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

init/archdetect.md

@@ -0,0 +1,96 @@
+# archdetect
+
+bash based script to detect e.g. cpu architectures and provide cpupath for setting pointer to optimized software
+
+
+example lscpu outputs:
+
+# Zen2
+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
+
+# Zen3
+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
+
+# Arm Ampere Altra
+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

init/eessi_archdetect.sh

@@ -0,0 +1,74 @@
+#!/bin/bash
+
+# current pathways implemented in EESSI
+# x86_64/generic
+# x86_64/intel/haswell
+# x86_64/intel/skylake_avx512
+# x86_64/amd/zen2
+# x86_64/amd/zen3
+# aarch64/generic
+# ppc64le/generic
+# ppc64le/power9le
+
+ARGUMENT=${1:-none}
+
+cpupath () {
+  # let the kernel tell base machine type
+  MACHINE_TYPE=$(uname -m)
+
+  # fallback path
+  CPU_PATH="${MACHINE_TYPE}/generic"
+
+  if [ ${MACHINE_TYPE} == "aarch64" ]; then
+    echo ${CPU_PATH}
+    exit
+  fi
+
+  if [ ${MACHINE_TYPE} == "ppc64le" ]; then
+    echo ${CPU_PATH} "not sure what to do next..."
+    echo "please mail output of lscpu to me..."
+    exit
+  fi
+
+  if [ ${MACHINE_TYPE} == "x86_64" ]; then
+    # check for vendor info, if available, for x86_64
+    CPUINFO_VENDOR_FLAG=$(grep -m 1 ^vendor_id /proc/cpuinfo)
+    [[ $CPUINFO_VENDOR_FLAG =~ .*GenuineIntel* ]] && CPU_VENDOR=intel
+    [[ $CPU_VENDOR_FLAG =~ .*AuthenticAMD* ]] && CPU_VENDOR=amd
+
+    CPU_FLAGS=$(grep -m 1 ^flags /proc/cpuinfo)
+    [[ $CPU_FLAGS =~ .*avx2* ]] && HAS_AVX2=true
+    [[ $CPU_FLAGS =~ .*fma* ]] && HAS_FMA=true
+    [[ $CPU_FLAGS =~ .*avx512f* ]] && HAS_AVX512F=true
+    [[ $CPU_FLAGS =~ .*avx512vl* ]] && HAS_AVX512VL=true
+    [[ $CPU_FLAGS =~ .*avx512ifma* ]] && HAS_AVX512IFMA=true
+    [[ $CPU_FLAGS =~ .*avx512_vbmi2* ]] && HAS_AVX512_VBMI2=true
+    [[ $CPU_FLAGS =~ .*avx512_vnni* ]] && HAS_AVX512_VNNI=true
+    [[ $CPU_FLAGS =~ .*avx512fp16* ]] && HAS_AVX512FP16=true
+    [[ $CPU_FLAGS =~ .*vaes* ]] && HAS_VAES=true
+
+    [[ ${CPU_VENDOR} == "intel" ]] && [[ ${HAS_AVX2} ]] && [[ ${HAS_FMA} ]] && CPU_TYPE=haswell 
+    [[ ${CPU_VENDOR} == "intel" ]] && [[ ${HAS_AVX512F} ]] && CPU_TYPE=skylake_avx512
+    # [[ ${HAS_AVX512IFMA} ]] && [[ ${HAS_AVX512_VBMI2} ]] && CPU_TYPE=icelake_avx512
+    # [[ ${HAS_AVX512_VNNI} ]] && [[ ${HAS_AVX512VL} ]] && [[ ${HAS_AVX512FP16} ]] && CPU_TYPE=sapphire_rapids_avx512
+
+    [[ ${CPU_VENDOR} == "amd" ]] && [[ ${HAS_AVX2} ]] && [[ ${HAS_FMA} ]] && CPU_TYPE=zen2
+    [[ ${CPU_VENDOR} == "amd" ]] && [[ ${HAS_AVX2} ]] && [[ ${HAS_FMA} ]] && [[ ${HAS_VAES} ]] && CPU_TYPE=zen3
+
+    [[ ${CPU_VENDOR} ]] && [[ $CPU_TYPE ]] && CPU_PATH="${MACHINE_TYPE}/${CPU_VENDOR}/${CPU_TYPE}"
+
+    echo ${CPU_PATH}
+    exit
+  fi
+
+  echo "should not see this...something weird going on..."
+  echo "please mail output of lscpu to me..."
+}
+
+if [ ${ARGUMENT} == "none" ]; then
+  echo usage: $0 cpupath
+  exit
+elif [ ${ARGUMENT} == "cpupath" ]; then
+  echo $(cpupath)
+  exit
+fi

init/eessi_environment_variables

@@ -25,9 +25,15 @@ 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 [ -z $EESSI_USE_ARCHDETECT ]; then
+      # if archdetect is enabled, use internal code
+      export EESSI_SOFTWARE_SUBDIR=$(${EESSI_INIT_DIR_PATH}/eessi_archdetect.sh cpupath)
+      echo "archdetect says ${EESSI_SOFTWARE_SUBDIR}"
+    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)
+    fi
     if [ ! -z $EESSI_SOFTWARE_SUBDIR ]; then
 
         echo "Using ${EESSI_SOFTWARE_SUBDIR} as software subdirectory." >> $output