...I'll have one for my windows7 system & games partition.
Once I've won the lottery, that is.
TMS has doubled the capacity of its PCIe flash card and almost tripled its performance. The RamSan-70, code-named Gorilla, has a capacity of 900GB of single-level cell (SLC) flash, twice that of the preceding RamSan-20. Gorilla, using 32nm NAND from Toshiba, is 2.75 times faster than the RamSan-20, half the size, and has a …
I saw an 15K rpm SCSI drive along with a very expensive top of the line ATTO card in a true gamer machine.
He couldn't stand to noise, that is why he replaced the HD with a sane one rather than datacenter one.
I am mailing this story to him, lets hope he doesn't read comments ;)
TMS architecture’s impact will be felt when the card begins to get pushed (device fully seasoned, full capacity utilization, multiple threads etc.). That’s where Virident tachIOn shines.
Ramsan is able to produce decent micro-benchmarks. But, the strength highlighted in the article: "The RamSan-70 does not rely on the host processor for flash translation as there is an on-board PowerPC CPU" -- is also its weakness.
This means that real-world application performance, where multiple cores are all accessing the flash in parallel, will be difficult to scale. The speed of the PowerPC CPU cannot keep up with multiple cores running at 2.5+ Ghz all pushing I/O in parallel. Straight micro-benchmarks create close comparisons, but the ‘offload’ architectures typically fall behind as soon as you put them into real-world applications.
Disclaimer: I am an employee of Virident!
Except, if you don't use the PPC to manage the flash translation but use the FPGA assisted by the PPC then you get line-speed processing. There are few devices in this world faster than a good FPGA and the Virtex-6 is really quite good. How effective it would be at interfacing the PCI-e bus to the NAND is a question, but if they have it right then it could be damn fast.
Disclaimer: I don't work for anyone involved.
Biting the hand that feeds IT © 1998–2019