Date: Fri, 17 Jun 2005 00:49:13 -0700 From: "David O'Brien" <obrien@freebsd.org> To: freebsd-sparc64@freebsd.org Subject: Affects of MHz & cache size Message-ID: <20050617074913.GC1485@dragon.NUXI.org>
next in thread | raw e-mail | index | archive | help
For the curious, I had a chance to do world-stone benchmarks[*] on a SunBlade100 500Mhz 256KB L2 cache 384MB RAM vs. SunBlade150 650Mhz 512KB L2 cache 640MB RAM: 6h25m41.50s real 5h29m9.58s user 49m23.80s sys vs. 4h37m54.42s real 3h56m10.41s user 35m42.51s sys GENERIC kernel builds times: 17m5.00s real 15m26.09s user 1m28.55s sys vs. 12m13.60s real 11m3.42s user 1m3.38s sys The hard disk was transplanted from one machine to another so differing hard disks would not affect the outcome. -- -- David (obrien@FreeBSD.org) [*] Actually this is 'rm -rf /usr/obj/* ; reboot ; time make buildworld'.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050617074913.GC1485>