floating-point hardware

英 [ˈfləʊtɪŋ pɔɪnt ˈhɑːdweə(r)]

美 [ˈfloʊtɪŋ pɔɪnt ˈhɑːrdwer]

网络浮点硬件

An implementation of a floating-point system conforming to this standard may be realized entirely in software, entirely in hardware, or in any combination of software and hardware.
此规范中的浮点数系统可以通过软件、硬件，或者软硬件相结合的形式来实现。
This algorithm compares the R-D slope value rapidly in the logarithmic domain, which can avoid the floating-point computation that makes it easy for hardware implementation.
在对数域中对率失真斜率进行快速比较，从而避免了斜率浮点模式的运算；
GPU is suited for parallel computing that can be expressed as the problem of parallel computing arithmetic density is very high, and floating-point computing power much higher than the CPU, the same amount of GPU computing hardware cost significantly lower than the CPU cost of hardware.
GPU非常适合处理那些能够表示为并行计算的问题，并行计算的算术计算密度非常高，且浮点运算能力大大超过CPU，相同计算量GPU的硬件成本也大大低于CPU硬件成本。