DARM: Control-Flow Melding for SIMT Thread Divergence Reduction -- Extended Version

Charitha Saumya, Kirshanthan Sundararajah, Milind Kulkarni

GPGPUs use the Single-Instruction-Multiple-Thread (SIMT) execution model where a group of threads-wavefront or warp-execute instructions in lockstep. When threads in a group encoun…