1. Este site usa cookies. Ao continuar a usar este site está a concordar com o nosso uso de cookies. Saber Mais.
  2. Está disponível o Comparador ZWAME em versão beta.
    Mais informações.
    Remover anúncio

Hammer 800Mhz >>> P4 1600MHz

Discussão em 'Novidades Hardware PC' iniciada por Tafinho, 6 de Junho de 2002. (Respostas: 2; Visualizações: 684)

  1. Tafinho

    Tafinho Power Member

    É desta que a Intel tem de passar a ideia que performance = mhz ,

    Since before the initial architectural disclosure of Hammer during October of last year, there has been quite a bit of speculation as to how AMD's next-generation microprocessor will perform. We've seen reports indicating that ClawHammer could be 25% faster than the Athlon XP at the same clockrate.

    Now, however, we have our first indication of what the ClawHammer's performance will be like, couresty of this article by Tecchannel.de (original German version is available here). The article features Quake 3 benchmarks comparing an 800 MHz ClawHammer sample to Athlon MPs at 800 MHz and 1667 MHz, as well as a Willamette Pentium 4 (256 KB L2, 400 MHz FSB) at 800 MHz and 1600 MHz. The test platform was an AMD Solo-2 motherboard based around the AMD-8000 chipset series.

    The benchmark results indicate a 40% performance increase over an Athlon MP for the ClawHammer. Additionally, the 800 MHz ClawHammer manages to tie (actually outperform by 1 FPS) the 1667 MHz Willamette Pentium 4. The 800 MHz ClawHammer scores 183 FPS with PC2700 (2.5-3-3) DDR SDRAM, while the 800 MHz Athlon MP scores 130 FPS with the same memory (though obviously only a 133 MHz FSB). The 800 MHz Willamette Pentium 4 scores 111 FPS with PC800-45 DRDRAM and the 1600 MHz version delivers 182 FPS. You can find the complete benchmark results beginning on page 3 of the article.

    Interestingly, this ClawHammer apparently features a 256 KB L2 cache. The article makes for some interesting reading as it also includes details from WCPUID as well as some memory bandwidth benchmarks, however, it's important to keep in mind that these are unauthorized tests of an early revision CPU and platform, and that there could be significant differences in performance from final shipping versions depending upon the state of the test hardware used here.
     
  2. pnabais

    pnabais Power Member

  3. Tafinho

    Tafinho Power Member

Partilhar esta Página