Repository navigation

feat(cuda-device): derive an SM floor cfg and use redux.sync in warp_reduce - #1305

Open

vyncint wants to merge 5 commits into

NVIDIA:mainfrom

vyncint:feat/arch-derived-sm-floor-cfg

Open

feat(cuda-device): derive an SM floor cfg and use redux.sync in warp_reduce#1305
vyncint wants to merge 5 commits into
NVIDIA:mainfrom
vyncint:feat/arch-derived-sm-floor-cfg

Commits on Oct 11, 2026
- fix(codegen): match redux.sync's f32 form on the instruction, not on nearby text
  vyncint
  committed
  ed917c5
- feat(cuda-device): derive an SM floor cfg and use redux.sync in warp_reduce
  vyncint
  committed
  e5bc97d
- example(warp_reduce_redux): show both forms of warp_reduce and their controls
  vyncint
  committed
  e8f6b24
- docs: clarify the shared SM floor contract
  
  nihalpasham
  authored and
  vyncint
  committed
  7ed4577
- test(codegen): pin that both readers of the device hint agree
  vyncint
  committed
  ab10984