580 likes | 1.42k Views
Computer Architecture SIMD. Ola Flygt Växjö University http://w3.msi.vxu.se/users/ofl/ Ola.Flygt@msi.vxu.se +46 470 70 86 49. Outline. Design space Granularity Connectivity Processor complexity Local Anotomy Fine grained architectures Course grained architectures. CH01.
E N D
Computer ArchitectureSIMD Ola Flygt Växjö University http://w3.msi.vxu.se/users/ofl/ Ola.Flygt@msi.vxu.se +46 470 70 86 49
Outline • Design space • Granularity • Connectivity • Processor complexity • Local Anotomy • Fine grained architectures • Course grained architectures CH01
Design space • There are several factors to consider when designing a SIMD. The most important ones are: • Granularity • Connectivity • Complexity of processing element • Local autonomy
Connectivity Not all the types of connectivity for data parallel arch. are used in SIMD arch.
Performance of interconnection networks • There are several important parameters in an interconnection network • Diameter, the shortest path between the two most distant nodes • Bandwidth, how many data exchanges simultaneous in the network • Blocking, how many exchanges are blocked
Performance of interconnection networks N=128*128 1 1 256 28 14 14 1 N=128*128 1 16384 16384 28 14 16384 16384
Processor complexity • The design space for processor precision • Single bit – fine grained, mainly for image processing • Integer – general computing • Floating point – Coarse grain, scientific computing • Fine grained -> more PEs