A Tile-Based EGPU with a Fused Universal Processing Engine and Graphics Coprocessor Cluster

Table 1

Performance analysis of a UP.

Case	Instruction package type: Number	Clock cycles used	Execution unit
1	1D 4:	+ 5	SPs
2	1D + 3D:	+ 4	SPs
3	2D + 2D:	+ 4	SPs
4	4D:	+ 4	SPs
5	Complex operation:	+ 7	SFU