https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99555
--- Comment #18 from CVS Commits <cvs-commit at gcc dot gnu.org> --- The master branch has been updated by Chung-Lin Tang <clt...@gcc.gnu.org>: https://gcc.gnu.org/g:fdc7469cf597ec11229ddfc3e9c7a06f3d0fba9d commit r13-4832-gfdc7469cf597ec11229ddfc3e9c7a06f3d0fba9d Author: Chung-Lin Tang <clt...@codesourcery.com> Date: Wed Dec 21 05:57:45 2022 -0800 nvptx: reimplement libgomp barriers [PR99555] Instead of trying to have the GPU do CPU-with-OS-like things, this new barriers implementation for NVPTX uses simplistic bar.* synchronization instructions. Tasks are processed after threads have joined, and only if team->task_count != 0 It is noted that: there might be a little bit of performance forfeited for cases where earlier arriving threads could've been used to process tasks ahead of other threads, but that has the requirement of implementing complex futex-wait/wake like behavior, which is what we're try to avoid with this patch. It is deemed that task processing is not what GPU target offloading is usually used for. Implementation highlight notes: 1. gomp_team_barrier_wake() is now an empty function (threads never "wake" in the usual manner) 2. gomp_team_barrier_cancel() now uses the "exit" PTX instruction. 3. gomp_barrier_wait_last() now is implemented using "bar.arrive" 4. gomp_team_barrier_wait_end()/gomp_team_barrier_wait_cancel_end(): The main synchronization is done using a 'bar.red' instruction. This reduces across all threads the condition (team->task_count != 0), to enable the task processing down below if any thread created a task. (this bar.red usage means that this patch is dependent on the prior NVPTX bar.red GCC patch) PR target/99555 libgomp/ChangeLog: * config/nvptx/bar.c (generation_to_barrier): Remove. (futex_wait,futex_wake,do_spin,do_wait): Remove. (GOMP_WAIT_H): Remove. (#include "../linux/bar.c"): Remove. (gomp_barrier_wait_end): New function. (gomp_barrier_wait): Likewise. (gomp_barrier_wait_last): Likewise. (gomp_team_barrier_wait_end): Likewise. (gomp_team_barrier_wait): Likewise. (gomp_team_barrier_wait_final): Likewise. (gomp_team_barrier_wait_cancel_end): Likewise. (gomp_team_barrier_wait_cancel): Likewise. (gomp_team_barrier_cancel): Likewise. * config/nvptx/bar.h (gomp_barrier_t): Remove waiters, lock fields. (gomp_barrier_init): Remove init of waiters, lock fields. (gomp_team_barrier_wake): Remove prototype, add new static inline function.
