alt Hacker NewsIt'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".
Replies
mschuetz • today at 4:32 AM
I don't see the issue. Just let wrong code do wrong things But let it do the expected wrong thing, rather than changing the code to something unexpected.
➕ show 1 reply
mitxela • today at 12:31 AM
Isn't that the strategy for most of the stuff in C++? It's the common denominator of a wide variety of platforms. That's why numbers didn't have to be two's complement and characters didn't have to be ASCII for ages.
So let it livelock the entire warp when someone writes an infinite loop. Should we start replacing integer division by zero with INT_MAX so that people aren't "surprised" by their program crashing?