What's the BUS speed on an Athlon64 FX...

[AnotherGuy]

Hi.
I've been reading around that the BUS speed on the fastest Intel P4 is 800 MHz, correct me if im wrong. I was wondering whats the bus speed on the new Athlon64 FX 51... ?
And to end it with... as we type in this moment... whats the best performance processor on the current 32 bit O/S... latest P4 Intel 3.2 GHz Extreme Edition or the latest AMD Athlon64 Fx 51 ?????

 

[jdogg707]

I believe it has the 1600MHZ HyperTransport Bus, but this is not how the CPU clock is derived. The Athlon64 FX-51 is faster in most circumstances than the 3.2GHZ EE, but they go back and forth depending on the task.

 

[Markfw]

I think this was argued to death a while back and the way I read the results was that the Athlon64FX won, however the P4 EE did win a few benches by a hare. It DEFINITELY runs cooler.

 

[sickcamry]

This isn't talking about the Athlon FX itself, but since it's basically a rebadged Opteron 148 processor, this should still relate. I got this from Anandtech, where they overclocked an Opteron 144 to the equivalent of 888mHz FSB:


In normal setups (e.g. Athlon/P4), the CPU gets its clock from the FSB clock and multiplies it by the â??clock multiplierâ?? to determine how fast its internal clock should be. With a 16x multiplier, when the external clock ticks once, the CPU ticks 16 times. However, with the Athlon 64/Opteron, there is no FSB, so the CPU must get its clock from somewhere. It doesn't produce it internally; instead, it derives it from the native HT (HyperTransport) frequency, which is 200MHz, but because of the bus' nature, it runs at an effective 800MHz.

So, for our 1.8GHz Opteron 144, the multiplier is 9x, which is why raising the HT frequency to 222MHz increases the clock speed to around 2GHz. But we are increasing the HyperTransport clock in our overclocking, and not a FSB clock, which does not exist on Opteron/Athlon64. In real terms, this means our CPU overclocking has a significant impact on Performance, but it is unlikely that our increase in memory speed will have nearly as much impact on performance. Since we are nowhere near saturating the Hypertransport bus at 200 (effective 800), increasing HyperTransport to 222 (888) will not likely have much, if any, impact on overall performance. Our performance improvements, with Opteron/Athlon64, are mainly coming from increase in CPU clock â?? much more so than on the Pentium 4 or Athlon architectures.

 

[AnotherGuy]

Actually i forgot to mention that i didnt want the overclocking to be considered when we measuring the Fastest/ Best Performer processor.

But i think as Athlon64 uses HyperTransport i think i read somewhere that the way it works is almost like the HyperThreading in Intel processors... like it directs the incoming data units in 2 directions... that means it processes 2 units of data at the same time, instead of just 1.
So does that make the "bus speed" 2 x 800MHz = 1600MHz as JDog said.... or the final bus speed is just 800MHz...

 

[sickcamry]

According to Anandtech, the FSB is the equivalent of Intel's 800MHz FSB.

"It doesn't produce it internally; instead, it derives it from the native HT (HyperTransport) frequency, which is 200MHz, but because of the bus' nature, it runs at an effective 800MHz."

 

[AnotherGuy]

thanks

 

[sandorski]

Well, if you could compare FSB's, it would still be pointless, as the difference doesn't mean anything. It's not like a FSB is a Universal part that offers a consistent final effect on a cpu's performance, it is more like a Method of Data transport, varying in performance from one architecture to another. This is why the P4's 800mhz FSB and the Athlon Socket A's 400mhz FSB achieves similar Final performance for their respective systems, though interestingly enough both those FSB speeds are derived by a base 200mhz clock(which might be the real issue).

Perhaps someone who knows what they are talking about can step in and respond to this thead, cause I ain't got no fancy learnin'. (and could be very wrong)