mastodon.ie is one of the many independent Mastodon servers you can use to participate in the fediverse.
Irish Mastodon - run from Ireland, we welcome all who respect the community rules and members.

Administered by:

Server stats:

1.6K
active users

#epyc

0 posts0 participants0 posts today
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p>Performance &amp; Power Of The Low-Cost <a href="https://hachyderm.io/tags/EPYC4005" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC4005</span></a> "Grado" vs. Original <a href="https://hachyderm.io/tags/EPYC7601" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC7601</span></a> Zen 1 Flagship CPU Review<br>Can an entry-level brand new <a href="https://hachyderm.io/tags/Zen5" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Zen5</span></a> Grado <a href="https://hachyderm.io/tags/server" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>server</span></a> processor with dual channel DDR5 memory outpace an original <a href="https://hachyderm.io/tags/EPYC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a> server with twice the core/thread counts and eight channel DDR4 server memory? Yes, with huge gains in performance and power efficiency.<br>Across HPC, compilation, video encoding, and a variety of other workloads, <a href="https://hachyderm.io/tags/EPYC4585PX" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC4585PX</span></a> processor was at 2.69x performance<br><a href="https://www.phoronix.com/review/amd-epyc-4005-server" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phoronix.com/review/amd-epyc-4</span><span class="invisible">005-server</span></a></p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p><a href="https://hachyderm.io/tags/Intel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Intel</span></a> <a href="https://hachyderm.io/tags/Xeon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Xeon</span></a> 6300 vs. <a href="https://hachyderm.io/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://hachyderm.io/tags/EPYC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a> 4005 <a href="https://hachyderm.io/tags/SMT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SMT</span></a>#/HT Performance Review<br>At the same core counts, <a href="https://hachyderm.io/tags/Zen5" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Zen5</span></a> based <a href="https://hachyderm.io/tags/EPYC4005" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC4005</span></a> series was showing great benefit out of SMT than the flagship <a href="https://hachyderm.io/tags/Xeon6300" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Xeon6300</span></a><br>Also fascinating to see was that AMD EPYC 4345P even with SMT disabled was still faster than the Xeon 6369P with its full load-out thanks to the EPYC Grado <a href="https://hachyderm.io/tags/CPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CPU</span></a> supporting AVX-512 and other advantages over the Xeon 6300 series that in turn is largely rehashed from the Xeon <a href="https://hachyderm.io/tags/E2400" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>E2400</span></a> series.<br><a href="https://www.phoronix.com/review/intel-xeon-6300-amd-epyc-4005-smt" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phoronix.com/review/intel-xeon</span><span class="invisible">-6300-amd-epyc-4005-smt</span></a></p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p><a href="https://hachyderm.io/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://hachyderm.io/tags/EPYC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a> <a href="https://hachyderm.io/tags/4345P" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>4345P</span></a> 8-Core <a href="https://hachyderm.io/tags/CPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CPU</span></a> Performance Review<br>The EPYC 4345P was delivering 1.31x the performance overall of the <a href="https://hachyderm.io/tags/Xeon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Xeon</span></a> <a href="https://hachyderm.io/tags/6369P" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>6369P</span></a> at the same core/thread count.<br>The EPYC 4345P can be purchased online right now for $329 USD compared to the Xeon 6369P at $606, or 2.4x the performance-per-dollar.<br><a href="https://www.phoronix.com/review/amd-epyc-4345p" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phoronix.com/review/amd-epyc-4</span><span class="invisible">345p</span></a></p>
Thorsten Leemhuis (acct. 1/4)<p>A document describes techniques that are useful for debugging suspend and resume issues with modern <a href="https://hachyderm.io/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> processors was merged for <a href="https://hachyderm.io/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a> 6.16: <a href="https://git.kernel.org/torvalds/c/cafb22242bfb7fad10fde6f9b99853fc924e691a" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">git.kernel.org/torvalds/c/cafb</span><span class="invisible">22242bfb7fad10fde6f9b99853fc924e691a</span></a></p><p>Rendered version: <a href="https://origin.kernel.org/doc/html/next/arch/x86/amd-debugging.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">origin.kernel.org/doc/html/nex</span><span class="invisible">t/arch/x86/amd-debugging.html</span></a></p><p><a href="https://hachyderm.io/tags/kernel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>kernel</span></a> <a href="https://hachyderm.io/tags/LinuxKernel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LinuxKernel</span></a> <a href="https://hachyderm.io/tags/Ryzen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ryzen</span></a> <a href="https://hachyderm.io/tags/Epyc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Epyc</span></a> <a href="https://hachyderm.io/tags/Linux616" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux616</span></a></p>
Aho<p><a href="https://ioc.exchange/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a> 6.16 will report the cause to a reset/reboot of system if you have a <a href="https://ioc.exchange/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://ioc.exchange/tags/Zen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Zen</span></a> based CPU like <a href="https://ioc.exchange/tags/Ryzen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ryzen</span></a> or <a href="https://ioc.exchange/tags/EPYC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a> </p><p>This can be handy to see it in the <a href="https://ioc.exchange/tags/dmesg" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dmesg</span></a> output, just hope this will be logged properly so it's easy to find if you have a lot of clutter reported.</p><p>Source: <a href="https://www.phoronix.com/news/AMD-Report-Previous-Reset-Cause" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phoronix.com/news/AMD-Report-P</span><span class="invisible">revious-Reset-Cause</span></a></p>
TechnoTim<p>So I guess I am building a super computer… Raspberry Pi for scale. </p><p>Thanks Wendell!</p><p><a href="https://mastodon.social/tags/amd" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>amd</span></a> <a href="https://mastodon.social/tags/epyc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>epyc</span></a></p>
Bernd<p>I'd like to hear your thoughts on a planned <a href="https://nb-fedi.de/tags/homeserver" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>homeserver</span></a> upgrade. Current set up is a Dual Xeon E5-2470 v2, running a NAS and multiple VMs under <a href="https://nb-fedi.de/tags/netbsd" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NetBSD</span></a> 10.<br><br>A 2U rackmount case is available.<br><br>Two M.2 slots and ECC RAM are hard requirements, AMD is preferred.<br><br>My currently favoured options:<br>- Asrock Rack X570D4U + Ryzen 9 5950X<br>- Asrock Rack B560D4U + Ryzen 9 9950X or 9900X<br>- Asrock Rack B560D4U + EPYC 4564P or 4584PX<br><br>The 9950X and the 4564P seem to be almost identical performance-wise, so I'm not quite sure what the advantage of the EPYC is.<br><br>Cooling 170 W TDP (4564P and 9950X) in 2U may not be trivial. The 4584PX has more cache, but lower single-thread performance, and also lower TDP, but is slightly more expensive, though all are within my budget.<br><br>Single-core-Performance is nice for some of my applications, but multiple cores are useful for running up to 6 parallel VMs.<br><br><a href="https://nb-fedi.de/tags/homelab" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>homelab</span></a> <a href="https://nb-fedi.de/tags/selfhosting" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>selfhosting</span></a> <a href="https://nb-fedi.de/tags/unplugtrump" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>unplugtrump</span></a> <a href="https://nb-fedi.de/tags/ryzen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ryzen</span></a> <a href="https://nb-fedi.de/tags/amd" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://nb-fedi.de/tags/epyc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a></p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p><a href="https://hachyderm.io/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://hachyderm.io/tags/EPYC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a> <a href="https://hachyderm.io/tags/4565P" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>4565P</span></a> &amp; <a href="https://hachyderm.io/tags/4585PX" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>4585PX</span></a> <a href="https://hachyderm.io/tags/Benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Benchmarks</span></a> Against <a href="https://hachyderm.io/tags/Xeon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Xeon</span></a> <a href="https://hachyderm.io/tags/6369P" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>6369P</span></a><br>For "conventional" <a href="https://hachyderm.io/tags/server" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>server</span></a> workloads like web serving and databases, the EPYC 4005 series dominates.<br>With up to 16C/32TH, <a href="https://hachyderm.io/tags/AVX512" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AVX512</span></a>, DDR5-5600 memory and other advantages, the EPYC 4005 series is the very easy answer for those that may be looking for affordable <a href="https://hachyderm.io/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HPC</span></a> <br>The AMD <a href="https://hachyderm.io/tags/EPYC4005" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC4005</span></a> series <a href="https://hachyderm.io/tags/CPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CPU</span></a> deliver excellent generational uplift over the EPYC 4004 series and outright obliterating the <a href="https://hachyderm.io/tags/Xeon6300" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Xeon6300</span></a> series<br><a href="https://www.phoronix.com/review/amd-epyc-4585px-4565p-benchmarks" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phoronix.com/review/amd-epyc-4</span><span class="invisible">585px-4565p-benchmarks</span></a></p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p><a href="https://hachyderm.io/tags/Intel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Intel</span></a>'s <a href="https://hachyderm.io/tags/ClearLinux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ClearLinux</span></a> Demonstrates Software Optimization Benefits On <a href="https://hachyderm.io/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://hachyderm.io/tags/EPYC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a> 9005 Series<br>Clear <a href="https://hachyderm.io/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a> easily took top spot. Clear was 6% faster than Ubuntu 25.04, which was running with the "performance" governor like the rest. Or compared to Ubuntu 24.04 LTS, the in-house Intel distribution was 23% faster. Ubuntu and other Linux distributions continue moving performance in right direction but Intel's Clear continues to deliver the fastest out-of-the-box x86_64 Linux. <br><a href="https://www.phoronix.com/review/amd-epyc-mid2025-linux" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phoronix.com/review/amd-epyc-m</span><span class="invisible">id2025-linux</span></a></p>
Eva Winterschön<p>💾 4am AMD Xorg/Kernel Debugging 💾</p><p>Ongoing fun ongoes, so much so. This iteration receives triple output: tty video (Display Port), COM1 redirect via DB9 to laptop running minicom, COM2 to the usual BMC SoL terminal watched from ipmitool on adjacent laptop. </p><p>Coming up, rebooting into GENERIC-DEBUG kernel rebuilt with remote GDM (kgdb) access via the COM1 link to laptop. </p><p><a href="https://mastodon.bsd.cafe/tags/freebsd" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>freebsd</span></a> <a href="https://mastodon.bsd.cafe/tags/epyc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>epyc</span></a> <a href="https://mastodon.bsd.cafe/tags/desktop" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>desktop</span></a> <a href="https://mastodon.bsd.cafe/tags/debugging" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>debugging</span></a> <a href="https://mastodon.bsd.cafe/tags/4amlife" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>4amlife</span></a> <a href="https://mastodon.bsd.cafe/tags/thinkpad" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>thinkpad</span></a></p>
Pyrzout :vm:<p>Duelo de titanes: procesadores Intel Xeon y AMD EPYC <a href="https://blog.elhacker.net/2025/04/duelo-titanes-procesadores-intel-xeon-vs-amd-epyc.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">blog.elhacker.net/2025/04/duel</span><span class="invisible">o-titanes-procesadores-intel-xeon-vs-amd-epyc.html</span></a> <a href="https://social.skynetcloud.site/tags/procesador" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>procesador</span></a> <a href="https://social.skynetcloud.site/tags/intel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>intel</span></a> <a href="https://social.skynetcloud.site/tags/epyc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>epyc</span></a> <a href="https://social.skynetcloud.site/tags/xeon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>xeon</span></a> <a href="https://social.skynetcloud.site/tags/amd" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>amd</span></a> <a href="https://social.skynetcloud.site/tags/cpd" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cpd</span></a> <a href="https://social.skynetcloud.site/tags/cpu" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cpu</span></a></p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p>SMT Remains Very Advantageous For <a href="https://hachyderm.io/tags/Zen5" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Zen5</span></a> <a href="https://hachyderm.io/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://hachyderm.io/tags/EPYC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a> Performance<br><a href="https://hachyderm.io/tags/SMT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SMT</span></a> typically was of measurable benefit to the 5th Gen AMD EPYC processor with the exception of some <a href="https://hachyderm.io/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HPC</span></a> workloads that perform better with SMT disabled or otherwise limited by memory bandwidth. SMT also hurt the OpenVINO inference latency but by and large Simultaneous Multi-Threading remains an important and valuable feature for AMD processors. <br><a href="https://www.phoronix.com/review/amd-epyc-zen5-smt" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phoronix.com/review/amd-epyc-z</span><span class="invisible">en5-smt</span></a></p>
Sturmflut<p>Memory throughput of contemporary CPUs:</p><p><a href="https://mastodon.social/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://mastodon.social/tags/EPYC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a> 9965: 576 GB/s (per Socket)</p><p><a href="https://mastodon.social/tags/Intel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Intel</span></a> <a href="https://mastodon.social/tags/Xeon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Xeon</span></a> 6980P: 614 GB/s (per Socket)</p><p><a href="https://mastodon.social/tags/Apple" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Apple</span></a> <a href="https://mastodon.social/tags/M4" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>M4</span></a> Max: 546 GB/s</p><p>AMD <a href="https://mastodon.social/tags/Ryzen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ryzen</span></a> AI Max+ 395: 256 GB/s</p><p><a href="https://mastodon.social/tags/Qualcomm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Qualcomm</span></a> <a href="https://mastodon.social/tags/Snapdragon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Snapdragon</span></a> X Elite: 133.9 GB/s</p><p>We are about to enter the "Terabytes per second" stage.</p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p>The Compelling <a href="https://hachyderm.io/tags/AVX512" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AVX512</span></a> Performance Advantage On <a href="https://hachyderm.io/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://hachyderm.io/tags/EPYC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a> 9005 "Turin"<br>Workloads tested on this <a href="https://hachyderm.io/tags/EPYC9655" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC9655</span></a> Supermicro server, with AVX-512 yielded 1.57x the performance of the same hardware/software but with AVX-512 forced off. <br><a href="https://www.phoronix.com/review/amd-epyc-turin-avx512" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phoronix.com/review/amd-epyc-t</span><span class="invisible">urin-avx512</span></a></p>
John E. Bartley, III (D) K7AAY<p>AMD's security cracked to modify the silicon's behaviour at will. This capability also undermines AMD's secure encrypted virtualization &amp; root-of-trust security mechanisms on Ryzen, Threadripper, &amp; Epyc CPUs. <a href="https://it.slashdot.org/story/25/02/09/2021244/how-to-make-any-amd-zen-cpu-always-generate-4-as-a-random-number" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">it.slashdot.org/story/25/02/09</span><span class="invisible">/2021244/how-to-make-any-amd-zen-cpu-always-generate-4-as-a-random-number</span></a> <a href="https://pdx.social/tags/security" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>security</span></a> <a href="https://pdx.social/tags/hacking" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>hacking</span></a> <a href="https://pdx.social/tags/amd" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>amd</span></a> <a href="https://pdx.social/tags/ryzen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ryzen</span></a> <a href="https://pdx.social/tags/threadripper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>threadripper</span></a> <a href="https://pdx.social/tags/epyc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>epyc</span></a></p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p><a href="https://hachyderm.io/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> Moves Up Instinct <a href="https://hachyderm.io/tags/MI350" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MI350</span></a>/#MI355X To Now Release By Mid-2025, <a href="https://hachyderm.io/tags/MI400" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MI400</span></a> Lineup Slated For 2026 As <a href="https://hachyderm.io/tags/Datacenter" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Datacenter</span></a> Biz Hits Records<br>Last year the datacenter business at AMD, which includes <a href="https://hachyderm.io/tags/EPYC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a> <a href="https://hachyderm.io/tags/CPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CPU</span></a>, Instinct <a href="https://hachyderm.io/tags/GPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GPU</span></a>, <a href="https://hachyderm.io/tags/Pensando" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Pensando</span></a> <a href="https://hachyderm.io/tags/DPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DPU</span></a>, and <a href="https://hachyderm.io/tags/Xilinx" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Xilinx</span></a> <a href="https://hachyderm.io/tags/FPGA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FPGA</span></a> accelerators, accounted for $12.58 billion in sales, or 48.8% of revenues. In both Q3 and Q4 of 2024, datacenter drove in excess of half of AMD’s revenues and nearly 60% of its operating income. <br><a href="https://www.nextplatform.com/2025/02/04/amd-moves-up-instinct-355x-launch-as-datacenter-biz-hits-records/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">nextplatform.com/2025/02/04/am</span><span class="invisible">d-moves-up-instinct-355x-launch-as-datacenter-biz-hits-records/</span></a></p>
Boiling Steam<p>How to Run DeepSeek R1 671B Locally on a $2000 EPYC Server: <a href="https://digitalspaceport.com/how-to-run-deepseek-r1-671b-fully-locally-on-2000-epyc-rig/" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="ellipsis">digitalspaceport.com/how-to-ru</span><span class="invisible">n-deepseek-r1-671b-fully-locally-on-2000-epyc-rig/</span></a> <a href="https://mastodon.cloud/tags/linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>linux</span></a> <a href="https://mastodon.cloud/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llm</span></a> <a href="https://mastodon.cloud/tags/deepseek" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>deepseek</span></a> <a href="https://mastodon.cloud/tags/r1" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>r1</span></a> <a href="https://mastodon.cloud/tags/epyc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>epyc</span></a> <a href="https://mastodon.cloud/tags/server" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>server</span></a> <a href="https://mastodon.cloud/tags/selfhosted" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>selfhosted</span></a></p>
Dendrobatus Azureus<p><span class="h-card" translate="no"><a href="https://fuzzies.wtf/@micr0" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>micr0</span></a></span></p><p>I've checked the prices of some AMD Epyc cpus and come to the conclusion that, given enough donations, you would be better of having a CPU like </p><p>AMD PS755PBDAFWOF EPYC x86 CPU Processor Model 7551P (32c/64t 2.0GHz) 16 DDR4 DIMM Slots with up to 2TB RAM and 128 Lanes of PCIe 3</p><p>which costs only USD 269 at amazon. You will have 32cores and enough PCIe3 lanes to do the task properly. It's just 69 USD more in price</p><p><a href="https://mastodon.bsd.cafe/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://mastodon.bsd.cafe/tags/Epyc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Epyc</span></a> <a href="https://mastodon.bsd.cafe/tags/ServerCPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ServerCPU</span></a> <a href="https://mastodon.bsd.cafe/tags/Server" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Server</span></a> <a href="https://mastodon.bsd.cafe/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.bsd.cafe/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a> <a href="https://mastodon.bsd.cafe/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a> <a href="https://mastodon.bsd.cafe/tags/POSIX" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>POSIX</span></a></p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p><a href="https://hachyderm.io/tags/Germany" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Germany</span></a> unleashes <a href="https://hachyderm.io/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a>-powered Hunter <a href="https://hachyderm.io/tags/supercomputer" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>supercomputer</span></a><br>€15 million system to serve as testbed for larger Herder supercomputer coming in 2027<br>Built by <a href="https://hachyderm.io/tags/HewlettPackardEnterprise" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HewlettPackardEnterprise</span></a> (<a href="https://hachyderm.io/tags/HPE" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HPE</span></a>), Hunter is based on a <a href="https://hachyderm.io/tags/Cray" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Cray</span></a> EX4000 platform and powered by a combination of AMD Instinct <a href="https://hachyderm.io/tags/MI300A" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MI300A</span></a> accelerated processing units (<a href="https://hachyderm.io/tags/APU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>APU</span></a>) and <a href="https://hachyderm.io/tags/Epyc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Epyc</span></a> Genoa <a href="https://hachyderm.io/tags/CPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CPU</span></a>. <br><a href="https://www.theregister.com/2025/01/17/hlrs_supercomputer_hunter/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">theregister.com/2025/01/17/hlr</span><span class="invisible">s_supercomputer_hunter/</span></a></p>
PrivacyDigest<p>New <a href="https://mas.to/tags/BadRAM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BadRAM</span></a> attack neuters <a href="https://mas.to/tags/security" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>security</span></a> assurances in <a href="https://mas.to/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://mas.to/tags/Epyc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Epyc</span></a> processors </p><p>One of the oldest maxims in hacking is that once an attacker has physical access to a device, it’s game over for its security. The basis is sound.<br><a href="https://mas.to/tags/AMDEpyc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMDEpyc</span></a></p><p><a href="https://arstechnica.com/information-technology/2024/12/new-badram-attack-neuters-security-assurances-in-amd-epyc-processors/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">arstechnica.com/information-te</span><span class="invisible">chnology/2024/12/new-badram-attack-neuters-security-assurances-in-amd-epyc-processors/</span></a></p>