not sure if that answers my question. ok so not a supercomputer? so the Mac Pro is now faster than a Sun Fire server farm?
Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
2009 Mac Pro in hand - unboxing etc.
- Thread starter WonderSausage
- Start date
- Sort by reaction score
not sure if that answers my question. ok so not a supercomputer? so the Mac Pro is now faster than a Sun Fire server farm?
The 4870?
When you get a moment...any chance you could take a pic or two of 4870?
I am especially interested in the back of card, area around ROM chip etc, like image I posted in "Race to Dump 4870 ROM" thread.
Curious how different Mac card is from PC .
And when you find a little more time....perhaps a ROM dump of 4870.....?????
When you get a moment...any chance you could take a pic or two of 4870?
I am especially interested in the back of card, area around ROM chip etc, like image I posted in "Race to Dump 4870 ROM" thread.
Curious how different Mac card is from PC .
And when you find a little more time....perhaps a ROM dump of 4870.....?????
How about running Cinebench?
http://www.maxon.net/pages/download/cinebench_e.html
http://www.3dfluff.com/mash/cinebench/top.php
http://www.maxon.net/pages/download/cinebench_e.html
http://www.3dfluff.com/mash/cinebench/top.php
I would love to, but I run CS4 under Vista because it's 64-bit on Windows
someone needs to read.
Well yes and no. I mean, let's face it ... until we get someone who can run real world tests we're basing everything on GB alone. While it is clearly faster, how much faster and more efficient is it?
Congrats! Nice to finally see some real numbers. They're not at all surprising considering that there are some 2.6Ghz quad core i7s scoring over 12,000. As soon as those dual socket motherboards hit the market you're going to see Windows and Hack GB scores above 20,000.
Thanks for taking the time to take and post the pictures! I would be dying to use it rather than photograph it.
I have a 2008 2.8 Octo Pro and it's interesting to see all of the interior changes. Nothing sweeping, but a lot of tweaks, especially with regards to dropping the IDE DVD drives and going to SATA. That will also give the newer models much better upgrade paths with Blu-Ray if Apple ever gets around to supporting Blu-Ray because most of the Blu-Ray drives that I've seen are SATA rather than IDE.
Very cool. Thanks again!
I have a 2008 2.8 Octo Pro and it's interesting to see all of the interior changes. Nothing sweeping, but a lot of tweaks, especially with regards to dropping the IDE DVD drives and going to SATA. That will also give the newer models much better upgrade paths with Blu-Ray if Apple ever gets around to supporting Blu-Ray because most of the Blu-Ray drives that I've seen are SATA rather than IDE.
Very cool. Thanks again!
someone needs to read.
Well yes and no. I mean, let's face it ... until we get someone who can run real world tests we're basing everything on GB alone. While it is clearly faster, how much faster and more efficient is it?
yes atm all im waiting for is to see if the 2.26 octo is in fact faster than the old 2.8 octo...i think this goes for the majority of the people who are to buy a 2009 mac pro. i would wait for barefeats to do some benchmarking but god knows when they will receive a rig from apple.
youre right though, geekbench is nice and all but doesnt give a clear picture what the computer's really worth.
One last shot for the moment.
The new hot swap tray has the drive in a different position due to the lack of separated backplane.
Thankfully the stock drive is a WD (Seagate's rep has been hammered lately due to firmware issues).
The new hot swap tray has the drive in a different position due to the lack of separated backplane.
Thankfully the stock drive is a WD (Seagate's rep has been hammered lately due to firmware issues).
Another bench marking idea:
In there a way to turn off HyperThreading (HT) so the system isn't using virtual CPUs? I would love to see the differences! The ones from 5 or 6 yeas back didn't add all that much. It would be nice to know how much difference there is in this go around.
(I wonder if that data is already available from the Corei7 systems that are out there using Windows based tests?)
In there a way to turn off HyperThreading (HT) so the system isn't using virtual CPUs? I would love to see the differences! The ones from 5 or 6 yeas back didn't add all that much. It would be nice to know how much difference there is in this go around.
(I wonder if that data is already available from the Corei7 systems that are out there using Windows based tests?)
I know very little about Geekbench, but just looking at the numbers the memory score is way up which might be expected, but there is also a major increase in the floating point (much bigger change than that for the integer). I wonder why? Better fpu or better utilization of it with the HT?
benchmarks and youll probably be on the front page of every single tech blog out there
do some photoshop tests plzzz!!!
I can't wait for all the news agencies to start buzzing about MacRumors user WonderSausage! I'm sure they'll skip his user name! LOL
Well that confirms it, your running a small datacenter.
Excellent questions. If there is indeed a way to turn off HT then we could find out.
Knowing Apple I bet there isn't a user-ish switch to do so.
Also remember tho... His is a 2.93GHz while mine is a 2.66. <me cries>
CINEBENCH R10
****************************************************
Tester : WonderSausage
Processor : Dual Nehalem Xeon
MHz : 2933
Number of CPUs : 16
Operating System : OS X 32 BIT 10.5.6
Graphics Card : ATI Radeon HD 4870 OpenGL Engine
Resolution : 2560x1600
Color Depth : 32
****************************************************
Rendering (Single CPU): 4074 CB-CPU
Rendering (Multiple CPU): 25644 CB-CPU
Multiprocessor Speedup: 6.29
Shading (OpenGL Standard) : 7016 CB-GFX
****************************************************
****************************************************
Tester : WonderSausage
Processor : Dual Nehalem Xeon
MHz : 2933
Number of CPUs : 16
Operating System : OS X 32 BIT 10.5.6
Graphics Card : ATI Radeon HD 4870 OpenGL Engine
Resolution : 2560x1600
Color Depth : 32
****************************************************
Rendering (Single CPU): 4074 CB-CPU
Rendering (Multiple CPU): 25644 CB-CPU
Multiprocessor Speedup: 6.29
Shading (OpenGL Standard) : 7016 CB-GFX
****************************************************
Staggering geekbench results for the highest-end 2009 mac pro!
I just did the 32bit geekbench on my 2008 8 core 3.2Ghz mac pro and got 9608! I just checked the Apple Store UK and your system spec costs almost DOUBLE my top end 3.2Ghz spec from a few months ago. Amazing results for the 2009 mac pro at a staggering price
One little weird thing. Some of my single threaded scores were higher than yours.
Just re-run the 64bit geekbench test on my 2008 3.2GHz mac pro and got 11240
This is a more accurate comparison as your 2009 mac pro geekbench test was in 64bit
I just did the 32bit geekbench on my 2008 8 core 3.2Ghz mac pro and got 9608! I just checked the Apple Store UK and your system spec costs almost DOUBLE my top end 3.2Ghz spec from a few months ago. Amazing results for the 2009 mac pro at a staggering price
One little weird thing. Some of my single threaded scores were higher than yours.
Just re-run the 64bit geekbench test on my 2008 3.2GHz mac pro and got 11240
This is a more accurate comparison as your 2009 mac pro geekbench test was in 64bit
CINEBENCH R10
****************************************************
Tester : Tesselator
Processor : X5355
MHz : 2.66
Number of CPUs : 8
Operating System : OS X 32 BIT 10.5.6
Graphics Card : NVIDIA GeForce 7300 GT OpenGL Engine
Resolution : 1920x1200
Color Depth : 32 bit
****************************************************
Rendering (Single CPU): 2873 CB-CPU
Rendering (Multiple CPU): 16615 CB-CPU
Multiprocessor Speedup: 5.78
Shading (OpenGL Standard) : 2294 CB-GFX
****************************************************
Here's my Mac Pro v1.1 2.66 for comparrison.
Interesting implications for the 4 - core
With 17k for the 8 core 2.92 numbers being so high, it doesn't take a lot to extrapolate some results from those to guess what the four-core nehalem is going to be like:
2.92 x 8 = 17665 geekbench
If that scales perfectly with 100% utilization of all cores, the base model 4-core would be:
17665/2.92/2*2.66= 8046 geekbench
This puts it just under the 2008 2.8 eight-core which isn't bad for a four core entry level Mac Pro.
More realistically, the second chip on the 2.92 is likely to be underutilized compared to the first, with diminishing returns as shown by the 6x results from the cinebench test. I'm guessing the four-core machine pulls at least an additional 15%, putting the GB around 9200, pretty much a dead heat with the 8-core 2008 model.
This creates a bit of a quandary for the new buyer. 8 core xeon 54xx on liquidation or four core nehalem? Applications that don't take advantage of the second cpu may prefer the nehalem system, and the GT120 is a better video card that the stock 2600 that comes with the 2008 model.
I think it will all come down to RAM and specific application performance. Personally, I'd love to see some Handbrake encode numbers from the 2.66 Nehalem....
With 17k for the 8 core 2.92 numbers being so high, it doesn't take a lot to extrapolate some results from those to guess what the four-core nehalem is going to be like:
2.92 x 8 = 17665 geekbench
If that scales perfectly with 100% utilization of all cores, the base model 4-core would be:
17665/2.92/2*2.66= 8046 geekbench
This puts it just under the 2008 2.8 eight-core which isn't bad for a four core entry level Mac Pro.
More realistically, the second chip on the 2.92 is likely to be underutilized compared to the first, with diminishing returns as shown by the 6x results from the cinebench test. I'm guessing the four-core machine pulls at least an additional 15%, putting the GB around 9200, pretty much a dead heat with the 8-core 2008 model.
This creates a bit of a quandary for the new buyer. 8 core xeon 54xx on liquidation or four core nehalem? Applications that don't take advantage of the second cpu may prefer the nehalem system, and the GT120 is a better video card that the stock 2600 that comes with the 2008 model.
I think it will all come down to RAM and specific application performance. Personally, I'd love to see some Handbrake encode numbers from the 2.66 Nehalem....
Thanks for running Cinebench and for answering everyone's queries in this thread, WonderSausage. I'm sure you'd rather be playing with your new MP in your own way, instead of responding to everyone here. You've scooped Barefeats and all the other sites. Congrats!
No?
When I still had an order for mine, it was to ship this week. I had the 4870 and a GT 120.
THAT'S FASTER THAN THE SUN SCORE. You've just topped the charts.
I'm curious from your sig.. why did you end up cancelling your nehalem mac pro?? You've been waiting forever for one!
considering the base model '06 > base model '07 was 2x performance... only fair would be that '09 base model would be 2x also he he.
id be sorry if i got my octo last year, but the price increase for the 09 octo is too big for me anyway (and probably overkill for audio )
anyway, screens of activity monitor
id be sorry if i got my octo last year, but the price increase for the 09 octo is too big for me anyway (and probably overkill for audio
)anyway, screens of activity monitor
ive been wondering that too, although my physical 8 cores cant be topped i wonder what would be with 8+(8) ..