Slashdot Mirror
Intel V8 Octa-Core System, Full Performance Tests
MojoKid writes "In the April time frame,
details of Intel's dual-socket 8-core system dubbed
'V8' became available but only preliminary performance numbers were shown.
The platform consists of quad-core Xeon processors in an Intel 5000X
chipset-based motherboard, along with FBDIMM (Fully Buffered DIMM) serial
memory. A follow-on article at HotHardWare goes into significantly more detail on the platform and showcases many more performance metrics on a Windows Vista 64-bit installation. The
POV-Ray and Cinebench 95 benchmark numbers alone are something to smile
about. 'Intel's V8 isn't about promoting a platform as much as it is a show of strength and a glimpse of things to come. What V8 and QuadFX show is that both Intel and AMD are on a path to offering true, enthusiast-class, dual-socket platforms. And that's a good thing. Perhaps AMD is a little further down the path thanks to a more tweaker-friendly motherboard in the QuadFX-compatible Asus L1N64-SLI WS, but until consumers have more motherboards to choose from and perhaps quad-core processors from AMD, we can't very well declare that the time for QuadFX has arrived. One motherboard does not a platform make.'"
indeed! in my job (I work at a small OEM in the Netherlands), I already sold several dual quad-core systems the last couple of months, build to order. This week I sold a similar system (with this exact same motherboard) but with 16GB of memory instead of 4. Luckily it's not going to run Vista ;-)
Not on a server. Forking on the accept call is embarrassingly parallel.
The question is, how many items do you have to sort, and does it even give a noticeable increase in speed once you distribute all the data to the seperate processors and gather it back up again. From my parallel programming course, I remembered you could do a sort in O(1) time, but that you had to have N processors, and that doesn't even count distribution and gathering time. The best parallel algothims get sorting time of O(n log(n)), which is the same a quicksort, but you can parallelize it, so on 4 processors, it would be O(n log(n)/4). But since you're suppose to get rid of the constants in Big-O notation, the complexity is pretty much the same. So for applications like email, wordprocessing, and web browsers, where you're probably only sorting less than 10,000 items (probably less than 1000)., it doesn't yield much of and improvement, especially not that the user would notice. Just for a test, I filled up all 65,000 rows in Excel with Data. Sorting the done in less time than I could even notice. Probably under 1/4 of a second.
Anthropic principle: We see the universe the way it is because if it were different we would not be here to see it.
FTFA:
Our testing showed the V8 ssytem consumping much more power than anything else while idling at the Windows desktop; almost 50W more than QuadFX and over 100W more than the QX6800. With the processors operating under full load, however, the tables turned somewhat.
Yeah, the tables did turn. Under full load, the QX6800 - which is already power-hungry - uses 319W. The V8 and the QuadFX are at 474W and 498W, respectively. That's an extra 155-179W... For what?!
Is this a continuation of the P4 Prescotts, which used 130W+, IIRC? These beasts use *even more* juice.
Yeah, such CPUs have their place, but if this is an indication of the future of desktop computers, fu*k it. The V8 uses more power over a QX6800 (50W) while idling than what my CPU (E4300) uses at full load. Are we going to be able to buy 50W CPUs in five years, or are we going to have to deal with insane cooling solutions for 200W CPU monsters?
the build in ports are on the pci-e bus as the 5000x chip set uses pci-e lanes for part of the chipset to chipset link and most pci-e hardware raid cards are x4 with x8 for cards with more ports http://www.3ware.com/.
also the 8800 cards are slowed down by a x8 pci-e slot.
pci-e video in cards may use 1-4 lanes also you may want a pci-e based firewire bus.