lammps编译（2Aug2023、intel2020、rtx4070ti）

说明：

[root@node101 ~]# cat /etc/redhat-release
CentOS Linux release 7.9.2009 (Core)
[root@node101 ~]# gcc -v
Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/libexec/gcc/x86_64-redhat-linux/4.8.5/lto-wrapper
Target: x86_64-redhat-linux
Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-gnu-unique-object --enable-linker-build-id --with-linker-hash-style=gnu --enable-languages=c,c++,objc,obj-c++,java,fortran,ada,go,lto --enable-plugin --enable-initfini-array --disable-libgcj --with-isl=/builddir/build/BUILD/gcc-4.8.5-20150702/obj-x86_64-redhat-linux/isl-install --with-cloog=/builddir/build/BUILD/gcc-4.8.5-20150702/obj-x86_64-redhat-linux/cloog-install --enable-gnu-indirect-function --with-tune=generic --with-arch_32=x86-64 --build=x86_64-redhat-linux
Thread model: posix
gcc version 4.8.5 20150623 (Red Hat 4.8.5-44) (GCC)
[root@node101 ~]# which mpirun
/opt/gpuApp/ompi/bin/mpirun
[root@node101 ~]# which icc
/opt/intel/compilers_and_libraries_2020.1.211/linux/bin/intel64/icc
[root@node101 ~]# which nvcc
/usr/local/cuda-12.3/bin/nvcc
[root@node101 ~]# lscpu
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                32
On-line CPU(s) list:   0-31
Thread(s) per core:    2
Core(s) per socket:    16
Socket(s):             1
NUMA node(s):          1
Vendor ID:             AuthenticAMD
CPU family:            23
Model:                 49
Model name:            AMD EPYC 7302 16-Core Processor
Stepping:              0
CPU MHz:               1500.000
CPU max MHz:           3000.0000
CPU min MHz:           1500.0000
BogoMIPS:              6000.34
Virtualization:        AMD-V
L1d cache:             32K
L1i cache:             32K
L2 cache:              512K
L3 cache:              16384K
NUMA node0 CPU(s):     0-31
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 constant_tsc art rep_good nopl nonstop_tsc extd_apicid aperfmperf eagerfpu pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_l2 cpb cat_l3 cdp_l3 hw_pstate sme retpoline_amd ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif umip overflow_recov succor smca
[root@node101 ~]# free -g
              total        used        free      shared  buff/cache   available
Mem:            251           5         227           0          18         244
Swap:           127           0         127
[root@node101 ~]#
 

lammps支持单精度，也支持双精度。受限于4070Ti，其双精度能力很差，故本次使用单精度方式进行使用。

显卡的SM值可以通过cuda自带的工具查询：

[root@node101 tools]#ls /usr/local/cuda/samples/1_Utilities/deviceQuery

deviceQuery deviceQuery.cpp deviceQuery.o Makefile NsightEclipse.xml readme.txt

[root@node101 tools]#cd /usr/local/cuda/samples/1_Utilities/deviceQuery

[root@node101 deviceQuery]#./deviceQuery

1、环境文件

cat << EOF > ~/lammps-gpu-env.sh

#!/bin/bash

source /opt/intel/compilers_and_libraries_2020/linux/bin/compilervars.sh intel64

export PATH=/usr/local/cuda-12.3/bin:$PATH

export LD_LIBRARY_PATH=/usr/local/cuda-12.3/targets/x86_64-linux/lib:$LD_LIBRARY_PATH

export C_INCLUDE_PATH=/usr/local/cuda-12.3/targets/x86_64-linux/include:$C_INCLUDE_PATH

EOF

2、gdrcopy