FAFNER-Accelerating Nesting Problems with FPGAs
FCCM '99 Proceedings of the Seventh Annual IEEE Symposium on Field-Programmable Custom Computing Machines
An FPGA-based VLIW processor with custom hardware execution
Proceedings of the 2005 ACM/SIGDA 13th international symposium on Field-programmable gate arrays
EURASIP Journal on Applied Signal Processing
Hi-index | 0.00 |
This paper presents RVC, a new reconfigurable platform for the implementation of custom computing machines, that is intended for vector coprocessors in low cost PC-based applications. The board includes 5 XILINX 4000E FPGAs and 4 fast static RAMs independently addressable, providing in each memory read cycle up to 64-bits of data to an application specific computation datapath. The design of this system was driven by the need to speedup a time consuming task in digital signal processing, making use of an application specific processor. Although executing integer arithmetic operations which tend to be efficiently performed by conventional processors, the vector architecture has demonstrated to reach more than an 8 times speedup with a 12.5 MHz clock frequency, compared to a PC Pentium running at 120 MHz.