Intel Compiler Compared To gcc

Screaming Lunatic writes "Here are some benchmarks comparing Intel's compiler and gcc on Linux. Gcc holds it own in a lot of cases. But Intel, not surprisingly, excels on their own hardware. With Intel offering a free (as in beer) non-commercial license for their compiler, how many people are using Intel's compiler on a regular basis?"

Comments

Re:Huh?

[Omega Hacker]

Both machines are running SMP kernels because Hyperthreading makes the single P4 processor look like two processors. If you don't run an SMP kernel, you don't get access to the second virtualized CPU.

some practical issues

[blackcoot]

i've been using icc on a realtime computer vision project that i'm working on. intel's compiler ended up giving me an approximately 30% boost over all --- a difference which is not to be sneezed at. in terms of empirical performance data for my application, icc wins hands down.

that said, icc does a lot of things that really irritate me. for one, it's diagnostic messages with -Wall are, well, 90% crap. note to intel: i don't care about temporaries being used when initializing std::strings from constants --- the compiler should be smart enough to do constructor eliding and quit bothering me. the command line arguments are somewhat cryptic, as are the error messages you get when you don't get the command line just right. the inter procedural optimization is very *very* nice; however, be prepared for *huge* temporary files if you're doing ipo across files (4+mb for a 20k source file adds up very quickly).

this all said, i don't think that i'm going to give up either compiler. gcc tends to be faster on the builds (especially with optimization turned on) and has diagnostics that are more meaningful to me. fortunately, my makefiles know how to deal with both ;-)

Re:Could this replace gcc ?

[T-Ranger]

Unfortunatly the reality of the compiler world is that everything has there own unique extensions to ANSI-C. And for that matter, there own unique bugs related to there implementation of ANSI C as well.

Any peice of software as large, complex, and critical, as a OS kernel is going to, at the very least, be tested agianst a specific compiler. Linux was developed primarly with free tools, ie GCC. So Linus and his cohorts have taken the test-on-gcc mindset one step further and used GCC extensions.

So what? What do they loose? No functionality, they could implement things in ASM if need be, so convience. And convienent things are probabaly understandable things, and understandable things mean less buggy code.

If people never used compiler extenstions, then you would never have to run ./configure :)

Mail sent to author

[guerby]

I sent this on December 10th, no answer or update to the page:

Hi, I just saw your posting on the GCC list and was surprised by your analysis about Scimark 2.0 "Overall, Intel produces code that is 15% faster". If you look at the detailed result, you'll find out that the Monte Carlo tests is an obvious problem for GCC since it produces code 3 times as slow as Intel whereas on other tests it is on par. This discrepency explains about all of the 15% difference in the composite difference (which is a simple arithmetic average), so "overall" is a bit strong :).

Interested I took a look at the Monte Carlo test, and it turns out to be 20 lines of code that generate random numbers using integer arithmetic, ie not floating point intensive stuff at all which is quite at odd with your statement "I've found this benchmark reflects the performance I can expect in my own numerical applications".

My conclusion is that GCC is probably missing one obvious integer optimisation that Intel compiler does, but I don't think we can generalize from this particular point.

You can quote me on a public forum if you want to. I write numerical intensive code for a living at a big bank.

Sincerely,

Re:c++ programs

[bunratty]

So does this mean tha mozilla compiled with the intel compiler would run comparable to it's windows counterpart?

The last I heard, the reason that Linux builds of Mozilla are slower than Windows builds is that Linux Mozilla builds use g++ 2.95 with -O optimization. When they can switch to g++ 3.2.1 with -O2 optimization, the speeds should be comparable.