The RAW benchmark suite: computation structures for general purpose computing

The RAW benchmark suite consists of twelve programs designed to facilitate comparing, validating, and improving reconfigurable computing systems. These benchmarks run the gamut of algorithms found in general purpose computing, including sorting, matrix operations, and graph algorithms. The suite includes an architecture-independent compilation framework, Raw Computation Structures (RawCS), to express each algorithm’s dependencies and to support automatic synthesis, partitioning, and mapping to a reconfigurable computer. Within this framework, each benchmark is portably designed in both C and Behavioral Verilog and scalably parameterized to consume a range of hardware resource capacities. To establish initial benchmark ratings, we have targeted a commercial logic emulation system based on virtual wires technologyto automatically generate designs up to millions of gates (14 to 379 FPGAs). Because the virtual wires es abstract away machine-level details like FPGA capacity and interco...

• Type: Conference
• Year: 1997
• Where: FCCM
• Authors: Jonathan Babb, Matthew Frank, Victor Lee, Elliot Waingold, Rajeev Barua, Michael Bedford Taylor, Jang Kim, Devabhaktuni Srikrishna, Anant Agarwal
• Keywords: FCCM 1997, Initial Benchmark Ratings, RAW Benchmark Suite, Virtual Wires, VLSI