Applications of Systolic Array

1. Applications of Systolic Array - Signal and image processing: • FTR , IIR filtering , and 1-D convolution. • 2-D convolution and correlation. • Discrete Furier transform • Interpolation • 1-D and 2-D median filtering • Geometric warping

2. Applications of Systolic Array - Matrix arithmetic: • Matrix-vector multiplication • Matrix-matrix multiplication • Matrix triangularization • (solution of linear systems , matrix inversion) • QR decomposition • (eigenvalue , least-square computation) • Solution of triangular linear systems

3. Applications of Systolic Array - Non-numeric applications: • Data structure • Graph algorithm • Language recognition • Dynamic programming • Encoder (polynomial division) • Relational data-base operations

4. Matrix Multiplication Recurences Cij(1) = 0 Cij(k+1) = Cij(k) + ajkbkj Cij = Cij(n+1) Band width wa, wb Total step : 3n + min(wa, wb)

5. Recurences Cij(1) = 0 Cij(k+1) = Cij(k) + ajkbkj Cij = Cij(n+1)

7. Systolic array multiplier of numbers • For n*n multiplier • (3n+1)n/2 cells are required • Before saturation, 3n clock cycles are required for the multiplication. • After saturation, a product will be output on every clock cycle.

8. Basic Cell Systolic array multiplier of numbers The main idea is calculate partial product and direct them to appropriate places

9. Multiplier structure Basic Cell Systolic array multiplier of numbers Delay elements

10. Performance of 8-bit multiplier

11. Triangular Architecture For solving triangular linear systems On-the-fly least-squares solutions using one and two dimensional systolic array, with p=4.

12. Systolic Organization for future (nano) technologies • To effectively utilize a given technology, the constraints of that technology must be well understood. • System designers must consider the limitations of the technology to design a system where those limitations do not impact the overall performance significantly.

13. Systolic Organization: requirements • reconfigurable — to exploit application dependent parallelisms, • high level language programmable— to provide task control and flexibility, • scalable— to easily extend the architecture to many applications, • capable of supporting SIMD organizations for vector operations and MIMD for non homogeneous parallelism requirements.

14. Systolic Organization is the future • Systolic operationandorganization is a design philosophy that is aimed to satisfy the architectural constraints imposed by the advances in silicon technology. • This design is becoming even more important for all new nano-technologies • It offerssimplicity, regularity, modularity,and localized communications.

15. Principle of Local Communication • Systolic arrays are typically characterized as having intensive local communicationsand computations yet, with decentralizedparallelismin acompact package. • Systolic arrays capitalize on processes which can be performed in a regular, modular, rhythmic, synchronous, and concurrent mannerthat require intensive repetitive computations.

16. New concept in Computer Architecture • Systolic arrays originally were proposed for fixed or special purpose instances, • However, this concept has been extended to more general purpose SIMD and MIMD architectures.

17. Systolic Characteristics • The systolic cells are synchronized by a single global clock. • The input data streams are fed to the systolic array only at its boundaries. • Different data streams can flow in different directionsat different speeds through the array.

18. Systolic different than pipelined • Systolic architectures differ from pipelined systems because; • Most of the stages are identical, • Input data is not consumed, • Input data streams can flow in different directions, • Modules may be organized in a two-dimensional (or higher) configuration.

19. Systolic different than array processors • Systolic architectures differ from array of processors because; • Processors in systolic organizations are synchronized by a single global clock, but are locally controlled — different systolic cells can perform different operations at the same time.

20. Systolic Characteristics • Systolic architectures allowhigher throughputs— concurrent operations of a large number of the processing cells. • Ability to increase the execution speed of compute-bound applications without increasing the I/O requirements —reusabilityof the input data.

21. Automatic Design? • Algorithms and Mapping:Designers must be intimately familiar with the algorithms that they are implementing on systolic arrays. • Theheuristic designof systolic arrays from an algorithm is slow, error prone, requires simulation for verification, and often results in a non optimum solution. • Automatic array synthesis is a research area of interest. However, most array designs are based on heuristics.

22. Integration • Integration into Existing Systems:Generally, systolic processors are integrated into an existing hostas a backend processor.

23. Systolic Issues • Integration into Existing Systems: • System integration is often nontrivial because of the array’s high I/O requirements. • Often, an additional memory subsystem is added between the existing host and the systolic array to support data access and data multiplexing and de-multiplexing since the existing I/O channel of the host rarely satisfies the bandwidth required by the systolic array.

24. Systolic Issues • Cell Granularity: • Low level or high level cell granularity will directly affect the array’s throughput, flexibility, and the set of algorithms which may be efficiently executed.

25. Systolic Issues • Cell Granularity: • The basic operation performed in each cycle by each cell can range from logical or bit wise operations to word level multiplication and addition to a complete program. • Granularity is subject to technology capabilities and limitations as well as design goals. • Packaging will also introduce input/output pin restrictions.

26. Systolic Issues • Extensibility:Since systolic arrays are built around the cellular building blocks, the cell design should be sufficiently flexible to allow it to be used in a wide variety of topologies implemented in a wide variety of substrate technologies.

27. Systolic Issues • Clock Synchronization:Clock lines of different lengths within integrated chips, as well as external to the chips, can introduce skews. • Clock skewrisk is greater when data flow within the systolic array is bi-directional. • Wave-front arrays reduce the clock skew problem by introducing more complicated asynchronous inter cellular communications.

28. Systolic Issues • Reliability:As integrated circuits grow larger and larger,inherent fault tolerantabilities must be added if the same degree of reliability is to be maintained. • Also diagnostics should be built in at design time so proper operation can more easily be verified.