Adoption of partial reconfiguration (PR) in mainstream FPGA system design remains underwhelming primarily due the significant FPGA design expertise that is required. We present an approach to fully automating a design flow that accepts a high level description of a dynamically adaptive application and generates a fully functional, optimised PR design. This tool can determine the most suitable FPGA for a design to meet a given reconfiguration time constraint and makes full use of available resources. The flow targets adaptive systems, where the dynamic behaviour and switching order are not known up front.
{"title":"An Approach to a Fully Automated Partial Reconfiguration Design Flow","authors":"Kizheppatt Vipin, Suhaib A. Fahmy","doi":"10.1109/FCCM.2013.33","DOIUrl":"https://doi.org/10.1109/FCCM.2013.33","url":null,"abstract":"Adoption of partial reconfiguration (PR) in mainstream FPGA system design remains underwhelming primarily due the significant FPGA design expertise that is required. We present an approach to fully automating a design flow that accepts a high level description of a dynamically adaptive application and generates a fully functional, optimised PR design. This tool can determine the most suitable FPGA for a design to meet a given reconfiguration time constraint and makes full use of available resources. The flow targets adaptive systems, where the dynamic behaviour and switching order are not known up front.","PeriodicalId":269887,"journal":{"name":"2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124215577","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}
Huabin Ruan, Xiaomeng Huang, H. Fu, Guangwen Yang, W. Luk, S. Racanière, O. Pell, Wenji Han
The Gaussian Copula Model (GCM) plays an important role in the state-of-the-art financial analysis field for modeling the dependence of financial assets. However, the existing implementations of GCM are all computationallydemanding and time-consuming. In this paper, we propose a Dataflow Engine (DFE) design to accelerate the GCM computation. Specifically, a commonly used CPU-friendly GCM algorithm is converted into a fully-pipelined dataflow graph through four steps of optimization: recomposing the algorithm to be pipeline-friendly, removing unnecessary computation, sharing common computing results, and reducing the computing precision while maintaining the same level of accuracy for the computation results. The performance of the proposed DFE design is compared with three CPU-based implementations that are well-optimized. Experimental results show that our DFE solution not only generates fairly accurate result, but also achieves a maximum of 467x speedup over a single-thread CPU-based solution, 120x speedup over a multi-thread CPUbased solution, and 47x speedup over an MPI-based solution.
{"title":"An FPGA-Based Data Flow Engine for Gaussian Copula Model","authors":"Huabin Ruan, Xiaomeng Huang, H. Fu, Guangwen Yang, W. Luk, S. Racanière, O. Pell, Wenji Han","doi":"10.1109/FCCM.2013.14","DOIUrl":"https://doi.org/10.1109/FCCM.2013.14","url":null,"abstract":"The Gaussian Copula Model (GCM) plays an important role in the state-of-the-art financial analysis field for modeling the dependence of financial assets. However, the existing implementations of GCM are all computationallydemanding and time-consuming. In this paper, we propose a Dataflow Engine (DFE) design to accelerate the GCM computation. Specifically, a commonly used CPU-friendly GCM algorithm is converted into a fully-pipelined dataflow graph through four steps of optimization: recomposing the algorithm to be pipeline-friendly, removing unnecessary computation, sharing common computing results, and reducing the computing precision while maintaining the same level of accuracy for the computation results. The performance of the proposed DFE design is compared with three CPU-based implementations that are well-optimized. Experimental results show that our DFE solution not only generates fairly accurate result, but also achieves a maximum of 467x speedup over a single-thread CPU-based solution, 120x speedup over a multi-thread CPUbased solution, and 47x speedup over an MPI-based solution.","PeriodicalId":269887,"journal":{"name":"2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124959465","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}
Decades of research in the field of high level hardware description now result in tools that are able to automatically transform C/C++ constructs into highly optimized parallel and pipelined architectures. Such approaches work fine when the control flow is a priory known since the computation results in a large dataflow graph that can be mapped into the available operators. Nevertheless, some applications have a control flow that is highly dependant on the data. This paper focuses on the hardware implementation of such applications and presents a high level synthesis methodology applied to a Hardware Description Language (HDL) in which assignments correspond to self-synchronized connections between predefined data streaming sources and sinks. A data transfer occurs over an established connection when both source and sink are ready, according to their synchronization interfaces. Founded on a high-level communicating FSM programming model, the language allows the user to describe and dynamically modify streaming architectures exploiting spatial and temporal parallelism. Our compiler attempts to maximize the number of transfers at each clock cycle and automatically fixes the potential combinatorial loops induced by the dynamic connection of dependant sources and sinks. The methodology is applied to the synthesis of a pipelined floating point accumulator using the Delayed-Buffering (DB) reduction method. The results we obtain are similar to state-of-the-art dedicated architectures but require much less design time and expertise.
{"title":"High-Level Description and Synthesis of Floating-Point Accumulators on FPGA","authors":"Marc-André Daigneault, J. David","doi":"10.1109/FCCM.2013.37","DOIUrl":"https://doi.org/10.1109/FCCM.2013.37","url":null,"abstract":"Decades of research in the field of high level hardware description now result in tools that are able to automatically transform C/C++ constructs into highly optimized parallel and pipelined architectures. Such approaches work fine when the control flow is a priory known since the computation results in a large dataflow graph that can be mapped into the available operators. Nevertheless, some applications have a control flow that is highly dependant on the data. This paper focuses on the hardware implementation of such applications and presents a high level synthesis methodology applied to a Hardware Description Language (HDL) in which assignments correspond to self-synchronized connections between predefined data streaming sources and sinks. A data transfer occurs over an established connection when both source and sink are ready, according to their synchronization interfaces. Founded on a high-level communicating FSM programming model, the language allows the user to describe and dynamically modify streaming architectures exploiting spatial and temporal parallelism. Our compiler attempts to maximize the number of transfers at each clock cycle and automatically fixes the potential combinatorial loops induced by the dynamic connection of dependant sources and sinks. The methodology is applied to the synthesis of a pipelined floating point accumulator using the Delayed-Buffering (DB) reduction method. The results we obtain are similar to state-of-the-art dedicated architectures but require much less design time and expertise.","PeriodicalId":269887,"journal":{"name":"2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116418531","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}
Due to stagnant clock speeds and high power consumption of commodity microprocessors, database vendors have started to explore massively parallel co-processors such as FPGAs to further increase performance. A typical approach is to push simple but compute-intensive operations (e.g., prefiltering, (de)compression) to FPGAs for acceleration. In this paper, we show how a significantly more complex operation- the computation of the skyline-can be holistically implemented on an FPGA. A skyline query computes the pareto optimal set of multi-dimensional data points. These queries have been studied in software extensively over the last decade but this paper is the first to examine skyline computation in hardware. We propose a methodology that interleaves data storage and computation, allowing multiple operations to be executed on the same working set in parallel, while accounting for all data dependencies. Our experiments show that we achieve very promising results compared to CPU-based solutions.
{"title":"Parallel Computation of Skyline Queries","authors":"L. Woods, G. Alonso, J. Teubner","doi":"10.1109/FCCM.2013.18","DOIUrl":"https://doi.org/10.1109/FCCM.2013.18","url":null,"abstract":"Due to stagnant clock speeds and high power consumption of commodity microprocessors, database vendors have started to explore massively parallel co-processors such as FPGAs to further increase performance. A typical approach is to push simple but compute-intensive operations (e.g., prefiltering, (de)compression) to FPGAs for acceleration. In this paper, we show how a significantly more complex operation- the computation of the skyline-can be holistically implemented on an FPGA. A skyline query computes the pareto optimal set of multi-dimensional data points. These queries have been studied in software extensively over the last decade but this paper is the first to examine skyline computation in hardware. We propose a methodology that interleaves data storage and computation, allowing multiple operations to be executed on the same working set in parallel, while accounting for all data dependencies. Our experiments show that we achieve very promising results compared to CPU-based solutions.","PeriodicalId":269887,"journal":{"name":"2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124398941","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}
Recent improvements in the throughput of nextgeneration DNA sequencing machines poses a great computational challenge in analysing the massive quantities of data produced. This paper proposes a novel approach, based on reconfigurable computing technology, for accelerating short read mapping, where the positions of millions of short reads are located relative to a known reference sequence. Our approach consists of two key components: an exact string matcher for the bulk of the alignment process, and an approximate string matcher for the remaining cases. We characterise interesting regions of the design space, including homogeneous, heterogeneous and run-time reconfigurable designs and provide back of envelope estimations of the corresponding performance. We show that a particular implementation of this architecture targeting a single FPGA can be up to 293 times faster than BWA on an Intel X5650 CPU, and 134 times faster than SOAP3 on an NVIDIA GTX 580 GPU.
{"title":"Reconfigurable Acceleration of Short Read Mapping","authors":"James Arram, K. H. Tsoi, W. Luk, P. Jiang","doi":"10.1109/FCCM.2013.57","DOIUrl":"https://doi.org/10.1109/FCCM.2013.57","url":null,"abstract":"Recent improvements in the throughput of nextgeneration DNA sequencing machines poses a great computational challenge in analysing the massive quantities of data produced. This paper proposes a novel approach, based on reconfigurable computing technology, for accelerating short read mapping, where the positions of millions of short reads are located relative to a known reference sequence. Our approach consists of two key components: an exact string matcher for the bulk of the alignment process, and an approximate string matcher for the remaining cases. We characterise interesting regions of the design space, including homogeneous, heterogeneous and run-time reconfigurable designs and provide back of envelope estimations of the corresponding performance. We show that a particular implementation of this architecture targeting a single FPGA can be up to 293 times faster than BWA on an Intel X5650 CPU, and 134 times faster than SOAP3 on an NVIDIA GTX 580 GPU.","PeriodicalId":269887,"journal":{"name":"2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131028315","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}
We present an FPGA (field programmable gate array) based PCI-E (PCI-Express) root complex architecture for SOPCs (System-on-a-Programmable-Chip) in this paper. In our work, the system on the FPGA serves as a PCIE master device rather than a PCIE endpoint, which is usually a common practice as a co-processing device driven by a desktop computer or a server. We use this system to control a PCIE endpoint, which is also an FPGA based endpoint implemented on another FPGA board. This architecture requires only IP cores free of charge. We also provide basic software driver so that specific device driver can be developed on it to control popular PCIE device in the future, i.e. ethernet card or graphic card. The whole architecture has been implemented on Xilinx Virtex-6 FPGAs to indicate that this architecture is a feasible approach to standalone SOPCs, which has better efficiencies than those with additional generic controlling processors.
{"title":"An FPGA Based PCI-E Root Complex Architecture for Standalone SOPCs","authors":"Yingjie Cao, Yongxin Zhu, Xu Wang, Jiang Jiang, Meikang Qiu","doi":"10.1109/FCCM.2013.29","DOIUrl":"https://doi.org/10.1109/FCCM.2013.29","url":null,"abstract":"We present an FPGA (field programmable gate array) based PCI-E (PCI-Express) root complex architecture for SOPCs (System-on-a-Programmable-Chip) in this paper. In our work, the system on the FPGA serves as a PCIE master device rather than a PCIE endpoint, which is usually a common practice as a co-processing device driven by a desktop computer or a server. We use this system to control a PCIE endpoint, which is also an FPGA based endpoint implemented on another FPGA board. This architecture requires only IP cores free of charge. We also provide basic software driver so that specific device driver can be developed on it to control popular PCIE device in the future, i.e. ethernet card or graphic card. The whole architecture has been implemented on Xilinx Virtex-6 FPGAs to indicate that this architecture is a feasible approach to standalone SOPCs, which has better efficiencies than those with additional generic controlling processors.","PeriodicalId":269887,"journal":{"name":"2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131262923","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}
Xinyu Niu, T. Chau, Qiwei Jin, W. Luk, Qiang Liu, O. Pell
A design approach is proposed to automatically identify and exploit run-time reconfiguration opportunities while optimising resource utilisation. We introduce Reconfiguration Data Flow Graph, a hierarchical graph structure enabling reconfigurable designs to be synthesised in three steps: function analysis, configuration organisation, and run-time solution generation. Three applications, based on barrier option pricing, particle filter, and reverse time migration are used in evaluating the proposed approach. The run-time solutions approximate the theoretical performance by eliminating idle functions, and are 1.31 to 2.19 times faster than optimised static designs. FPGA designs developed with the proposed approach are up to 28.8 times faster than optimised CPU reference designs and 1.55 times faster than optimised GPU designs.
{"title":"Automating Elimination of Idle Functions by Run-Time Reconfiguration","authors":"Xinyu Niu, T. Chau, Qiwei Jin, W. Luk, Qiang Liu, O. Pell","doi":"10.1145/2700415","DOIUrl":"https://doi.org/10.1145/2700415","url":null,"abstract":"A design approach is proposed to automatically identify and exploit run-time reconfiguration opportunities while optimising resource utilisation. We introduce Reconfiguration Data Flow Graph, a hierarchical graph structure enabling reconfigurable designs to be synthesised in three steps: function analysis, configuration organisation, and run-time solution generation. Three applications, based on barrier option pricing, particle filter, and reverse time migration are used in evaluating the proposed approach. The run-time solutions approximate the theoretical performance by eliminating idle functions, and are 1.31 to 2.19 times faster than optimised static designs. FPGA designs developed with the proposed approach are up to 28.8 times faster than optimised CPU reference designs and 1.55 times faster than optimised GPU designs.","PeriodicalId":269887,"journal":{"name":"2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131437428","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}
Summary form only given. There is growing commercial interest in using FPGAs for compute acceleration. To ease the programming task for non-hardware-expert programmers, systems are emerging that can map high-level languages such as C and OpenCL to FPGAs-targeting compiler-generated circuits and soft processing engines. Soft processing engines such as CPUs are familiar to programmers, can be reprogrammed quickly without rebuilding the FPGA image, and by their general nature can support multiple software functions in a smaller area than the alternative of multiple per-function synthesized circuits. Finally, compelling processing engines can be incorporated into the output of high-level synthesis systems. For FPGA-based soft compute engines to be compelling they must be computationally dense: they must achieve high throughput per area. For simple CPUs with simple functional units (FUs) it is relatively straightforward to achieve good utilization, and it is not overly-detrimental if a small, single-pipeline-stage FU such as an integer adder is under-utilized. In contrast, larger, more deeply pipelined, more numerous, and more varied FUs can be quite challenging to keep busy-even for an engine capable of extracting instruction-level parallelism (ILP) from an application. Hence a key challenge for FPGA-based compute engines is how to maximize compute density (throughput per-area) by achieving high utilization of a datapath composed of multiple varying FUs of significant and varying pipeline depth. In this work, we propose a highly-parameterizable template architecture of a multi-threaded FPGA-based compute engine designed to highly-utilize varied and deeply pipelined FUs. Our approach to achieving high utilization is to leverage (i) support for multiple thread contexts (ii) thread-level and instruction-level parallelism, and (iii) static compiler analysis and scheduling. We focus on deeply-pipelined, IEEE-754 floating-point FUs of widely-varying latency, executing both Hodgkin-Huxley neuron simulation and Black-Scholes options pricing models as example applications, compiled with our LLVM-based scheduler. Targeting a Stratix IV FPGA, we explore architectural tradeoffs by measuring area and throughput for designs with varying numbers of FUs, thread contexts (T), memory banks (B), and bank multi-porting. To determine the most efficient designs that would be suitable for replicating we measure compute density (application throughput per unit of FPGA area), and report which architectural choices lead to the most computationally-dense designs.The most computationally dense design is not necessarily the one with highest throughput and (i) for maximizing throughput, having each thread reside in its own bank is best; (ii) when only moderate numbers of independent threads are available, the compute engine has higher compute density than a custom hardware implementation eg., 2.3x for 32 threads; (iii) the best FU mix does not necessarily match the FU usage in th
只提供摘要形式。使用fpga进行计算加速的商业兴趣越来越大。为了减轻非硬件专家程序员的编程任务，可以将C和OpenCL等高级语言映射到针对fpga的编译器生成电路和软处理引擎的系统正在出现。像cpu这样的软处理引擎是程序员所熟悉的，可以在不重建FPGA映像的情况下快速重新编程，并且由于其一般性质，可以在比多个功能合成电路的替代方案更小的区域内支持多个软件功能。最后，引人注目的处理引擎可以被纳入高级合成系统的输出。为了使基于fpga的软计算引擎引人注目，它们必须计算密集:它们必须实现每个区域的高吞吐量。对于具有简单功能单元(FU)的简单cpu来说，实现良好的利用率是相对简单的，如果一个小的、单管道级的FU(如整数加法器)没有得到充分利用，也不会造成太大的损害。相比之下，更大、更深入的流水线化、更多数量和更多样化的FUs可能非常难以保持忙碌——即使对于能够从应用程序中提取指令级并行性(ILP)的引擎也是如此。因此，基于fpga的计算引擎面临的一个关键挑战是，如何通过实现由多个具有显著和不同管道深度的不同FUs组成的数据路径的高利用率来最大化计算密度(每区域的吞吐量)。在这项工作中，我们提出了一个基于fpga的多线程计算引擎的高度可参数化的模板架构，旨在高度利用各种深度流水线化的FUs。我们实现高利用率的方法是利用(i)对多线程上下文的支持(ii)线程级和指令级并行性，以及(iii)静态编译器分析和调度。我们专注于深度流水线，IEEE-754浮点FUs具有广泛的延迟，执行Hodgkin-Huxley神经元模拟和Black-Scholes期权定价模型作为示例应用程序，使用我们基于llvm的调度程序编译。针对Stratix IV FPGA，我们通过测量具有不同数量的FUs，线程上下文(T)，内存库(B)和银行多端口的设计的面积和吞吐量来探索架构权衡。为了确定适合复制的最有效的设计，我们测量了计算密度(FPGA面积单位的应用程序吞吐量)，并报告了哪些架构选择导致了最计算密度的设计。计算密度最高的设计不一定是具有最高吞吐量的设计，并且(i)为了最大限度地提高吞吐量，让每个线程驻留在自己的线程组中是最好的;(ii)当只有中等数量的独立线程可用时，计算引擎比自定义硬件实现具有更高的计算密度。， 2.3倍，32线程;(iii)最佳的傅里叶混合不一定符合应用程序数据流图中的傅里叶使用情况;(四)建筑参数。
{"title":"A Multithreaded VLIW Soft Processor Family","authors":"Kalin Ovtcharov, Ilian Tili, J. Steffan","doi":"10.1109/FCCM.2013.36","DOIUrl":"https://doi.org/10.1109/FCCM.2013.36","url":null,"abstract":"Summary form only given. There is growing commercial interest in using FPGAs for compute acceleration. To ease the programming task for non-hardware-expert programmers, systems are emerging that can map high-level languages such as C and OpenCL to FPGAs-targeting compiler-generated circuits and soft processing engines. Soft processing engines such as CPUs are familiar to programmers, can be reprogrammed quickly without rebuilding the FPGA image, and by their general nature can support multiple software functions in a smaller area than the alternative of multiple per-function synthesized circuits. Finally, compelling processing engines can be incorporated into the output of high-level synthesis systems. For FPGA-based soft compute engines to be compelling they must be computationally dense: they must achieve high throughput per area. For simple CPUs with simple functional units (FUs) it is relatively straightforward to achieve good utilization, and it is not overly-detrimental if a small, single-pipeline-stage FU such as an integer adder is under-utilized. In contrast, larger, more deeply pipelined, more numerous, and more varied FUs can be quite challenging to keep busy-even for an engine capable of extracting instruction-level parallelism (ILP) from an application. Hence a key challenge for FPGA-based compute engines is how to maximize compute density (throughput per-area) by achieving high utilization of a datapath composed of multiple varying FUs of significant and varying pipeline depth. In this work, we propose a highly-parameterizable template architecture of a multi-threaded FPGA-based compute engine designed to highly-utilize varied and deeply pipelined FUs. Our approach to achieving high utilization is to leverage (i) support for multiple thread contexts (ii) thread-level and instruction-level parallelism, and (iii) static compiler analysis and scheduling. We focus on deeply-pipelined, IEEE-754 floating-point FUs of widely-varying latency, executing both Hodgkin-Huxley neuron simulation and Black-Scholes options pricing models as example applications, compiled with our LLVM-based scheduler. Targeting a Stratix IV FPGA, we explore architectural tradeoffs by measuring area and throughput for designs with varying numbers of FUs, thread contexts (T), memory banks (B), and bank multi-porting. To determine the most efficient designs that would be suitable for replicating we measure compute density (application throughput per unit of FPGA area), and report which architectural choices lead to the most computationally-dense designs.The most computationally dense design is not necessarily the one with highest throughput and (i) for maximizing throughput, having each thread reside in its own bank is best; (ii) when only moderate numbers of independent threads are available, the compute engine has higher compute density than a custom hardware implementation eg., 2.3x for 32 threads; (iii) the best FU mix does not necessarily match the FU usage in th","PeriodicalId":269887,"journal":{"name":"2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133863245","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}
Richard Neil Pittman, A. Forin, A. Criminisi, J. Shotton, A. Mahram
Image segmentation is the process of partitioning an image into segments or subsets of pixels for purposes of further analysis, such as separating the interesting objects in the foreground from the un-interesting objects in the background. In many image processing applications, the process requires a sequence of computational steps on a per pixel basis, thereby binding the performance to the size and resolution of the image. As applications require greater resolution and larger images the computational resources of this step can quickly exceed those of available CPUs, especially in the power and thermal constrained areas of consumer electronics and mobile. In this work, we use a hardware tree-based classifier to solve the image segmentation problem. The application is background removal (BGR) from depth-maps obtained from the Microsoft Kinect sensor. After the image is segmented, subsequent steps then classify the objects in the scene. The approach is flexible: to address different application domains we only need to change the trees used by the classifiers. We describe two distinct approaches and evaluate their performance using the commercial-grade testing environment used for the Microsoft Xbox gaming console.
{"title":"Image Segmentation Using Hardware Forest Classifiers","authors":"Richard Neil Pittman, A. Forin, A. Criminisi, J. Shotton, A. Mahram","doi":"10.1109/FCCM.2013.20","DOIUrl":"https://doi.org/10.1109/FCCM.2013.20","url":null,"abstract":"Image segmentation is the process of partitioning an image into segments or subsets of pixels for purposes of further analysis, such as separating the interesting objects in the foreground from the un-interesting objects in the background. In many image processing applications, the process requires a sequence of computational steps on a per pixel basis, thereby binding the performance to the size and resolution of the image. As applications require greater resolution and larger images the computational resources of this step can quickly exceed those of available CPUs, especially in the power and thermal constrained areas of consumer electronics and mobile. In this work, we use a hardware tree-based classifier to solve the image segmentation problem. The application is background removal (BGR) from depth-maps obtained from the Microsoft Kinect sensor. After the image is segmented, subsequent steps then classify the objects in the scene. The approach is flexible: to address different application domains we only need to change the trees used by the classifiers. We describe two distinct approaches and evaluate their performance using the commercial-grade testing environment used for the Microsoft Xbox gaming console.","PeriodicalId":269887,"journal":{"name":"2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123974294","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}
This work presents an open-source bitstream generation tool for Torc. Bitstream generation has traditionally been the single part of the FPGA design flow that could not be openly reproduced, but our novel approach enables this without reverse-engineering or violating End-User License Agreement terms. We begin by creating a library of “micro-bitstreams” which constitute a collection of primitives at a granularity of our choosing. These primitives can then be combined to create larger designs, or portions thereof, with simple merging operations. Our effort is motivated by a desire to resume earlier work on embedded bitstream generation and autonomous hardware. This is not feasible with Xilinx bitgen because there is no reasonable way to run an x86 binary with complex library and data dependencies on most embedded systems. Initial support is limited to the Virtex5, but we intend to extend this to other Xilinx architectures. We are able to support nearly all routing resources in the device, as well as the most common logic resources.
{"title":"Open-Source Bitstream Generation","authors":"Ritesh Soni, Neil Steiner, M. French","doi":"10.1109/FCCM.2013.45","DOIUrl":"https://doi.org/10.1109/FCCM.2013.45","url":null,"abstract":"This work presents an open-source bitstream generation tool for Torc. Bitstream generation has traditionally been the single part of the FPGA design flow that could not be openly reproduced, but our novel approach enables this without reverse-engineering or violating End-User License Agreement terms. We begin by creating a library of “micro-bitstreams” which constitute a collection of primitives at a granularity of our choosing. These primitives can then be combined to create larger designs, or portions thereof, with simple merging operations. Our effort is motivated by a desire to resume earlier work on embedded bitstream generation and autonomous hardware. This is not feasible with Xilinx bitgen because there is no reasonable way to run an x86 binary with complex library and data dependencies on most embedded systems. Initial support is limited to the Virtex5, but we intend to extend this to other Xilinx architectures. We are able to support nearly all routing resources in the device, as well as the most common logic resources.","PeriodicalId":269887,"journal":{"name":"2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129189278","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：