Anyone know: Does read speed top out at 300MB/sec on SATA II? Is write speed of the 128GB and 256GB models essentially unchanged on SATA II? Or does SATA II impose enough overhead that they slow down...
Type: Posts; User: hyc; Keyword(s):
Anyone know: Does read speed top out at 300MB/sec on SATA II? Is write speed of the 128GB and 256GB models essentially unchanged on SATA II? Or does SATA II impose enough overhead that they slow down...
The obvious solution is to quit using closed source software that you can't recompile when you wish.
Did you check to see if your system clock was still showing the correct time of day?
I recall running a bench on an old machine, ages ago. It had a turbo button in it, but the machine design was...
Doh.... I see, thanks for the heads up.
So, 8.85/5.25 = 1.6857: the 4 extra cores are only worth 2.7 real cores.
Thanks Dumo. But just to be certain, what if you ran your 8C and 4C tests at the exact same clock speeds? Then we should see 8C being exactly 2x 4C result, right? Or 4C result will be higher than...
OK, I guess that makes sense. So really the Phenom X4 and X6 scores are most comparable.
DG Lee's thread gives a data point for FX with only 4 cores, too bad his CB11.5 slide's scores are obscured...
That seems to indicate that there's a clock domain mismatch somewhere, and using 250MHz HTT fixes the mismatch for that particular combination of clocks/multipliers. (But there's no guarantee it...
Those numbers were pulled from the Cinebench results table. They're Athlon X2s and X4s, (and yes, X6 Thubans). http://www.xtremesystems.org/forums/showthread.php?t=255323
I was thinking FX-81xx but it would be interesting to see one or two tests for Thuban too. I'd figure Thuban results would be perfectly uniform; for FX it will obviously depend on which cores you use...
Has anyone done any analysis of scaling on these results? (Sorry, I've only read thru 5 pages of this thread.) It seems pretty inconsistent. E.g., X3@3900MHz: 3.02, X4@3900MHZ: 4.65. 4.65/3.02 =...
mobo manufacturers should just be using open source BIOSes. There'd be zero licensing cost to them, and they can continue to offer zero support to old boards (face it, that's the basic reality...
If stuff running on random cores is causing problems, you should try re-testing with manually set processor/thread affinity.
I've seen this make a pretty big difference in server code as well.
...
Personally I think that Piledriver slide is pure BS. There's no way AMD would talk about that to anybody outside of AMD, before BD has even been released. Not even to big partners like Cray, it would...
Obviously it depends on the number of samples, which is unknown here.
Assuming only two samples, then 115 = (X + 71) / 2 and 114 = (Y + 80) / 2, therefore X = 159 (1100T) and Y = 148 (i7).
...
Something is still wrong with the graph. The legend says min and *average* FPS. For the 1100T's average to be higher than the i7's, even tho its min rate is lower, means the 1100T's *max* FPS was...
Duuuuuuude........
OK, so you don't wanna crap on family. They sent it to you for a reason, not just to be nice. You should test and give them feedback. Out of sheer respect, you owe it to them...
Eh? Why is the top bar the i7-930 at 114fps, when the 1100T got 115fps ?
I would guess FMA will be much more important for X264 and any other codecs.
It may well be unfortunate that you feel that, but it's only unfortunate for you.
Lol so true. Haven't been back in ages but I remember the cats in every corner of every building...
64GB is still pretty light for that many cores. My 16 core HP DL585 G5 (4 Opteron 8354s) has 128GB of DDR2 ECC and I'm still wishing we had gone for more. Been juggling a bunch of 300GB data files...
32GB sounds about right for a video editing workstation. As soon as you need to mix more than a couple video tracks, that'll fill right up.
Sounds like clock skew/jitter; with a single lane there's only one signal so nothing to worry about. With 16 lanes running at insane speed, a "minor" variance in propagation in any of those lanes...
You're quibbling over semantics. Instead of "vacuum" you should just be saying "reduced pressure" because it obviously is not a total vacuum.
Remember, this is Apple we're talking about. For them, a program that does what you tell it to is *novel*...