Exploiting Contemporary Memory Techniques in Reconfigurable Accelerators

This paper discusses the memory interface of custom computing machines. We present a high speed parallel memory for the MoM-PDA machine, which is based on the Xputer paradigm. The memory employs DRAMs instead of the more expensive SRAMs. To enhance the memory bandwidth, we use a threefold approach: modern memory devices featuring burst mode, an efficient memory architecture with multiple parallel modules, and memory access optimization for single applications. To exploit the features of the memory architecture, we introduce a strategy to determine optimized storage schemes for a class of applications.

[1]  Jürgen Becker,et al.  High‐performance computing using a reconfigurable accelerator , 1996 .

[2]  Reiner W. Hartenstein,et al.  A Novel Paradigm of Parallel Computation and its Use to Implement Simple High Performance Hardware , 1990, CONPAR.

[3]  Karin Schmidt A program partitioning, restructuring, and mapping method for Xputers , 1995 .

[4]  Viktor K. Prasanna,et al.  Seeking Solutions in Configurable Computing , 1997, Computer.

[5]  Reiner W. Hartenstein,et al.  A novel paradigm of parallel computation and its use to implement simple high-performance hardware , 1992, Future Gener. Comput. Syst..

[6]  Paul Budnik,et al.  The Organization and Use of Parallel Memories , 1971, IEEE Transactions on Computers.

[7]  Ashoke Deb Multiskewing-A Novel Technique for Optimal Parallel Memory Access , 1996, IEEE Trans. Parallel Distributed Syst..

[8]  David A. Patterson,et al.  Computer Architecture: A Quantitative Approach , 1969 .

[9]  Monica S. Lam,et al.  Data and computation transformations for multiprocessors , 1995, PPOPP '95.

[10]  Reiner W. Hartenstein,et al.  A datapath synthesis system for the reconfigurable datapath architecture , 1995, ASP-DAC '95.

[11]  Jürgen Becker,et al.  High-performance computing using a reconfigurable accelerator , 1996, Concurr. Pract. Exp..

[12]  Jürgen Becker A partitioning compiler for computers with Xputer-based accelerators , 1997 .

[13]  Rainer Kress A fast reconfigurable ALU for Xputers , 1996 .

[14]  V. K. Prasanna-Kumar,et al.  Perfect Latin squares and parallel array access , 1989, ISCA '89.

[15]  Jürgen Becker,et al.  Custom Computing Machines vs. Hardware/Software Codesign: From a globalized point of view , 1996, FPL.

[16]  Jürgen Becker,et al.  A Novel Universal Sequencer Hardware , 1997, ARCS.

[17]  Monica S. Lam,et al.  A data locality optimizing algorithm , 1991, PLDI '91.