arXiv subjects

Viktor Prasanna

Publications and source records attributed to Viktor Prasanna.

At least 91 records · Page 5Linked to original sources

arXiv2023

GraphAGILE: An FPGA-based Overlay Accelerator for Low-latency GNN Inference

This paper presents GraphAGILE, a domain-specific FPGA-based overlay accelerator for graph neural network (GNN) inference. GraphAGILE consists of (1) \emph{a novel unified architecture design} with an \emph{instruction set}, and (2) \emph{a compiler} built upon the instruction set that can quickly generate optimized code. Due to the proposed instruction set architecture (ISA) and the compiler, GraphAGILE does not require any FPGA reconfiguration when performing inference on various GNN models and input graphs. For the architecture design, we propose a novel hardware module named Adaptive Computation Kernel (ACK), that can execute various computation kernels of GNNs, including general matrix multiplication (GEMM), sparse-dense matrix multiplication (SpDMM) and sampled dense-dense matrix multiplication (SDDMM). The compiler takes the specifications of a GNN model and the graph meta data (e.g., the number of vertices and edges) as input, and generates a sequence of instructions for inference execution. We develop the following compiler optimizations to reduce inference latency: (1) computation order optimization that automatically reorders the computation graph to reduce the total computation complexity, (2) layer fusion that merges adjacent layers to reduce data communication volume, (3) data partitioning with a partition-centric execution scheme that partitions the input graph to fit the available on-chip memory of FPGA, (4) kernel mapping that automatically selects execution mode for ACK, and performs task scheduling to overlap computation with data communication and achieves dynamic load balance. We implement GraphAGILE on a state-of-the-art FPGA platform, Xilinx Alveo U250. GraphAGILE can execute widely used GNN models, including GCN, GAT, GIN, GraphSAGE, SGC and other GNN models supported by GraphGym.

cs.DC↗

arXiv2023

HTNet: Dynamic WLAN Performance Prediction using Heterogenous Temporal GNN

Predicting the throughput of WLAN deployments is a classic problem that occurs in the design of robust and high performance WLAN systems. However, due to the increasingly complex communication protocols and the increase in interference between devices in denser and denser WLAN deployments, traditional methods either have substantial runtime or enormous prediction error and hence cannot be applied in downstream tasks. Recently, Graph Neural Networks have been proven to be powerful graph analytic models and have been broadly applied to various networking problems such as link scheduling and power allocation. In this work, we propose HTNet, a specialized Heterogeneous Temporal Graph Neural Network that extracts features from dynamic WLAN deployments. Analyzing the unique graph structure of WLAN deployment graphs, we show that HTNet achieves the maximum expressive power on each snapshot. Based on a powerful message passing scheme, HTNet requires fewer number of layers compared with other GNN-based methods which entails less supporting data and runtime. To evaluate the performance of HTNet, we prepare six different setups with more than five thousands dense dynamic WLAN deployments that cover a wide range of real-world scenarios. HTNet achieves the lowest prediction error on all six setups with an average improvement of 25.3\% over the state-of-the-art methods.

cs.NI↗

arXiv2023

Dynasparse: Accelerating GNN Inference through Dynamic Sparsity Exploitation

Graph Neural Network (GNN) inference is used in many real-world applications. Data sparsity in GNN inference, including sparsity in the input graph and the GNN model, offer opportunities to further speed up inference. Also, many pruning techniques have been proposed for model compression that increase the data sparsity of GNNs. We propose Dynasparse, a comprehensive hardware-software codesign on FPGA to accelerate GNN inference through dynamic sparsity exploitation. For this, we decouple the GNN computation kernels from the basic computation primitives, and explore hardware-software codesign as follows: 1) Hardware design: We propose a novel unified accelerator design on FPGA to efficiently execute various computation primitives. We develop a customized soft processor that is tightly coupled with the accelerator to execute a runtime system. Moreover, we develop efficient hardware mechanisms to profile the data sparsity and perform on-the-fly data format transformation to prepare the input data for various computation primitives; 2) Software design: We develop a runtime system that works synergistically with the accelerator to perform dynamic kernel-to-primitive mapping based on data sparsity. We implement Dynasparse on a state-of-the-art FPGA platform, Xilinx Alveo U250, and evaluate the design using widely used GNN models (GCN, GraphSAGE, GIN and SGC). For the above GNN models and various input graphs, the proposed accelerator and dynamic kernel-to-primitive mapping reduces the inference latency by $3.73\times$ on the average compared with the static mapping strategies employed in the state-of-the-art GNN accelerators. Compared with state-of-the-art CPU (GPU) implementations, Dynasparse achieves up to $56.9\times$ ($2.37\times$) speedup in end-to-end latency.

cs.DC↗

arXiv2023

HitGNN: High-throughput GNN Training Framework on CPU+Multi-FPGA Heterogeneous Platform

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 synchronous GNN training algorithm, GNN model, and platform metadata as input, determines the design parameters based on the platform metadata, and performs hardware mapping onto the CPU+Multi-FPGA platform, automatically. HitGNN consists of the following building blocks: (1) high-level application programming interfaces (APIs) that allow users to specify various synchronous GNN training algorithms and GNN models with only a handful of lines of code; (2) a software generator that generates a host program that performs mini-batch sampling, manages CPU-FPGA communication, and handles workload balancing among the FPGAs; (3) an accelerator generator that generates GNN kernels with optimized datapath and memory organization. We show that existing synchronous GNN training algorithms such as DistDGL and PaGraph can be easily deployed on a CPU+Multi-FPGA platform using our framework, while achieving high training throughput. Compared with the state-of-the-art frameworks that accelerate synchronous GNN training on a multi-GPU platform, HitGNN achieves up to 27.21x bandwidth efficiency, and up to 4.26x speedup using much less compute power and memory bandwidth than GPUs. In addition, HitGNN demonstrates good scalability to 16 FPGAs on a CPU+Multi-FPGA platform.

cs.DC↗

arXiv2023

HyScale-GNN: A Scalable Hybrid GNN Training System on Single-Node Heterogeneous Architecture

Graph Neural Networks (GNNs) have shown success in many real-world applications that involve graph-structured data. Most of the existing single-node GNN training systems are capable of training medium-scale graphs with tens of millions of edges; however, scaling them to large-scale graphs with billions of edges remains challenging. In addition, it is challenging to map GNN training algorithms onto a computation node as state-of-the-art machines feature heterogeneous architecture consisting of multiple processors and a variety of accelerators. We propose HyScale-GNN, a novel system to train GNN models on a single-node heterogeneous architecture. HyScale- GNN performs hybrid training which utilizes both the processors and the accelerators to train a model collaboratively. Our system design overcomes the memory size limitation of existing works and is optimized for training GNNs on large-scale graphs. We propose a two-stage data pre-fetching scheme to reduce the communication overhead during GNN training. To improve task mapping efficiency, we propose a dynamic resource management mechanism, which adjusts the workload assignment and resource allocation during runtime. We evaluate HyScale-GNN on a CPU-GPU and a CPU-FPGA heterogeneous architecture. Using several large-scale datasets and two widely-used GNN models, we compare the performance of our design with a multi-GPU baseline implemented in PyTorch-Geometric. The CPU-GPU design and the CPU-FPGA design achieve up to 2.08x speedup and 12.6x speedup, respectively. Compared with the state-of-the-art large-scale multi-node GNN training systems such as P3 and DistDGL, our CPU-FPGA design achieves up to 5.27x speedup using a single node.

cs.DC↗

arXiv2023

Accurate, Low-latency, Efficient SAR Automatic Target Recognition on FPGA

Synthetic aperture radar (SAR) automatic target recognition (ATR) is the key technique for remote-sensing image recognition. The state-of-the-art convolutional neural networks (CNNs) for SAR ATR suffer from \emph{high computation cost} and \emph{large memory footprint}, making them unsuitable to be deployed on resource-limited platforms, such as small/micro satellites. In this paper, we propose a comprehensive GNN-based model-architecture {co-design} on FPGA to address the above issues. \emph{Model design}: we design a novel graph neural network (GNN) for SAR ATR. The proposed GNN model incorporates GraphSAGE layer operators and attention mechanism, achieving comparable accuracy as the state-of-the-art work with near $1/100$ computation cost. Then, we propose a pruning approach including weight pruning and input pruning. While weight pruning through lasso regression reduces most parameters without accuracy drop, input pruning eliminates most input pixels with negligible accuracy drop. \emph{Architecture design}: to fully unleash the computation parallelism within the proposed model, we develop a novel unified hardware architecture that can execute various computation kernels (feature aggregation, feature transformation, graph pooling). The proposed hardware design adopts the Scatter-Gather paradigm to efficiently handle the irregular computation {patterns} of various computation kernels. We deploy the proposed design on an embedded FPGA (AMD Xilinx ZCU104) and evaluate the performance using MSTAR dataset. Compared with the state-of-the-art CNNs, the proposed GNN achieves comparable accuracy with $1/3258$ computation cost and $1/83$ model size. Compared with the state-of-the-art CPU/GPU, our FPGA accelerator achieves $14.8\times$/$2.5\times$ speedup (latency) and is $62\times$/$39\times$ more energy efficient.

cs.AR↗

arXiv2022

Learning Practical Communication Strategies in Cooperative Multi-Agent Reinforcement Learning

In Multi-Agent Reinforcement Learning, communication is critical to encourage cooperation among agents. Communication in realistic wireless networks can be highly unreliable due to network conditions varying with agents' mobility, and stochasticity in the transmission process. We propose a framework to learn practical communication strategies by addressing three fundamental questions: (1) When: Agents learn the timing of communication based on not only message importance but also wireless channel conditions. (2) What: Agents augment message contents with wireless network measurements to better select the game and communication actions. (3) How: Agents use a novel neural message encoder to preserve all information from received messages, regardless of the number and order of messages. Simulating standard benchmarks under realistic wireless network settings, we show significant improvements in game performance, convergence speed and communication efficiency compared with state-of-the-art.

cs.AI↗

arXiv2022

Accelerating Monte-Carlo Tree Search on CPU-FPGA Heterogeneous Platform

Monte Carlo Tree Search (MCTS) methods have achieved great success in many Artificial Intelligence (AI) benchmarks. The in-tree operations become a critical performance bottleneck in realizing parallel MCTS on CPUs. In this work, we develop a scalable CPU-FPGA system for Tree-Parallel MCTS. We propose a novel decomposition and mapping of MCTS data structure and computation onto CPU and FPGA to reduce communication and coordination. High scalability of our system is achieved by encapsulating in-tree operations in an SRAM-based FPGA accelerator. To lower the high data access latency and inter-worker synchronization overheads, we develop several hardware optimizations. We show that by using our accelerator, we obtain up to $35\times$ speedup for in-tree operations, and $3\times$ higher overall system throughput. Our CPU-FPGA system also achieves superior scalability wrt number of parallel workers than state-of-the-art parallel MCTS implementations on CPU.

cs.DC↗

arXiv2022

Performance Modeling Sparse MTTKRP Using Optical Static Random Access Memory on FPGA

Electrical static random memory (E-SRAM) is the current standard for internal static memory in Field Programmable Gate Array (FPGA). Despite the dramatic improvement in E-SRAM technology over the past decade, the goal of ultra-fast, energy-efficient static random memory has yet to be achieved with E-SRAM technology. However, preliminary research into optical static random access memory (O-SRAM) has shown promising results in creating energy-efficient ultra-fast static memories. This paper investigates the advantage of O-SRAM over E-SRAM in access speed and energy performance while executing sparse Matricized Tensor Times Khatri-Rao Product (spMTTKRP). spMTTKRP is an essential component of tensor decomposition algorithms which is heavily used in data science applications. The evaluation results show O-SRAMs can achieve speeds of 1.1x - 2.9x while saving 2.8x - 8.1x energy compared to conventional E-SRAM technology.

cs.DC↗

arXiv2022

Towards Programmable Memory Controller for Tensor Decomposition

Tensor decomposition has become an essential tool in many data science applications. Sparse Matricized Tensor Times Khatri-Rao Product (MTTKRP) is the pivotal kernel in tensor decomposition algorithms that decompose higher-order real-world large tensors into multiple matrices. Accelerating MTTKRP can speed up the tensor decomposition process immensely. Sparse MTTKRP is a challenging kernel to accelerate due to its irregular memory access characteristics. Implementing accelerators on Field Programmable Gate Array (FPGA) for kernels such as MTTKRP is attractive due to the energy efficiency and the inherent parallelism of FPGA. This paper explores the opportunities, key challenges, and an approach for designing a custom memory controller on FPGA for MTTKRP while exploring the parameter space of such a custom memory controller.

cs.DC↗

arXiv2022

Low-latency Mini-batch GNN Inference on CPU-FPGA Heterogeneous Platform

Mini-batch inference of Graph Neural Networks (GNNs) is a key problem in many real-world applications. Recently, a GNN design principle of model depth-receptive field decoupling has been proposed to address the well-known issue of neighborhood explosion. Decoupled GNN models achieve higher accuracy than original models and demonstrate excellent scalability for mini-batch inference. We map Decoupled GNNs onto CPU-FPGA heterogeneous platforms to achieve low-latency mini-batch inference. On the FPGA platform, we design a novel GNN hardware accelerator with an adaptive datapath denoted Adaptive Computation Kernel (ACK) that can execute various computation kernels of GNNs with low-latency: (1) for dense computation kernels expressed as matrix multiplication, ACK works as a systolic array with fully localized connections, (2) for sparse computation kernels, ACK follows the scatter-gather paradigm and works as multiple parallel pipelines to support the irregular connectivity of graphs. The proposed task scheduling hides the CPU-FPGA data communication overhead to reduce the inference latency. We develop a fast design space exploration algorithm to generate a single accelerator for multiple target GNN models. We implement our accelerator on a state-of-the-art CPU-FPGA platform and evaluate the performance using three representative models (GCN, GraphSAGE, and GAT). Results show that our CPU-FPGA implementation achieves $21.4-50.8\times$, $2.9-21.6\times$, $4.7\times$ latency reduction compared with state-of-the-art implementations on CPU-only, CPU-GPU and CPU-FPGA platforms.

cs.DC↗

arXiv2022

Design and Implementation of Knowledge Base for Runtime Management of Software Defined Hardware

Runtime-reconfigurable software coupled with reconfigurable hardware is highly desirable as a means towards maximizing runtime efficiency without compromising programmability. Compilers for such software systems are extremely difficult to design as they must leverage different types of hardware at runtime. To address the need for static and dynamic compiler optimization of workflows matched to dynamically reconfigurable hardware, we propose a novel design of the central component of a dynamic software compiler for software defined hardware. Our comprehensive design focuses not just on static knowledge but also on semi-supervised extraction of knowledge from program executions and developing their performance models. Specifically, our novel {\it dynamic and extensible knowledge base} 1) continuously gathers knowledge during execution of workflows 2) identifies {\it optimal} implementations of workflows on {\it optimal} (available) hardware configurations. It plays a hub role in storing information from, and providing information to other components of the compiler, as well as the human analyst. Through a rich tripartite graph representation, the knowledge base captures and learns extensive information on decomposition and mapping of code steps to kernels and mapping of kernels to available hardware configurations. The knowledge base is implemented using the C++ Boost Library and is capable of quickly processing offline and online queries and updates. We show that our knowledge base can answer queries in $1ms$ regardless of the number of workflows it stores. To the best of our knowledge, this is the first design of a dynamic and extensible knowledge base to support compilation of high-level languages to leverage arbitrary reconfigurable platforms.

cs.SE↗

arXiv2022

Deep Graph Neural Networks with Shallow Subgraph Samplers

While Graph Neural Networks (GNNs) are powerful models for learning representations on graphs, most state-of-the-art models do not have significant accuracy gain beyond two to three layers. Deep GNNs fundamentally need to address: 1). expressivity challenge due to oversmoothing, and 2). computation challenge due to neighborhood explosion. We propose a simple "deep GNN, shallow sampler" design principle to improve both the GNN accuracy and efficiency -- to generate representation of a target node, we use a deep GNN to pass messages only within a shallow, localized subgraph. A properly sampled subgraph may exclude irrelevant or even noisy nodes, and still preserve the critical neighbor features and graph structures. The deep GNN then smooths the informative local signals to enhance feature learning, rather than oversmoothing the global graph signals into just "white noise". We theoretically justify why the combination of deep GNNs with shallow samplers yields the best learning performance. We then propose various sampling algorithms and neural architecture extensions to achieve good empirical results. On the largest public graph dataset, ogbn-papers100M, we achieve state-of-the-art accuracy with an order of magnitude reduction in hardware cost.

cs.LG↗

arXiv2022

Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA

Temporal Graph Neural Networks (TGNNs) are powerful models to capture temporal, structural, and contextual information on temporal graphs. The generated temporal node embeddings outperform other methods in many downstream tasks. Real-world applications require high performance inference on real-time streaming dynamic graphs. However, these models usually rely on complex attention mechanisms to capture relationships between temporal neighbors. In addition, maintaining vertex memory suffers from intrinsic temporal data dependency that hinders task-level parallelism, making it inefficient on general-purpose processors. In this work, we present a novel model-architecture co-design for inference in memory-based TGNNs on FPGAs. The key modeling optimizations we propose include a light-weight method to compute attention scores and a related temporal neighbor pruning strategy to further reduce computation and memory accesses. These are holistically coupled with key hardware optimizations that leverage FPGA hardware. We replace the temporal sampler with an on-chip FIFO based hardware sampler and the time encoder with a look-up-table. We train our simplified models using knowledge distillation to ensure similar accuracy vis-á-vis the original model. Taking advantage of the model optimizations, we propose a principled hardware architecture using batching, pipelining, and prefetching techniques to further improve the performance. We also propose a hardware mechanism to ensure the chronological vertex updating without sacrificing the computation parallelism. We evaluate the performance of the proposed hardware accelerator on three real-world datasets.

cs.AR↗

arXiv2022

Decoupling the Depth and Scope of Graph Neural Networks

State-of-the-art Graph Neural Networks (GNNs) have limited scalability with respect to the graph and model sizes. On large graphs, increasing the model depth often means exponential expansion of the scope (i.e., receptive field). Beyond just a few layers, two fundamental challenges emerge: 1. degraded expressivity due to oversmoothing, and 2. expensive computation due to neighborhood explosion. We propose a design principle to decouple the depth and scope of GNNs -- to generate representation of a target entity (i.e., a node or an edge), we first extract a localized subgraph as the bounded-size scope, and then apply a GNN of arbitrary depth on top of the subgraph. A properly extracted subgraph consists of a small number of critical neighbors, while excluding irrelevant ones. The GNN, no matter how deep it is, smooths the local neighborhood into informative representation rather than oversmoothing the global graph into "white noise". Theoretically, decoupling improves the GNN expressive power from the perspectives of graph signal processing (GCN), function approximation (GraphSAGE) and topological learning (GIN). Empirically, on seven graphs (with up to 110M nodes) and six backbone GNN architectures, our design achieves significant accuracy improvement with orders of magnitude reduction in computation and hardware cost.

cs.LG↗

arXiv2021

HP-GNN: Generating High Throughput GNN Training Implementation on CPU-FPGA Heterogeneous Platform

Graph Neural Networks (GNNs) have shown great success in many applications such as recommendation systems, molecular property prediction, traffic prediction, etc. Recently, CPU-FPGA heterogeneous platforms have been used to accelerate many applications by exploiting customizable data path and abundant user-controllable on-chip memory resources of FPGAs. Yet, accelerating and deploying GNN training on such platforms requires not only expertise in hardware design but also substantial development efforts. We propose HP-GNN, a novel framework that generates high throughput GNN training implementations on a given CPU-FPGA platform that can benefit both application developers and machine learning researchers. HP-GNN takes GNN training algorithms, GNN models as the inputs, and automatically performs hardware mapping onto the target CPU-FPGA platform. HP-GNN consists of: (1) data layout and internal representation that reduce the memory traffic and random memory accesses; (2) optimized hardware templates that support various GNN models; (3) a design space exploration engine for automatic hardware mapping; (4) high-level application programming interfaces (APIs) that allows users to specify GNN training with only a handful of lines of code. To evaluate HP-GNN, we experiment with two well-known sampling-based GNN training algorithms and two GNN models. For each training algorithm and model, HP-GNN generates implementation on a state-of-the-art CPU-FPGA platform. Compared with CPU-only and CPU-GPU platforms, experimental results show that the generated implementations achieve $55.67\times$ and $2.17\times$ speedup on the average, respectively. Compared with the state-of-the-art GNN training implementations, HP-GNN achieves up to $4.45\times$ speedup.

cs.DC↗

arXiv2021

Parallel Peeling of Bipartite Networks for Hierarchical Dense Subgraph Discovery

Wing and Tip decomposition construct a hierarchy of butterfly-dense edge and vertex induced bipartite subgraphs, respectively. They have applications in several domains including e-commerce, recommendation systems and document analysis. Existing decomposition algorithms use a bottom-up approach that constructs the hierarchy in an increasing order of subgraph density. They iteratively peel the entities with minimum butterfly count i.e. remove them from the graph and update the butterfly count of other entities. However, the amount of butterflies in large bipartite graphs makes bottom-up peeling computationally demanding. Furthermore, the strict order of peeling entities results in a numerous sequentially dependent iterations, which makes parallelization challenging. In this paper, we propose a novel Parallel Bipartite Network peelinG (PBNG) framework which adopts a two-phased peeling approach to relax the order of peeling, and in turn, reduce synchronization. The first phase divides the decomposition hierarchy into several partitions using very few peeling iterations. The second phase concurrently processes these partitions to generate the final hierarchy, and requires no global synchronization. The two-phased peeling further enables batching optimizations that dramatically improve the computational efficiency. We empirically evaluate PBNG using several real-world bipartite graphs. Compared to the state-of-the-art frameworks and decomposition algorithms, PBNG achieves up to four orders of magnitude reduction in synchronization and two orders of magnitude speedup, respectively. We also present the first decomposition results of some of the largest public real-world datasets, which PBNG can peel in few minutes but existing algorithms fail to process even in several days.

cs.DC↗

arXiv2021

Reconfigurable Low-latency Memory System for Sparse Matricized Tensor Times Khatri-Rao Product on FPGA

Tensor decomposition has become an essential tool in many applications in various domains, including machine learning. Sparse Matricized Tensor Times Khatri-Rao Product (MTTKRP) is one of the most computationally expensive kernels in tensor computations. Despite having significant computational parallelism, MTTKRP is a challenging kernel to optimize due to its irregular memory access characteristics. This paper focuses on a multi-faceted memory system, which explores the spatial and temporal locality of the data structures of MTTKRP. Further, users can reconfigure our design depending on the behavior of the compute units used in the FPGA accelerator. Our system efficiently accesses all the MTTKRP data structures while reducing the total memory access time, using a distributed cache and Direct Memory Access (DMA) subsystem. Moreover, our work improves the memory access time by 3.5x compared with commercial memory controller IPs. Also, our system shows 2x and 1.26x speedups compared with cache-only and DMA-only memory systems, respectively.

cs.AR↗