Automated application acceleration using software to hardware transformation

This paper describes an approach that allows applications to be developed in a software language, while taking advantage of hardware by facilities that automatically transform such software programs for hardware accelerators. A demonstration of this approach has been built for the C# language. Three case studies in numerical integration show that the automatically generated hardware accelerators can achieve similar speed-ups to manually optimised versions. In particular, the automatically generated accelerator running on an xc4vlx160 FPGA at 83 MHz with single precision arithmetic can be more than 18 times faster and up to 143 times more power efficient than a Pentium 4 processor at 3.6 GHz, while the double precision accelerator running at 64 MHz is 7 times faster and 77 times more power efficient.