Prices for Epyc Genoa CPUs are all over the place these days.
The 32-core 9354 starts at 2700€ retail.
The 64-core 9534 starts at 3800€ retail.
Don't know how much you are paying. But at this price difference, considering the cost for the whole system, I would pay that premium any day to get...
It sure can get confusing and intimidating, when reading some of the horror stories here and in other places.
But it's really not that difficult, if you can accept a moderate amount of noise from workstation. And if you use 2nd/3rd gen Epyc CPUs with less than 64 cores, and DIMMs with less than...
I guess this kind of question is usually related to gaming. I understand the concern, but it is impossible to make a blanket statement.
Playing CS:GO with competitive settings -> yes, the CPU will be the limiting factor
Playing modern AAA titles with high resolution / high settings / raytracing...
Memtest86 is not the right tool, at least the free version.
I don't know how exactly the paid version operates. I think it can be used for ECC, but the question remains how the load is applied.
The better and free way to do it has already been posted. Apply heavy load on memory and CPU cores...
It's not even that cheap I think? Just the cheapest (or sometimes only?) RDIMM on Newegg.
I'd pick used RAM from reputable brands over this, if I really had no way to get it new for a reasonable price.
The backstory here is that erock has had a few problems with trying to get the 7F52 to run stable. Corrupting disks, inexplicable resets, dfferent behaviour with different CPUs. There are a few threads here.
The other part of that backstory is Nemix RAM itself. I have read from too many people...
Waitaminute... during all this time of trying to diagnose cryptic and unexplainable errors and resets, we have been dealing with Nemix RAM?
Because f them. If you still can, return that memory.
I have the previous version of that case. One of the other benefits of Phanteks cases: The SSI-EEB boards from Supermicro fit without any modifications. The motherboard tray even has all the right holes for standoffs. Don't worry about 1mm, it will fit.
Stability aside, it's just not possible to go beyond 3200MT/s. No bios lets you set anything higher. Assuming you somehow get your hands on a bios that is not capped at 3200, the retail CPUs are probably locked too.
That's very low for a full CPU load. Quite suspiciously so. Maybe it was not the right sensor values? The CPU VRMs can and will go above 100°C.
I get up to 60°C with two 7551 CPUs, SMT off, and a water block on the VRMs.
For easy bios update via IPMI: GitHub - bwachter/supermicro-ipmi-key...
Have you tried keeping an eye on the VRM temperatures? The 7F52 are much higher TDP, and the H11DSi definitely can run into trouble with CPU VRMs overheating in workstation cases. You can use Supermicros "SuperDoctor" software to read the sensors.
There are contact pads on the H11DSi to clear CMOS. You need to bridge them with a screwdriver (or some other conductive tool).
The manual knows where to find it.
Looks like part of the pin is still there. Someone who is really good with a soldering iron could try to attach an extension to that.
On the other hand, that is a risky operation. And success is far from guaranteed. I would probably cut my losses and get another board.
Infiniband has been the industry standard for HPC clusters for quite a while now. No need to re-invent the wheel.
And the hardware is well within your budget, at least when buying used on ebay.
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.