All public logs
Jump to navigation
Jump to search
Combined display of all available logs of HPCWIKI. You can narrow down the view by selecting a log type, the username (case-sensitive), or the affected page (also case-sensitive).
- 18:42, 14 October 2023 Admin talk contribs deleted page Manual:DLSSystem gcc (content was: "== GCC on DLS == To extend flexibility, pre-install multiple version of GCC/G++ - gcc 7, 8, 9 and 10 on DLS To change system wide default gcc/g++ version, execut following command and select number $sudo update-alternatives --config gcc $sudo update-alternatives --config g++ Another way to set specific gcc or g++ version in command line or sheel script is o $sudo update-a...", and the only contributor was "Admin" (talk))
- 18:38, 14 October 2023 Admin talk contribs created page Manual:DLSSystem gcc (Created page with "== GCC on DLS == To extend flexibility, pre-install multiple version of GCC/G++ - gcc 7, 8, 9 and 10 on DLS To change system wide default gcc/g++ version, execut following command and select number $sudo update-alternatives --config gcc $sudo update-alternatives --config g++ Another way to set specific gcc or g++ version in command line or sheel script is o $sudo update-alternatives --set g++ /usr/bin/g++-9 or o $sudo update-alternatives --set gcc /usr/b...") Tag: Visual edit
- 18:32, 14 October 2023 Admin talk contribs created page Manual:DLSSystem (Created page with "== HPCMATE DLS (Deep Learning Station) Framework == {| class="wikitable" |+ !Version !Change log !Applicable |- |1.4 |Initial version on wiki site |DLS stand alone system since Sept 2023 |} To provide idle development environment, HPCMATE system ship with Optimized DL (Deep Learning) framework. This document describes how to utilize pre-installed DL framework on your DLS (Deep Learning Station) environment '''HPCMATE user has license to use and modify pre-installed c...") Tag: Visual edit
- 18:31, 14 October 2023 Admin talk contribs created page Template:Terminology and Acronyms (Created page with "* Node – A single server that shipped with HPCMATE DL framework * Cluster – An appliance system which supports scale diskless compute nodes.") Tag: Visual edit
- 18:28, 14 October 2023 Admin talk contribs created page File:DLS Archtecture.png
- 18:28, 14 October 2023 Admin talk contribs uploaded File:DLS Archtecture.png
- 11:06, 12 October 2023 Admin talk contribs created page Enable AMD CPU with Multi-GPU System (Created page with "== AMC CPU cause deadlocks with multi-GPU in single system == There is an issue report<ref>https://github.com/pytorch/pytorch/issues/52142</ref> to use multi-GPU training with AMD CPU and multi-gpu when using Pytorch or Tensorflow regardless of type of GPU whether Nvidia or AMD Instinct. AMD also reported Multi-GPU environments are failing due to deadlocks from limitations of the IOMMU enablement<ref>https://community.amd.com/t5/knowledge-base/iommu-advisory-for-multi-gp...") Tag: Visual edit
- 12:26, 23 September 2023 Admin talk contribs created page Nginx Tips and Tricks (Created page with "== Build Nginx from source == [https://gist.github.com/noelli/489c5c0cf5a561a32f757d7513465344?permalink_comment_id=3798425 This page] provides how to build Nginx from source == Nginx RTMP? == One of the most common video streaming protocols is an HLS Streaming Server. HLS is an adaptive streaming technology which allows you to stream media content that is tailored to the user’s device and network conditions for the best streaming performance. HLS and RTMP can be ea...") Tag: Visual edit
- 17:48, 6 September 2023 Admin talk contribs created page Monitor user activity in Linux (Created page with "On Linux-based systems, '''process accounting''' offers useful information to assist you in monitoring user activities. Process accounting is a way of keeping track of and summarizing processes and commands on a system. Monitoring user activity in Linux systems is crucial for ensuring system security, optimizing resource usage, and identifying potential issues. By keeping track of user actions, administrators can gain valuable insights into system behavior, detect unauth...") Tag: Visual edit
- 17:12, 2 September 2023 Admin talk contribs created page NIC Bonding (Created page with "Network bonding is the aggregation or combination of multiple LAN cards into a single bonded interface to provide high availability and redundancy. Network bonding is also known as NIC teaming. [https://www.server-world.info/en/note?os=Ubuntu_22.04&p=bonding This pages] shows how to bind multiple network interfaces into a single load balanced or fault-toleranced interface and so on. == Bonding mode == The Linux bonding driver allows system administrators to set up bon...") Tag: Visual edit
- 14:34, 2 September 2023 Admin talk contribs created page Systemd-networkd (Created page with "== Systemd-networkd == ''systemd-networkd'' is a system daemon that manages network, can detect and configure network devices and is also capable of creating virtual network devices configurations sinde 2010. systemd-network can be especially useful to set up complex network configurations for a container managed by systemd-nspawn or for virtual machines. [https://wiki.archlinux.org/title/systemd-networkd This site] explains technical details including system service de...") Tag: Visual edit
- 14:12, 2 September 2023 Admin talk contribs created page File:Netplan-overview.png
- 14:12, 2 September 2023 Admin talk contribs uploaded File:Netplan-overview.png
- 16:14, 30 August 2023 Admin talk contribs created page Federal Information Processing Standard (FIPS) (Created page with "== What is FIPS Certification<ref>https://www.entrust.com/resources/hsm/faq/data-protection-security-regulations/what-fips-140-2</ref> == FIPS stands for Federal Information Processing Standard, FIPS 140-2 is the benchmark for validating the effectiveness of cryptographic hardware. Although FIPS 140-2 is a U.S./Canadian Federal standard, FIPS 140-2 compliance has been widely adopted around the world in both governmental and non-governmental sectors as a practical securit...") Tag: Visual edit
- 14:31, 28 August 2023 Admin talk contribs created page How to compile HPL-GPU (Created page with "== Background == There are many combination to compile High Performance LINPACK (HPL) with different configurations such as different compiler, different basic linear algebra subprograms (BLAS), massage passing interface (MPI) libraries: for example * Which compiler + HPL + which Blas (OpenBLAS / Intel MKL / CuBLAS) + which MPI (OpenMPI, MPICH, Intel MPI) == Build High Performance LINPACK with CUDA == In this post, we are going to use GNU compiler, OpenBLAS, OpenMPI f...") Tag: Visual edit
- 14:13, 4 August 2023 Admin talk contribs created page TDP (Created page with "== What is TDP == TDP (The '''thermal design power''' ('''TDP'''), sometimes called '''thermal design point''') is the maximum amount of heat generated by a computer chip or component (often a CPU, GPU or system on a chip) that the cooling system in a computer is designed to dissipate under any workload<ref>https://en.wikipedia.org/wiki/Thermal_design_power</ref> Although Some sources state that the peak power rating for a microprocessor is usually 1.5 times the TDP rat...") Tag: Visual edit
- 15:03, 30 July 2023 Admin talk contribs created page Nouveau (Created page with "TODO == References == <references />") Tag: Visual edit
- 11:20, 29 July 2023 Admin talk contribs created page LGA 3647 (Created page with "Intel 3rd gen Xeon scalable use two difference Socket LGA 3647 type Narrow ILM v Square ILM on motherboard. So need to identify which type of socket does your mother board supports to install different type of socket. fortunatly it is easy to identify the type of socket by looking your mother board layout.<ref>https://www.servethehome.com/narrow-square-ilm-socket-lga-3647-heatsink-differences/</ref> == Narrow ILM vs Square ILM == File:LGA 3647 Narrow ILM.png|left|thu...") Tag: Visual edit
- 11:18, 29 July 2023 Admin talk contribs created page File:LGA 3647 square.png
- 11:18, 29 July 2023 Admin talk contribs uploaded File:LGA 3647 square.png
- 11:16, 29 July 2023 Admin talk contribs created page File:LGA 3647 Narrow ILM.png
- 11:16, 29 July 2023 Admin talk contribs uploaded File:LGA 3647 Narrow ILM.png
- 08:50, 28 July 2023 Admin talk contribs created page Linux signal (Created page with "== Linux signal and number == all have names starting with SIG. Some are from POSIX. The number of possible signals is limited. The first 31 signals are standardized in LINUX<ref>https://faculty.cs.niu.edu/~hutchins/csci480/signals.htm</ref> # Signal Default Comment POSIX Name Action 1 SIGHUP Terminate Hang up controlling terminal or Yes process 2 SIGINT Terminate Int...") Tag: Visual edit
- 08:31, 28 July 2023 Admin talk contribs created page File:Linux Process States.png
- 08:31, 28 July 2023 Admin talk contribs uploaded File:Linux Process States.png
- 11:05, 27 July 2023 Admin talk contribs moved page Template:CoolUX to Template:CoolUX Technology
- 11:01, 27 July 2023 Admin talk contribs created page Template:CoolUX (Created page with "CoolUX technology has been developed from CoolGX to support rack scaled liquid cooling sytem solution. with UCM technology user operate multiple HPC system cluster without unlimited TDP for high performance CPUs and GPUs in any size of form factor servers. CoolUX has been selected as innovative production by m'''inistry of SMEs and startups 2023''' in Korea.") Tag: Visual edit
- 10:54, 27 July 2023 Admin talk contribs created page Template:CoolGX Technology (Created page with "== CoolGX Technology == CoolGX technology is a thermal dynamic optimization technology by intergrating active thermal monitoring and control hardware components to maximize liquid cooling capability on a stand alone liquid cooing system. CoolGX has been developed since 2018 for the series of CoolGX systems and evolved to {{CoolUX}} technology for rack scaled liquid cooling system solution.") Tag: Visual edit
- 11:38, 25 July 2023 Admin talk contribs created page 0 JBOD(s) handled by BIOS (Created page with "For some issue, working server could not find boot disk from JBOD mode exported boot disk in BIOS. Boot screen shows 0 JBOD(s) handled by BIOS so that the BIOS cannot see boot disk for some reason. frameless|647x647px To solve this issue, we need to reset RAID controller to factory default and reboot save our time to show correct message 5 JBOD(s) found on the host adapter as well as 5 JBOD(s) handled by BIOS == References == <refe...") Tag: Visual edit
- 11:33, 25 July 2023 Admin talk contribs created page File:0jbodshandledbybios.png
- 11:33, 25 July 2023 Admin talk contribs uploaded File:0jbodshandledbybios.png
- 11:53, 24 July 2023 Admin talk contribs created page File:4090 nvidia-smi.png
- 11:53, 24 July 2023 Admin talk contribs uploaded File:4090 nvidia-smi.png
- 14:17, 23 July 2023 Admin talk contribs created page Nvidia GPU Tips and Tricks (Created page with " == Xid errors along with the potential causes for each<ref>https://docs.nvidia.com/deploy/xid-errors/index.html</ref> == {| class="wikitable" ! colspan="1" rowspan="1" |XID ! colspan="1" rowspan="1" |Nvidia GPU Failure !Linux Kernel message ! colspan="7" rowspan="1" |Causes |- ! colspan="1" rowspan="1" | ! colspan="1" rowspan="1" | ! ! colspan="1" rowspan="1" |HW Error ! colspan="1" rowspan="1" |Driver Error ! colspan="1" rowspan="1" |User App Error ! colspan="1" rowspa...") Tag: Visual edit
- 14:15, 23 July 2023 Admin talk contribs created page Nvdia-smi tips and tricks (Created page with "== Understand ouput == <syntaxhighlight lang="bash"> +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 535.86.05 Driver Version: 535.86.05 CUDA Version: 12.2 | |-----------------------------------------+----------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usa...") Tag: Visual edit
- 11:20, 23 July 2023 Admin talk contribs created page File:4090 power consumption.png
- 11:20, 23 July 2023 Admin talk contribs uploaded File:4090 power consumption.png
- 10:22, 23 July 2023 Admin talk contribs created page GPU dual bios (Created page with "== What is a Dual Bios? == Dual Bios feature was about overclocking. How so? Users would leave Bios1 default as a fallback while they would flash a custom Bios on Bios2 for overclocking purposes. But the Dual Bios functionality has changed over the years. The Dual Bios function now is more about performance == Example == ZOTAC GAMING GPUs feature two profiles: AMPLIFY and QUIET<ref>https://www.zotac.com/hk/news/dual-bios</ref> * AMPLIFY, the default bios out of the...") Tag: Visual edit
- 09:47, 23 July 2023 Admin talk contribs created page Kernel tips and tricks (Created page with " == perf interrupt took too long in system log == phenomenon system log shows "perf interrupt took too long (aaa > bbb), lowering kernel.perf_event_max_sample_rate to ccc" Action Nothing to worry about. It has to do with the Linux perf tool which is included in the kernel. The kernel automagically determines the sample rate that could be used without impacting system performance too much; and it logs this even when perf isn't active, or even installed. Messages like...") Tag: Visual edit
- 18:38, 22 July 2023 Admin talk contribs created page DKMS (Created page with " == Force to remove installed dkms module<ref>https://www.mkammerer.de/blog/broken-nvidia-driver-or-clean-up-old-dkms-modules/</ref> == <code>sudo rm -rf /var/lib/dkms/modulename/*</code> == References == <references />") Tag: Visual edit
- 09:53, 21 July 2023 Admin talk contribs created page NFS (Created page with "It is important to know them NFS export and mount options especially when you are facing a performance issue or a functional issue with the NFS mount over network. == Basic command == {| class="wikitable sortable" |+ !Commands !Description !Command on |- |# exportfs -r |Re-export your shares |Server |- |# exportfs -a |Export your shares |Server |- |# exportfs -v |Verify the NFS Share permissions |Server |- |$nfsstat -m |'''Verify Current NFS Mount Options'''...") Tag: Visual edit
- 05:22, 21 July 2023 Admin talk contribs created page Silicon Root of Trust (Created page with "== What is Silicon Root of Trust == Silicon Root of Trust is firmware technology that integrates security directly into the hardware level of servers, making an immutable fingerprint in the silicon that provides advanced levels of protection against firmware attacks. It detects changes being introduced by cyber attackers and disables the server, so malicious code never penetrates and allows operation to quickly regain its original state. [https://www.rambus.com/blogs/ha...") Tag: Visual edit
- 12:31, 20 July 2023 Admin talk contribs created page Storcli (Created page with "'''StorCLI''' is a command line tool for the administration of '''MegaRAID Controllers''' and the '''successor of MegaCLI.''' More background and overall introduction is available [https://docs.broadcom.com/doc/12352476 this old document] == Install storcli under Ubuntu == Download the latest version of storecli from [https://www.broadcom.com/site-search?q=megacli Broadcom URL] then unzip the zip file. Unzip will create folder name Unified_storcli_all_os to support v...") Tag: Visual edit
- 08:51, 19 July 2023 Admin talk contribs created page RAM Generations (Created page with "All computer devices use random-access memory (RAM) to store the short-term data. As computer process evolve, RAM improves too. Each generation of RAM increases speed and frequency while decreasing power consumption. This page summarize the differences between the generations of RAM<ref>https://www.crucial.com/articles/about-memory/difference-among-ddr2-ddr3-ddr4-and-ddr5-memory</ref>. {| class="wikitable sortable" |+ !Generation !History !Prefetch !Data Rate(MT/s) !T...") Tag: Visual edit
- 11:33, 7 July 2023 Admin talk contribs created page HBA/RAID controller (Created page with "== RAID Controller Port == There is a concept in RAID controller, that are '''Native Supported Disks and Maximum Supported Disks.''' * Native support # means the number of disks that can be direct connected to the RAID controller usinb brakeout cable * Maximum Supported Disks # means when to use of port expanders such as Intel RES2SV240 == RAID Controller Interface == The RAID controller has an interface that connects to the storage drive and an interface that conn...") Tag: Visual edit
- 08:47, 6 July 2023 Admin talk contribs created page File:IP Address Classification.png
- 08:47, 6 July 2023 Admin talk contribs uploaded File:IP Address Classification.png
- 11:59, 5 July 2023 Admin talk contribs created page Network Class (Created page with "== The Five IPv4 Classes == there are five classes: A, B, C, D and E in the IPv4 IP address space. Primarily, class A, B, and C are used by the majority of devices on the Internet. Class D and class E are for special uses. Each class has a specific range of IP addresses.<ref>https://www.meridianoutpost.com/resources/articles/IP-classes.php</ref> Within each network class, there are designated IP address that is reserved specifically for private/internal use only. This I...") Tag: Visual edit
- 14:54, 1 July 2023 Admin talk contribs created page Type of SATA and SAS connector (Created page with "== SATA and SAS Cables - Combined Connectors<ref>https://www.lindy.com.au/sata-and-sas-cables-combined-connectors-explained/</ref> == center|frameless|550x550px * '''22pin (7pin + 15pin) SATA Combo''' - The most common type of connector, this can be found in most 5.25", 3.5", 2.5" and a variety of 1.8" drives and hard drives. * '''29pin SAS Combo''' - A connecter socket for SAS drives as a SATA combination 22p plug does not fit SAS Drives...") Tag: Visual edit
- 14:51, 1 July 2023 Admin talk contribs created page File:Sas connector type.png