To: Tenchusatsu who wrote (74563 ) 10/7/1999 8:35:00 PM From: Cirruslvr Respond to of 1584438
Tench - RE: "Also noteworthy was the estimated scalability in performance when the clock speed reaches 800 MHz. Extracting performance numbers, SpecInt would go to 36.8 and SpecFP would go to 29.2." Those 800MHz estimates aren't too shabby, UNTIL you compare them to the Athlon 700's (on a 266 fsb) estimates which would show this future 700MHz Athlon FASTER than a future 800MHz Coppermine WITH a 100MHz handicap! (Paul - Remember the 100MHz handicap you were talking about yesterday with Coppermine 600 vs. Athlon 700, well it seems like this Athlon does NOT even need a handicap. Shoots a straight up 72.) "By the way, one correction here. The scores are SPECint_base95 and SPECfp_base95. So to extrapolate numbers here: SPECint_base95 SPECfp_base95 -------------- ------------- PIII 600, no SSE 24.6 14.9 PIII 600B, w/ SSE 25.9 20.8 PIII 600EB, w/ SSE 29 25" So Coppermine is 67.8% faster than the PIII and 10.6% faster than the Athlon (using actual SPEC scores) at 600MHz in fp?. I CAN'T WAIT to see the benchmarks which can back up this claim. These numbers would lead me to believe Coppermine will be faster than the AThlon in most FPU intensive applications. I'm gonna bookmark this post and when the benchmarks come out, we'll see if this claim can hold up to the light. Speaking of actual Coppermine benchmarks, I think I've posted too many messages the past few days, and now currently I'm bored with AMD. So since nothing much is happening until Coppermine comes out, I'm off this thread. BTW - Sorry for the ugly formatting. Tench - This isn't exactly a reply to you, just the data. ;) Thanks for providing the data we wouldn't have been able to confirm otherwise.