The stuff Hacker News actually recommends.

GPUs and CPUs

AMD EPYC vs AMD Ryzen

Hacker News owners slightly favor the AMD Ryzen.

AMD EPYCAMD Ryzen
Owners with an opinion33355
Positive verdicts78% of 2777% of 265
Positive/negative since 202414/3109/24
Happy after 3+ years05
Longest happy owner1 yrs7 yrs
Praised forperformance and valueperformance and reliability
Criticized fornoisenoise
Newest comment

Updated

What owners wrote about both

AMD EPYC: Doesn’t like itAMD Ryzen: Likes it
Is using virtualization the only good way of taking a 288-core box and splitting it up into multiple parallel workloads? One time I rented a 384-core AMD EPYC baremetal VM in GCP and I could not for the life of me get parallelized workloads to scale just using baremetal linux. I wanted to run a bunch of CPU inference jobs in parallel (with each one getting 16 cores), but the scaling was atrocious - the more parallel jobs you tried to add, the slower all of them ran. When I checked htop the CPU was very underutilized, so my theory was that there was a memory bottleneck somewhere happening with ONNX/torch (something to do with NUMA nodes?) Anyway, I wasn't able to test using proxmox or vmware on there to split up cpu/memory resources; we decided instead to just buy a bunch of smaller-core-count AMD Ryzen 1Us instead, which scaled way better with my naive approach.
AMD EPYC: Likes itAMD Ryzen: Likes it
Programs whose performance is dominated by array operations, as it is the case for most scientific/technical/engineering applications, achieve a much better energy efficiency on the AMD or Intel CPUs with good AVX-512 support, e.g. Zen 5 Ryzen or Epyc CPUs and Granite Rapids Xeons, than on almost all ARM-based CPUs, including on all Apple CPUs (the only ARM-based CPUs with good energy efficiency for such applications are made by Fujitsu, but they are unobtainium). So if you want maximum energy efficiency, you should choose well your CPU, but a prejudice like believing that ARM-based CPUs are always better is guaranteed to lead to incorrect decisions. The Apple CPUs have exceptional and unmatched energy efficiency in single-thread applications, but their energy efficiency in multi-threaded applications is not better than that of Intel/AMD CPUs made with the same TSMC CMOS fabrication process, so Apple can have only a temporary advantage, when they use first some process to which competitors do not have access. Except for personal computers, the energy efficiency that matters is that of multi-threaded applications, so there Apple does not have anything to offer.
AMD EPYC: Likes itAMD Ryzen: Likes it
Zen began to be really better than the competition only with Zen 2 (Ryzen 3000), when the production of its CPU chips was transferred to TSMC. For Zen 1 or Zen 1+, only the Epyc CPUs seem to have been free of problems. I have a 24-core Zen 1 Epyc that has always worked flawlessly, but when I have preordered the very first Ryzen, the 1750X, I had to dump it as useless garbage after only a couple of weeks, because I was using it in Linux, where any intensive multi-threaded task was crashed by a nasty bug that was not seen on the Ryzens used just for playing games in Windows. AMD has never given any explanation about their bug, and they did not recall their CPUs, which were completely unusable for professional purposes. However, like Intel today, they at least honored the RMA requests. However I did not bother with an RMA, especially because the procedure would have been complicated, as I do not live in the USA and I would have had to ship internationally the bad CPU. I have just dumped both the Ryzen 1750X and the expensive motherboard, keeping only the DIMMs, and then I have bought a Kaby Lake instead. Nevertheless, I did not hold a grudge against AMD, despite losing more than EUR 800, and later I have bought an Epyc and then a Zen 2 Ryzen and then a Zen 3 Ryzen, all of which have worked perfectly.
AMD EPYC: Likes itAMD Ryzen: Likes it
>which is insecure Splitting IOMMU groups is not inherently insecure; doing so without ACS is insecure. It is true that's not the motherboard vendors fault - it is because Intel designed it that way. ACS (the part of PCIe which makes sane IOMMU group splitting possible) works great on my Zen products (Ryzen, Threadripper, EPYC, etc.) It also works fine on my Intel Xeon products. Intel client silicon is the odd man out here, and if you ask me that's hardly an accident. It falls neatly in line w/ their other artificial market segmentation. (They do the exact same thing w/ ECC RAM.) I'm mostly just jaded because my use-case (PCIe passthrough for a 'gaming VM') is hardly conducive to enterprise grade hardware (Xeon SKUs w/ low base clocks, headless GPUs designed for compute, etc.) yet vendors like NVidia and Intel choose to make this use-case difficult/impossible to implement on their consumer grade offerings. It gets old after a while. I, for one, am really glad AMD shook things up in this regard in the CPU space.