16 Feb
2003
16 Feb
'03
6:38 a.m.
On Sun, Feb 16, 2003 at 12:28:57 +1100, Erik de Castro Lopo wrote:
As a C fan I was rather curious about this. I
didn't want people getting the
wrong impression that C++ is automatically faster than C (it isn't) or that in
the long term improvements in the C++ compiler will make it faster than C
(it won't). So I asked Steve for more details and he pointed me at the code:
I was actually expecting c++ to be marginally faster, because it
could understand that nature of the objects and might be able to do some
optimisation around them - partial because the arangement in the code
wasn't particularly realistic.
and suggested that further discussion of this issue
should probably be moved
from the jackit-devel list to this one. So here we are. (Steve, please don't
take this as a slight on you, I simply want to get the facts right).
Absolutely. The only reason I mentioned the results at all was that I
had inspected the assembler outputs from the compilers I was testing on
(2.95 and 2.96, the only commonly used compilers at the time), and knew it
was reasonable. I didn't check it for 3.x.
I was very keen to point out (and still am) that I dont think the code
is representative of anything. I just wanted to be sure I wasn't missing
any 5-10% efficiency gains by using OO-style C over C++.
I think that for applications like audio processing
where speed is one of
the main goals benchmarking is extremely important. Personally I would
love to see more people do it properly and publish their results like I
did here:
Agreed. If someone that knows c, c++ and objective c were to write up an
audio focused benchmark that would be great. I've not realy used GObject,
but I guess it should include that too.
- Steve