公开(公告)号：US20220027194A1

公开(公告)日：2022-01-27

申请号：US17184420

申请日：2021-02-24

Applicant: NVIDIA Corp.

Inventor： Sana Damani ,  Mark Stephenson ,  Ram Rangan ,  Daniel Robert Johnson ,  Rishkul Kulkarni

IPC: G06F9/48 ,  G06F9/52 ,  G06F9/30

Abstract: Warp sharding techniques to switch execution between divergent shards on instructions that trigger a long stall, thereby interleaving execution between diverged threads within a warp instead of across warps. The technique may be applied to mitigate pipeline stalls in applications with low warp occupancy and high divergence. Warp data cache locality may also be improved by concentrating memory accesses within a warp rather than spreading them across warps.

公开(公告)号：US11934867B2

公开(公告)日：2024-03-19

申请号：US17184420

申请日：2021-02-24

Applicant: NVIDIA Corp.

Inventor： Sana Damani ,  Mark Stephenson ,  Ram Rangan ,  Daniel Robert Johnson ,  Rishkul Kulkarni

IPC: G06F9/46 ,  G06F9/30 ,  G06F9/48 ,  G06F9/52

CPC classification number: G06F9/4881 ,  G06F9/3009 ,  G06F9/522

Abstract: Warp sharding techniques to switch execution between divergent shards on instructions that trigger a long stall, thereby interleaving execution between diverged threads within a warp instead of across warps. The technique may be applied to mitigate pipeline stalls in applications with low warp occupancy and high divergence. Warp data cache locality may also be improved by concentrating memory accesses within a warp rather than spreading them across warps.