Re: 32-bit vs. 64-bit x86 Speed

On 2007-04-12, Jon Forrest <jlforrest@berkeley.edu> wrote:
> I don't think it's worth messing with 64-bit computing for apps that
> don't need the address space."


Dr Dobbs march 2005 has a nice summary that seems to confirm your view, and
my own little experiments agree with them.


With the added remark that a lot of benchmarks seem to be biassed due to
the fact that on 64-bit you can always use SSE2. In general the base
level of instructions that one can used is raised on 64-bit, and to really
isolate the 64-bit issue one has to carefully check that the RTL (most
notably memory move) is on equal footing.


IIRC Dr Dobbs also made some other exceptions for apps that are really
heavily bound by something that really benefits from larger register size.
(e.g. some hashing or checksumming functions)


> Let's say you're a Linux user who never needs to run programs that
> don't fit in 32-bits. Would you run a 32-bit or a 64-bit version of
> Linux? You compiler people probably have intimate knowledge of the ISA
> issues here so I'm interested in what you have to say.


32-bit.

Return to the comp.compilers page.
Search the comp.compilers archives again.