Well, what's the capacity point you're aiming for? These days a single M.2 NVMe drive will get you up to 8TB with zero hassle at €$100-150/TB and all you need is one of those M.2-> PCIe x4 adapters to have it fit into a slot. Even with a bit of metal for cooling these are below €$20 in price.
I've been hunting for switch based cards myself but generally those were so expensive you really had to hurt for the capacity to buy them, even from companies like HighPoint-Tech, which used to be economy oriented.
But recently some ASmedia switch based cards have popped up, which brought some...
I wonder what you're trying to achieve: when it comes to simply using an x16 slot to mount more M.2 form factor NVMe drives, there are far simpler boards with very short traces. I've used this, which is supposed to support PCIe v4 and sports a little fan, but also similar ones designed for PCIe...
It's getting worse and worse...
I did try the replacement 9261, but no luck. I first upgraded its firmware so it would have the same latest revision and then tried using it with the 8x2TB RAID5 from the backup machine, which failed with the same message ("Foreign drives cannot be imported as...
I've had a bit of a scare after a BIOS update on my mainboard: my RAID6 drives had dropped off the system, and those had survived a mainboard transplant with relative ease a year or two back (Xeon E3-1276 v3 --> Ryzen 7 5800X3D).
The BIOS update was supposed to fix the GigaByte UEFI...
I tried upgrading my MSM, too, to the latest available on downloads (17.05.06.00, I believe).
Hit across the same Java issues, tried all kinds of runtimes, to no avail, even when I matched it to the exact same release mentioned in the release notes.
In the end I went back to the last release in...
The N305 only has one extra PCIe lane 9 vs. 8 on Jasper Lake: there just isn't enough bandwidth to make a 25 Gbit/s net work.
I aggree the n305 seems a nice chip and very much like a great replacement for say a Xeon D-1541 and I'd like to get my finger on one, but it's rather limited by its I/O...
The Sabrent PC-P3X4 finally arrived and I've had a chance to look at it.
It's using one ASM2812 chip with 2 PCIe 3.0 lanes allocated to each M.2 slot. It's a bit of a compromise between a "perfect" switch which allows full device bandwidth at 4:1 oversubscription and a "cheapo" solution that...
Honestly the write amplification of RAID6 on QLC drives doesn't sound like it will last long, either. Now if you had really large non-volatile write caches to assemble large stripes and eliminate the write amplification (pretty much what PURE does in my understanding), this wouldn't be all that...
I've just discovered and ordered a Sabrent PC-P3X4 quad M.2 to PCIe x4 board, which very likely is using this ASM1480 PCIe switch chip as well, which will do 16 x 8 lanes (obviously also 16 x 4) and seems to be economical enough to sell at €170 including VAT, much less than what HighPoint-Tech...
Well, prices have changed significantly, but given that ECC RAM is typically a bit slower anyway I just couldn't see the benefit of doing DDR5 there, even now. I'm also doing a mix of Windows and Linux and the E/P core mess is far from getting sorted out, either.
And since I was aiming more...
The smaller and closer the DRAM cells, the more suceptible they are to cross-talk and energy events. On-die ECC was considered necessary to compensate the additional risks created from shrinking cell dimensions, much like flash generations built extra layers of checksums and block management to...
I keep hearing from the inventors of the Rowhammer attack that it can only get worse because of physics: the closer the cells, the higher their effect on each other. They constantly keep finding new attack patterns and additional potential with new technology.
ECC completely stopped being a...
64GB must be a BIOS issue then, because I've tested 64GB (2 DDR4-3200 modules, which run at DDR4-2933 on Jasper Lake) on my Intel NUC11ATK with the same SoC.
But it took almost an eternity to boot after switching from 2x8GB DDR4-2400: I was ready to turn it off, thinking it had failed, when I...
I've been using Geizhals myself for some years. It's truly great in terms of filtering capabilities, especially because it's actually respecting the hard constraints on your search and doesn't waste your brain cycles with false positives, like Amazon or the generic search engines...
Of course...
Yes, perhaps.
But then I'll never know, because while OWC wastes my brain cycles quoting lofty business tautologies like "Government agencies, companies, and institutions need the ability to reliably access and quickly analyze enormous data files to make decisions", but it takes great care to...
Well, my personal use case is really more about operational experimentation and for production we use P100, V100 and successors anyway, simply because they pack a bigger punch and are server cooled passive variants that have no fan whatsoever.
And for non-ML use cases in HPC or engineering it...
EULA are works of fiction. And in the EU we have laws that invalidate most of the controls that vendors like to place on things they sell: somehow many fail to accept that a sale is a transfer of ownership, not an agreement to become an indentured servant.
We also have privacy laws lots of...
3090 are still holding remarkably firm in Europe, nothing like the price drops news flashes keep throwing around elsewhere. But yes, this is €100 more than the equivalent new non-blower 3 slot card I got a few weeks ago after giving up on available two slot cards with shipping and VAT included...
I had actually been looking for a 2 slot 3090, because one of my 40-lane Xeon systems, which might wind up using it at one point in time, has a precious x16 slot (currently holding a FusionIO drive) that a >2 slot card would cover up. But those were hard to find or only had fake offers, so I...
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.