String hashing was: Thou shalt have no other gods before the ANSI C standard 1541
String hashing was: Thou shalt have no other gods before the ANSI C standard 1543
Randy Howard Yeah but rather than forcing all the other hashes to notice '-0' termination, I chose instead to force this hash function to obey length...
Agreed. That's why I mentioned it above.
I think most (if not all) of the notebook vendors play games with the CPU speed to try and win battery life contests. I need to figure out how to turn that off (if possible) and rerun the test. Also, which really slows it down, which I have already disabled (boot.ini).
Michael Amling Yes. :) Yes. :) Sorry for posting this in sci.crypt, but my hash function is...
I know, I'm just curious about using any of the hash routines in portable code that will run on both 32 and 64 targets. I'd like to see it, despite you not explicitly trying to take advantage of it in order to get a feel for which love-hate what processors. Also, gcc may do a bit better job of code generation on Opteron. Or it may be a lot worse. *shrug* Only one way to find out.
I've seen some very large improvements in crypto code. Some of the benchmarks on the various encrypt-decrypt sources run very nicely on Opteron (and Itanium). EM64t isn't bad at all, it's the memory performance that is pathetic in comparison to Opteron, *IF* you have SMP. Hypertransport doesn't really buy you much at all with only one CPU (although the gamers don't want to hear that), but it makes a huge difference with 2, 4, etc. CPUs. The more, the merrier, scales beautifully.
-- Randy Howard (2reply remove FOOBAR) "Making it hard to do stupid things often makes it hard to do smart ones too." -- Andrew Koenig
Alt Folklore Computers Newsgroups