Applications of Small-Scale Reconfigurability to Graphics Processors

We explore the application of Small-Scale Reconfigurability (SSR) to graphics hardware. SSR is an architectural technique wherein functionality common to multiple subunits is reused rather than replicated, yielding high-performance reconfigurable hardware with reduced area requirements. We show that SSR can be used effectively in programmable graphics architectures to allow double-precision computation without affecting the performance of single-precision calculations and to increase fragment shader performance with a minimal impact on chip area.

[1]  S.M. Mueller,et al.  A dual mode IEEE multiplier , 1997, 1997 Proceedings Second Annual IEEE International Conference on Innovative Systems in Silicon.

[2]  Randima Fernando,et al.  The GeForce 6 series GPU architecture , 2005, SIGGRAPH Courses.

[3]  Miodrag Potkonjak,et al.  Behavioral-level synthesis of heterogeneous BISR reconfigurable ASIC's , 1998, IEEE Trans. Very Large Scale Integr. Syst..

[4]  Scott Hauck,et al.  Flexibility measurement of domain-specific reconfigurable hardware , 2004, FPGA '04.

[5]  John Lach,et al.  Designing, Scheduling, and Allocating Flexible Arithmetic Components , 2003, FPL.

[6]  Miodrag Potkonjak,et al.  Synthesis of application specific programmable processors , 1997, DAC.

[7]  Greg Humphreys,et al.  Chromium: a stream-processing framework for interactive rendering on clusters , 2002, SIGGRAPH.

[8]  Kevin Skadron,et al.  A flexible simulation framework for graphics architectures , 2004, Graphics Hardware.

[9]  Kaushik Roy,et al.  Synthesis of application-specific highly efficient multi-mode cores for embedded systems , 2005, TECS.

[10]  Pat Hanrahan,et al.  Brook for GPUs: stream computing on graphics hardware , 2004, SIGGRAPH 2004.

[11]  Michael A. Schuette,et al.  Morphable Multipliers , 2002, FPL.

[12]  Kevin Skadron,et al.  Studying Thermal Management for Graphics-Processor Architectures , 2005, IEEE International Symposium on Performance Analysis of Systems and Software, 2005. ISPASS 2005..