floating-point operation
英 [ˈfləʊtɪŋ pɔɪnt ˌɒpəˈreɪʃn]
美 [ˈfloʊtɪŋ pɔɪnt ˌɑːpəˈreɪʃn]
浮点运算
英英释义
noun
- an arithmetic operation performed on floating-point numbers
- this computer can perform a million flops per second
双语例句
- Rapid Relative Shift Algorithm for Floating-Point Multiple Bytes Square Root of Extraction Operation
快速相对移位法浮点多字节开平方运算 - Logical Design of Hypersurface Neuron for Single-Cycle Floating-Point Arithmetic Operation
单节拍浮点运算神经元的组合逻辑设计 - For precious registration, the regional counting method based on joint-histogram is used for reference to define a global criterion function in statistical gray feature space, thus avoiding heavy floating-point operation while keeping processing precision.
精配准时，借鉴联合直方图区域记数法的思路，在灰度信息的统计特性空间上巧妙定义一种全局准则函数，既能保证精度又摆脱了大量的浮点运算。 - The floating-point multiply-add fused ( MAF) operation treats the multiplication and the addition as an inseparable operation. There is no need to round the internal results, and the precision of the result and FLOP are improved.
浮点乘加融合MAF（Floating-PointMultiply-AddFused）将浮点乘法和加法看成一个不可分割的操作，不对中间结果进行舍入，提高了浮点计算精度和吞吐率。 - We have added new API calls that allow applications to do their own CPU benchmarking, or directly report their floating-point operation count.
我们增加了一些新的API调用，允许计算程序进行自己的CPU测试，或者直接报告它们的浮点操作数目。 - Round toward negative infinity means round the result of a floating-point operation to the representable value nearest to and no greater than the result.
四舍五入到负无限意思是调整浮点运算的结果成最接近结果并且不大于结果的最接近值。 - A logical design method of hypersurface neuron for single-cycle floating-point arithmetic operation is presented.
介绍了通用神经计算机CASSANDRA-中单节拍浮点运算神经元的硬件设计方法。 - Rounding error study of calculator floating-point numbers arithmetic operation
计算机浮点数算术运算的舍入误差研究 - After the simulation, DSP implementation was implemented according to the fixed-point algorithm, and the results of the DSP operation was examined, then comparison between MATLAB floating-point simulation results and the DSP operation results are performed.
在完成仿真以后，根据定点算法进行DSP实现，测试DSP运行的结果，并于与MATLAB浮点仿真的结果进行比对。 - A special algorithm is put forward to calculate in program, it solves the problem about low precision of fixed-point operation and high computation cost and long computation time of floating-point operation.
提出了一种特定算法用于程序中的计算，有效地解决了定点运算精度低和浮点运算计算量大、计算时间长的问题。