Hacker News Reader

Comment by not2b | Hacker News Reader

AMD should concentrate on making LLVM and GCC work great on AMD processors, by contributing the needed code. They are already making some contributions but could be doing more, and they could be funding experts to work on that and giving those experts the information they need.

View on HN

But they already do this. AMD is one of the largest corporate contributors to LLVM and GCC.

It's Intel that tends to phone this in and make everyone else pick up the slack.

Per https://www.phoronix.com/scan.php?page=news_item&px=LLVM-Rec..., Intel actually contributes (slightly) more to LLVM than AMD does.

They do. Actually their own (LLVM based) compilers are about as fast as GCC and LLVM

https://www.phoronix.com/scan.php?page=article&item=aocc32-c...

I don't know if it necessarily says much that their LLVM-based compiler is about as fast as LLVM.

It says they might as well stop dividing their effort and focus on the upstream LLVM (or alternatively treat their own version as just a development branch that they can push upstream from). While they have expertise on the details of their processor they may benefit more by cooperating with all the compiler experts outside their company.

To fix this problem AMD would have to work on making LLVM and GCC work great on Intel processors. That would be the only way to make people not use the Intel compiler for extra performance and ending up with binaries that are crippled for AMD. Clearly that's not a solution for this problem.

Reply on news.ycombinator.com