Comments on alphagemini: ICC vs GCC-4.3

Shitty and misleading barcharts.

2011-07-18T15:10:06.980-07:00

Shitty and misleading barcharts.

just as said here, there the facts, currentgcc its...

2009-12-31T10:42:54.587-08:00

just as said here, there the facts, currentgcc its poor,developers today not work well due too many resources propised a lazy programing curse, a more decend and minimal resource hardware its better for devel..

i update the massenkoh devel solution here

http://74.86.158.5/~op0014t/mckayemu/massenkoh/index.html

Generally I do not post on blogs, but I would like...

2009-12-30T10:25:05.390-08:00

Generally I do not post on blogs, but I would like to say that this post really forced me to do so! really nice post.

rH3uYcBX

thats the facts, the curent gcc cuarse, and all re...

2009-05-09T07:50:00.000-07:00

thats the facts, the curent gcc cuarse, and all recent proyects curse its that developers dont take care of performance on code, all recent apps/proyects are very resource consumers, cos as u see, everybody have a powered resource full machine like u, dual core's etc, gigas of RAM etc etc, in this machine performance tests are very less perceptible!

a great example its the VisualBoyAdvance emulator, that not compile ith optimize falgs, hands and spend much memory

in my live cd http://qgqlochekone.host22.com/massenkoh/ i must compile mayority of apps with gcc-3.4 cvs, the 3.4 brand are a paralel gcc best solution to gcc-4.X on some builds! i recommend!

very distributions still include both versions, gcc-4.X for recend and also the 3.4

Perhaps you want some more math related killbits -...

2009-04-11T15:52:00.000-07:00

Perhaps you want some more math related killbits -mno-ieee-fp -IPF_fp_relaxed -rcd -ftz -fp-model fast=1 -fp-port -auto_ilp32 -prec-sqrt -pc64 -no-prec-div

I've built ffmpeg before and it's not exactly clea...

2008-11-10T16:51:00.000-08:00

I've built ffmpeg before and it's not exactly clean code. From what I remember, you could only build it with older versions of binutils.

As for the 'missing symbols', link it... thats right add it to your CFLAGS or LDFLAGS(-Wl,-?) and that's it. I used to do it all the time with Compaq C (-Wl,-lots).

I betcha, if you turn up the CFLAGS, you would see more of a difference! Something like -O3 -fstrict-aliasing -funroll-loops -mieee -mtune=cpu etc... I can tell ya, the code is damn near the same size and runs about 30-50% faster for GCC and ICC!

march=nocona is no good for anything other than Ne...

2008-08-23T12:24:00.000-07:00

march=nocona is no good for anything other than Netburst.
To optimize for core2 before march=core2 was introduced, you should have used march=k8, and then you would see much less difference between gcc 4.2 and 4.3

how about icc's option "-parallel". it would be in...

2008-07-12T14:13:00.000-07:00

how about icc's option "-parallel". it would be interesting to see if autoparallelization improves anything.

I've tried to compare icc 10.1 against gcc 4.2.3 o...

2008-06-09T13:35:00.000-07:00

I've tried to compare icc 10.1 against gcc 4.2.3 on a pentium 4 "C" microprocessor whith my own code using the following options :
-O2 -march=pentium4 on GCC
and
-fast -march=pentium4
The results scared me because of the binary generated using icc was twice as fast as gcc one.
After that i tried to see whats going on, so i compiled with the -S option and i figured out that gcc does'nt generate see instructions. Finally i've got similar speed differences using
-O2 -march=pentium4 -mfpmath=sse
forcing gcc to use see instruction set

I've observed similar speed differences, though I ...

2008-05-16T04:53:00.000-07:00

I've observed similar speed differences, though I haven't tried gcc 4.3 yet. This is on my own code, more details can be found here.

Very insightful, thanks a lot. I'll look into it f...

2008-03-18T03:52:00.000-07:00

Very insightful, thanks a lot. I'll look into it for sure and might use some of these flags on a per-package basis or even as global flags (such as -ffast-math).

It would be very interesting to know how things be...

2008-03-17T08:09:00.000-07:00

It would be very interesting to know how things behave with profiling (ie -fprofile-generate and -fprofile-use). ICC is enabling some of more aggressive loop optimization (such as loop unrolling you need to ask GCC specially for with -frunoll-loops). Also enabling vectorizer and using -ffast-math might help and get GCC closer to what ICC really does.

Honza

Great post. Was about to do something similiar. No...

2008-03-15T08:26:00.000-07:00

Great post. Was about to do something similiar. Now i don't have to ;-) Thanks!

That's right. I chose to truncate the graphs to sh...

2008-03-12T09:36:00.000-07:00

That's right. I chose to truncate the graphs to show the relative difference, for example that GCC 4.3 is roughly between ICC and GCC 4.2 which would be impossible to see if I had chosen absolute bar lengths.
Anyway, the y axis is properly labled, so at least at the second glance it should become clear.

Your graphs aren't optimal, because if you look on...

2008-03-12T00:38:00.000-07:00

Your graphs aren't optimal, because if you look only at the graphs, you think icc is twice as fast as gcc.