基于一階泰勒級數(shù)查表法單精度倒數(shù)的設(shè)計與實現(xiàn)
發(fā)布時間:2018-10-18 13:17
【摘要】:在分析了單精度倒數(shù)算法在圖形處理器中存在的不足的基礎(chǔ)上,設(shè)計了一階泰勒級數(shù)單精度倒數(shù)算法。與傳統(tǒng)算法相比,在資源消耗、運算周期和效率方面得到了有效改善。本浮點倒數(shù)算法的主要邏輯模塊由一個24位整數(shù)加法器、一個ROM和一個24位乘法器組成。將在[1,2)范圍的尾數(shù)平均分為4 096個區(qū)間,將每個區(qū)間起始點倒數(shù)平方放入查找表,并對每個區(qū)間采用一階泰勒級數(shù)計算倒數(shù)值。仿真結(jié)果表明:仿真的結(jié)果與理論結(jié)果一致,滿足單精度浮點數(shù)的精度要求。目前此算法已經(jīng)成功流片,應(yīng)用于國產(chǎn)第三代圖形處理器JM7200。
[Abstract]:Based on the analysis of the shortcomings of single-precision reciprocal algorithm in GPU, the one-order Taylor series single-precision reciprocal algorithm is designed. Compared with the traditional algorithm, the resource consumption, operation cycle and efficiency are improved effectively. The main logic module of the floating-point reciprocal algorithm consists of a 24-bit integer adder, a ROM and a 24-bit multiplier. The average Mantissa in the range of [1] is divided into 4 096 intervals, the reciprocal square of the starting point of each interval is put into the lookup table, and the inverse value of each interval is calculated by the first order Taylor series. The simulation results show that the simulation results are consistent with the theoretical results and meet the precision requirements of single precision floating-point points. The algorithm has been successfully used in the third generation graphics processor (JM7200.).
【作者單位】: 湖南大學(xué)物理與微電子科學(xué)學(xué)院;湖南城市學(xué)院市政與測繪工程學(xué)院;
【分類號】:TP332
[Abstract]:Based on the analysis of the shortcomings of single-precision reciprocal algorithm in GPU, the one-order Taylor series single-precision reciprocal algorithm is designed. Compared with the traditional algorithm, the resource consumption, operation cycle and efficiency are improved effectively. The main logic module of the floating-point reciprocal algorithm consists of a 24-bit integer adder, a ROM and a 24-bit multiplier. The average Mantissa in the range of [1] is divided into 4 096 intervals, the reciprocal square of the starting point of each interval is put into the lookup table, and the inverse value of each interval is calculated by the first order Taylor series. The simulation results show that the simulation results are consistent with the theoretical results and meet the precision requirements of single precision floating-point points. The algorithm has been successfully used in the third generation graphics processor (JM7200.).
【作者單位】: 湖南大學(xué)物理與微電子科學(xué)學(xué)院;湖南城市學(xué)院市政與測繪工程學(xué)院;
【分類號】:TP332
【參考文獻(xiàn)】
相關(guān)期刊論文 前4條
1 劉金碩;劉天曉;吳慧;曾秋梅;任夢菲;顧宜淳;;從圖形處理器到基于GPU的通用計算[J];武漢大學(xué)學(xué)報(理學(xué)版);2013年02期
2 王海峰;陳慶奎;;圖形處理器通用計算關(guān)鍵技術(shù)研究綜述[J];計算機學(xué)報;2013年04期
3 馬千里;徐華勛;岳凱;李思昆;;基于GPU的非結(jié)構(gòu)化網(wǎng)格數(shù)據(jù)體光照計算與實現(xiàn)方法[J];計算機工程與科學(xué);2011年01期
4 牟勝梅;楊曉東;;高吞吐率浮點FFT處理器的FPGA實現(xiàn)研究[J];計算機工程與科學(xué);2008年07期
【共引文獻(xiàn)】
相關(guān)期刊論文 前10條
1 唐坤杰;董樹鋒;宋永華;;基于不完全LU分解預(yù)處理迭代法的電力系統(tǒng)潮流算法[J];中國電機工程學(xué)報;2017年S1期
2 晏敏;何欣;李沙;祝龍;趙麗;;基于一階泰勒級數(shù)查表法單精度倒數(shù)的設(shè)計與實現(xiàn)[J];計算機工程與科學(xué);2017年07期
3 李n,
本文編號:2279241
本文鏈接:http://sikaile.net/kejilunwen/jisuanjikexuelunwen/2279241.html
最近更新
教材專著