N. Harward, Michael R. Gardiner, Luke W. Hsiao, M. Wirthlin
{"title":"Estimating Soft Processor Soft Error Sensitivity through Fault Injection","authors":"N. Harward, Michael R. Gardiner, Luke W. Hsiao, M. Wirthlin","doi":"10.1109/FCCM.2015.61","DOIUrl":"https://doi.org/10.1109/FCCM.2015.61","url":null,"abstract":"Soft processors are increasingly used on SRAM-based FPGAs for reliable computing systems. In a radiation environment like space, the configuration memory used to configure a soft processor is sensitive to single event upsets (SEUs). Tools are needed to evaluate and estimate the reliability of soft processors in these environments. Fault injection is used to evaluate the configuration memory sensitivity of soft processor designs. This paper describes our fault injection experiments and the sensitivity results on each soft processor experiment. A suite of five benchmarks were executed on the MicroBlaze soft processor to measure the sensitivity of the processor to the software being executed. In addition, several soft processors were evaluated on a Virtex-5 FPGA: Micro Blaze, LEON3, Arm Cortex-M0, Open RISC, and Pico Blaze. For the software benchmarks, we find that the sensitivity varies as much as 54%. For simple processor configurations running the Towers of Hanoi benchmark, we measure as low as 7,116 sensitive bits for the Pico Blaze, and as high as 112,223 sensitive bits for the Cortex M0.","PeriodicalId":356953,"journal":{"name":"2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130416776","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":"Using Dynamic Signal-Tracing to Debug Compiler-Optimized HLS Circuits on FPGAs","authors":"Jeffrey B. Goeders, S. Wilton","doi":"10.1109/FCCM.2015.25","DOIUrl":"https://doi.org/10.1109/FCCM.2015.25","url":null,"abstract":"High-level synthesis (HLS) for FPGA designs has received considerable attention in recent years. To make this design methodology mainstream, improved debugging technologies are essential. Ideally, a user should be able to debug their design using the original source code, without detailed knowledge of the underlying hardware, while the circuit executes in-situ. Although recent work has made progress toward this goal, existing solutions are unable to provide visibility into circuits that have been heavily optimized by the compiler. HLS compilers typically perform many optimizations, including moving variable values out of memories and into registers distributed throughout the design. Debugging such circuits typically requires either understanding the hardware and probing the appropriate RTL level registers, or ignoring these variables while debugging the design, neither of which is desirable. In this work we present a new signal-tracing technique, specifically designed for circuits that have been optimized by an HLS tool. Information is extracted from the HLS process to determine which signals are relevant to record each cycle. We automatically embed circuitry which dynamically selects the relevant signals, cycle-by-cycle, and records them into on-chip memories. In addition, we explore techniques to balance tracing between cycles to further improve memory efficiency. For each 100Kb of memory allocated to trace buffers, our technique can, on average, record and replay 4322 lines of source code, versus 141 lines using traditional tracing methods.","PeriodicalId":356953,"journal":{"name":"2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines","volume":"49 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130451337","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":"Rapid Overlay Builder for Xilinx FPGAs","authors":"Michael Xi Yue, Dirk Koch, G. Lemieux","doi":"10.1109/FCCM.2015.48","DOIUrl":"https://doi.org/10.1109/FCCM.2015.48","url":null,"abstract":"Overlays are emerging as useful design patterns for solving reconfigurable computing problems. Overlays consist of compiler-like tools and an architecture written in RTL, making it easier for users to quickly compile high-level languages into FPGAs. Despite a high degree of regularity and repetition present in most overlays, it takes a long time for FPGA tools to generate the configuration bit stream. This paper proposes a methodology called Rapid Overlay Builder, or ROB, that combines module relocation, module variants and an efficient form of \"router less\" module stitching that we call zipping. Our case study demonstrates up to 22 times speedup in compile-time over a regular Xilinx ISE compilation, while achieving higher clock speeds. By applying ROB, we anticipate that overlays can be implemented more quickly and with more consistent clock rates.","PeriodicalId":356953,"journal":{"name":"2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115269106","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":"Massively Parallel Dynamically Reconfigurable Multi-FPGA Computing System","authors":"V. Viswanathan, R. B. Atitallah, J. Dekeyser","doi":"10.1109/FCCM.2015.13","DOIUrl":"https://doi.org/10.1109/FCCM.2015.13","url":null,"abstract":"High Performance Embedded Computing (HPEC) applications are becoming highly sophisticated as they capture and process real-time data from several sources. In addition, they should adapt their functionalities according to the operational environments. The inherent hardware parallelism that allows Single Program Multiple Data (SPMD) execution model, high-speed serial I/O and Dynamic Partial Reconfiguration (DPR) features make FPGAs a highly attractive solution. The problem with current generation reconfigurable HPEC systems is that, they are usually built to meet the needs of a specific application i.e., Lacks flexibility to upgrade hardware resources or adaptability to different applications. In order to address these challenges, we propose a scalable and modular multi-FPGA computing platform, with a parallel full-duplex customizable communication network, that redefines the computation, communication and reconfiguration paradigms in such applications. Furthermore, in order to adapt to real-time application constraints, we propose a parallel DPR model. It is well-traced on the execution model (SPMD), to reconfigure all or a subset of the computing nodes in parallel during runtime.","PeriodicalId":356953,"journal":{"name":"2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122587085","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":"Improving Data Partitioning Performance on OpenCL-Based FPGAs","authors":"Ze-ke Wang, Bingsheng He, Wei Zhang","doi":"10.1109/FCCM.2015.34","DOIUrl":"https://doi.org/10.1109/FCCM.2015.34","url":null,"abstract":"We investigate the performance of relational database applications on recent OpenCL-based FPGAs. As a start, we study the performance of data partitioning, a core operation widely used in relational databases. Due to the random memory accesses, data partitioning is time-consuming and can become a major bottleneck for database operators such as hash joins. We start with the state-of-the-art OpenCL implementation which was originally designed for the CPU/GPU, and find that such an implementation suffers from lock overhead and memory stalls. To resolve those overheads, we develop a simple yet efficient multi-kernel approach to leverage two emerging features in Alter a OpenCL SDK, namely task kernel and channel. We evaluate the proposed design on a recent Alter a Stratix V GX FPGA. Our results demonstrate that our proposed approach can achieve roughly 10.7X speedup over the state-of-the-art OpenCL implementation.","PeriodicalId":356953,"journal":{"name":"2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121047057","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}
C. Rodriguez-Donate, Guillermo Botella Juan, Carlos García, E. Cabal-Yépez, M. Prieto
{"title":"Early Experiences with OpenCL on FPGAs: Convolution Case Study","authors":"C. Rodriguez-Donate, Guillermo Botella Juan, Carlos García, E. Cabal-Yépez, M. Prieto","doi":"10.1109/FCCM.2015.19","DOIUrl":"https://doi.org/10.1109/FCCM.2015.19","url":null,"abstract":"Many proprietary standards and tools have been designed in order to cover a closed set of architectures, and OpenCL has become a free standard for parallel programming on heterogeneous systems, which include custom devices, CPUs, GPUs, FPGAs. This work evaluates the use of the well-known convolution operator in signal processing disciplines focused on FPGA evaluation under different optimizations with respect to thread and memory level exploitation.","PeriodicalId":356953,"journal":{"name":"2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127144210","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":"Accelerating SpMV on FPGAs by Compressing Nonzero Values","authors":"Paul Grigoras, P. Burovskiy, Eddie Hung, W. Luk","doi":"10.1109/FCCM.2015.30","DOIUrl":"https://doi.org/10.1109/FCCM.2015.30","url":null,"abstract":"Sparse matrix vector multiplication (SpMV) is an important kernel in many areas of scientific computing, especially as a building block for iterative linear system solvers. We study how loss less nonzero compression can be used to overcome memory bandwidth limitations in FPGA-based SpMV implementations. We introduce a dictionary-based compression algorithm which reduces redundant nonzero values to improve memory bandwidth without reducing computation efficiency by making use of spare FPGA resources. We show how a sparse matrix in the CSR format can be converted to the proposed storage format on the CPU and that average compression ratios of 1.14 - 1.40 and up to 2.65 times can be achieved, over CSR, for relevant matrices in our benchmarks.","PeriodicalId":356953,"journal":{"name":"2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121807852","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":"Enabling Fast and Accurate Emulation of Large-Scale Network on Chip Architectures on a Single FPGA","authors":"Thiem Van Chu, Shimpei Sato, Kenji Kise","doi":"10.1109/FCCM.2015.35","DOIUrl":"https://doi.org/10.1109/FCCM.2015.35","url":null,"abstract":"Network on Chip (NoC) has become the de facto on-chip communication architecture of many-core systems. This paper proposes an FPGA-based NoC emulator which can achieve an ultra-fast simulation speed. We improve the scalability of the NoC emulator without simplifying the emulated architectures or using off-chip resources. We introduce a novel method which enables to accurately emulate NoC designs under synthetic workloads without using a large amount of memory by decoupling the time of the emulated NoC and the time of the traffic generators. Additionally, we propose a method based on the time-division multiplexing technique to emulate the behavior of the entire network using several physical nodes while effectively using FPGA resources. We show that an implementation of the proposed NoC emulator on a Virtex-7 FPGA can achieve 2, 745x simulation speedup over Booksim, one of the most widely used software-based NoC simulator, while maintaining the simulation accuracy.","PeriodicalId":356953,"journal":{"name":"2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132073382","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}
Lesley Shannon, V. Cojocaru, Cong Nguyen Dao, P. Leong
{"title":"Technology Scaling in FPGAs: Trends in Applications and Architectures","authors":"Lesley Shannon, V. Cojocaru, Cong Nguyen Dao, P. Leong","doi":"10.1109/FCCM.2015.11","DOIUrl":"https://doi.org/10.1109/FCCM.2015.11","url":null,"abstract":"Since the release of the first commercial field programmable gate array (FPGA) in 1985, devices have enjoyed continuous improvements in all metrics due to technology scaling, architectural advances and the addition of features. In this paper, we explore performance and utilization trends associated with research designs as a function of FPGA technology progression. The data used is a subset of designs presented at the IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM) over the past 20 years. These are compared to trends from theoretical and vendor sources, models generated and comparisons made. Finally, we compare operating frequency trends from our analysis to the trends exhibited by a set of vendor IP cores mapped to four generations of devices. The results of this investigation suggest that design implementations are generally following the theoretical trends and that the inclusion of embedded hard IP blocks has provided designers with additional performance benefits.","PeriodicalId":356953,"journal":{"name":"2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134081389","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":"Adjustable-Cost Overlays for Runtime Compilation","authors":"J. Coole, G. Stitt","doi":"10.1109/FCCM.2015.49","DOIUrl":"https://doi.org/10.1109/FCCM.2015.49","url":null,"abstract":"Previous work has shown that virtual architectures, or overlays, can greatly reduce lengthy FPGA compile times by providing application-specialized resources along with a flexible interconnect to support application changes. However, retaining full configurability of interconnect has also required significant area overhead. In this paper, we introduce a family of overlay architectures called super nets and an associated design methodology that uses data path merging to provide minimal-overhead support for multiple source net lists, and optionally provides an adjustable amount of source flexibility through a secondary interconnect network. We demonstrate that super nets can enable runtime compilation up to 13,000× faster than direct register-transfer logic (RTL) implementation, with up to 70% lower area than selectively enabled RTL data paths. Finally, we explore the design space of this family of overlays and show that it affords significant freedom to trade additional area for increased flexibility to support deviations from the source set, as introduced during development or by optimizations performed at runtime.","PeriodicalId":356953,"journal":{"name":"2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines","volume":"264 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132658260","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}