• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Athlon 64 benches? I don't think so.

Ilmater

Diamond Member
These were found from a reference in Ace's Hardware forums which was referenced by The Inquirer. I'm pretty sure they're fake, but I can't be for sure. The page is here.

If you notice, one CPU-Z screen lists the FSB as 221MHz, while the other doesn't list one. Neither of them should have a FSB because the Athlon 64 doesn't have one. But the fact that one shows a FSB and one doesn't tells me that these are BS. You can make up your own mind, though, as I'm not one to tell people what to think.
 
It has an FSB, just not in the usual form. Look at the technical layout for the new Apple G5, thats exactly how the Athlon64 bus is using an 800MHz clock.
 
Originally posted by: AtomicDude512
It has an FSB, just not in the usual form. Look at the technical layout for the new Apple G5, thats exactly how the Athlon64 bus is using an 800MHz clock.
The athlon 64 isn't using an 800MHz bus, is it? Link maybe?
 
It is 800 MHz... techniocally... kind of hard to call it a "front side bus" when the memory controller is on the chip, but the Hypertransport link beyond the CPU is 800MHz.

Anyhoo... I've seen what crazy things the AMD64 architecture can do to a benchmarking program, so I'm not surprised with the mixed up results. Sandra says that my 1.4 GHz Opteron has a 1.4 GHz front side bus. 😀
 
Originally posted by: jonnyGURU
It is 800 MHz... techniocally... kind of hard to call it a "front side bus" when the memory controller is on the chip, but the Hypertransport link beyond the CPU is 800MHz.

Anyhoo... I've seen what crazy things the AMD64 architecture can do to a benchmarking program, so I'm not surprised with the mixed up results. Sandra says that my 1.4 GHz Opteron has a 1.4 GHz front side bus. 😀

Well, it acutually has two 400Mhz links, one 3.2GB/s link to the CPU and one 3.2GB/s link from the CPU. So AMD just calls it 800Mhz FSB to compete with Intel's Prescott.

You can probably see how two links can help, so data going back and forth has seperate buses now instead of having to compete for one. It's kind of a very organized highway system...
 
Originally posted by: shady06
i wouldnt take that as conclusive benchmarks...
Yeah, The FPU on the Claw should be stellar. On FP-heavy apps, the Claw should win. But on others it won't.

Here is a bench suite of the 2800+ Claw. For ScienceMark (which is heavily FP-ified), the 2800+ Claw easily beats the P4 2.8C. OTOH, in Sandra, the 2.8C blows the 2800+ out of the water on many benchmarks, particularly when it comes to SSE2 (which has now been implemented by AMD).
 
Originally posted by: AtomicDude512
Originally posted by: jonnyGURU
It is 800 MHz... techniocally... kind of hard to call it a "front side bus" when the memory controller is on the chip, but the Hypertransport link beyond the CPU is 800MHz.

Anyhoo... I've seen what crazy things the AMD64 architecture can do to a benchmarking program, so I'm not surprised with the mixed up results. Sandra says that my 1.4 GHz Opteron has a 1.4 GHz front side bus. 😀

Well, it acutually has two 400Mhz links, one 3.2GB/s link to the CPU and one 3.2GB/s link from the CPU. So AMD just calls it 800Mhz FSB to compete with Intel's Prescott.

You can probably see how two links can help, so data going back and forth has seperate buses now instead of having to compete for one. It's kind of a very organized highway system...

That's true and something very important to point out since the typical x86 "front side bus" (including Prescott's) only move direction in one direction at a time. 😉

 
Back
Top