Talk:GPU
AMD architectures
AMD has some kind of NDA in their newest whitepapers, so I will put this into the discussion section...my own conclusions are:
- TeraScale has VLIW design
- GCN has 16 wide SIMD, executing a Wavefront of 64 threads over 4 cycles.
- RDNA has 32 wide SIMD, executing a Wavefront:32 over 1 cycle and Wavefront:64 over two cycles.
Nvidia architectures
Afaik Nvidia did never official mention SIMD in their papers as hardware architecture, with Tesla they only referred to as SIMT.
Nevertheless, my own conclusions are:
- Tesla has 8 wide SIMD, executing a Warp of 32 threads over 4 cycles.
- Fermi has 16 wide SIMD, executing a Warp of 32 threads over 2 cycles.
- Kepler is somehow odd, not sure how the compute units are partitioned.
- Maxwell and Pascal have 32 wide SIMD, executing a Warp of 32 threads over 1 cycle.
- Volta and Turing seem to have 16 wide FPU SIMDs, but my own experiments show 32 wide VALU.
SIMD + Scalar Unit
According to AMD papers every SIMD unit has one scalar unit, Nvidia seems to have SFUs, special function units.