floating-point


Also found in: Encyclopedia, Wikipedia.

float·ing-point

(flō′tĭng-point′)
adj.
Of, relating to, or being a method of writing numeric quantities with a mantissa representing the value of the digits and a characteristic indicating the power of the number base, such as 3 × 10-5.
American Heritage® Dictionary of the English Language, Fifth Edition. Copyright © 2016 by Houghton Mifflin Harcourt Publishing Company. Published by Houghton Mifflin Harcourt Publishing Company. All rights reserved.
References in periodicals archive ?
Current generation DNNs, such as AlexNet and VGG, rely on dense floating-point matrix multiplication (GEMM) which maps well to the capabilities of GPUs, with their regular parallelism and high Tflops.
Block-floating point (BFP) arithmetic is a way of emulating floating-point arithmetic by using fixed-point.
Fractional or floating-point arithmetic is one of the key areas in adaptive filters, dealing not with the filter coefficients in factional values but also the intermediate arithmetic operations.
Additionally, we often need a mathematic modeling method to analyze a patient's health data, which may utilize complex functions taking floating-point numbers as input.
The Arria 10 SoCs offer a processor with rich feature set of embedded peripherals, hardened floating-point variable-precision digital signal processing blocks, high-speed transceivers, hard memory controllers, Secure boot capability, using Elliptic Curve Digital Signature Algorithm and Advanced Encryption Standard, and protocol intellectual property controllers all in a single highly integrated package.
The integrated digital signal processing engine and floating-point core of the processor enable a multitude of high performance applications, such as signal conditioning and sensor processing, while maintaining performance headroom for product differentiation.
Compatible with the Vision P5 DSP, this newest vision DSP offers an optional 32-way SIMD vector floating-point unit that includes the IEEE half precision standard (FP16).
Powered by a dual-core CPU with a floating-point unit (FPU), the two-bay NAS is designed for home and personal users.
The prototype of this new supercomputer will show performance at 10 to 18 degrees of computational floating-point operations per second.
A quadruple precision and dual double precision floating-point multiplier, in Proceeding of the Euromicro Symposium on Digital System Design, 76-81.
M.: FFT Implementation with Fused Floating-Point Operations.

Full browser ?