Cache-set-locking Non-blocking cache MSHR (Miss Information/Status Holding Register) Tail pointer (Xbox 360) Store gathering buffer Pre-decode Branch scan ECC CUDA GFlop/s Bandwidth GPU PCI Express Block Thread Warp Warp scheduling scoreboarding Divergent warp Predication Thread execution manager SFP (Special functional unit) Registers Local memory Constant memory Texture memory Global memory Shared memory PTX Idle threads Parallel reduction (parallel sum) Coalescing/uncoalscing Loop unrolling Occupancy AOS (Array of structure) SOA (Structure of array) DRAM Burst Mode SM (Stream Multiprocessors) Geometry stage Rasterizer stage Vertex processor Fragment processor Frame buffer lighting Clipping Culling ROP Z-buffer Depth test Stencil buffer Anti-aliasing Alpha blending Unified shader