+                log "DEBUG" "cpupath: host CPU best match updated to $best_arch_match"
+        fi
+    done
+
+    log "INFO" "cpupath: best match for host CPU: $best_arch_match"
+    echo "$best_arch_match"
+}
+
+# Parse command line arguments
+USAGE="Usage: eessi_archdetect.sh [-h][-d] <action>"
+
+while getopts 'hdv' OPTION; do
+    case "$OPTION" in
+        h) echo "$USAGE"; exit 0;;
+        d) LOG_LEVEL="DEBUG";;
+        v) echo "eessi_archdetect.sh v$VERSION"; exit 0;;
+        ?) echo "$USAGE"; exit 1;;
+    esac
+done
+shift "$(($OPTIND -1))"
+
+ARGUMENT=${1:-none}
+
+case "$ARGUMENT" in
+    "cpupath") cpupath; exit;;
+    *) echo "$USAGE"; log "ERROR" "Missing <action> argument";;
+esac

init/eessi_environment_variables

@@ -25,9 +25,16 @@ if [ -d $EESSI_PREFIX ]; then
   if [ -d $EESSI_EPREFIX ]; then
 
     # determine subdirectory in software layer
-    # note: eessi_software_subdir_for_host.py will pick up value from $EESSI_SOFTWARE_SUBDIR_OVERRIDE if it's defined!
-    export EESSI_EPREFIX_PYTHON=$EESSI_EPREFIX/usr/bin/python3
-    export EESSI_SOFTWARE_SUBDIR=$($EESSI_EPREFIX_PYTHON ${EESSI_INIT_DIR_PATH}/eessi_software_subdir_for_host.py $EESSI_PREFIX)
+    if [ "$EESSI_USE_ARCHDETECT" == "1" ]; then
+      # if archdetect is enabled, use internal code
+      export EESSI_SOFTWARE_SUBDIR=$(${EESSI_INIT_DIR_PATH}/eessi_archdetect.sh cpupath)
+      echo "archdetect says ${EESSI_SOFTWARE_SUBDIR}" >> $output
+    else
+      # note: eessi_software_subdir_for_host.py will pick up value from $EESSI_SOFTWARE_SUBDIR_OVERRIDE if it's defined!
+      export EESSI_EPREFIX_PYTHON=$EESSI_EPREFIX/usr/bin/python3
+      export EESSI_SOFTWARE_SUBDIR=$($EESSI_EPREFIX_PYTHON ${EESSI_INIT_DIR_PATH}/eessi_software_subdir_for_host.py $EESSI_PREFIX)
+      echo "archspec says ${EESSI_SOFTWARE_SUBDIR}" >> $output
+    fi
     if [ ! -z $EESSI_SOFTWARE_SUBDIR ]; then
 
         echo "Using ${EESSI_SOFTWARE_SUBDIR} as software subdirectory." >> $output

tests/archdetect/aarch64/arm/neoverse-n1/AWS-awslinux-graviton2.cpuinfo

@@ -0,0 +1,8 @@
+processor       : 0
+BogoMIPS        : 243.75
+Features        : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm lrcpc dcpop asimddp ssbs
+CPU implementer : 0x41
+CPU architecture: 8
+CPU variant     : 0x3
+CPU part        : 0xd0c
+CPU revision    : 1

tests/archdetect/aarch64/arm/neoverse-n1/AWS-awslinux-graviton2.output

@@ -0,0 +1 @@
+aarch64/arm/neoverse-n1

tests/archdetect/aarch64/arm/neoverse-n1/Azure-Ubuntu20-Altra.cpuinfo

@@ -0,0 +1,30 @@
+Architecture:                    aarch64
+CPU op-mode(s):                  32-bit, 64-bit
+Byte Order:                      Little Endian
+CPU(s):                          64
+On-line CPU(s) list:             0-63
+Thread(s) per core:              1
+Core(s) per socket:              64
+Socket(s):                       1
+NUMA node(s):                    1
+Vendor ID:                       ARM
+Model:                           1
+Model name:                      Neoverse-N1
+Stepping:                        r3p1
+BogoMIPS:                        50.00
+L1d cache:                       4 MiB
+L1i cache:                       4 MiB
+L2 cache:                        64 MiB
+L3 cache:                        32 MiB
+NUMA node0 CPU(s):               0-63
+Vulnerability Itlb multihit:     Not affected
+Vulnerability L1tf:              Not affected
+Vulnerability Mds:               Not affected
+Vulnerability Meltdown:          Mitigation; PTI
+Vulnerability Mmio stale data:   Not affected
+Vulnerability Spec store bypass: Not affected
+Vulnerability Spectre v1:        Mitigation; __user pointer sanitization
+Vulnerability Spectre v2:        Mitigation; CSV2, BHB
+Vulnerability Srbds:             Not affected
+Vulnerability Tsx async abort:   Not affected
+Flags:                           fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm lrcpc dcpop asimddp

tests/archdetect/aarch64/arm/neoverse-n1/Azure-Ubuntu20-Altra.output

@@ -0,0 +1 @@
+aarch64/arm/neoverse-n1

tests/archdetect/aarch64/arm/neoverse-v1/AWS-awslinux-graviton3.cpuinfo

@@ -0,0 +1,8 @@
+processor	: 0
+BogoMIPS	: 2100.00
+Features	: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm ssbs paca pacg dcpodp svei8mm svebf16 i8mm bf16 dgh rng
+CPU implementer	: 0x41
+CPU architecture: 8
+CPU variant	: 0x1
+CPU part	: 0xd40
+CPU revision	: 1

tests/archdetect/aarch64/arm/neoverse-v1/AWS-awslinux-graviton3.output

@@ -0,0 +1 @@
+aarch64/arm/neoverse-v1

tests/archdetect/ppc64le/power9le/unknown-power9le.cpuinfo

@@ -0,0 +1,4 @@
+processor	: 0
+cpu		: POWER9 (architected), altivec supported
+clock		: 2200.000000MHz
+revision	: 2.2 (pvr 004e 1202)

tests/archdetect/ppc64le/power9le/unknown-power9le.output

@@ -0,0 +1 @@
+ppc64le/power9le

tests/archdetect/x86_64/amd/zen2/Azure-CentOS7-7V12.cpuinfo

@@ -0,0 +1,27 @@
+Architecture:          x86_64
+CPU op-mode(s):        32-bit, 64-bit
+Byte Order:            Little Endian
+CPU(s):                120
+On-line CPU(s) list:   0-119
+Thread(s) per core:    1
+Core(s) per socket:    60
+Socket(s):             2
+NUMA node(s):          4
+Vendor ID:             AuthenticAMD
+CPU family:            23
+Model:                 49
+Model name:            AMD EPYC 7V12 64-Core Processor
+Stepping:              0
+CPU MHz:               2445.424
+BogoMIPS:              4890.84
+Hypervisor vendor:     Microsoft
+Virtualization type:   full
+L1d cache:             32K
+L1i cache:             32K
+L2 cache:              512K
+L3 cache:              16384K
+NUMA node0 CPU(s):     0-29
+NUMA node1 CPU(s):     30-59
+NUMA node2 CPU(s):     60-89
+NUMA node3 CPU(s):     90-119
+Flags:                 fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm art rep_good nopl extd_apicid aperfmperf eagerfpu pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext retpoline_amd ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr arat umip

tests/archdetect/x86_64/amd/zen2/Azure-CentOS7-7V12.output

@@ -0,0 +1 @@
+x86_64/amd/zen2

tests/archdetect/x86_64/amd/zen3/Azure-CentOS7-7V73X.cpuinfo

@@ -0,0 +1,27 @@
+Architecture:          x86_64
+CPU op-mode(s):        32-bit, 64-bit
+Byte Order:            Little Endian
+CPU(s):                120
+On-line CPU(s) list:   0-119
+Thread(s) per core:    1
+Core(s) per socket:    60
+Socket(s):             2
+NUMA node(s):          4
+Vendor ID:             AuthenticAMD
+CPU family:            25
+Model:                 1
+Model name:            AMD EPYC 7V73X 64-Core Processor
+Stepping:              2
+CPU MHz:               1846.550
+BogoMIPS:              3693.10
+Hypervisor vendor:     Microsoft
+Virtualization type:   full
+L1d cache:             32K
+L1i cache:             32K
+L2 cache:              512K
+L3 cache:              98304K
+NUMA node0 CPU(s):     0-29
+NUMA node1 CPU(s):     30-59
+NUMA node2 CPU(s):     60-89
+NUMA node3 CPU(s):     90-119
+Flags:                 fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm art rep_good nopl extd_apicid aperfmperf eagerfpu pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single retpoline_amd vmmcall fsgsbase bmi1 avx2 smep bmi2 invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr arat umip vaes vpclmulqdq

tests/archdetect/x86_64/amd/zen3/Azure-CentOS7-7V73X.output

@@ -0,0 +1 @@
+x86_64/amd/zen3

tests/archdetect/x86_64/intel/haswell/archspec-linux-E5-2680-v3.cpuinfo

@@ -0,0 +1,25 @@
+processor	: 0
+vendor_id	: GenuineIntel
+cpu family	: 6
+model		: 63
+model name	: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
+stepping	: 2
+microcode	: 0x3c
+cpu MHz		: 1757.910
+cache size	: 30720 KB
+physical id	: 0
+siblings	: 12
+core id		: 0
+cpu cores	: 12
+apicid		: 0
+initial apicid	: 0
+fpu		: yes
+fpu_exception	: yes
+cpuid level	: 15
+wp		: yes
+flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm epb invpcid_single tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm xsaveopt cqm_llc cqm_occup_llc ibpb ibrs stibp dtherm arat pln pts spec_ctrl intel_stibp
+bogomips	: 4987.97
+clflush size	: 64
+cache_alignment	: 64
+address sizes	: 46 bits physical, 48 bits virtual
+power management:

tests/archdetect/x86_64/intel/haswell/archspec-linux-E5-2680-v3.output

@@ -0,0 +1 @@
+x86_64/intel/haswell

tests/archdetect/x86_64/intel/skylake_avx512/archspec-linux-6132.cpuinfo

@@ -0,0 +1,25 @@
+processor	: 0
+vendor_id	: GenuineIntel
+cpu family	: 6
+model		: 85
+model name	: Intel(R) Xeon(R) Gold 6132 CPU @ 2.60GHz
+stepping	: 4
+microcode	: 0x200004d
+cpu MHz		: 2600.000
+cache size	: 19712 KB
+physical id	: 0
+siblings	: 14
+core id		: 0
+cpu cores	: 14
+apicid		: 0
+initial apicid	: 0
+fpu		: yes
+fpu_exception	: yes
+cpuid level	: 22
+wp		: yes
+flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch epb cat_l3 cdp_l3 invpcid_single intel_pt tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local ibpb ibrs stibp dtherm ida arat pln pts spec_ctrl intel_stibp ssbd
+bogomips	: 5200.00
+clflush size	: 64
+cache_alignment	: 64
+address sizes	: 46 bits physical, 48 bits virtual
+power management:

tests/archdetect/x86_64/intel/skylake_avx512/archspec-linux-6132.output

@@ -0,0 +1 @@
+x86_64/intel/skylake_avx512