Oh look another business using "Market conditions" to raise prices on already produced stocked products just because there is news of a shortage in the future.
Yeah I've never seen this from anyone else outside of FPGA NICs. It requires considerations on the FIFO and and MACs that may not have been done at tape out so you generally will only see 4x 10gbps or 40gbps ports. Same deal exists on 100gbps / 25gbps NICs. Usually they are either ganged or not...
Mostly for hardware emulation of RISC-V SoCs for application acceleration on 100gbps network cards using the corundum project. Using RDMA PeerDirect to communicated between the FPGAs and other end point such as NVMe or GPUs without using the host processor. It'd be nice to have some local...
https://www.crucial.com/memory/server-ddr4/mta18asf4g72az-3g2r
A the bottom of the page there is a discount of 10% on the first order if you join their mailing list.
Looks like a good deal for NAS / Workstation system that use desktop CPUs.
Just over $2/gb delivered.
https://www.ioi.com.cn/products/product_detail.php?pid=P0010&tid=&no=20191118001
So you could do something like this to have it mounted internally instead of hotswap... sadly this won't work for my 1U but could work for my T5820.
Sadly too much power to fit in a M.2, the U.2 drives hold around $160, I managed to low ball a U.2 for $95 and I've never seen that deal again lol. I'd really like to get 3 of them to have 2 in each of my test nodes for NVME-over-Fabric and RDMA testing. Instead I have the most random collection...
https://www.ebay.com/itm/275957524255
Looks like the market is falling out from under the 900p I had bought 3 recently at $75 each and I thought that was a good deal…
It’s a real shame that there are so many of the AIC 280gb version but no excess supply of the u.2 version.
I have a dual E5-2670v4 blade with a U.2 900P drive in it and I'm able to push 596K/454k with 4 jobs 3 iodepth and 4k blocks. So we are no where near the drive limit lol.
I think the PCI-E 2.0 is a J5005 SOC limitation.
I think this this box is just going to get a quad gig NIC and call it a...
From my recent testing the best I've been able to get is still that 233k/159k read/write bandwidth, I think the problem is that the CPU is bottleneck the benchmark, you get better performance for the first few seconds when it's boosting. The performance tops out at 4 jobs and 3+ iodepth...
I'm not 100% what the FIO command PTS uses for their backed but here is what I have:
https://openbenchmarking.org/result/2307031-NE-STH96009388
If you want to provide an FIO command to test I'd be happy to try it.
I'd expect at PCI-E 2.0 that we should be closer to 2.0 GB/S and real world...
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.