This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
cluster:172 [2018/08/23 18:17] hmeij07 [mapd] |
cluster:172 [2018/09/25 18:44] hmeij07 [Finish] |
||
---|---|---|---|
Line 20: | Line 20: | ||
* unmount NFS mounts while installing nvidia as root | * unmount NFS mounts while installing nvidia as root | ||
* install other software as regular user | * install other software as regular user | ||
- | * | ||
==== Nvidia ==== | ==== Nvidia ==== | ||
Line 34: | Line 33: | ||
yum update kernel kernel-tools kernel-tools-libs | yum update kernel kernel-tools kernel-tools-libs | ||
yum install kernel-devel kernel-headers (remove old headers after reboot) | yum install kernel-devel kernel-headers (remove old headers after reboot) | ||
- | yum install gcc gcc-devel | + | yum install gcc gcc-gfortran gcc-c++ |
# download runfiles from https:// | # download runfiles from https:// | ||
- | sh cuda_name_of_runfile | + | # files in / |
- | sh cuda_name_of_runfile_patch | + | sh cuda_9.2.148_396.37_linux.run |
Install NVIDIA Accelerated Graphics Driver for Linux-x86_64 396.26? | Install NVIDIA Accelerated Graphics Driver for Linux-x86_64 396.26? | ||
Line 55: | Line 55: | ||
(y)es/ | (y)es/ | ||
- | #/ | + | # / |
+ | # reboot before driver | ||
blacklist nouveau | blacklist nouveau | ||
options nouveau modeset=0 | options nouveau modeset=0 | ||
Line 61: | Line 62: | ||
# nvidia driver | # nvidia driver | ||
- | ./ | + | ./ |
# backup | # backup | ||
Line 72: | Line 73: | ||
[root@n37 src]# find / | [root@n37 src]# find / | ||
[root@n37 src]# | [root@n37 src]# | ||
- | [root@n37 src]# scp n78:/ | + | [root@n37 src]# scp n78:/ |
# Device files/ | # Device files/ | ||
Line 80: | Line 81: | ||
# new kernel initramfs, load | # new kernel initramfs, load | ||
dracut --force | dracut --force | ||
+ | |||
+ | # for mapd graphics support needs to be enabled | ||
+ | nvidia-smi --gom=0 | ||
+ | # have left persistence and exclusivity at defaults for now | ||
+ | |||
reboot | reboot | ||
Line 157: | Line 163: | ||
** Finish ** | ** Finish ** | ||
- | * yum install freeglut-devel libX11-devel libXi-devel libXmu-devel \ make mesa-libGLU-devel | + | * yum install freeglut-devel libX11-devel libXi-devel libXmu-devel \ make mesa-libGLU-devel |
* check for / | * check for / | ||
* [root@n37 /]# tar -cvf / | * [root@n37 /]# tar -cvf / | ||
Line 167: | Line 173: | ||
< | < | ||
- | # As root check requirements | + | # As root check requirements |
rpm -qa | grep ^gcc | rpm -qa | grep ^gcc | ||
rpm -qa | grep ^g++ | rpm -qa | grep ^g++ | ||
Line 187: | Line 193: | ||
rpm -qa | grep ^bison | rpm -qa | grep ^bison | ||
- | # As root install missing | + | # As root install missing |
yum install flex bzip2-devel libXdmcp zlib zlib-devel | yum install flex bzip2-devel libXdmcp zlib zlib-devel | ||
yum install tkinter openmpi perl-ExtUtils-MakeMaker patch bison | yum install tkinter openmpi perl-ExtUtils-MakeMaker patch bison | ||
Line 296: | Line 302: | ||
</ | </ | ||
+ | |||
==== Lammps ==== | ==== Lammps ==== | ||
As root install | As root install | ||
- | * yum install libjpeg libjpeg-devel libjpeg-turbo libjpeg-turbo-devel | + | * yum install libjpeg libjpeg-devel libjpeg-turbo libjpeg-turbo-devel |
- | * yum install blas blas-devel lapack lapack-devel boost boost-devel | + | * yum install blas blas-devel lapack lapack-devel boost boost-devel |
For Lammps-22Aug18 I followed the top installation instructions at this page | For Lammps-22Aug18 I followed the top installation instructions at this page | ||
Line 310: | Line 317: | ||
* to stay with openmpi-1.8.4 (not mpich3...) | * to stay with openmpi-1.8.4 (not mpich3...) | ||
- | * consulting the ARCH web page I choose -arch=sm_35 | + | * consulting the ARCH web page I choose -arch=sm_35 |
- | Good thing we're doing this now, future versions of CUDA will not support the K20s anymore. In fact on that web site they are not mentioned, only the K40/K80 gpus. So we'll see what testing reveals. | + | Good thing we're doing this now, future versions of CUDA will not support the K20s anymore. In fact on that web site they are not mentioned, only the K40/K80 gpus. So we'll see what testing reveals. |
< | < | ||
Line 318: | Line 325: | ||
[hmeij@n37 src]$ ll / | [hmeij@n37 src]$ ll / | ||
total 104356 | total 104356 | ||
- | -rwxr-xr-x 1 hmeij its 35739800 Aug 23 08:49 lmp_mpi-double-double-with-cuda | + | -rwxr-xr-x 1 hmeij its 35739800 Aug 23 08:49 lmp_mpi-double-double-with-gpu |
- | -rwxr-xr-x 1 hmeij its 35555672 Aug 23 09:11 lmp_mpi-single-double-with-cuda | + | -rwxr-xr-x 1 hmeij its 35555672 Aug 23 09:11 lmp_mpi-single-double-with-gpu |
- | -rwxr-xr-x 1 hmeij its 35559552 Aug 23 09:53 lmp_mpi-single-single-with-cuda | + | -rwxr-xr-x 1 hmeij its 35559552 Aug 23 09:53 lmp_mpi-single-single-with-gpu |
</ | </ | ||
Line 343: | Line 350: | ||
javapackages-tools libxslt \ | javapackages-tools libxslt \ | ||
lksctp-tools python-javapackages \ | lksctp-tools python-javapackages \ | ||
- | python-lxml tzdata-java | + | python-lxml tzdata-java |
- | mapd | + | |
- | | + | yum install |
# User specific aliases and functions | # User specific aliases and functions | ||
Line 358: | Line 365: | ||
==== Finish ==== | ==== Finish ==== | ||
- | * Make the final tar file for /usr/local and post with CHROOT | + | * Make the final tar file for /usr/local and post with CHROOT |
- | * Install all the packages of this page in CHROOT | + | * Install all the packages of this page in CHROOT |
+ | |||
+ | |||
+ | To do another node, the steps are | ||
+ | |||
+ | * add node in deploy.txt of n36.chroot/ | ||
+ | * ./ | ||
+ | * scp in place passwd, shadow, group, hosts, fstab from global archive | ||
+ | * umount -a | ||
+ | * ONBOOT=no, ib0 ??? connectX mlx4_0 IB interface breaks in CentOS 7.3+ | ||
+ | * bootlocal=EXIT then reboot then check polkit user … screws up systemd-logind | ||
+ | |||
+ | * hostnamectl set-hostname node_name (logout/ | ||
+ | * eth1 on 129.133 | ||
+ | * yum update | ||
+ | * yum install kernel-headers kernel-devel | ||
+ | * put n37 tarball in /, unpack, remove cuda-9.2 | ||
+ | * reboot | ||
+ | |||
+ | * Nvidia install: files in / | ||
+ | * sh runfile | ||
+ | * reboot (nouveau) | ||
+ | * ./runfile -silent -driver | ||
+ | * reboot | ||
+ | |||
+ | |||
\\ | \\ | ||
**[[cluster: | **[[cluster: |