اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدScalaBFS: A Scalable BFS Accelerator on HBM-Enhanced FPGAs
78
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
High Bandwidth Memory (HBM) provides massive aggregated memory bandwidth by exposing multiple memory channels to the processing units. To achieve high performance, an accelerator built on top of an FPGA configured with HBM (i.e., FPGA-HBM platform) needs to scale its performance according to the available memory channels. In this paper, we propose an accelerator for BFS (Breadth-First Search) algorithm, named as ScalaBFS, that builds multiple processing elements to sufficiently exploit the high bandwidth of HBM to improve efficiency. We implement the prototype system of ScalaBFS and conduct BFS in both real-world and synthetic scale-free graphs on Xilinx Alveo U280 FPGA card real hardware. The experimental results show that ScalaBFS scales its performance almost linearly according to the available memory pseudo channels (PCs) from the HBM2 subsystem of U280. By fully using the 32 PCs and building 64 processing elements (PEs) on U280, ScalaBFS achieves a performance up to 19.7 GTEPS (Giga Traversed Edges Per Second). When conducting BFS in sparse real-world graphs, ScalaBFS achieves equivalent GTEPS to Gunrock running on the state-of-art Nvidia V100 GPU that features 64-PC HBM2 (twice memory bandwidth than U280).
قيم البحث
اقرأ أيضاً
64 -
Mario Fischer
, Juergen Wassner (Department of Engineering andn Architecture
, Lucerne University of Applied Sciences
2020
Deep Convolutional Neural Networks (CNNs) have become state-of-the art for computer vision and other signal processing tasks due to their superior accuracy. In recent years, large efforts have been made to reduce the computational costs of CNNs in or
der to achieve real-time operation on low-power embedded devices. Towards this goal we present BinArray, a custom hardware accelerator for CNNs with binary approximated weights. The binary approximation used in this paper is an improved version of a network compression technique initially suggested in [1]. It drastically reduces the number of multiplications required per inference with no or very little accuracy degradation. BinArray easily scales and allows to compromise between hardware resource usage and throughput by means of three design parameters transparent to the user. Furthermore, it is possible to select between high accuracy or throughput dynamically during runtime. BinArray has been optimized at the register transfer level and operates at 400 MHz as instruction-set processor within a heterogenous XC7Z045-2 FPGA-SoC platform. Experimental results show that BinArray scales to match the performance of other accelerators like EdgeTPU [2] for different network sizes. Even for the largest MobileNet only 50% of the target device and only 96 DSP blocks are utilized.
With the recent release of High Bandwidth Memory (HBM) based FPGA boards, developers can now exploit unprecedented external memory bandwidth. This allows more memory-bounded applications to benefit from FPGA acceleration. However, we found that it is
not easy to fully utilize the available bandwidth when developing some applications with high-level synthesis (HLS) tools. This is due to the limitation of existing HLS tools when accessing HBM boards large number of independent external memory channels. In this paper, we measure the performance of three recent representative HBM FPGA boards (Intels Stratix 10 MX and Xilinxs Alveo U50/U280 boards) with microbenchmarks and analyze the HLS overhead. Next, we propose HLS-based optimization techniques to improve the effective bandwidth when a PE accesses multiple HBM channels or multiple PEs access an HBM channel. Our experiment demonstrates that the effective bandwidth improves by 2.4X-3.8X. We also provide a list of insights for future improvement of the HBM FPGA HLS design flow.
FPGAs have become emerging computing infrastructures for accelerating applications in datacenters. Meanwhile, high-level synthesis (HLS) tools have been proposed to ease the programming of FPGAs. Even with HLS, irregular data-intensive applications r
equire explicit optimizations, among which multiple processing elements (PEs) with each owning a private BRAM-based buffer are usually adopted to process multiple data per cycle. Data routing, which dynamically dispatches multiple data to designated PEs, avoids data replication in buffers compared to statically assigning data to PEs, hence saving BRAM usage. However, the workload imbalance among PEs vastly diminishes performance when processing skew datasets. In this paper, we propose a skew-oblivious data routing architecture that allocates secondary PEs and schedules them to share the workload of the overloaded PEs at run-time. In addition, we integrate the proposed architecture into a framework called Ditto to minimize the development efforts for applications that require skew handling. We evaluate Ditto on five commonly used applications: histogram building, data partitioning, pagerank, heavy hitter detection and hyperloglog. The results demonstrate that the generated implementations are robust to skew datasets and outperform the stateof-the-art designs in both throughput and BRAM usage efficiency.
Triple Modular Redundancy (TMR) is a suitable fault tolerant technique for SRAM-based FPGA. However, one of the main challenges in achieving 100% robustness in designs protected by TMR running on programmable platforms is to prevent upsets in the rou
ting from provoking undesirable connections between signals from distinct redundant logic parts, which can generate an error in the output. This paper investigates the optimal design of the TMR logic (e.g., by cleverly inserting voters) to ensure robustness. Four differe
The combination of Winograds algorithm and systolic array architecture has demonstrated the capability of improving DSP efficiency in accelerating convolutional neural networks (CNNs) on FPGA platforms. However, handling arbitrary convolution kernel
sizes in FPGA-based Winograd processing elements and supporting efficient data access remain underexplored. In this work, we are the first to propose an optimized Winograd processing element (WinoPE), which can naturally support multiple convolution kernel sizes with the same amount of computing resources and maintains high runtime DSP efficiency. Using the proposed WinoPE, we construct a highly efficient systolic array accelerator, termed WinoCNN. We also propose a dedicated memory subsystem to optimize the data access. Based on the accelerator architecture, we build accurate resource and performance modeling to explore optimal accelerator configurations under different resource constraints. We implement our proposed accelerator on multiple FPGAs, which outperforms the state-of-the-art designs in terms of both throughput and DSP efficiency. Our implementation achieves DSP efficiency up to 1.33 GOPS/DSP and throughput up to 3.1 TOPS with the Xilinx ZCU102 FPGA. These are 29.1% and 20.0% better than the best solutions reported previously, respectively.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
