By: Michael S (already5chosen.delete@this.yahoo.com), February 4, 2013 1:50 pm
Room: Moderated Discussions
Patrick Chase (patrickjchase.delete@this.gmail.com) on February 4, 2013 11:47 am wrote:
> Michael S (already5chosen.delete@this.yahoo.com) on February 4, 2013 2:27 am wrote:
>
> Also those weren't contemporaneous systems. The PIII-500 HW availability is 3/99, versus
> 7/01 for the R14K. A *lot* changes in 2 years in this industry. The best Intel SpecFP2k
> submission with 7/01 availability was for the 1.8 GHz P4, which scored 631. Here: http://www.spec.org/cpu2000/results/res2001q3/cpu2000-20010702-00741.html
>
> -- Patrick
Different objectives.
P4 is built for single-thread performance and consumes 80W or so. R14K is build for density, so only 17W.
Of course, it's not just uArch and objectives, R14K also was built on more advanced silicon process (130 nm Cu vs 180 nm Al), which also helped perf/Watt.
> Michael S (already5chosen.delete@this.yahoo.com) on February 4, 2013 2:27 am wrote:
>
> Also those weren't contemporaneous systems. The PIII-500 HW availability is 3/99, versus
> 7/01 for the R14K. A *lot* changes in 2 years in this industry. The best Intel SpecFP2k
> submission with 7/01 availability was for the 1.8 GHz P4, which scored 631. Here: http://www.spec.org/cpu2000/results/res2001q3/cpu2000-20010702-00741.html
>
> -- Patrick
Different objectives.
P4 is built for single-thread performance and consumes 80W or so. R14K is build for density, so only 17W.
Of course, it's not just uArch and objectives, R14K also was built on more advanced silicon process (130 nm Cu vs 180 nm Al), which also helped perf/Watt.
