PCMark Vanatage WR is now 29272

[SteveRo]

Good morning,

Having a bit more success with pcmark vantage, moving up a bit - http://service.futuremark.com/compare?pcmv=305488
I think I will need better cooling to catch Mike -

[Anvil]

Great achievement Steve,

I browsed the results yesterday, what brought you the last 300 points, fine-tuning or OC?

[SteveRo]

Great achievement Steve,

I browsed the results yesterday, what brought you the last 300 points, fine-tuning or OC?

Thanks!
Fine-tuning and a bit of luck that I wouldn't fail the cpu gaming test (again).
I'm on the hairy edge of instability.

[Computurd]

wow that is totally awesome man. great job just moving right on up! great work!
considering that corsair labs ran it at 5.8 you beating them at 4.8 is just outstanding

[GullLars]

Congratz. Fun to see the top5 going:
1. Mike
2. Steve
3. *Company* labs.
4. Nizzen 24/7 (EDIT: and from Aug 09)
5. mbreslin

I'm hoping nizzen will pass corsair when he gets a new CPU and Areca 1880, possibly with ATI 6xxx if it's after the summer.

BTW, steve and mike, are your scores doable at 24/7 settings? If not, how high are your scores with your 24/7 settings?

I'm also wondering, are any of you guys in top5 sponsored? And have you asked for sponsors?

[mbreslin]

I hope Nizzen blows all his money on women and beer and can't upgrade. I should be ready to start throwing scores up by the weekend. My 980 isn't even installed yet.

Edit: I had no budget and I wasn't sponsored. Disposable income ftw.

[GullLars]

Nizzen got a woman, and a kid too i belive...

BTW, have you tried a 6R0 on ICH10R? It could be interresting. It seems like PCmark Vantage likes 16KB stripes, possibly 8KB too, we're investigating a bit on the norwegian forum.
The pro of using ICH10R is that you aren't IOPS limited, untill you hit like 400MB/s (or higher). We have listed Anvil with 117K 4KB random read IOPS @ QD 64, with 1 worker (4R0 x25-M). That's like 468MB/s... He's also listed at 103K IOPS with 3R0 x25-M.
I just keep thinking of the IOPS from 6R0 C300 on ICH10R... You will max its bandwidth at 4KB random :P You could do 300K IOPS with 6 C300, but that would be 1200MB/s bandwidth...

[mbreslin]

To be honest I've never even hooked up more than 1 drive on ich, I went right to 9211 and then on to 9260, sometimes using 1 on ich for os and 7 in r0 on the lsis. I can try it, the problem becomes trying to run cabling in my case, even temporarily it's not easy. I have 10 5.25 bay devices and 10 drives, 2 360 rads and 1 480, 5970/5870/sound card/nic/9260, literally every single slot is filled. Throw in all the tubing and "permanent" type cables and even a mm ascension runs out of space.

[onex]

wow, steve, that is superb!
on 4.8, man, U'R almost up there!!! again!!
just a little bit more, imagine what u can do with 5.5 and up with this array!!
u can beat them all !!
beautiful!!
great accomplishment!

p.s - lowfat, great spirit! way to go on this 5Ghz

[GullLars]

mbreslin, what about just letting the 6 drives lay loose on the bench with the side-door off, or if you need to close the door, let them lay on the bottom of the cabinet or on top of other HDDs. There is no point in mounting them if you're not going to move the case.
You can also go McGuyver and use some duct tape against the door of the case, or any other surface.

When you hook it up, plz make a new thread, i have some suggestions and a couple of tests i'd like you to run. (among other things a IOmeter setup wich should take only a couple of minutes)
If you also have the possibility later of running OS from a single drive on 9211/9260, it could be cool to do stripe sizes 4 through 256KB and look how it effects PCmark Vantage HDD scores.

[SteveRo]

wow that is totally awesome man. great job just moving right on up! great work!
considering that corsair labs ran it at 5.8 you beating them at 4.8 is just outstanding

Thanks.
Also regarding 5.8 vs. 4.8 - I think Planet didn't use 4GB cache and wasn't allowed to use acards.

Congratz. Fun to see the top5 going:
1. Mike
2. Steve
3. *Company* labs.
4. Nizzen 24/7 (EDIT: and from Aug 09)
5. mbreslin

I'm hoping nizzen will pass corsair when he gets a new CPU and Areca 1880, possibly with ATI 6xxx if it's after the summer.

BTW, steve and mike, are your scores doable at 24/7 settings? If not, how high are your scores with your 24/7 settings?

I'm also wondering, are any of you guys in top5 sponsored? And have you asked for sponsors?

I can do 4.5 with vcore and qpi/vtt under 1.4v (intel max) and with temps?
Temps probably under 60C at full load - pcmv score for this is approx 31K.
I have no sponsorship - the closest I have to sponsorship is above average tolerance in my wife.

wow, steve, that is superb!
on 4.8, man, U'R almost up there!!! again!!
just a little bit more, imagine what u can do with 5.5 and up with this array!!
u can beat them all !!
beautiful!!
great accomplishment!

p.s - lowfat, great spirit! way to go on this 5Ghz

Thanks.
Once lowfat gets his cascade I expect him to post some new huge oc's into the 4.5 linx stable club
He has a top performer 920 chip that is waiting.

[onex]

i don't understand u steve, are u going to use his system to cool u'r chip?

lol, i've got a 920 week 49 waiting here boxed for a mobo and some RAM sticks .

[SteveRo]

i don't understand u steve, are u going to use his system to cool u'r chip?

lol, i've got a 920 week 49 waiting here boxed for a mobo and some RAM sticks .

I think you are referring to Lowfat's cascade - I had previously suggested I could go to Lowfat's - that in jest.
If Lowfat was closer that would be a great idea.
I wonder how much trouble I could get into trying to handcarry a bag full of acards onto an airplane bound for Canada.
I do have a single stage phase change on the way from sdumper - hopefully have it in a couple weeks.

[onex]

I wonder how much trouble I could get into trying to handcarry a bag full of acards onto an airplane bound for Canada.

lol, with U.S ground check and laws, probably a lot .

[mbreslin]

@GullLars: I mount my ssds because the computer is supposed to be 24/7, hopefully getting to the point where I don't need to open the case anymore :p. I'm rebuilding loops this week for 980x, I will connect 6 extra sata cables to ich, shouldn't be too hard to switch them even with hard drives mounted. I did run 9260 with 1 drive on different stripe sizes, but I didn't ever go smaller than 64k. Also I didn't specifically run pcmv hdd suite as you're asking, I just ran the 3 iometer tests anvil linked me. 64k was the clear winner but maybe smaller will do better in vantage, I'd be willing to try.

[SteveRo]

For the 30GB Kingston see - http://www.bit-tech.net/hardware/201...128gb-review/1

"Results Analysis
With Toshiba having had 18 months on the SSD sidelines watching the competition learn and optimise their controllers, we were hoping for a solid showing. For the most part, we weren’t disappointed.

Sequential speeds as recorded in AS SSD averaged at 222MB/sec read and 177MB/sec write, and showed no deterioration following our 1TB write load and subsequent TRIM command. The sequential write performance was very good in particular, outpacing the Indilinx-powered OCZ Vertex by a commendable 30MB/sec.

Access times weren’t as unaffected by our 1TB write, rising from 0.139ms to 0.212ms for read and from 0.392ms to 0.439ms for write. However, these times are still pleasingly low, and comparable to competing SSDs.

Sequential performance measured in ATTO Disk Benchmark was also good, and while the new Toshiba controller shares the Indilinx drive controller’s poor 4KB sequential read performance, 64KB and 1,024KB performance was much better, with the 64KB sequential reads comfortably outpacing the Samsung controller in the Corsair P128.

One cause for concern with the Kingston is the sequential write performance with 64KB and 1,024KB files – we saw some minor, but noticeable, performance degradation following our writing of 1TB to the drive, despite the successful execution of the TRIM command. This is an issue we’ve also observed with the Samsung drive controller. While this issue won’t reduce performance by a horrendous amount, it still isn’t the perfect TRIM-based performance recovery displayed by the Intel and Indilinx drives.

What’s perhaps most surprising though is the comparatively poor random read and random write performance. We saw a random read speed of 18.8MB/sec, which is just half that of the OCZ Vertex and similar Indilinx-controlled drives. While a random write speed of 6.79MB/sec when clean and of 4.59MB/sec post-TRIM is a little better than the Samsung controller used in the original SSDNow V+, maximum write latencies, are worryingly high from the outset at 590ms, and peaked at 768ms post-TRIM. This is close to a whole second of random write lag, and approaches the sort of maximum write latencies we thought had been eliminated since the first generation of JMicron drive controllers.

Finally, looking to our remaining real world test of booting Windows 7, the drive performed identically in clean and TRIMed state, with a boot time of 34 seconds. This is roughly the same as all the competing high end drives, with the extra second of waiting likely due to the comparatively inferior read speeds of the Kingston.

[Computurd]

@mbreslin-
your case will never stay closed, your on the bleeding edge bro

[mbreslin]

If I were in ks or you were in cali I'd make you come over and do it for me ct ;p

[Jor3lBR]

SteveRo, any significant difference between using 2Gb cache and 4Gb?

[Computurd]

and i would do it mr.breslin !

[SteveRo]

SteveRo, any significant difference between using 2Gb cache and 4Gb?

Seems like only in pcmv but in pcmv it was a big improvement.
Seems like the suite score went up 1-2K.
Probably dependant on drives used and the speed of the rest of the machine.
I think a large cache can really improve an even bad array.
Not that 2x x25-v R0 is bad but it is nothing compared to 12xacard9010R0, yet the pcmv scores are only 10k apart or so (pcmv HDD test) when using 1231ml4g.

[Tiltevros]

stevero
im expecting to see similar numbers from u!!!! i know what is ur new toy

LSI HBA 9211 R0 with 8xIntels G2

[SteveRo]

Tilt - wow, nice numbers - all are excellent except i would of expected seq write closer to 8*80=640 - closest is AS SSD of 530?
What stripe size was best for the x25m's and can you now adjust the stripe size?
Seems like I couldn't adjust the stripe size when i had the 9211 last December.

[Tiltevros]

u cant lol just play with settings

[Tiltevros]

just breaking the lines with 9211