{"title":"Technological hybridization for efficient runtime reconfigurable FPGAs","authors":"N. Bruchon, L. Torres, G. Sassatelli, G. Cambon","doi":"10.1109/ISVLSI.2007.96","DOIUrl":"https://doi.org/10.1109/ISVLSI.2007.96","url":null,"abstract":"The goal of this paper is to propose an FPGA using emerging non volatile technologies for its configuration memory. Studies on magnetic memories have already been carried out (Bruchon et al., 2006) but solid electrolyte and phase change memories are also good candidates for such type of application. Features of these technologies can provide some interesting characteristics to the FPGA such as short writing time with non volatile technology. A small structure (RSRAM) for remanent SRAM is used to convert information from these technologies into electrical information. This structure naturally provides some more features like partial and shadowed reconfiguration","PeriodicalId":282817,"journal":{"name":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI '07)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114661716","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":"Interconnect Power Optimization Based on Timing Analysis","authors":"Liu Yang, Sheqin Dong, Yuchun Ma, Xianlong Hong","doi":"10.1109/ISVLSI.2007.61","DOIUrl":"https://doi.org/10.1109/ISVLSI.2007.61","url":null,"abstract":"In traditional floorplanners, the lack of information about timing schedule from high level synthesis (HLS) often leads to the failure or iterations of timing schedule design. In this paper, timing analysis with interconnect delay is introduced to the process of floorplanning, which enables the timing schedule information considered in physical design. Furthermore, based on timing schedule information, the timing slacks along datapaths are used to optimize the interconnect power consumptions. Without violating timing specification, we propose a delay budget method to distribute the slacks along interconnects in order to optimize the total interconnect power. Experimental results show that our interconnect power optimization method based on timing analysis can optimize the packing to meet the cycle time requirement effectively and save the interconnect power consumption about 13.2% on average","PeriodicalId":282817,"journal":{"name":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI '07)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124318200","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":"Generating Realistic Stimuli for Accurate Power Grid Analysis","authors":"P. Morgado, P. Flores, L. M. Silveira","doi":"10.1145/1529255.1529262","DOIUrl":"https://doi.org/10.1145/1529255.1529262","url":null,"abstract":"Power distribution systems in integrated circuits are used to provide the voltages and currents the devices need to operate properly. As the semiconductor industry moves into deep nanometer nodes, problems like voltage drop, ground bounce and electromigration which may cause chip failures, are worsening, as more devices, operating at higher frequencies are placed closer together. Verification of a power distribution system is therefore paramount to silicon success. This type of verification is usually done by simulation, targeting a worst-case scenario, typically characterized by the almost simultaneous switching of several devices in the circuit. The definition of the worst-case situation is therefore crucial, since it influences the result of the simulation and ultimately the design target. Supposedly safe but unrealistic settings such as assuming that all signals switch simultaneously, could lead to costly over-designs in terms of die area. In this paper we describe a software tool that generates a reasonable, realistic, worst-case set of stimuli for simulation, based on timing and spatial restrictions that arise from the circuit's netlist and placement. Generating such stimuli is akin to performing a standard static timing analysis, as is done before signoff so the tool fits well within conventional design frameworks. The resulting stimuli indicates that only a fraction of the gates change in any given timing window, leading to a more robust verification methodology, specially in the dynamic case.","PeriodicalId":282817,"journal":{"name":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI '07)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126529949","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":"Minimum-Congestion Placement for Y-interconnects: Some studies and observations","authors":"T. Samanta, P. Ghosal, H. Rahaman, P. Dasgupta","doi":"10.1109/ISVLSI.2007.66","DOIUrl":"https://doi.org/10.1109/ISVLSI.2007.66","url":null,"abstract":"Y-interconnects for VLSI chips are based on the use of global and semi-global wiring in only 0deg, 60deg, and 120deg. Though X-interconnects are fast replacing the traditional Manhattan (M) interconnects, the very recently proposed Y-interconnects have been observed to possess certain key advantages, Y-interconnects tend to consume less routing resources than M-interconnects. Unlike the X-interconnect architectures, Y-interconnect architectures support regular routing grid. This is indeed very important for simplifying manufacturing processes and applying the routing and design rule checking algorithms. Several efficient Y-routing algorithms have been proposed in literature. However, to the best of our knowledge, not much have been reported so far in designing algorithms for Y-interconnect-based VLSI module placement and its effects on the congestion or wire-lengths. In this paper, in an attempt to fill the gap in the existing literature, we propose a novel simulated-annealing-based placement technique for mixed-sized cells which tries to reduce the congestion for Y-interconnects. The proposed method attempts to reduce the congestion, and observes the corresponding changes in the estimated lengths of the Y-interconnects. It has been implemented in Linux environment and experiments performed with randomly generated instances, and some well-known benchmarks. The wirelength estimates for the Y-interconnects, and Manhattan interconnects for the same placement instances are compared. Results obtained are quite encouraging. The experimental results for a specific number of iterations and cooling schedule show improvements in congestion in most of the cases","PeriodicalId":282817,"journal":{"name":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI '07)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128121779","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}
Antonino Tumeo, M. Monchiero, G. Palermo, Fabrizio Ferrandi, D. Sciuto
{"title":"A Pipelined Fast 2D-DCT Accelerator for FPGA-based SoCs","authors":"Antonino Tumeo, M. Monchiero, G. Palermo, Fabrizio Ferrandi, D. Sciuto","doi":"10.1109/ISVLSI.2007.13","DOIUrl":"https://doi.org/10.1109/ISVLSI.2007.13","url":null,"abstract":"Multimedia applications, and in particular the encoding and decoding of standard image and video formats, are usually a typical target for systems-on-chip (SoC). The bi-dimensional discrete cosine transformation (2D-DCT) is a commonly used frequency transformation in graphic compression algorithms. Many hardware implementations, adopting disparate algorithms, have been proposed for field programmable gate arrays (FPGA). These designs focus either on performance or area, and often do not succeed in balancing the two aspects. In this paper, we present a design of a fast 2D-DCT hardware accelerator for a FPGA-based SoC. This accelerator makes use of a single seven stages 1D-DCT pipeline able to alternate computation for the even and odd coefficients in every cycle. In addition, it uses special memories to perform the transpose operations. Our hardware takes 80 clock cycles at 107MHz to generate a complete 8times8 2D DCT, from the writing of the first input sample to the reading of the last result (including the overhead of the interface logic). We show that this architecture provides optimal performance/area ratio with respect to several alternative designs.","PeriodicalId":282817,"journal":{"name":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI '07)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129433214","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. Corbetta, Fabrizio Ferrandi, M. Morandi, M. Novati, M. Santambrogio, D. Sciuto
{"title":"Two Novel Approaches to Online Partial Bitstream Relocation in a Dynamically Reconfigurable System","authors":"S. Corbetta, Fabrizio Ferrandi, M. Morandi, M. Novati, M. Santambrogio, D. Sciuto","doi":"10.1109/ISVLSI.2007.99","DOIUrl":"https://doi.org/10.1109/ISVLSI.2007.99","url":null,"abstract":"FPGAs allow the creation of partially reconfigurable systems; when compared to traditional reconfigurable systems based on total reconfiguration, recent approaches offer significant innovations. One of these is the possibility of dynamically change the functionalities hosted on the device only when needed and while the rest of the system keeps working. This permits better performance but increases the complexity of both module creation and placement. This paper describes and compares two different solutions, a HW and a SW one, to perform bitstream relocation: BiRF and BAnMaT Light. The former is a hardware filter in the fixed part of the reconfigurable architecture, the latter is a software solution, run on the internal processor of the FPGA.","PeriodicalId":282817,"journal":{"name":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI '07)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132180376","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":"Design and Analysis of Low Power Dynamic Bus Based on RLC simulation","authors":"S. Ruan, Shang-Fang Tsai, Yu-Ting Pai","doi":"10.1109/ISVLSI.2007.36","DOIUrl":"https://doi.org/10.1109/ISVLSI.2007.36","url":null,"abstract":"In this paper, we propose a low power dynamic bus encoding scheme which simultaneously reduces the capacitive and inductive effects by the measurement of real RLC model. It should be noted that our method does not need a sufficient knowledge of the patterns on the bus. Our experimental results show that the proposed approach can save power consumption of the bus up to 12% compared to the nonencoded case. We also propose an area-aware scheme to optimize our circuits in terms of power consumption and area. The scheme can reduce the circuit area up to 29% while keeping almost the same power reduction","PeriodicalId":282817,"journal":{"name":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI '07)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126240766","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":"Low Area Adaptive Fail-Data Compression Methodology for Defect Classification and Production Phase Prognosis","authors":"P. Dubey, A. Garg, Sravan Kumar Bhaskarani","doi":"10.1109/ISVLSI.2007.63","DOIUrl":"https://doi.org/10.1109/ISVLSI.2007.63","url":null,"abstract":"With the shrinking technology and increasing statistical defects, multiple design respins are required based on yield learning. Hence, a solution is required to efficiently diagnose the failure types of memory during production in the shortest time frame possible. This paper introduces a novel method of fault classification through image based prognosis of predefined fail signature dictionary. In contrary to the existing Bitmap Diagnosis methodologies, this method predicts the compressed failure map without generating and transferring complete Bitmap to the tester. The proposed methodology supports testing through a very low cost ATE. This architecture is partitioned to achieve sharing among various memories and at-speed testing.","PeriodicalId":282817,"journal":{"name":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI '07)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121342483","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":"Subthreshold Pass Transistor Logic for Ultra-Low Power Operation","authors":"V. Moalemi, A. Afzali-Kusha","doi":"10.1109/ISVLSI.2007.94","DOIUrl":"https://doi.org/10.1109/ISVLSI.2007.94","url":null,"abstract":"In this paper, we investigate subthreshold pass-transistor logics for ultra-low-power applications. The performance characteristics of different pass-transistor XOR structures operating in the subthreshold region have been compared in 65nm and 90nm technologies. The results of the simulations show that the subthreshold logics have some advantages compared to their strong inversion counterparts. The study includes both normal subthreshold pass-transistor logic (sub-PT) and dynamic threshold pass-transistor logic (sub-DTPT). When compared to the former, the latter logic reveals lower sensitivities to temperature and process variations.","PeriodicalId":282817,"journal":{"name":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI '07)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123002710","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}
Erico Bastos, E. Carara, Daniel V. Pigatto, Ney Laert Vilar Calazans, F. Moraes
{"title":"MOTIM - A Scalable Architecture for Ethernet Switches","authors":"Erico Bastos, E. Carara, Daniel V. Pigatto, Ney Laert Vilar Calazans, F. Moraes","doi":"10.1109/ISVLSI.2007.70","DOIUrl":"https://doi.org/10.1109/ISVLSI.2007.70","url":null,"abstract":"The main goal of this work is to describe a scalable and reusable architecture useful for the construction of Ethernet switches, named MOTIM. The main requirement of MOTIM is to allow achieving low latency and high throughput with a generic structure that can be easily scaled. In order to make the architecture scalable, its design is based on the use of a network on chip (NoC), a concept recently proposed for enhancing SoC interconnect design (Benini, 2002). NoCs stand as a good compromise between silicon cost and performance scalability, easing to attain design requirements. Minkenberg et al. recently identified a set of trends arising in packet switch design and discussed their consequences (Minkenberg, 2003). The most important of these trends indicates that the aggregate throughput grow by increasing the amount of ports in switches, rather than by increasing port speed. This imposes a demand for larger crossbars, a structure that do not scale well. Scalable NoCs are a feasible alternative to implement switches with fully interconnected ports.","PeriodicalId":282817,"journal":{"name":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI '07)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123808188","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}