Brunno Alves de Abreu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Brunno Alves de Abreu has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Sergio Bampi
Graduate Program in Microelectronics (PGMICRO), Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil
9 shared publications - Guilherme Paim
Graduate Program in Microelectronics (PGMICRO), Institute of Informatics (INF), Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, Brazil
8 shared publications - Eduardo Antonio Cesar da Costa
Graduate Program on Electronic Engineering and Computing, Catholic University of Pelotas (UCPel), Pelotas, Brazil
4 shared publications - Mateus Grellert
Informatics Institute, Federal University of Rio Grande Do Sul, Porto Alegre, Brazil
4 shared publications - Hussam Amrouch
Technical University of Munich
3 shared publications - Augusto Berndt
Universidade Federal de Santa Catarina Florianópolis, Santa Catarina, Brasil
2 shared publications
Latest Publications
- 1 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 72 (1) , 180-191
On the Efficacy and Vulnerabilities of Logic Locking in Tree-Based Machine Learning
The popularity and widespread usage of machine learning (ML) hardware have created challenges for its intellectual property (IP) protection. Logic locking is a widely used technique for IP protection but has received little attention in error-resilient applications such as ML hardware modules. This work investigates the effectiveness of logic locking when applied to tree-based ML circuits and reveals a critical vulnerability that undermines its effectiveness for single-label ML classifiers. We propose a logic locking scheme to eliminate the vulnerabilities in decision trees (DTs) and random forests (RFs) circuits. In our extensive simulation involving 16 DTs and 16 RFs, our solution consistently thwarts the vulnerability. We further evaluated the security of our approach by considering different obfuscation percentages and launching state-of-the-art oracle-less attacks on logic locking. Our method proves resilient, indicating that by fixing the identified vulnerability, we did not introduce new attack vectors. Further, our investigation indicates that DT/RF accelerators are significantly less vulnerable to oracle-less attacks compared to exact circuits. Overall, our work lays the foundation for future investigations into the effectiveness of logic locking for ML circuits.
- 1 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 72 (1) , 180-191
On the Efficacy and Vulnerabilities of Logic Locking in Tree-Based Machine Learning
The popularity and widespread usage of machine learning (ML) hardware have created challenges for its intellectual property (IP) protection. Logic locking is a widely used technique for IP protection but has received little attention in error-resilient applications such as ML hardware modules. This work investigates the effectiveness of logic locking when applied to tree-based ML circuits and reveals a critical vulnerability that undermines its effectiveness for single-label ML classifiers. We propose a logic locking scheme to eliminate the vulnerabilities in decision trees (DTs) and random forests (RFs) circuits. In our extensive simulation involving 16 DTs and 16 RFs, our solution consistently thwarts the vulnerability. We further evaluated the security of our approach by considering different obfuscation percentages and launching state-of-the-art oracle-less attacks on logic locking. Our method proves resilient, indicating that by fixing the identified vulnerability, we did not introduce new attack vectors. Further, our investigation indicates that DT/RF accelerators are significantly less vulnerable to oracle-less attacks compared to exact circuits. Overall, our work lays the foundation for future investigations into the effectiveness of logic locking for ML circuits.
- 6 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 13 (1) , 86-95
Compact CMOS-Compatible Majority Gate Using Body Biasing in FDSOI Technology
This is the first work that employs the body biasing feature, available in fully depleted silicon on insulator (FDSOI) technology nodes, to build CMOS-compatible compact majority (MAJ) and minority (MIN) logic gates. Compared to their CMOS counterpart, our novel MAJ/MIN gates exhibit considerably fewer transistors, 2.3x and 2x, respectively. The use of MAJ/MIN gates for logic synthesis has been widely investigated in the literature since any function can be realized using only these two gates. Nevertheless, the use of MAJ/MIN gates to synthesize circuits remained very limited because such gates are area hungry when implemented using conventional standard cells. Therefore, state-of-the-art research in the last decade has extensively focused on exploring beyond-CMOS technologies to build alternative MAJ/MIN gates. However, such emerging technologies are still immature and suffering considerably from variability. On the other hand, our novel FDSOI-based MAJ/MIN gates are based on mature CMOS commercial technologies. Our analysis of the proposed gates has been conducted using accurate SPICE simulations with an industry-compact transistor model, BSIM-IMG, calibrated for an industrial 14nm FDSOI technology. Using our developed MAJ/MIN synthesis and error injection framework called MAJinBoo, we demonstrate that MAJ/MIN-based circuits exhibit an outstanding resiliency against errors due to the inherent voting-based computing. This encourages the employment of our MAJ/MIN gates in safety-critical applications where reliability is a prime concern. Our MAJinBoo framework is available at https://github.com/Brunno815/MAJinBoo.
- 6 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 13 (1) , 86-95
Compact CMOS-Compatible Majority Gate Using Body Biasing in FDSOI Technology
This is the first work that employs the body biasing feature, available in fully depleted silicon on insulator (FDSOI) technology nodes, to build CMOS-compatible compact majority (MAJ) and minority (MIN) logic gates. Compared to their CMOS counterpart, our novel MAJ/MIN gates exhibit considerably fewer transistors, 2.3x and 2x, respectively. The use of MAJ/MIN gates for logic synthesis has been widely investigated in the literature since any function can be realized using only these two gates. Nevertheless, the use of MAJ/MIN gates to synthesize circuits remained very limited because such gates are area hungry when implemented using conventional standard cells. Therefore, state-of-the-art research in the last decade has extensively focused on exploring beyond-CMOS technologies to build alternative MAJ/MIN gates. However, such emerging technologies are still immature and suffering considerably from variability. On the other hand, our novel FDSOI-based MAJ/MIN gates are based on mature CMOS commercial technologies. Our analysis of the proposed gates has been conducted using accurate SPICE simulations with an industry-compact transistor model, BSIM-IMG, calibrated for an industrial 14nm FDSOI technology. Using our developed MAJ/MIN synthesis and error injection framework called MAJinBoo, we demonstrate that MAJ/MIN-based circuits exhibit an outstanding resiliency against errors due to the inherent voting-based computing. This encourages the employment of our MAJ/MIN gates in safety-critical applications where reliability is a prime concern. Our MAJinBoo framework is available at https://github.com/Brunno815/MAJinBoo.
- 3 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 71 (11) , 4748-4752
MAxPy: A Framework for Bridging Approximate Computing Circuits to Its Applications
This brief presents MAxPy, a framework for bridging approximate computing (AxC) circuit design to its applications. MAxPy is an application-agnostic framework able to automatically build a cycle-accurate Python model of an approximate hardware design. This model can easily be emulated and integrated as a module in Python-based applications. We are herein proposing this framework aiming to build an AxC toolbox stimulating open research in academia to promote the integration of the existing and future open-source (i) AxC benchmarks, (ii) approximate logic synthesis tools, and (iii) approximate arithmetic unit insights. In this brief, we demonstrate the use of MAxPy to explore the AxC design space of a Sobel filter hardware design as a case study exploiting a set of approximate adders combined with the data-driven approximate logic synthesis via probabilistic pruning. Then, we present a Pareto front for circuit area, energy, and delay reduction versus the application-level metrics: edge detection accuracy and structural similarity index (SSIM). The Pareto front results of the multiple AxC techniques herein explored show circuit area savings ranging from 40.4% to 59.1% for a 98.1% to 99.6% accuracy on edge detection application. MAxPy code is open source in: github.com/MAxPy-Project.
- 3 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 71 (11) , 4748-4752
MAxPy: A Framework for Bridging Approximate Computing Circuits to Its Applications
This brief presents MAxPy, a framework for bridging approximate computing (AxC) circuit design to its applications. MAxPy is an application-agnostic framework able to automatically build a cycle-accurate Python model of an approximate hardware design. This model can easily be emulated and integrated as a module in Python-based applications. We are herein proposing this framework aiming to build an AxC toolbox stimulating open research in academia to promote the integration of the existing and future open-source (i) AxC benchmarks, (ii) approximate logic synthesis tools, and (iii) approximate arithmetic unit insights. In this brief, we demonstrate the use of MAxPy to explore the AxC design space of a Sobel filter hardware design as a case study exploiting a set of approximate adders combined with the data-driven approximate logic synthesis via probabilistic pruning. Then, we present a Pareto front for circuit area, energy, and delay reduction versus the application-level metrics: edge detection accuracy and structural similarity index (SSIM). The Pareto front results of the multiple AxC techniques herein explored show circuit area savings ranging from 40.4% to 59.1% for a 98.1% to 99.6% accuracy on edge detection application. MAxPy code is open source in: github.com/MAxPy-Project.
- 28 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 69 (11) , 4524-4534
Energy-Quality Scalable Design Space Exploration of Approximate FFT Hardware Architectures
This paper presents a comprehensive design space exploration for boosting energy efficiency of a fast Fourier transform (FFT) VLSI accelerator, exploiting several approximate multipliers (AxM) combined with approximate adder (AxA) circuits. The FFT hardware herein presented consists of a fixed-point sequential architecture using a radix-2 butterfly with decimation in time. We explore a set of AxMs – namely Dynamic Range Unbiased (DRUM), Rounding-based Approximate (RoBA), leading one Bit-based Approximate (LoBA), and Truncated approach – jointly with the LOA, ETA-I, CopyA, CopyB, Trunc0, Trunc1 approximate adders. The approximate arithmetic operators are used in the butterfly kernel with exploration of the approximation levels (for the ${L}$ and ${K}$ least-significant bits, respectively, for the AxM and AxA), aiming at discovering the most energy-efficient configuration under a design-time QoR constraint. The mean square error and peak signal-to-noise ratio metrics define which approximate levels combining ${L}$ and ${K}$ variations will enable the FFT to process signals to generate spectrograms without significant losses. Our results show that the LoBA multiplier with $L$ =8 together with the LOA, Trunc1 and Trunc0, at different approximation levels, provide most energy savings with controllable quality degradation, presenting a minimum decrease of 20.2% in power dissipation without degrading the spectrogram generation quality.
- 28 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 69 (11) , 4524-4534
Energy-Quality Scalable Design Space Exploration of Approximate FFT Hardware Architectures
This paper presents a comprehensive design space exploration for boosting energy efficiency of a fast Fourier transform (FFT) VLSI accelerator, exploiting several approximate multipliers (AxM) combined with approximate adder (AxA) circuits. The FFT hardware herein presented consists of a fixed-point sequential architecture using a radix-2 butterfly with decimation in time. We explore a set of AxMs – namely Dynamic Range Unbiased (DRUM), Rounding-based Approximate (RoBA), leading one Bit-based Approximate (LoBA), and Truncated approach – jointly with the LOA, ETA-I, CopyA, CopyB, Trunc0, Trunc1 approximate adders. The approximate arithmetic operators are used in the butterfly kernel with exploration of the approximation levels (for the ${L}$ and ${K}$ least-significant bits, respectively, for the AxM and AxA), aiming at discovering the most energy-efficient configuration under a design-time QoR constraint. The mean square error and peak signal-to-noise ratio metrics define which approximate levels combining ${L}$ and ${K}$ variations will enable the FFT to process signals to generate spectrograms without significant losses. Our results show that the LoBA multiplier with $L$ =8 together with the LOA, Trunc1 and Trunc0, at different approximation levels, provide most energy savings with controllable quality degradation, presenting a minimum decrease of 20.2% in power dissipation without degrading the spectrogram generation quality.
- 27 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 69 (7) , 2683-2693
C2PAx: Complexity-Aware Constant Parameter Approximation for Energy-Efficient Tree-Based Machine Learning Accelerators
Tree-based machine learning models, like random forests and decision trees, are low-complexity solutions that provide an efficient prediction for a wide range of applications. These models are particularly interesting for energy-constrained platforms since they can be implemented with simple logical operations. Tree-based accelerators are also intrinsically resilient to errors, and this can be leveraged to boost energy efficiency with approximate computing techniques. The key operations in these models are comparisons to constants, making comparators excellent candidates for approximation. This paper presents a technique to approximate comparisons to constants called C2PAx, which is capable of reducing the area and energy of tree-based accelerators. The method consists in finding alternative constants that reduce circuit area while keeping an efficient prediction performance. It is also shown that the selection of the constant parameters directly influences both hardware complexity and model performance, demanding cross-layer optimization. For that, we extend an existing framework that generates VLSI tree-based accelerators, inserting our approximation proposal that allows selecting the constant parameters that maximize energy efficiency at the cost of minor accuracy drops. Simulation results demonstrate that C2PAx outperforms the Don’t Care logic approximation technique when accuracy and energy are jointly considered. C2PAx trades accuracy for significant reductions in the VLSI area, power, delay, and energy consumption compared to precise models.
- 27 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 69 (7) , 2683-2693
C2PAx: Complexity-Aware Constant Parameter Approximation for Energy-Efficient Tree-Based Machine Learning Accelerators
Tree-based machine learning models, like random forests and decision trees, are low-complexity solutions that provide an efficient prediction for a wide range of applications. These models are particularly interesting for energy-constrained platforms since they can be implemented with simple logical operations. Tree-based accelerators are also intrinsically resilient to errors, and this can be leveraged to boost energy efficiency with approximate computing techniques. The key operations in these models are comparisons to constants, making comparators excellent candidates for approximation. This paper presents a technique to approximate comparisons to constants called C2PAx, which is capable of reducing the area and energy of tree-based accelerators. The method consists in finding alternative constants that reduce circuit area while keeping an efficient prediction performance. It is also shown that the selection of the constant parameters directly influences both hardware complexity and model performance, demanding cross-layer optimization. For that, we extend an existing framework that generates VLSI tree-based accelerators, inserting our approximation proposal that allows selecting the constant parameters that maximize energy efficiency at the cost of minor accuracy drops. Simulation results demonstrate that C2PAx outperforms the Don’t Care logic approximation technique when accuracy and energy are jointly considered. C2PAx trades accuracy for significant reductions in the VLSI area, power, delay, and energy consumption compared to precise models.
- 16 September 2021
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 41 (3) , 1577-1595
The 4-2 Fused Adder–Subtractor Compressor for Low-Power Butterfly-Based Hardware Architectures
- 16 September 2021
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 41 (3) , 1577-1595
The 4-2 Fused Adder–Subtractor Compressor for Low-Power Butterfly-Based Hardware Architectures
- 23 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Accuracy and Size Trade-off of a Cartesian Genetic Programming Flow for Logic Optimization
Logic synthesis tools face tough challenges when providing algorithms for synthesizing circuits with increased inputs and complexity. Traditional approaches for logic synthesis have been in the spotlight so far. However, due to advances in machine learning and their high performance in solving specific problems, such algorithms appear as an attractive option to improve electronic design tools. In our work, we explore Cartesian Genetic Programming for logic optimization of exact or approximate combinational circuits. The proposed CGP flow receives input from the circuit description in the format of AND-Inverter Graphs and its expected behavior as a truth-table. The CGP may improve solutions found by other techniques used for bootstrapping the evolutionary process or initialize the search from random (unbiased) individuals seeking optimal circuits. We propose two different evaluation methods for the CGP: to minimize the number of AIG nodes or optimize the circuit accuracy. We obtain at least 22.6% superior results when considering the ratio between accuracy and size for the benchmarks used, compared with the teams from the IWLS 2020 contest that obtained the best accuracy and size results. It is noteworthy that any logic synthesis approach based on AIGs can easily incorporate the proposed flow. The results obtained show that their usage may achieve improved logic circuits.
- 23 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Accuracy and Size Trade-off of a Cartesian Genetic Programming Flow for Logic Optimization
Logic synthesis tools face tough challenges when providing algorithms for synthesizing circuits with increased inputs and complexity. Traditional approaches for logic synthesis have been in the spotlight so far. However, due to advances in machine learning and their high performance in solving specific problems, such algorithms appear as an attractive option to improve electronic design tools. In our work, we explore Cartesian Genetic Programming for logic optimization of exact or approximate combinational circuits. The proposed CGP flow receives input from the circuit description in the format of AND-Inverter Graphs and its expected behavior as a truth-table. The CGP may improve solutions found by other techniques used for bootstrapping the evolutionary process or initialize the search from random (unbiased) individuals seeking optimal circuits. We propose two different evaluation methods for the CGP: to minimize the number of AIG nodes or optimize the circuit accuracy. We obtain at least 22.6% superior results when considering the ratio between accuracy and size for the benchmarks used, compared with the teams from the IWLS 2020 contest that obtained the best accuracy and size results. It is noteworthy that any logic synthesis approach based on AIGs can easily incorporate the proposed flow. The results obtained show that their usage may achieve improved logic circuits.
- Open Access
- 1 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1026-1031
Logic Synthesis Meets Machine Learning: Trading Exactness for Generalization
Logic synthesis is a fundamental step in hardware design whose goal is to find structural representations of Boolean functions while minimizing delay and area. If the function is completely-specified, the implementation accurately represents the function. If the function is incompletely-specified, the implementation has to be true only on the care set. While most of the algorithms in logic synthesis rely on SAT and Boolean methods to exactly implement the care set, we investigate learning in logic synthesis, attempting to trade exactness for generalization. This work is directly related to machine learning where the care set is the training set and the implementation is expected to generalize on a validation set. We present learning incompletely-specified functions based on the results of a competition conducted at IWLS 2020. The goal of the competition was to implement 100 functions given by a set of care minterms for training, while testing the implementation using a set of validation minterms sampled from the same function. We make this benchmark suite available and offer a detailed comparative analysis of the different approaches to learning.
- 1 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1026-1031
Open AccessLogic Synthesis Meets Machine Learning: Trading Exactness for Generalization
Logic synthesis is a fundamental step in hardware design whose goal is to find structural representations of Boolean functions while minimizing delay and area. If the function is completely-specified, the implementation accurately represents the function. If the function is incompletely-specified, the implementation has to be true only on the care set. While most of the algorithms in logic synthesis rely on SAT and Boolean methods to exactly implement the care set, we investigate learning in logic synthesis, attempting to trade exactness for generalization. This work is directly related to machine learning where the care set is the training set and the implementation is expected to generalize on a validation set. We present learning incompletely-specified functions based on the results of a competition conducted at IWLS 2020. The goal of the competition was to implement 100 functions given by a set of care minterms for training, while testing the implementation using a set of validation minterms sampled from the same function. We make this benchmark suite available and offer a detailed comparative analysis of the different approaches to learning.
- 12 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 71 (2) , 349-363
A Framework for Crossing Temperature-Induced Timing Errors Underlying Hardware Accelerators to the Algorithm and Application Layers
Temperature rising is an unavoidable effect on VLSI and has always been a critical issue in any system-on-chip – especially when targeting compute-intensive applications. This effect increases the delay in hardware accelerators, resulting in timing errors due to unsustainable clock frequency, whose impact must be carefully evaluated on design time to measure the performance degradation of the hardware accelerator. Further, a hardware operating at a higher temperature accelerates device aging, which incurs in more timing errors. This issue is usually addressed with the inclusion of timing guardbands that compensate for the deleterious effects of temperature, ensuring the hardware accelerator works within a reliable zone, i.e., without any timing errors caused by temperature effects at runtime. However, guardbands directly result in considerable performance and efficiency losses because the circuit will be clocked at a frequency lower than its full potential. Accelerators on edge devices often dismiss such guardbands to explore the full potential of the designed circuits, posing an enormous design challenge as this approach requires a careful evaluation of the impact of timing errors on the quality of the target applications. Many algorithms, such as in multimedia and machine learning applications, are capable of tolerating hardware errors. Yet, these algorithms have a dynamic behavior (i.e., closed-loop) where a timing error can be propagated, affecting subsequent steps. Measuring the degradation-induced errors in these applications is very challenging given that an accurate gate-level simulation to investigate degradation-induced timing errors needs to be coupled dynamically with a system-level simulator to unveil how induced errors in the underlying hardware ultimately impact the algorithm execution in the hardware accelerator. This is the first work to achieve this goal. State-of-the-art works have studied accelerators under timing-errors when removing (or narrowing) guardbands. However, their approach was suitable only for open-loop hardware accelerators which are entirely agnostic of complex interactions of the algorithms. Unlike prior work, this paper investigates temperature- and aging-induced timing-errors in the joint accelerator-algorithm interactions and their runtime impacts. Our framework investigates aging effects across the different layers starting from transistor physics all the way up to the algorithm layer. The hardware accelerator employed as a case study in this work is the sum of absolute differences (SAD), which is the most compute-intensive accelerator on commercial video encoder for mobile applications. Our results demonstrate the runtime behavior impacts of three advanced block-matching algorithms of the video encoder in a joint operation by a SAD accelerator under timing-errors induced by temperature and aging effects considering a 14nm FinFET technology.
- 12 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 71 (2) , 349-363
A Framework for Crossing Temperature-Induced Timing Errors Underlying Hardware Accelerators to the Algorithm and Application Layers
Temperature rising is an unavoidable effect on VLSI and has always been a critical issue in any system-on-chip – especially when targeting compute-intensive applications. This effect increases the delay in hardware accelerators, resulting in timing errors due to unsustainable clock frequency, whose impact must be carefully evaluated on design time to measure the performance degradation of the hardware accelerator. Further, a hardware operating at a higher temperature accelerates device aging, which incurs in more timing errors. This issue is usually addressed with the inclusion of timing guardbands that compensate for the deleterious effects of temperature, ensuring the hardware accelerator works within a reliable zone, i.e., without any timing errors caused by temperature effects at runtime. However, guardbands directly result in considerable performance and efficiency losses because the circuit will be clocked at a frequency lower than its full potential. Accelerators on edge devices often dismiss such guardbands to explore the full potential of the designed circuits, posing an enormous design challenge as this approach requires a careful evaluation of the impact of timing errors on the quality of the target applications. Many algorithms, such as in multimedia and machine learning applications, are capable of tolerating hardware errors. Yet, these algorithms have a dynamic behavior (i.e., closed-loop) where a timing error can be propagated, affecting subsequent steps. Measuring the degradation-induced errors in these applications is very challenging given that an accurate gate-level simulation to investigate degradation-induced timing errors needs to be coupled dynamically with a system-level simulator to unveil how induced errors in the underlying hardware ultimately impact the algorithm execution in the hardware accelerator. This is the first work to achieve this goal. State-of-the-art works have studied accelerators under timing-errors when removing (or narrowing) guardbands. However, their approach was suitable only for open-loop hardware accelerators which are entirely agnostic of complex interactions of the algorithms. Unlike prior work, this paper investigates temperature- and aging-induced timing-errors in the joint accelerator-algorithm interactions and their runtime impacts. Our framework investigates aging effects across the different layers starting from transistor physics all the way up to the algorithm layer. The hardware accelerator employed as a case study in this work is the sum of absolute differences (SAD), which is the most compute-intensive accelerator on commercial video encoder for mobile applications. Our results demonstrate the runtime behavior impacts of three advanced block-matching algorithms of the video encoder in a joint operation by a SAD accelerator under timing-errors induced by temperature and aging effects considering a 14nm FinFET technology.
- Open Access
- 26 May 2020
- Published by Journal of Integrated Circuits and Systems in Journal of Integrated Circuits and Systems
- Vol. 15 (1) , 1-9
Exploring Absolute Differences Arithmetic Operators for Power and Area-Efficient SAD Hardware Architectures
Managing the energy requirements of video encoders has been an important research topic throughout the latest years, given the limited resources of battery-powered systems. Sum of Absolute Differences (SAD) stands out among the most costly steps in the video encoding process compliant with the High Efficiency Video Coding (HEVC) standard. This metric is mainly used to explore temporal redundancies during the inter prediction stage of the encoder, and it is applied by adding the absolute differences of the colocalized pixels of two video blocks, as a means of measuring the similarity between them. SAD architectures are usually designed by using an adder tree, with its first level consisting of subtractors and absolute operators. This paper explores various structures of absolute operators in the context of SAD architectures, in order to define the most suitable implementation for a power-efficient SAD module. Besides the analysis of several different models, we exploit the use of pipelining, and the impact of varying block input bitwidth, to determine which versions scale better with the increase of input size. We have synthesized the architectures for ASIC CMOS technology using real-input vectors taking the delays into consideration, with an ST 65 nm standard cells library, and compared them with the default absolute operator macrofunction from the synthesis tool.
- 26 May 2020
- Published by Journal of Integrated Circuits and Systems in Journal of Integrated Circuits and Systems
- Vol. 15 (1) , 1-9
Open AccessExploring Absolute Differences Arithmetic Operators for Power and Area-Efficient SAD Hardware Architectures
Managing the energy requirements of video encoders has been an important research topic throughout the latest years, given the limited resources of battery-powered systems. Sum of Absolute Differences (SAD) stands out among the most costly steps in the video encoding process compliant with the High Efficiency Video Coding (HEVC) standard. This metric is mainly used to explore temporal redundancies during the inter prediction stage of the encoder, and it is applied by adding the absolute differences of the colocalized pixels of two video blocks, as a means of measuring the similarity between them. SAD architectures are usually designed by using an adder tree, with its first level consisting of subtractors and absolute operators. This paper explores various structures of absolute operators in the context of SAD architectures, in order to define the most suitable implementation for a power-efficient SAD module. Besides the analysis of several different models, we exploit the use of pipelining, and the impact of varying block input bitwidth, to determine which versions scale better with the increase of input size. We have synthesized the architectures for ASIC CMOS technology using real-input vectors taking the delays into consideration, with an ST 65 nm standard cells library, and compared them with the default absolute operator macrofunction from the synthesis tool.