Slashdot Mirror
Intel 800 MHz FSB Processor Family Review
David writes "Techware Labs recently had the opportunity to spend some time with Intel's new 800 MHz front-side bus (FSB) processor family. The review includes a overview of the features in this processor family, Intel's new Springdale and Canterwood chipsets, and an analysis of processor scaling within this family. The article focuses on how the relationship between CPU and video card affect various aspects of performance."
Spending time is nice but This is the page I think they should have linked to .
Basically in the review they compare different chips (2.4Ghz, 2.8Ghz) etc. against each other all with 800Mhz FSB
.ACMD setaloiv siht gnidaeR
Read all about it here
___________________________________
The spiders are coming
Conclusion:
The Intel 800 MHz FSB Family of processors truly lives up to its name. After looking at the results which tests are CPU limited and which are video card limited, the data concludes that there is a certain balance between the dependency of the video card and the processor. As the graphics get more intense, the performance becomes more dependent on the video card. The Intel 3.0GHz 800MHz FSB is definitely cutting edge and the CPU really shines during programs that require the most calculations and complexity. For example, the Unreal Tournament Botmatch is CPU dependent because the program requires many calculations and factors of each bot or player. On the other hand, there are other programs where the CPU is not needed as much, such as programs that require complex lighting and transform calculations by the video card or other video card specific features. The power of the CPU allows it to shine in conjuncture with older APIs or engines, such as DirectX8 or the Quake3 Engine, which are not as dependent on the video card. These programs allow the CPU to have more of an influence on the performance, creating greater improvements. With brand new programs or software based on DirectX9, the graphics are so intensive that a stronger video card is needed, with the CPU playing a lesser role (at least the high end CPUs, this may be different with lower end CPUs). This causes a less noticeable effect on improvement with greater CPU speeds, but that will only improve over time when the development of video cards are increased. In the future, the software based on DirectX9 won't be so dependent on the video cards due to new technology and the CPU will be able to shine in these regions as well. This comes to show that the potential of the Intel 3.0GHz 800MHz FSB is still uncharted and performance with the CPU should dramatically increase when coupled with future video cards. After seeing the capabilities and performance during strenuous tests, the Intel's family of 800MHz FSB processors have earned our Editor's Choice Award.
The 2.4c will be finding a home in my box soon because of it's amazing overclocking.
At this forum (click on Intel cpus) almost everyone has successfully overclocked theirs over 3Ghz on air, with most hitting 3.2 or 3.4 (and don't forget a 1 Ghz fsb).
A popular motherboard to go with it is Abit's IC-7 with the i875 chipset. The processor and motherboard are just $180 and $145 respectively over at Newegg, so don't waste your money on 3.0s.
I've been planning to upgrade my computer at the end of this month, and have been keeping a pretty close eye on the 865/875 motherboard and chip performance reviews. This article didn't really enlighten me as much as the following Tom's Hardware reviews:
here
and
here
The FSB on a P4-C is actually clocked at 200Mhz, but data is transferred four times per clock cycle, boosting the effective bandwidth to equal that of an 800Mhz FSB. Latencies are, however, still equal to that of a 200Mhz FSB.
I believe the problem with your calculation is that you calculated that the bus is 8 bytes wide. 8 bytes is 64 bits, the standard bus width on modern systems.
That article showed that lower latency doesn't mean higher bandwidth (and this is only true if your original latency is low enough, mind you!), but it didn't consider overall performance. Latency has indeed an impact on the performance -- look at Tom's Hardware article on performance improvements when Intel's PAT is enabled. All PAT does is lower latency by 2 cycles.
Never underestimate the bandwidth of a 747 filled with CD-ROMs.
They will be in early 2004 it seems...
http://www.theinquirer.net/?article=9823
The Doormat
If you're not outraged, then you're not paying attention.
AMD has Opteron and Athlon 64 with Ultra Low Latancy controllers. Previews say that performance often is not a matter of maximum bandwith (3,2GB/s Athlon 64 and 6,4GB/s Opteron) and the Athlon 64 performs just like a P4 xxxxC with FSB 800 in memory dependent benchmarks like q3a. Have fun :-)
No modern CPU will continue to operate through a catastrophic cooling failure. The P4 will crash when it throttles below 25% (errata), and will completely shutdown if the heatsink is removed. The P3 will burn up without a heatsink, unless the motherboard shuts it down (I don't know of any motherboards that do this). An Athlon XP will be shut down by the motherboard before damage occurs (ideally). Regardless, what possible set of circumstances could occur that would cause your heatsink to come off your processor without destroying it or the motherboard in the process?
THG's infamous video was clearly faked, or at least misleadingly edited. The P3 was shown running at 38C after it crashed, which is lower than it would run WITH A PROPERLY OPERATING COOLER. The P4 was also shown clocking back up to full speed immediately after the heatsink was merely SET on top of the processor, this is completely impossible. The processor would have shutdown due to the temperature it was running at, and regardless it would have taken at least a few seconds for the processor to be cooled enough by the heatsink before it clocked back up, and it wouldn't be cooled at all if the heatsink was merely SITTING ON TOP, unmounted!