In this paper, we propose an approximate multiplier that is high speed yet energy efficient. The approach is to round the operands to the nearest exponent of two. This way the computational intensive part of the multiplication is omitted improving speed and energy consumption at the price of a small error. The proposed approach is applicable to both signed and unsigned multiplications. We propose three hardware implementations of the approximate multiplier that includes one for the unsigned and two for the signed operations. The efficiency of the proposed multiplier is evaluated by comparing its performance with those of some approximate and accurate multipliers using different design parameters. In addition, the efficacy of the proposed approximate multiplier is studied in two image processing applications, i.e., image sharpening and smoothing.
25 January 2019 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
A scalable approximate multiplier, called truncation- and rounding-based scalable approximate multiplier (TOSAM) is presented, which reduces the number of partial products by truncating each of the input operands based on their leading one-bit position. In the proposed design, multiplication is performed by shift, add, and small fixed-width multiplication operations resulting in large improvements in the energy consumption and area occupation compared to those of the exact multiplier. To improve the total accuracy, input operands of the multiplication part are rounded to the nearest odd number. Because input operands are truncated based on their leading one-bit positions, the accuracy becomes weakly dependent on the width of the input operands and the multiplier becomes scalable. Higher improvements in design parameters (e.g., area and energy consumption) can be achieved as the input operand widths increase. To evaluate the efficiency of the proposed approximate multiplier, its design parameters are compared with those of an exact multiplier and some other recently proposed approximate multipliers. Results reveal that the proposed approximate multiplier with a mean absolute relative error in the range of 11%-0.3% improves delay, area, and energy consumption up to 41%, 90%, and 98%, respectively, compared to those of the exact multiplier. It also outperforms other approximate multipliers in terms of speed, area, and energy consumption. The proposed approximate multiplier has an almost Gaussian error distribution with a near-zero mean value. We exploit it in the structure of a JPEG encoder, sharpening, and classification applications. The results indicate that the quality degradation of the output is negligible. In addition, we suggest an accuracy configurable TOSAM where the energy consumption of the multiplication operation can be adjusted based on the minimum required accuracy.
16 August 2018 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
In this paper, a reverse carry propagate adder (RCPA) is presented. In the RCPA structure, the carry signal propagates in a counter-flow manner from the most significant bit to the least significant bit; hence, the carry input signal has higher significance than the output carry. This method of carry propagation leads to higher stability in the presence of delay variations. Three implementations of the reverse carry propagate full-adder (RCPFA) cell with different delay, power, energy, and accuracy levels are introduced. The proposed structure may be combined with an exact (forward) carry adder to form hybrid adders with tunable levels of accuracy. The design parameters of the proposed RCPA implementations and some hybrid adders realized utilizing these structures are studied and compared with those of the state-of-the-art approximate adders using HSPICE simulations in a 45-nm CMOS technology. The results indicate that employing the proposed RCPAs in the hybrid adders may provide, on average, 27%, 6%, and 31% improvements in delay, energy, and energy-delay-product while providing higher levels of accuracy. In addition, the structure is more resilient to delay variation compared to the conventional approximate adder. Finally, the efficacy of the proposed RCPAs is investigated in the discrete cosine transform (DCT) block of the JPEG compression and finite-impulse response (FIR) filter applications. The investigation reveals 60% and 39% energy saving in the DCT of JPEG and FIR filter, respectively, for the proposed RCPAs.
22 February 2019 in IEEE Transactions on Circuits and Systems II: Express Briefs
In this article, a technique, based on using Residue Number System (RNS) is suggested to improve the energy efficiency of Deep Neural Networks (DNNs). In the DNN architecture, which is fully RNS-based, only weights and the primary inputs in the main memory are in the binary number system (BNS). The architecture, which is called Res-DNN, offers a high energy saving while requiring higher bit count for data to handle the overflow compared to that of a BNS one. Scaling techniques in the processing elements are employed in the RNS-based computations to make the computation bit widths the same as the BNS bit width. In this architecture, the MAX pooling and ReLU activation function are implemented in the RNS format. To lower the memory usage and required memory bandwidth, we suggest a Huffman-based coding. Additionally, for accessing the weights stored in the main memory, to obtain further energy reduction, we propose a structural modification to the memory hierarchy where a lower level register file is added to the data path of these accesses. The effectiveness of the proposed architecture is evaluated under seven state-of-the-art DNNs with the datasets of ImageNet and CIFAR-10. The obtained results show that Res-DNN leads to $2.5\times $ lower energy for computations and an average of 30% overall energy reduction compared to those of the binary counterpart.
27 August 2019 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems