arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2407.08975cs.ARcs.ET
收藏

面向低功耗硬件加速器的混合时序计算

Hybrid Temporal Computing for Lower Power Hardware Accelerators

Maliha Tasnim, Sachin Sachdeva, Yibo Liu, Sheldon X. -D. Tan

AI总结:

本研究提出混合时序计算框架,结合时序与脉冲速率编码突破传统竞争逻辑局限,实现低功耗通用算术运算,经FIR滤波器、DCT/iDCT引擎验证,较现有设计显著降低功耗与面积。

摘要:

本文提出了一种新型混合时序计算(HTC,Hybrid Temporal Computing)框架,该框架同时利用脉冲速率与时序数据编码来设计超低能耗硬件加速器。我们的方法受近期提出的时序计算(又称竞争逻辑)启发,该技术将数据值编码为单延迟量,由于信号切换被最小化,可显著降低能耗。但竞争逻辑因固有局限性,应用场景受限。\n新型HTC框架通过对乘法运算采用时序与脉冲速率双格式编码信号、对传播运算采用时序格式编码信号,克服了上述局限。该方法在保持开关能耗降低特性的同时,具备足够通用性,可实现广泛的算术运算。我们演示了HTC乘法如何针对单极性与双极性数据编码执行,并给出了乘法器、加法器与MAC(乘累加)单元的基础设计。\n此外,我们实现了两款硬件加速器:一款有限脉冲响应(FIR,Finite Impulse Response)滤波器,以及一款用于图像压缩与DSP(数字信号处理)应用的离散余弦变换(DCT,Discrete Cosine Transform)/逆DCT(iDCT)引擎。实验结果表明,HTC MAC与Unary MAC设计相比,功耗与面积占比显著更小,且速度快数个数量级;与CBSC MAC相比,HTC MAC功耗降低45.2%,面积占比降低50.13%。\n在FIR设计方面,HTC设计在所有指标上均显著优于Unary设计;与CBSC设计相比,基于HTC的FIR滤波器功耗降低36.61%,面积成本降低45.85%。基于HTC的DCT滤波器可保持原始图像质量,具备不错的PSNR(峰值信噪比),同时与基于CBSC MAC的DCT滤波器相比,功耗降低23.34%,面积占用减少18.20%。

英文摘要:

In this paper, we propose a new hybrid temporal computing (HTC) framework that leverages both pulse rate and temporal data encoding to design ultra-low energy hardware accelerators. Our approach is inspired by the recently proposed temporal computing, or race logic, which encodes data values as single delays, leading to significantly lower energy consumption due to minimized signal switching. However, race logic is limited in its applications due to inherent restrictions. The new HTC framework overcomes these limitations by encoding signals in both temporal and pulse rate formats for multiplication and in temporal format for propagation. This approach maintains reduced switch energy while being general enough to implement a wide range of arithmetic operations. We demonstrate how HTC multiplication is performed for both unipolar and bipolar data encoding and present the basic designs for multipliers, adders, and MAC units. Additionally, we implement two hardware accelerators: a Finite Impulse Response (FIR) filter and a Discrete Cosine Transform (DCT)/iDCT engine for image compression and DSP applications. Experimental results show that the HTC MAC has a significantly smaller power and area footprint compared to the Unary MAC design and is orders of magnitude faster. Compared to the CBSC MAC, the HTC MAC reduces power consumption by $45.2\%$ and area footprint by $50.13\%$. For the FIR design, the HTC design significantly outperforms the Unary design on all metrics. Compared to the CBSC design, the HTC-based FIR filter reduces power consumption by $36.61\%$ and area cost by $45.85\%$. The HTC-based DCT filter retains the quality of the original image with a decent PSNR, while consuming $23.34\%$ less power and occupying $18.20\%$ less area than the CBSC MAC-based DCT filter.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑