On Oct 30 2007 14:42, Buddy Coffey wrote:
Has anyone run benchmarks on an identical system with 32 bit vrs 64 bit?
I have both 32 bit and 64 bit versions installed in separate partitions on the same system with all updates applied.
I ran my computationally intensive code GEMACS (http://www.gemacs.com) compiled natively for both 32 and 64 bits with the Intel 9.1 compilers.
One can cheat too much. You can compile your 32-bit binary with -mfpmath=sse -msse (and -msse2 and -msse3, if you have it) and bring the running time on par with a 64-bit binary. What does that prove? Just that the CPU executes both ISAs at roughtly the same speed, and that it is hence marketable. What is really interesting for the casual user (IMHO) is how a *stock* 32-bit SUSE compares to a *stock* 64-bit SUSE. So here is the result of encoding a 1h:57m WAV file using the stock i586 libvorbis+oggenc vs. stock x86_64 libvorbis+oggenc using lbuild to provide a clean, chrooted install. -q3 in 32-bit: 8m24.3s 8m24.6s 8m22.8s -q3 in 64-bit: 5m36.9s 5m34.5s 5m33.0s -- To unsubscribe, e-mail: opensuse+unsubscribe@opensuse.org For additional commands, e-mail: opensuse+help@opensuse.org