Energy reduction in queues and stacks by adaptive bitwidth compression
ISLPED '01 Proceedings of the 2001 international symposium on Low power electronics and design
SHAPES:: a tiled scalable software hardware architecture platform for embedded systems
CODES+ISSS '06 Proceedings of the 4th international conference on Hardware/software codesign and system synthesis
Design of a low-power, high performance, 8×8bit multiplier using a Shannon-based adder cell
Microelectronics Journal
EURASIP Journal on Embedded Systems - FPGA supercomputing platforms, architectures, and techniques for accelerating computationally complex algorithms
Green: a framework for supporting energy-conscious programming using controlled approximation
PLDI '10 Proceedings of the 2010 ACM SIGPLAN conference on Programming language design and implementation
Variable-latency floating-point multipliers for low-power applications
IEEE Transactions on Very Large Scale Integration (VLSI) Systems
EnerJ: approximate data types for safe and general low-power computation
Proceedings of the 32nd ACM SIGPLAN conference on Programming language design and implementation
Precision selection for energy-efficient pixel shaders
Proceedings of the ACM SIGGRAPH Symposium on High Performance Graphics
Architecture support for disciplined approximate programming
ASPLOS XVII Proceedings of the seventeenth international conference on Architectural Support for Programming Languages and Operating Systems
Lossless and lossy memory I/O link compression for improving performance of GPGPU workloads
Proceedings of the 21st international conference on Parallel architectures and compilation techniques
Energy-Efficient Multiple-Precision Floating-Point Multiplier for Embedded Applications
Journal of Signal Processing Systems
International Journal of Computational Science and Engineering
| Hi-index | 0.00 |
Low-power systems often find the power cost of floating-point (FP) hardware prohibitively expensive. This paper explores ways of reducing FP power consumption by minimizing the bitwidth representation of FP data. Analysis of several FP programs that manipulate low-resolution human sensory data shows that these programs suffer no loss of accuracy even with a significant reduction in bitwidth. Most FP programs in our benchmark suite maintain the same output even when the mantissa bitwidth is reduced by half. This FP bitwidth reduction can deliver a significant power saving through the use of a variable bitwidth FP unit. Our results show that up to 66% reduction in multiplier energy/operation can be achieved in the FP unit by this bitwidth reduction technique without sacrificing any program accuracy.