摘要: 前导1预测(Leading One Prediction,LOP)算法常被用在浮点数的加减运算中,它能与尾数加法器并行工作,从而加快了尾数加法器计算结果的规格化过程,同时,这种方法会带来最多1位的误差。根据对误差的处理方式不同,将预测算法分成了3类,并详细介绍了其中的串行纠错前导1预测算法的具体结构,对其关键的组成部分在算法上进行了选择和优化。它与并行纠错LOP以及传统前导1检测(Leading One Detector,LOD)的逻辑综合的实验结果表明,该算法取得了面积、功耗和延时之间的较好均衡。在实际的应用中,该算法成功地运用在了工作频率为1GHz的三站式双通路(Two-Path)浮点加法器中。
[1] Bruguera J D,Lang T.Leading-One Prediction with Concurrent Position Correction[J].IEEE Transactions on Computers,1999,48(10):298-305 [2] Ji Rong,Ling Zhi-qiang,Zeng Xian-jun,et al.Comments onLeading-One Prediction with Concurrent Position Correction[J].IEEE Transaction on Computer,2009,58(12) [3] Suzuki H,Morinaka H,Makino H,et al.Leading Zero Anticipatory Logic for High Speed Floating-Point Addition[J].IEEE Journal of Solid State Circuits,1996,31(8):1157-1164 [4] Schmookler M S,Nowka K J.Leading zero anticipation and detection:A comparision of methods.Colorado[C]∥Proc.of the 15th IEEE Symposium on Computer Arithmetic.July 2001:7-12 [5] Dimitrakopoulos G,Galanopoulos K,Mavrokefalidis C,et al.Low-Power Leading-Zero Counting and Anticipation Logic for High-Speed Floating Point Units[J].IEEE Transactions on Very Large Scale Integration System,2008,16(7) [6] Lee K T,Nowkda K J.1GHz leading-zero anticipator using independent sign-bit determination logic[C]∥Symposium on VLSI Circuit Digest of Technical Papers.2000 [7] Zhang Ge,Hu Wei-wu,Qi ZI-chu.Parallel Error Detection for Leading Zero Anticipation[J].J.Comput.Sci.&Technol,2006,1(6):901-906 [8] Yao Tao,Gao De-yuan.A Novel Concurrent Error DetectionCircuit for Leading Zero Anticipator[C]∥2nd Intermational Conference on Computer Engineering and Technology.2010 [9] Oklobdzija V.An Algorithmic and Novel Design of a LeadingZero Detector Circuit:Comparison with Logic Synthesis[J].IEEE Transactions on VLSI System,1993,2(1):124-128 [10] Hinds C N,Lutz D R.A Small and Fast Leading One Predictor Corrector Circuit[C]∥Asilomar Conference on Signals,Systems and Computers.2005:1181-1185 [11] Oberman S F,Flynn M J.A variable Latency Pipelined Floating-point Adder[R].CSL-TR-96-689.Stanford University,1996 [12] 黄迟.64位高速浮点加法器的VLSI实现和结构研究[D].上海:复旦大学,2004 [13] 王颖.高性能CPU中浮点加法器的设计与实现[D].上海:同济大学,2005 |
No related articles found! |
|