Efficient conditional operations for data-parallel architectures
Ujval J. Kapasi, W.J. Dally, Scott Rixner et al. · 2000
Many data-parallel applications, including emerging media applications, have regular structures that can easily be expressed as a series of arithmetic kernels operating on data streams.Data-parallel architectures are designed to exploit this regularity by performing the same operation on many data elements concurrently.However, applications containing data-dependent control constructs perform poorly on these architectures.Conditional streams convert these constructs into data-dependent data movement.This allows data-parallel architectures to efficiently execute applications with data-dependent control flow.Essentially, conditional streams extend the range of applications that a data-parallel architecture can execute efficiently.For example, polygon rendering speeds up by a factor of 1.8 with the use of conditional streams.
Cited by 88 works. doi:10.1145/360128.360145 Open-access PDF
Authors
References
- Computer Architecture: A Quantitative Approach
- The SOLOMON computer
- Computer architecture (2nd ed.): a quantitative approach
- The CRAY-1 computer system
- MMX technology extension to the Intel architecture
- VIS speeds new media processing
- Advanced computer architecture: parallelism, scalability, programmability
- A Bandwidth-Efficient Architecture for Media Processing
- Register organization for media processing
- Video Demystified: A Handbook for the Digital Engineer