GCC 12 Looking At Enabling Its Vectorizer For "-O2" Optimization Level

[archkde]

my computer runs fedora and fedora contains gcc 11.2.1 with patches from master. rpm is maintained by one of gcc upstream comaintainers. when i had bugs in my gcc, i was submitting them to fedora bugzilla and they were quickly fixed. fedora is the best distro for development

That's all fine, as long as there is a fixed version available. The bugs I'm talking about are open upstream.

[pal666]

And I have found a deterministic ICE in GCC 11.2 (re-discovery) as well as multiple codegen bugs. So this version is also bad. The interesting question is whether there is a newer version that actually fixes the bug. The answer is no in my case, and I can't tell in your case.

my computer runs fedora and fedora contains gcc 11.2.1 with patches from master. rpm is maintained by one of gcc upstream comaintainers. when i had bugs in my gcc, i was submitting them to fedora bugzilla and they were quickly fixed. fedora is the best distro for development

[archkde]

last version in 9 branch is 9.4. i happen to use 9.3 in current project and i found deterministic ice in it(sometimes it ices but succeeds on rerun, but this one required disabling one optimization pass). i.e. 9.3 is definitely bad version

And I have found a deterministic ICE in GCC 11.2 (re-discovery) as well as multiple codegen bugs. So this version is also bad. The interesting question is whether there is a newer version that actually fixes the bug. The answer is no in my case, and I can't tell in your case.

[perpetually high]

most optimizations are not chip-specific. new complier is always better and it's not limited to optimizations
not necessarily. sometimes it can be shorter execution time and more bugs found in your program at compile time.
last version in 9 branch is 9.4. i happen to use 9.3 in current project and i found deterministic ice in it(sometimes it ices but succeeds on rerun, but this one required disabling one optimization pass). i.e. 9.3 is definitely bad version

Thanks. I think the LTS version is getting the backported fixes (gcc-9/focal-updates,focal-security,now 9.3.0-17ubuntu1~20.04), but I'm gonna look into just using the latest and greatest instead. And will run benchmarks and report back. Glad I asked though.

[pal666]

someone asked why an old compiler would be best for any chip. My answer is that the optimizations are likely not coming in for Haswell anymore

most optimizations are not chip-specific. new complier is always better and it's not limited to optimizations

and more code = longer execution time

not necessarily. sometimes it can be shorter execution time and more bugs found in your program at compile time.

the last, greatest, stable version (9.3.0 in my case)

last version in 9 branch is 9.4. i happen to use 9.3 in current project and i found deterministic ice in it(sometimes it ices but succeeds on rerun, but this one required disabling one optimization pass). i.e. 9.3 is definitely bad version

[brad0]

Thats an AVX2 chip. You would definitely benefit from a newer compiler

For the most part that is very unlikely.

[sdack]

Together with the pseudo x86-architectures for GCC's -march= switch that were added some time ago such as x86-64-v3 for AVX2 and x86-64-v4 for AVX512 do I hope to see distros picking up at least x86-64-v3 here and to provide more than the standard 64-bit binary packages.

By the time GCC 12 becomes stable would it be nice for distros like Debian to a add second x86-64 repository for AVX2-optimised binaries to make these gains available to all the Debian-based x86 distros. Perhaps the multimedia repository could start adding this.

[carewolf]

Which architectures will it support?

All of them?

It even have a generic mode that can operate without using SIMD instructions (2/4 16bit integers in 64bit word). Though that mode is naturally limited, and sometimes needs to be halved to deal with overflows.

[perpetually high]

Most of the work that goes into the compiler is not tuning the pipeline descriptions for some particular CPU, so you're missing out on all that work.

That being said, in most cases the benefits are not huge, and the least-hassle way is to use the default version that comes with your distro (which is what you're using).

Yeah, I need to do benchmarks soon to really get to the bottom of this. Appreciate the reply.

[jabl]

I'm still using gcc 9.3.0 (9.3.0-17ubuntu1~20.04) for my i5-4670K Haswell. Stupid move? Feels like maybe the best compiler for this chip but if anyone strongly disagrees, do share.

edit: someone asked why an old compiler would be best for any chip. My answer is that the optimizations are likely not coming in for Haswell anymore, and more code = longer execution time on stuff you don't need or gonna use. So I might as well use the last, greatest, stable version (9.3.0 in my case) instead of the bleeding edge 10/11/12. Put dumbly, of course. I'd love to be corrected.

Most of the work that goes into the compiler is not tuning the pipeline descriptions for some particular CPU, so you're missing out on all that work.

That being said, in most cases the benefits are not huge, and the least-hassle way is to use the default version that comes with your distro (which is what you're using).