Re: Atomic operations on floating-point data types

On Mon, 5 Jul 2021, Thomas Schwinge wrote: > But: why, what's the rationale? Are potential floating point exceptions > the problem, maybe? "Simply, because nobody bothered implementing it __atomic_* more or less correspond to some of the atomic_* operations in , which only include atomic_fetch

Atomic operations on floating-point data types

Hi! Per we've found that GCC's nvptx back end doesn't make use of the PTX 32-bit floating-point add instruction, , as declared in 'gcc/config/nvptx/nv