Yu Wang, Lixue Xia, Ming Cheng, Tianqi Tang, Boxun Li, Huazhong Yang
{"title":"RRAM based Learning acceleration","authors":"Yu Wang, Lixue Xia, Ming Cheng, Tianqi Tang, Boxun Li, Huazhong Yang","doi":"10.1145/2968455.2981124","DOIUrl":"https://doi.org/10.1145/2968455.2981124","url":null,"abstract":"Deep Learning (DL) is becoming popular in a wide range of domains. Many emerging applications, ranging from image and speech recognition to natural language processing and information retrieval, rely heavily on deep learning techniques, especially the Neural Networks (NNs). NNs have led to great advances in recognition accuracy compared with other traditional methods in recent years. NN-based methods demand much more computation and memory resource, and therefore a number of NN accelerators have been proposed on CMOS-based platforms, such as FPGA and GPU [1]. However, it becomes more and more difficult to obtain substantial power efficiency and gains directly through the scaling down of traditional CMOS technique. Meanwhile, the large data amount in DL applications also meets an ever-increasing “memory wall” challenge because of the efficiency of von Neumann architecture. Consequently, there is a growing research interest of exploring emerging nano-devices and new computing architectures to further improve power efficiency [2].","PeriodicalId":346096,"journal":{"name":"2016 International Conference on Compliers, Architectures, and Sythesis of Embedded Systems (CASES)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127131029","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":"Neural network transformation under hardware constraints","authors":"Youhui Zhang, Yu Ji, Wenguang Chen, Yuan Xie","doi":"10.1145/2968455.2981122","DOIUrl":"https://doi.org/10.1145/2968455.2981122","url":null,"abstract":"There are a number of mature ways to train various kinds of ANNs (artificial neural networks), including the BP (back propagation) based algorithm and so on. These training procedures are usually carried out on some GPU-enabled machine(s); 16-/32-bit-width floating point numbers are used as the NN parameters, without any limitation on the maximum fan-in/fan-out of a single neuron or on the type of activation functions. In contrast, for neuromorphic chips [1][2][3], quite a few hardware-specific constraints (the limited fan-in/fan-out of a single neuron, the limited range of synaptic weights, and the hardware types of neurons or activation functions are usually simpler than the software counterparts) do exist, which makes programming such chips difficult.","PeriodicalId":346096,"journal":{"name":"2016 International Conference on Compliers, Architectures, and Sythesis of Embedded Systems (CASES)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128497534","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":"On-the-fly load data value tracing in multicores","authors":"Mounika Ponugoti, Amrish K. Tewar, A. Milenković","doi":"10.1145/2968455.2968507","DOIUrl":"https://doi.org/10.1145/2968455.2968507","url":null,"abstract":"Software testing and debugging of modern multicore-based embedded systems is a challenging proposition because of growing hardware and software complexity, increased integration, and tightening time-to-market. To find more bugs faster, software developers of real-time embedded systems increasingly rely on on-chip trace and debug resources, including hefty on-chip buffers and wide trace ports. However, these resources often offer limited visibility of the system, increase the system cost, and do not scale well with a growing number of cores. This paper introduces mlvCFiat, a hardware/software mechanism for capturing and filtering load data value traces in multicores. It relies on first-access tracking in data caches and equivalent modules in the software debugger to significantly reduce the number of trace events streamed out of the target platform. Our experimental evaluation explores the effectiveness of the proposed technique as a function of cache sizes, encoding mechanism, and the number of cores. The results show that mlvCFiat significantly reduces the total trace port bandwidth. The improvements relative to the existing Nexus-like load data value tracing range from 15 to 33 times for a single core and from 14 to 20 times for an octa core.","PeriodicalId":346096,"journal":{"name":"2016 International Conference on Compliers, Architectures, and Sythesis of Embedded Systems (CASES)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133948692","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 jump-target identification method for multi-architecture static binary translation","authors":"A. Federico, G. Agosta","doi":"10.1145/2968455.2968514","DOIUrl":"https://doi.org/10.1145/2968455.2968514","url":null,"abstract":"Static binary translation is a technique that allows an executable program for a given architecture to be translated into a different one, with a reduced overhead compared to emulators and dynamic binary translators. The main downside of the static approach lies in the absence of runtime information, which is available in other solutions. In particular, one of the key issues consists in the identification of data and code in the program, and, more specifically, in the detection of basic block start addresses (jump targets). The presence of indirect jump instructions whose target is not immediately evident, in particular due to C switch statements, makes the recovery of jump targets a challenging task.","PeriodicalId":346096,"journal":{"name":"2016 International Conference on Compliers, Architectures, and Sythesis of Embedded Systems (CASES)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128302034","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}
Thomas Carle, Dimitra Papagiannopoulou, T. Moreshet, A. Marongiu, M. Herlihy, R. I. Bahar
{"title":"Thrifty-malloc: A HW/SW codesign for the dynamic management of hardware transactional memory in embedded multicore systems","authors":"Thomas Carle, Dimitra Papagiannopoulou, T. Moreshet, A. Marongiu, M. Herlihy, R. I. Bahar","doi":"10.1145/2968455.2968513","DOIUrl":"https://doi.org/10.1145/2968455.2968513","url":null,"abstract":"We present thrifty-malloc: a transaction-friendly dynamic memory manager for high-end embedded multicore systems. The manager combines modularity, ease-of-use and hardware transactional memory (HTM) compatibility in a lightweight and memory-effcient design. Thrifty-malloc is easy to deploy and configure for non-expert programmers, yet provides good performance with low memory overhead for highly-parallel embedded applications running on massively parallel processor arrays (MPPAs) or many-core architectures. In addition, the transparent mechanisms that increase our manager's resilience to unpredictable dynamic situations incur a low timing overhead in comparison to established techniques.","PeriodicalId":346096,"journal":{"name":"2016 International Conference on Compliers, Architectures, and Sythesis of Embedded Systems (CASES)","volume":"30 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113936188","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}
Giuseppe Tagliavini, Germain Haugou, A. Marongiu, L. Benini
{"title":"Enabling OpenVX support in mW-scale parallel accelerators","authors":"Giuseppe Tagliavini, Germain Haugou, A. Marongiu, L. Benini","doi":"10.1145/2968455.2968518","DOIUrl":"https://doi.org/10.1145/2968455.2968518","url":null,"abstract":"mW-scale parallel accelerators are a promising target for application domains such as the Internet of Thing (IoT), which require a strong compliance with a limited power budget combined with high performance capabilities. An important use case is given by smart sensing devices featuring increasingly sophisticated vision capabilities, at the cost of an increasing amount of near-sensor computation power. OpenVX is an emerging standard for the embedded vision, and provides a C-based application programming interface and a runtime environment. OpenVX is designed to maximize functional and performance portability across diverse hardware platforms. However, state-of-the-art implementations rely on memory-hungry data structures, which cannot be supported in constrained devices. In this paper we propose an alternative and novel approach to provide OpenVX support in mW-scale parallel accelerators. Our main contributions are: (i) an extension to the original OpenVX model to support static management of application graphs in the form of binary files; (ii) the definition of a companion run-time environment providing a lightweight support to execute binary graphs in a resource-constrained environment. Our approach achieves 68% memory footprint reduction and 3× execution speed-up compared to a baseline implementation. At the same time, data memory bandwidth is reduced by 10% and energy efficiency is improved by 2×.","PeriodicalId":346096,"journal":{"name":"2016 International Conference on Compliers, Architectures, and Sythesis of Embedded Systems (CASES)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131648004","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}
P. Bogdan, P. Pande, H. Amrouch, M. Shafique, J. Henkel
{"title":"Power and thermal management in massive multicore chips: Theoretical foundation meets architectural innovation and resource allocation","authors":"P. Bogdan, P. Pande, H. Amrouch, M. Shafique, J. Henkel","doi":"10.1145/2968455.2974013","DOIUrl":"https://doi.org/10.1145/2968455.2974013","url":null,"abstract":"Continuing progress and integration levels in silicon technologies make possible complete end-user systems consisting of extremely high number of cores on a single chip targeting either embedded or high-performance computing. However, without new paradigms of energy- and thermally-efficient designs, producing information and communication systems capable of meeting the computing, storage and communication demands of the emerging applications will be unlikely. The broad topic of power and thermal management of massive multicore chips is actively being pursued by a number of researchers worldwide, from a variety of different perspectives, ranging from workload modeling to efficient on-chip network infrastructure design to resource allocation. Successful solutions will likely adopt and encompass elements from all or at least several levels of abstraction. Starting from these ideas, we consider a holistic approach in establishing the Power-Thermal-Performance (PTP) trade-offs of massive multicore processors by considering three inter-related but varying angles, viz., on-chip traffic modeling, novel Networks-on-Chip (NoC) architecture and resource allocation/mapping.","PeriodicalId":346096,"journal":{"name":"2016 International Conference on Compliers, Architectures, and Sythesis of Embedded Systems (CASES)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126302963","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}
S. Tzilis, I. Sourdis, V. Vasilikos, D. Rodopoulos, D. Soudris
{"title":"Runtime management of adaptive MPSoCs for graceful degradation","authors":"S. Tzilis, I. Sourdis, V. Vasilikos, D. Rodopoulos, D. Soudris","doi":"10.1145/2968455.2968517","DOIUrl":"https://doi.org/10.1145/2968455.2968517","url":null,"abstract":"In this paper we propose optimization algorithms for the runtime management of gracefully degradable adaptive MP-SoCs. Assuring the reliability of all hardware components in a system becomes increasingly difficult. On top of the growing defect densities and rising complexity of conventional testing, wear-out effects may reduce the availability of on-chip resources during system lifetime. However, adaptability of modern MPSoCs can provide the means for permanent fault tolerance and graceful degradation via runtime system management. We have developed custom heuristics as well as tailored existing optimization techniques (simulated annealing and genetic algorithm), to deliver a fast and efficient response to unpredictable loss of system resources. We have emulated the resulting runtime manager on the Intel Single-Chip Cloud Computer (SCC), an experimental chip multiprocessor developed by Intel Labs. Comparison of the different algorithms in terms of solution quality and response time, and the scaling of their response time with the size of problem input, indicate that our custom heuristics are faster by at least one order of magnitude, but simulated annealing and genetic algorithm are more consistent in dealing with constraints to the allowed solutions, e.g. limited system reconfiguration time. All algorithms scale well, since their response time, in almost every case, grows sub-linearly with respect to the input size.","PeriodicalId":346096,"journal":{"name":"2016 International Conference on Compliers, Architectures, and Sythesis of Embedded Systems (CASES)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132700702","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}
Cheng Tan, Aditi Kulkarni Mohite, Vanchinathan Venkataramani, Manupa Karunaratne, T. Mitra, L. Peh
{"title":"LOCUS: Low-power customizable many-core architecture for wearables","authors":"Cheng Tan, Aditi Kulkarni Mohite, Vanchinathan Venkataramani, Manupa Karunaratne, T. Mitra, L. Peh","doi":"10.1145/2968455.2968506","DOIUrl":"https://doi.org/10.1145/2968455.2968506","url":null,"abstract":"The requirements' demands of applications, such as real-time response, are pushing the wearable devices to leverage more power-efficient processors inside the SoC (System-on-chip). However, existing wearable devices are not well suited for such challenging applications due to poor performance, while the conventional powerful many-core architectures are not appropriate either due to the stringent power budget in this domain. We propose LOCUS - a low-power, customizable, many-core processor for next-generation wearable devices. LOCUS combines customizable processor cores with a customizable network on a message-passing architecture to deliver very competitive performance/watt - an average 3.1× compared to quad-core ARM processors used in the state-of-the-art wearable devices. A combination of full-system simulation with representative applications from wearable domain and RTL synthesis of the architecture show that 16-core LOCUS achieves an average 1.52× performance/watt improvement over a conventional 16-core shared-memory many-core architecture.","PeriodicalId":346096,"journal":{"name":"2016 International Conference on Compliers, Architectures, and Sythesis of Embedded Systems (CASES)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130278740","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}
Mohamed Ibrahim, C. Boswell, K. Chakrabarty, Kristin Scott, M. Pajic
{"title":"A real-time digital-microfluidic platform for epigenetics","authors":"Mohamed Ibrahim, C. Boswell, K. Chakrabarty, Kristin Scott, M. Pajic","doi":"10.1145/2968455.2968516","DOIUrl":"https://doi.org/10.1145/2968455.2968516","url":null,"abstract":"Advances in digital-microfluidic biochips have led to miniaturized platforms that can implement biomolecular assays. However, these designs are not adequate for running multiple sample pathways because they consider unrealistic static schedules; hence runtime adaptation based on assay outcomes is not supported and only a rigid path of bioassays can be run on the chip. We present a design framework that performs fluidic task assignment, scheduling, and dynamic decision-making for quantitative epigenetics. We first describe our benchtop experimental studies to understand the relevance of chromatin structure on the regulation of gene function and its relationship to biochip design specifications. The proposed method models biochip design in terms of real-time multiprocessor scheduling and utilizes a heuristic algorithm to solve this NP-hard problem. Simulation results show that the proposed algorithm is computationally efficient and it generates effective solutions for multiple sample pathways on a resource-limited biochip. We also present experimental results using an embedded microcontroller as a testbed.","PeriodicalId":346096,"journal":{"name":"2016 International Conference on Compliers, Architectures, and Sythesis of Embedded Systems (CASES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129137511","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}