| 1. |
- Chen, Hui, et al.
(författare)
-
An Efficient Hardware Architecture with Adjustable Precision and Extensible Range to Implement Sigmoid and Tanh Functions
- 2020
-
Ingår i: Electronics. - : MDPI. - 2079-9292. ; 9:10
-
Tidskriftsartikel (refereegranskat)abstract
- The efficient and precise hardware implementations of tanh and sigmoid functions play an important role in various neural network algorithms. Different applications have different requirements for accuracy. However, it is difficult for traditional methods to achieve adjustable precision. Therefore, we propose an efficient-hardware, adjustable-precision and high-speed architecture to implement them for the first time. Firstly, we present two methods to implement sigmoid and tanh functions. One is based on the rotation mode of hyperbolic CORDIC and the vector mode of linear CORDIC (called RHC-VLC), another is based on the carry-save method and the vector mode of linear CORDIC (called CSM-VLC). We validate the two methods by MATLAB and RTL implementations. Synthesized under the TSMC 40 nm CMOS technology, we find that a special case AR divide VR(3,0), based on RHC-VLC method, has the area of 4290.98 mu m2 and the power of 1.69 mW at the frequency of 1.5 GHz. However, under the same frequency, AR divide VC(3) (a special case based on CSM-VLC method) costs 3196.36 mu m2 area and 1.38 mW power. They are both superior to existing methods for implementing such an architecture with adjustable precision.
|
|
| 2. |
- Chen, Hui, et al.
(författare)
-
Symmetric-Mapping LUT-Based Method and Architecture for Computing X-Y-Like Functions
- 2021
-
Ingår i: IEEE Transactions on Circuits and Systems Part 1. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 1549-8328 .- 1558-0806. ; 68:3, s. 1231-1244
-
Tidskriftsartikel (refereegranskat)abstract
- We propose a new method and hardware architecture to compute the functions expressed as XY ( X and Y are arbitrary floating-point numbers), which can support arbitrary Nth root, exponential and power operations. Because of the complexity of direct computation, we usually convert it to logarithm, multiplication, and antilogarithm operations. Traditional approaches suffer from long latency, large area and high power consumption. To solve this problem, we propose a symmetric-mapping lookup table (SM-LUT) to be capable of computing log(2) x (x is an element of [1, 2]) and 2 x (x is an element of [0, 1]) simultaneously. It lays the foundation for computing XY. To further improve hardware performance of our architecture, we propose a multi-region address searcher to speed up the calculation of SM-LUT. In addition, we use an optimized Vedic multiplier to shorten the critical path and improve the efficiency of multiplication, which is included in computing X-Y. Under the TSMC 40nm CMOS technology, we design and synthesize a reference circuit to compute X-Y with a maximum relative error of 10(-3). The report shows that the reference circuit achieves the area of 14338.50 mu m(2) and the power consumption of 4.59 mW at the frequency of 1 GHz. In comparison with the state-of-the-art work under the same input range and similar precision, it saves 78.57% area and 80.42% power consumption for (N)root R computation and 82.89% area and 81.89% power consumption for R-N computation averagely. On top of that, our architecture reduces the computation latency by 62.77% averagely and has one more order of magnitude of energy efficiency than others.
|
|
| 3. |
- He, Kun, et al.
(författare)
-
Experimental study on flame characteristics of double fires in a naturally ventilated tunnel : Flame merging, flame tilt angle and flame height
- 2021
-
Ingår i: Tunnelling and Underground Space Technology. - : Elsevier Ltd. - 0886-7798 .- 1878-4364. ; 114
-
Tidskriftsartikel (refereegranskat)abstract
- A series of fire tests was carried out to investigate the diffusion flame characteristics of double fires generated from separated burners in a naturally ventilated tunnel, considering different heat release rates and fire separation distances. The results show that the flame tilt angle, as well as the horizontal projected flame length, first increases with fire separation distance and then remains constant, but the vertical flame length first decreases and then remains constant, which is different from two fires in free spaces where flames do not tilt when the separation distance is relatively long. This difference is caused by the non-dimensional fire induced air flow velocity in the tunnel, which is mainly related to the tunnel cross-section dimensions and burner radius. Three regions can be identified, i.e. flame vertical merging, plume vertical merging and non-merging with flame tilted. The critical flame merging separation distance, estimated by the flame merging probability, is greater than that of two fires in an open environment due to the fire-induced air flows. The merging flame height is lower than that of a single fire with a same heat release rate. A correlation was proposed to estimate flame height of two fires in a tunnel by the modified non-dimensional heat release rate using an air entrainment perimeter as the characteristic length. This work enhances the understanding of diffusion flame behaviors of double fires in naturally ventilated tunnels.
|
|
