Root cause of TMEM epilogue hang: tmem_store/tmem_load are
warp-collective operations requiring ALL 32 lanes to participate.
The loop 'for (col = lane; col < TMEM_O_COLS; col += WARP)' with
TMEM_O_COLS=16 and WARP=32 means only lanes 0-15 execute the op.
Lanes 16-31 skip it = warp divergence on collective = HANG.
Fix: loop over TMEM_N (>= 32, power of 2) so all 32 lanes
participate. Columns beyond TMEM_O_COLS write don't-care data
to allocated-but-unused TMEM columns.
biondizzle
33cedbee0a