GCC 10 vs. GCC 11 Compiler Performance On The Threadripper 3990X

[Paradigm Shifter]

The FFTW improvements have me interested.

[dev_null]

IMHO adding compilation time to geometric mean with performance is incorrect, these are different entities and it is like add mass and loudness. End users never see compilation time when launch already built software.

[Brane215]

At this point, they should just increase minor version.
There are no big changes in backend, anyway.

[CaptainLugnuts]

Grammar police!
The title of the article should be "GCC 10 vs. GCC 11 Compiler Performance For The Threadripper 3990X"
Using "On" there means you are testing the functionality of the compilers rather than the compiler's output.

[pyler]

Can you add LLVM 13 trunk to future comparison with LLVM 12 and gcc 11 as well?

I am very interested about changes caused by new pass manager in llvm 13

[phoronix]

Phoronix: GCC 10 vs. GCC 11 Compiler Performance On The Threadripper 3990X

With GCC 11 stable likely to be released next month, here is the latest in our compiler testing against the current GCC 10 stable release. This round of tests was carried out on a System76 Thelio Major with Ryzen Threadripper 3990X HEDT processor.

https://www.phoronix.com/vr.php?view=30008