Advanced Micro Devices - Moderated (AMD) Message Board

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Advanced Micro Devices - Moderated (AMD)

AMD 231.83

+1.7%

Jan 16 9:30 AM EST

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: Elmer Phud who wrote (148592)	1/20/2005 11:13:04 PM
From: pgerassi	Read Replies (1) of 275872

Ephud: That is not what I claimed. I claimed that a 2.8GHz Smithfield is probably slower on the typical office app or game than a 1.8GHz Opteron. You claimed that a 2GHz 4 way Opteron was slower than a P4 3.6E on single threaded apps. This is not self evident. And I showed you one app where it was faster (Primordia and QMC of SciMark 1.0 fame). Any heavy x87 based app would do and there are plenty. Since your next claim is that a 512 way Supercomputer is slower on a single threaded app than a single processor. It can be if the CPUs in them are of different types as in my claim. A 512 way 1.9GHz Power5+ is faster than a 2GHz Celeron on a single threaded app. Thus the "self evident" claim is out and out wrong. The only self evident claim is when those two are using the exact same CPU, the same chipset, etc. A 512 way with a huge L3 and lots of quad channel PC3200 may indeed be faster at a single threaded app than the same CPU with single channel PC133. So prove that a P4 3.6E is quicker than a 4P 846 using same type RAM and video card, etc on a single threaded app like typical office apps or games. And that does prevent you from comparing a HP585DL with registered CAS3 ECC PC2100 and a PCI based Geforce4 MX video vs a P4 3.6E with dual channel DDR2/533 PCIe XT800. Use the same memory and video card (a Nvidia 6800GT AGP vs a PCIe one would be ok though, but not vs PCIe SLI). I will permit you to use a single 846, if the tested app doesn't go faster on duals with exact same CPU by test. I realise this reduces the available links, but I didn't make the claim, you did. Most likely is that you will refuse to prove it. Thus proving your inability to back your claim up. Pete

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next