FPGA-based data processing in datacenters is increasing in popularity due to the demands of modern workloads and the ensuing necessity for specialization in hardware. Driven by this trend, vendors are rapidly adapting reconfigurable devices to suit data and compute intensive workloads. Inclusion of High Bandwidth Memory (HBM) in FPGA devices is a recent example. HBM promises overcoming the bandwidth bottleneck, faced often by FPGA-based accelerators due to their throughput oriented design. In this paper, we study the usage and benefits of HBM on FPGAs from a data analytics perspective. We consider three workloads that are often performed in analytics oriented databases and implement them on FPGA showing in which cases they benefit from HBM: range selection, hash join, and stochastic gradient descent for linear model training. We integrate our designs into a columnar database (MonetDB) and show the trade-offs arising from the integration related to data movement and partitioning. In certain cases, FPGA+HBM based solutions are able to surpass the highest performance provided by either a 2-socket POWER9 system or a 14-core XeonE5 by up to 1.8x (selection), 12.9x (join), and 3.2x (SGD).
The emergence of high-bandwidth memory (HBM) brings new opportunities to boost the performance of sorting acceleration on FPGAs, which was conventionally bounded by the available off-chip memory bandwidth. However, it is nontrivial for designers to fully utilize this immense bandwidth. First, the existing sorter designs cannot be directly scaled at the increasing rate of available off-chip bandwidth, as the required on-chip resource usage grows at a much faster rate and would bound the sorting performance in turn. Second, designers need an in-depth understanding of HBM characteristics to effec…
Supported by their high power efficiency and recent advancements in High Level Synthesis (HLS), FPGAs are quickly finding their way into HPC and cloud systems. Large amounts of work have been done so far on loop and area optimizations for different applications on FPGAs using HLS. However, a comprehensive analysis of the behavior and efficiency of the memory controller of FPGAs is missing in literature, which becomes even more crucial when the limited memory bandwidth of modern FPGAs compared to their GPU counterparts is taken into account. In this work, we will analyze the memory interface ge…
Modern data-intensive applications demand high computation capabilities with strict power constraints. Unfortunately, such applications suffer from a significant waste of both execution cycles and energy in current computing systems due to the costly data movement between the computation units and the memory units. Genome analysis and weather prediction are two examples of such applications. Recent FPGAs couple a reconfigurable fabric with high-bandwidth memory (HBM) to enable more efficient data movement and improve overall performance and energy efficiency. This trend is an example of a para…
As the size of real-world graphs increases, training Graph Neural Networks (GNNs) has become time-consuming and requires acceleration. While previous works have demonstrated the potential of utilizing FPGA for accelerating GNN training, few works have been carried out to accelerate GNN training with multiple FPGAs due to the necessity of hardware expertise and substantial development effort. To this end, we propose HitGNN, a framework that enables users to effortlessly map GNN training workloads onto a CPU-Multi-FPGA platform for acceleration. In particular, HitGNN takes the user-defined synch…
The continued growth in the processing power of FPGAs coupled with high bandwidth memories (HBM), makes systems like the Xilinx U280 credible platforms for linear solvers which often dominate the run time of scientific and engineering applications. In this paper, we present Callipepla, an accelerator for a preconditioned conjugate gradient linear solver (CG). FPGA acceleration of CG faces three challenges: (1) how to support an arbitrary problem and terminate acceleration processing on the fly, (2) how to coordinate long-vector data flow among processing modules, and (3) how to save off-chip m…
Convolutional neural nets (CNNs) have become a practical means to perform vision tasks, particularly in the area of image classification. FPGAs are well known to be able to perform convolutions efficiently, however, most recent efforts to run CNNs on FPGAs have shown limited advantages over other devices such as GPUs. Previous approaches on FPGAs have often been memory bound due to the limited external memory bandwidth on the FPGA device. We show a novel architecture written in OpenCL(TM), which we refer to as a Deep Learning Accelerator (DLA), that maximizes data reuse and minimizes external …
Real-time Deep Neural Network (DNN) inference with low-latency requirement has become increasingly important for numerous applications in both cloud computing (e.g., Apple's Siri) and edge computing (e.g., Google/Waymo's driverless car). FPGA-based DNN accelerators have demonstrated both superior flexibility and performance; in addition, for real-time inference with low batch size, FPGA is expected to achieve further performance improvement. However, the performance gain from the single-FPGA design is obstructed by the limited on-chip resource. In this paper, we employ multiple FPGAs to cooper…
We present a design space exploration for synthesizing optimized, high-throughput implementations of multiple multi-dimensional tridiagonal system solvers on FPGAs. Re-evaluating the characteristics of algorithms for the direct solution of tridiagonal systems, we develop a new tridiagonal solver library aimed at implementing high-performance computing applications on Xilinx FPGA hardware. Key new features of the library are (1) the unification of standard state-of-the-art techniques for implementing implicit numerical solvers with a number of novel high-gain optimizations such as vectorization…
This paper presents a workflow for synthesizing near-optimal FPGA implementations for structured-mesh based stencil applications for explicit solvers. It leverages key characteristics of the application class, its computation-communication pattern, and the architectural capabilities of the FPGA to accelerate solvers from the high-performance computing domain. Key new features of the workflow are (1) the unification of standard state-of-the-art techniques with a number of high-gain optimizations such as batching and spatial blocking/tiling, motivated by increasing throughput for real-world work…
University of Southern California（南加州大学）；US Army Research Lab（美国陆军研究实验室）
Even with generational improvements in DRAM technology, memory access latency still remains the major bottleneck for application accelerators, primarily due to limitations in memory interface IPs which cannot fully account for variations in target applications, the algorithms used, and accelerator architectures. Since developing memory controllers for different applications is time-consuming, this paper introduces a modular and programmable memory controller that can be configured for different target applications on available hardware resources. The proposed memory controller efficiently supp…
Sparse matrix-vector multiplication is often employed in many data-analytic workloads in which low latency and high throughput are more valuable than exact numerical convergence. FPGAs provide quick execution times while offering precise control over the accuracy of the results thanks to reduced-precision fixed-point arithmetic. In this work, we propose a novel streaming implementation of Coordinate Format (COO) sparse matrix-vector multiplication, and study its effectiveness when applied to the Personalized PageRank algorithm, a common building block of recommender systems in e-commerce websi…
Sparse matrix-vector multiplication (SpMV) multiplies a sparse matrix with a dense vector. SpMV plays a crucial role in many applications, from graph analytics to deep learning. The random memory accesses of the sparse matrix make accelerator design challenging. However, high bandwidth memory (HBM) based FPGAs are a good fit for designing accelerators for SpMV. In this paper, we present Serpens, an HBM based accelerator for general-purpose SpMV.Serpens features (1) a general-purpose design, (2) memory-centric processing engines, and (3) index coalescing to support the efficient processing of a…
The deployment of the next generation computing platform at ExaFlops scale requires to solve new technological challenges mainly related to the impressive number (up to 10^6) of compute elements required. This impacts on system power consumption, in terms of feasibility and costs, and on system scalability and computing efficiency. In this perspective analysis, exploration and evaluation of technologies characterized by low power, high efficiency and high degree of customization is strongly needed. Among the various European initiative targeting the design of ExaFlops system, ExaNeSt and EuroE…
Stream computation is one of the approaches suitable for FPGA-based custom computing due to its high throughput capability brought by pipelining with regular memory access. To increase performance of iterative stream computation, we can exploit both temporal and spatial parallelism by deepening and duplicating pipelines, respectively. However, the performance is constrained by several factors including available hardware resources on FPGA, an external memory bandwidth, and utilization of pipeline stages, and therefore we need to find the best mix of the different parallelism to achieve the hig…
Data-intensive applications like distributed AI-training may require multi-terabytes memory capacity with multi-terabits bandwidth. We directly attach the memory to the ethernet controller with some programable logic to design an efficient hardware "template" for Memory pooling and in-memory / in-network computing. We built an FPGA prototype of the NetDAM, andwe demonstrate MPI-Allreduce communication case, the NetDAM can be used as a software and hardware friendly programmable architeture with high performance alternative for RDMA.
The SpMV kernel is characterized by high performance variation per input matrix and computing platform. While GPUs were considered State-of-the-Art for SpMV, with the emergence of advanced multicore CPUs and low-power FPGA accelerators, we need to revisit its performance and energy efficiency. This paper provides a high-level SpMV performance analysis based on structural features of matrices related to common bottlenecks of memory-bandwidth intensity, low ILP, load imbalance and memory latency overheads. Towards this, we create a wide artificial matrix dataset that spans these features and stu…
