Exploiting loop-level parallelism on coarse-grained reconfigurable architectures using modulo scheduling
Bingfeng Mei, Serge Vernalde, Diederik Verkest et al. · Design, Automation, and Test in Europe · 2003
Coarse-grained reconfigurable architectures have become increasingly important in recent years. Automatic design or compilation tools are essential to their success. In this paper, we present a modulo scheduling algorithm to exploit loop-level parallelism for coarse-grained reconfigurable architectures. This algorithm is a key part of our dynamically reconfigurable embedded systems compiler (DRESC). It is capable of solving placement, scheduling and routing of operations simultaneously in a modulo-constrained 3D space and uses an abstract architecture representation to model a wide class of coarse-grained architectures. The experimental results show high performance and efficient resource utilization on tested kernels.
Cited by 113 works. doi:10.1109/date.2003.1253623
Authors
References
- Software pipelining: an effective scheduling technique for VLIW machines
- MorphoSys: an integrated reconfigurable system for data-parallel and computation-intensive applications
- RaPiD — Reconfigurable pipelined datapath
- Placement and routing tools for the Triptych FPGA
- MATRIX: a reconfigurable computing architecture with configurable instruction distribution and deployable resources
- Space-time scheduling of instruction-level parallelism on a raw machine
- Effective Compiler Support For Predicated Execution Using The Hyperblock
- Iterative Modulo Scheduling
- PipeRench: A virtualized programmable datapath in 0.18 micron technology
- DRESC: a retargetable compiler for coarse-grained reconfigurable architectures