Gigabyte's i-RAM: Affordable Solid State Storage
by Anand Lal Shimpi on July 25, 2005 3:50 PM EST- Posted in
- Storage
i-RAM Pure I/O Performance
We begin our usual hard disk drive test session with Intel's IPEAK benchmarking utility. We first run a trace capture on Winstone 2004's Business and Multimedia Content Creation benchmark runs to catch all of the IO operations that take place during each test. We then play each capture back using RankDisk, which reports back to us a mean service time, or average time that the drive takes to complete an IO operation.| Pure I/O Performance Comparison (Results in IO ops/second Higher is Better) | |||||
IPEAK Business Winstone 2004 |
IPEAK Multimedia Content Creation Winstone 2004 |
||||
| Gigabyte i-RAM (4GB) | 4347.8 |
1754.4 |
|||
| Western Digital Raptor (74GB) | 735.3 |
467.3 |
|||
Not too surprising is the i-RAM's dominance here, performing almost 6x the speed of the Raptor in the IPEAK trace of Business Winstone 2004 and 3.75x in the IPEAK MMCC trace.
Absolutely incredible I/O performance is to be expected from the i-RAM. The question is, how does it translate into real world performance?
Facebook
Twitter
RSS
133 Comments
View All Comments
Aganack1 - Monday, July 25, 2005 - link
i thought they said that they were only going to make 1000. enought for the crazies who have money to burn...P.S. if any of you crazies are reading this i could burn some of that money for you... just let me know.
Houdani - Monday, July 25, 2005 - link
Thanks for running through the multiple roles for which the iRam might be useful. I'm rather surprised it wasn't MORE useful in the benches. I'd be interested in learning (i.e. slacking back and reading the results of someone else's research) why the i-Ram is still as large a bottleneck as it is. Yes it's faster than the HD, but why isn't it much, much faster? Are we seeing OS inefficiency or something else altogether?In the end, though, it doesn't fit my needs particularly well, so I'll pass this round. Maybe a future version will be more appealing in terms of cost, speed, size.
Sunbird - Monday, July 25, 2005 - link
maybe the SATA interface isn't fast enough?pio!pio! - Monday, July 25, 2005 - link
I'm constantly shuffling 1--3 gb mpeg2 files around...this would be greatGed - Monday, July 25, 2005 - link
Would it be possible for an NVIDIA or ATI graphics card that used TurboCache or HyperMemory to make use of the i-RAM?That might be interesting.
Anton74 - Monday, July 25, 2005 - link
No, absolutely not. Even if it were, the SATA interface is *way* too slow to be of use for something like that.And even if that were not a factor, why spend that kind of money on the i-RAM where the same amount would buy a *much* superior video card with its own dedicated memory?
Anton
kleinwl - Monday, July 25, 2005 - link
I think that this would be very helpful as a page file for workstations. Older workstations may be maxed out with 4GB and windows 2000 (which the company does not want to move over to xp-64) and still need additional ram for CAD/CFD/etc. This would be an easy upgrade with a reasonable amount of performance increase.sandorski - Monday, July 25, 2005 - link
Was hoping it would offer more, especially as a Pagefile. Any plans to make a PCI-e version(IIRC PCI-e has a ton more bandwidth than SATA), that would likely make this a Must-have. As it stands now I'd only use it for the silence in a HT Setup.Gatak - Monday, July 25, 2005 - link
Using PCI/PCI-e for transfers would require OS drivers which wouldn't be available for all OSes.sprockkets - Tuesday, July 26, 2005 - link
Keep in mind that for many years the ide/sata controllers are NOT on the PCI bus of the southbridge, so PCI is not a limitation.