It's not even about optimizing some big tech codebase by 0.5%. The progress guarantees in particular are in place s.t. Nvidia can choose a certain implementation strategy in Cuda C++ that has "surprising" consequences for users (one thread getting stuck in an infinite loop that never yields can livelock its entire warp) but still get to claim "full C++ standards compliance".
It's not even about optimizing some big tech codebase by 0.5%. The progress guarantees in particular are in place s.t. Nvidia can choose a certain implementation strategy in Cuda C++ that has "surprising" consequences for users (one thread getting stuck in an infinite loop that never yields can livelock its entire warp) but still get to claim "full C++ standards compliance".