{"title":"Methodologies of Loop Offset voltage Trimming for Inverting-Buck-Boost for AMOLED Display Application","authors":"Venkatesh Kadlimatti, Sumit Bhat","doi":"10.1109/MOCAST49295.2020.9200259","DOIUrl":"https://doi.org/10.1109/MOCAST49295.2020.9200259","url":null,"abstract":"Methodologies of loop offset voltage trimming are presented in this paper for an inverting-Buck-Boost (IBB) having a wide output voltage (VNEG) range (-0.9V to -5.3V) used in an AMOLED display driver. Furthermore, the circuit is proposed and analyzed to meet the brightness control requirement of the AMOLED display. The error contribution from each sub-blocks of the brightness control circuit to VNEG is noted, and efficient ways of trimming the output voltage are analyzed. Achieving 0.3% of trimmed accuracy becomes challenging with the optimum number of trim bits as the magnitude of VNEG voltage reduces. Three different ways of trimming the VNEG, namely; three-step trimming, two-point trimming, and three-point trimming, are proposed and compared in terms of complexity and accuracy. The proposed methodologies of trimming are implemented for Inverting-Buck-Boost in BCD-180nm technology. Three-step trimming uses 17 bits (5-6-6 bits) resistor trimming and has the worst accuracy of $pm 0.17%$ across VNEG. Two-point trimming uses 11 bits (6-5 bits) and has the worst accuracy of $pm 0.3%$, whereas the three-point trimming uses only 14bits (6-4-4 bits) and has the worst accuracy of $pm 0.21%$.","PeriodicalId":444899,"journal":{"name":"2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125927072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A novel Approach for Extending the Bandwidth Limitation of Tracking-ADCs","authors":"O. Bachmann, K. Hofmann","doi":"10.1109/MOCAST49295.2020.9200297","DOIUrl":"https://doi.org/10.1109/MOCAST49295.2020.9200297","url":null,"abstract":"A method for extending the bandwidth limitation of tracking ADCs is presented. It takes advantage of the conventional tracking approach regarding conversion speed. The proposed concept of generating reference steps improves the traditional tracking limits of the input signal slope. MATLAB evaluations of an ideal tracking ADC demonstrate the ability of the novel approach to extend the bandwidth. An implementation in a 65nm process demonstrates the applicability. Verification by post layout simulation results offer an effective resolution of 6.47bit at a sampling rate of 323MS/s while consuming a power of 2.8mW. Nonlinearity caused by internal mismatch or PVT variations can be compensated with an correction system. Compared to state-of-the-art SAR ADCs the proposed ADC matches the characteristics and advances the limitations of the conventional tracking ADC. A 94% digital implementation by standard cells and the ability to digital compensate nonlinearity demonstrate the excellent scalability with technology.","PeriodicalId":444899,"journal":{"name":"2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123230262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Johannes Knödtel, Markus Fritscher, Daniel Reiser, D. Fey, M. Breiling, M. Reichenbach
{"title":"A Model-to-Circuit Compiler for Evaluation of DNN Accelerators based on Systolic Arrays and Multibit Emerging Memories","authors":"Johannes Knödtel, Markus Fritscher, Daniel Reiser, D. Fey, M. Breiling, M. Reichenbach","doi":"10.1109/MOCAST49295.2020.9200241","DOIUrl":"https://doi.org/10.1109/MOCAST49295.2020.9200241","url":null,"abstract":"With the emergence of DNN accelerators the main focus of such systems usually lies on utilizing local memories and reducing the size of the processed data, since delay and energy consumption are dominated by data transfer. Utilizig emerging memory technologies, such as ReRAMs, these goals might be attained much easier, due to advantageous non-functional and functional properties.One of the key drawbacks of such systems are reliability and variability of devices of such technologies. To certain degree, DNNs are resilient to soft and hard errors in their memory cells, so these issues might be surmountable depending on the device properties, but eludes trivial analyses known from the digital domain. Here the dynamic behavior of the devices comes into play and must be simulated in order to get a decent degree of confidence on the reliability of the hardware and therefore also yield.In order to tackle this issue we present an accelerator architecture and matching analysis pipeline that allows the user to specify and train a net topology and then test the design against some input activations with different randomized device properties. Using this approach we can estimate the inference results and other system and algorithm level properties in presence of different device level properties which might for example be extracted from real world measurements. Such a system can help the user in the design of their net or give them hints on the required device properties for a given net or aid them in evaluating existing designs.","PeriodicalId":444899,"journal":{"name":"2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116090730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lukas Gerlach, Fabian Stuckmann, H. Blume, G. P. Vayá
{"title":"Issue-Slot Based Predication Encoding Technique for VLIW Processors","authors":"Lukas Gerlach, Fabian Stuckmann, H. Blume, G. P. Vayá","doi":"10.1109/MOCAST49295.2020.9200304","DOIUrl":"https://doi.org/10.1109/MOCAST49295.2020.9200304","url":null,"abstract":"Predication is a well-known alternative to conditional branching. However, the implementation of predication is costly in terms of extending the instruction set of the processor architecture. In this paper, a predication encoding technique for VLIW processors is proposed. Instead of using additional bits in the instruction encoding, the assigned issue-slot of a conditionally executed instruction encodes the associated predicate register. The number of addressable predicate registers scales with the number of issue-slots. All predicate registers have only one read and write port and can be accessed in parallel. Compared to the related work, no additional instruction encoding bits for selecting a predicate register are required and the processor core area increases only by about 1% per predicate register set. With the proposed predication technique, the processing performance increases by up to 4.5% when using two instead of one predicate register for a digital filter case study with floating-point emulation operations. A second case study shows, that conditional execution with two predicate register in combination with loop unrolling and operation merging almost doubles the achieved parallel instructions per cycle for a bit-reversal permutation algorithm.","PeriodicalId":444899,"journal":{"name":"2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129622702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"ReRAM-based Ratioed Combinational Circuit Design: a Solution for in-Memory Computing","authors":"C. Fernandez, I. Vourkas","doi":"10.1109/MOCAST49295.2020.9200279","DOIUrl":"https://doi.org/10.1109/MOCAST49295.2020.9200279","url":null,"abstract":"While the von Neumann architecture played a leading role in CMOS-based computing systems for several decades, nowadays in-memory computing is an alternative approach being pursued, with resistive switching devices (memristors) in crossbar arrays considered as the enabling technology. In this context, this paper provides a practical solution for a viable in-memory computing architecture within the reach of today’s technology, through a variability-tolerant ReRAM-based ratioed combinational logic design scheme, inspired on the pseudo-NMOS logic design. The reason we focus on this scheme is because it is simple, crossbar-compatible, completely tolerant to variability, compatible with either filamentary or interfacial switching type devices, and it does not affect the memristor endurance. We highlight all the important characteristics and advantages offered by this scheme, compared to other stateful logic schemes based on memristors, such as IMPLY and MAGIC. We conclude this paper presenting SPICEbased circuit simulation results concerning a 1-bit full adder implementation and show that our proposed ratioed logic design outperforms the rest in terms of speed and area requirements.","PeriodicalId":444899,"journal":{"name":"2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114795565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Nonlinear pitch control of a large scale wind turbine by considering aerodynamic behavior of wind","authors":"Farshad Golnary, H. Moradi","doi":"10.1109/MOCAST49295.2020.9200303","DOIUrl":"https://doi.org/10.1109/MOCAST49295.2020.9200303","url":null,"abstract":"In this research, nonlinear sliding mode pitch control of a wind turbine has been investigated by considering aerodynamic nonlinearities. For modeling aerodynamic interaction between the wind and the drive-train system, blade element momentum theory is used by considering Prandtl’s tip loss factor and Glaurt correction. Finally, the two-degrees of freedom model of the drive-train is extracted and the sliding mode approach is examined for regulating the output power into its nominal value by controlling the pitch angle. The implementation of the above proposed control law in its related electronic circuit of the wind turbine will be considered as the future stage of the current research.","PeriodicalId":444899,"journal":{"name":"2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132071682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"FPGA Implementation of High-Speed Data Acquisition System for High-Resolution Millimeter Wave Radar","authors":"Yaping Xie, Qiangwen Zheng, Junjie Li, Lijie Yang, Chunyi Song, Zhiwei Xu","doi":"10.1109/MOCAST49295.2020.9200252","DOIUrl":"https://doi.org/10.1109/MOCAST49295.2020.9200252","url":null,"abstract":"This paper introduces FPGA implementation of high-speed data acquisition system for high-resolution millimeter wave radar. The transfer bandwidth of the Low Voltage Differential Signaling (LVDS) interface of the high-speed data acquisition system is 7200Mbps, which supports the cascade of four millimeter-wave radar sensors. The maximum transfer bandwidth of the DDR3 interface in the system is 12800Mbps, which is able to support high-bandwidth sample data storage of twelve millimeter-wave radar sensors. The maximum transfer bandwidth of Gigabit Ethernet interface in the system is 1000Mbps, which can adjust the transfer rate according to the system requirements, with good scalability. By using the high-speed data acquisition system designed in the article for the cascade of four high resolution 77GHz FMCW millimeter wave radar sensors, the system can achieve imaging with angular resolution close to 1.3 degrees.","PeriodicalId":444899,"journal":{"name":"2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"237 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133534495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Thready: A fast scheduling simulator for real-time task systems","authors":"Robert Schmidt, A. Ortiz","doi":"10.1109/MOCAST49295.2020.9200275","DOIUrl":"https://doi.org/10.1109/MOCAST49295.2020.9200275","url":null,"abstract":"Correct scheduling in hard real-time systems is of utmost importance to guarantee that deadlines are not missed. By mathematical proof, correctness can be demonstrated for the worst case. Such demonstrations usually do not consider errors during system run-time, and do not provide quality of service insights. Such insights can be derived from simulations, but typical simulators are too slow for long term simulations.We developed Thready, a fast simulator for sporadic task systems under errors to investigate the long term behavior of scheduled systems. Thready’s three order of magnitude speedup in latency compared with the fastest state of the art simulator framework allows designers to investigate system performance in the average case, which facilitates understanding and better design decisions.","PeriodicalId":444899,"journal":{"name":"2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116811364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lei Zhang, D. Borggreve, F. Vanselow, R. Brederlow
{"title":"Quantization Considerations of Dense Layers in Convolutional Neural Networks for Resistive Crossbar Implementation","authors":"Lei Zhang, D. Borggreve, F. Vanselow, R. Brederlow","doi":"10.1109/MOCAST49295.2020.9200280","DOIUrl":"https://doi.org/10.1109/MOCAST49295.2020.9200280","url":null,"abstract":"The accuracy and power consumption of resistive crossbar circuits in use for neuromorphic computing is restricted by the process variation of the resistance-switching (memristive) device and the power overhead of the mixed-signal circuits, such as analog-digital converters (ADCs) and digitalanalog converters (DACs). Reducing the signal- and weightresolution can improve the robustness against process variation, relax requirements for mixed-signal devices, and simplify the implementation of crossbar circuits. This work aims to establish a methodology to achieve low-resolution dense layers for CNNs in terms of network architecture selection and quantization method. To this end, this work studies the impact of the dense layer configuration on the required resolution for its inputs and weights in a small convolutional neural network (CNN). This analysis shows that carefully selecting the network architecture for the dense layer can significantly reduce the required resolution for its input signals and weights. This work reviews criteria for appropriate architecture selection and the quantization method for the binary and ternary neural network (BNN and TNN) to reduce the weight resolution of CNN dense layers. Furthermore, this work presents a method to reduce the input resolution for the dense layer down to one bit by analyzing the distribution of the input values. A small CNN for inference with one-bit quantization for inputs signals and weights can be realized with only 0.68% accuracy degradation for MNIST Dataset.","PeriodicalId":444899,"journal":{"name":"2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124086841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Athanassios Tziouvaras, Georgios Dimitriou, Michael F. Dossis, G. Stamoulis
{"title":"Adaptive Operation-Based ALU and FPU Clocking","authors":"Athanassios Tziouvaras, Georgios Dimitriou, Michael F. Dossis, G. Stamoulis","doi":"10.1109/MOCAST49295.2020.9200282","DOIUrl":"https://doi.org/10.1109/MOCAST49295.2020.9200282","url":null,"abstract":"The operating clock period in modern circuits is designated under worst-case operating conditions, in order to ensure error free functionality. To accomplish this goal, designers take into account the timing of the circuit critical path that provides an upper limit for the clock rate. However, that limit imposes heavy performance penalties on the design, since the critical path is not frequently excited during runtime. In contrast with the prevailing methodology, the better-thanworst-case (BTWC) paradigm treats the circuit timing requirements in a more flexible way, as it does not commit to serve the demands of the worst-case scenario. In this work we develop a novel timing analysis methodology inspired by the BTWC approach. Instead of performing the standard critical path analysis, we focus on analyzing the timing requirements of each operation separately. In the sequel we specify an adaptive clock period that is derived by the timing requirements of each supported circuit operation. As a result, we are guaranteed error-free circuit functionality, as no timing violations of individual operations are ever allowed to occur. To this end no error correction mechanisms are required. We verify the proposed methodology by applying it on four different post-layout implementations of ALUs and FPUs. The results we obtain display an average 2.05x throughput increase compared to the implementations operating under the worstcase clock period. We also demonstrate that the area requirements of our methodology are trivial as the overhead is less than 2% of the original design.","PeriodicalId":444899,"journal":{"name":"2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129534964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}