arXiv subjects

Zhiru Zhang

Publications and source records attributed to Zhiru Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2022

Analysis and Optimization of GNN-Based Recommender Systems on Persistent Memory

Graph neural networks (GNNs), which have emerged as an effective method for handling machine learning tasks on graphs, bring a new approach to building recommender systems, where the task of recommendation can be formulated as the link prediction problem on user-item bipartite graphs. Training GNN-based recommender systems (GNNRecSys) on large graphs incurs a large memory footprint, easily exceeding the DRAM capacity on a typical server. Existing solutions resort to distributed subgraph training, which is inefficient due to the high cost of dynamically constructing subgraphs and significant redundancy across subgraphs. The emerging persistent memory technologies provide a significantly larger memory capacity than DRAMs at an affordable cost, making single-machine GNNRecSys training feasible, which eliminates the inefficiencies in distributed training. One major concern of using persistent memory devices for GNNRecSys is their relatively low bandwidth compared with DRAMs. This limitation can be particularly detrimental to achieving high performance for GNNRecSys workloads since their dominant compute kernels are sparse and memory access intensive. To understand whether persistent memory is a good fit for GNNRecSys training, we perform an in-depth characterization of GNNRecSys workloads and a comprehensive analysis of their performance on a persistent memory device, namely, Intel Optane. Based on the analysis, we provide guidance on how to configure Optane for GNNRecSys workloads. Furthermore, we present techniques for large-batch training to fully realize the advantages of single-machine GNNRecSys training. Our experiment results show that with the tuned batch size and optimal system configuration, Optane-based single-machine GNNRecSys training outperforms distributed training by a large margin, especially when handling deep GNN models.

cs.IR↗

arXiv2022

TAPA: A Scalable Task-Parallel Dataflow Programming Framework for Modern FPGAs with Co-Optimization of HLS and Physical Design

In this paper, we propose TAPA, an end-to-end framework that compiles a C++ task-parallel dataflow program into a high-frequency FPGA accelerator. Compared to existing solutions, TAPA has two major advantages. First, TAPA provides a set of convenient APIs that allow users to easily express flexible and complex inter-task communication structures. Second, TAPA adopts a coarse-grained floorplanning step during HLS compilation for accurate pipelining of potential critical paths. In addition, TAPA implements several optimization techniques specifically tailored for modern HBM-based FPGAs. In our experiments with a total of 43 designs, we improve the average frequency from 147 MHz to 297 MHz (a 102% improvement) with no loss of throughput and a negligible change in resource utilization. Notably, in 16 experiments we make the originally unroutable designs achieve 274 MHz on average. The framework is available at https://github.com/UCLA-VAST/tapa and the core floorplan module is available at https://github.com/UCLA-VAST/AutoBridge.

cs.AR↗

arXiv2022

Structured Pruning is All You Need for Pruning CNNs at Initialization

Pruning is a popular technique for reducing the model size and computational cost of convolutional neural networks (CNNs). However, a slow retraining or fine-tuning procedure is often required to recover the accuracy loss caused by pruning. Recently, a new research direction on weight pruning, pruning-at-initialization (PAI), is proposed to directly prune CNNs before training so that fine-tuning or retraining can be avoided. While PAI has shown promising results in reducing the model size, existing approaches rely on fine-grained weight pruning which requires unstructured sparse matrix computation, making it difficult to achieve real speedup in practice unless the sparsity is very high. This work is the first to show that fine-grained weight pruning is in fact not necessary for PAI. Instead, the layerwise compression ratio is the main critical factor to determine the accuracy of a CNN model pruned at initialization. Based on this key observation, we propose PreCropping, a structured hardware-efficient model compression scheme. PreCropping directly compresses the model at the channel level following the layerwise compression ratio. Compared to weight pruning, the proposed scheme is regular and dense in both storage and computation without sacrificing accuracy. In addition, since PreCropping compresses CNNs at initialization, the computational and memory costs of CNNs are reduced for both training and inference on commodity hardware. We empirically demonstrate our approaches on several modern CNN architectures, including ResNet, ShuffleNet, and MobileNet for both CIFAR-10 and ImageNet.

cs.CV↗

arXiv2022

MGX: Near-Zero Overhead Memory Protection for Data-Intensive Accelerators

This paper introduces MGX, a near-zero overhead memory protection scheme for hardware accelerators. MGX minimizes the performance overhead of off-chip memory encryption and integrity verification by exploiting the application-specific properties of the accelerator execution. In particular, accelerators tend to explicitly manage data movement between on-chip and off-chip memories. Therefore, the general memory access pattern of an accelerator can largely be determined for a given application. Exploiting these characteristics, MGX generates version numbers used in memory encryption and integrity verification using on-chip accelerator state rather than storing them in the off-chip memory; it also customizes the granularity of the memory protection to match the granularity used by the accelerator. To demonstrate the efficacy of MGX, we present an in-depth study of MGX for DNN and graph algorithms. Experimental results show that on average, MGX lowers the performance overhead of memory protection from 28% and 33% to 4% and 5% for DNN and graph processing accelerators in a wide range of benchmarks, respectively.

cs.CR↗

arXiv2022

GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learning

This paper proposes GuardNN, a secure DNN accelerator that provides hardware-based protection for user data and model parameters even in an untrusted environment. GuardNN shows that the architecture and protection can be customized for a specific application to provide strong confidentiality and integrity guarantees with negligible overhead. The design of the GuardNN instruction set reduces the TCB to just the accelerator and allows confidentiality protection even when the instructions from a host cannot be trusted. GuardNN minimizes the overhead of memory encryption and integrity verification by customizing the off-chip memory protection for the known memory access patterns of a DNN accelerator. GuardNN is prototyped on an FPGA, demonstrating effective confidentiality protection with ~3% performance overhead for inference.

cs.CR↗

arXiv2022

PokeBNN: A Binary Pursuit of Lightweight Accuracy

Optimization of Top-1 ImageNet promotes enormous networks that may be impractical in inference settings. Binary neural networks (BNNs) have the potential to significantly lower the compute intensity but existing models suffer from low quality. To overcome this deficiency, we propose PokeConv, a binary convolution block which improves quality of BNNs by techniques such as adding multiple residual paths, and tuning the activation function. We apply it to ResNet-50 and optimize ResNet's initial convolutional layer which is hard to binarize. We name the resulting network family PokeBNN. These techniques are chosen to yield favorable improvements in both top-1 accuracy and the network's cost. In order to enable joint optimization of the cost together with accuracy, we define arithmetic computation effort (ACE), a hardware- and energy-inspired cost metric for quantized and binarized networks. We also identify a need to optimize an under-explored hyper-parameter controlling the binarization gradient approximation. We establish a new, strong state-of-the-art (SOTA) on top-1 accuracy together with commonly-used CPU64 cost, ACE cost and network size metrics. ReActNet-Adam, the previous SOTA in BNNs, achieved a 70.5% top-1 accuracy with 7.9 ACE. A small variant of PokeBNN achieves 70.5% top-1 with 2.6 ACE, more than 3x reduction in cost; a larger PokeBNN achieves 75.6% top-1 with 7.8 ACE, more than 5% improvement in accuracy without increasing the cost. PokeBNN implementation in JAX/Flax and reproduction instructions are available in AQT repository: https://github.com/google/aqt

cs.LG↗

arXiv2021

BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining

Neural network robustness has become a central topic in machine learning in recent years. Most training algorithms that improve the model's robustness to adversarial and common corruptions also introduce a large computational overhead, requiring as many as ten times the number of forward and backward passes in order to converge. To combat this inefficiency, we propose BulletTrain $-$ a boundary example mining technique to drastically reduce the computational cost of robust training. Our key observation is that only a small fraction of examples are beneficial for improving robustness. BulletTrain dynamically predicts these important examples and optimizes robust training algorithms to focus on the important examples. We apply our technique to several existing robust training algorithms and achieve a 2.1$\times$ speed-up for TRADES and MART on CIFAR-10 and a 1.7$\times$ speed-up for AugMix on CIFAR-10-C and CIFAR-100-C without any reduction in clean and robust accuracy.

cs.LG↗

arXiv2021

A Roadmap for Enabling a Future-Proof In-Network Computing Data Plane Ecosystem

As the vision of in-network computing becomes more mature, we see two parallel evolutionary trends. First, we see the evolution of richer, more demanding applications that require capabilities beyond programmable switching ASICs. Second, we see the evolution of diverse data plane technologies with many other future capabilities on the horizon. While some point solutions exist to tackle the intersection of these trends, we see several ecosystem-level disconnects today; e.g., the need to refactor applications for new data planes, lack of systematic guidelines to inform the development of future data plane capabilities, and lack of holistic runtime frameworks for network operators. In this paper, we use a simple-yet-instructive emerging application-data plane combination to highlight these disconnects. Drawing on these lessons, we sketch a high-level roadmap and guidelines for the community to tackle these to create a more thriving "future-proof" data plane ecosystem.

cs.NI↗

arXiv2021

Dense Pruning of Pointwise Convolutions in the Frequency Domain

Depthwise separable convolutions and frequency-domain convolutions are two recent ideas for building efficient convolutional neural networks. They are seemingly incompatible: the vast majority of operations in depthwise separable CNNs are in pointwise convolutional layers, but pointwise layers use 1x1 kernels, which do not benefit from frequency transformation. This paper unifies these two ideas by transforming the activations, not the kernels. Our key insights are that 1) pointwise convolutions commute with frequency transformation and thus can be computed in the frequency domain without modification, 2) each channel within a given layer has a different level of sensitivity to frequency domain pruning, and 3) each channel's sensitivity to frequency pruning is approximately monotonic with respect to frequency. We leverage this knowledge by proposing a new technique which wraps each pointwise layer in a discrete cosine transform (DCT) which is truncated to selectively prune coefficients above a given threshold as per the needs of each channel. To learn which frequencies should be pruned from which channels, we introduce a novel learned parameter which specifies each channel's pruning threshold. We add a new regularization term which incentivizes the model to decrease the number of retained frequencies while still maintaining task accuracy. Unlike weight pruning techniques which rely on sparse operators, our contiguous frequency band pruning results in fully dense computation. We apply our technique to MobileNetV2 and in the process reduce computation time by 22% and incur <1% accuracy degradation.

cs.CV↗

arXiv2021

Scaling Up Hardware Accelerator Verification using A-QED with Functional Decomposition

Hardware accelerators (HAs) are essential building blocks for fast and energy-efficient computing systems. Accelerator Quick Error Detection (A-QED) is a recent formal technique which uses Bounded Model Checking for pre-silicon verification of HAs. A-QED checks an HA for self-consistency, i.e., whether identical inputs within a sequence of operations always produce the same output. Under modest assumptions, A-QED is both sound and complete. However, as is well-known, large design sizes significantly limit the scalability of formal verification, including A-QED. We overcome this scalability challenge through a new decomposition technique for A-QED, called A-QED with Decomposition (A-QED$^2$). A-QED$^2$ systematically decomposes an HA into smaller, functional sub-modules, called sub-accelerators, which are then verified independently using A-QED. We prove completeness of A-QED$^2$; in particular, if the full HA under verification contains a bug, then A-QED$^2$ ensures detection of that bug during A-QED verification of the corresponding sub-accelerators. Results on over 100 (buggy) versions of a wide variety of HAs with millions of logic gates demonstrate the effectiveness and practicality of A-QED$^2$.

cs.LO↗

arXiv2021

SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation

A black-box spectral method is introduced for evaluating the adversarial robustness of a given machine learning (ML) model. Our approach, named SPADE, exploits bijective distance mapping between the input/output graphs constructed for approximating the manifolds corresponding to the input/output data. By leveraging the generalized Courant-Fischer theorem, we propose a SPADE score for evaluating the adversarial robustness of a given model, which is proved to be an upper bound of the best Lipschitz constant under the manifold setting. To reveal the most non-robust data samples highly vulnerable to adversarial attacks, we develop a spectral graph embedding procedure leveraging dominant generalized eigenvectors. This embedding step allows assigning each data sample a robustness score that can be further harnessed for more effective adversarial training. Our experiments show the proposed SPADE method leads to promising empirical results for neural network models that are adversarially trained with the MNIST and CIFAR-10 data sets.

cs.LG↗

arXiv2021

Dagger: Accelerating RPCs in Cloud Microservices Through Tightly-Coupled Reconfigurable NICs

The ongoing shift of cloud services from monolithic designs to microservices creates high demand for efficient and high performance datacenter networking stacks, optimized for fine-grained workloads. Commodity networking systems based on software stacks and peripheral NICs introduce high overheads when it comes to delivering small messages. We present Dagger, a hardware acceleration fabric for cloud RPCs based on FPGAs, where the accelerator is closely-coupled with the host processor over a configurable memory interconnect. The three key design principle of Dagger are: (1) offloading the entire RPC stack to an FPGA-based NIC, (2) leveraging memory interconnects instead of PCIe buses as the interface with the host CPU, and (3) making the acceleration fabric reconfigurable, so it can accommodate the diverse needs of microservices. We show that the combination of these principles significantly improves the efficiency and performance of cloud RPC systems while preserving their generality. Dagger achieves 1.3-3.8x higher per-core RPC throughput compared to both highly-optimized software stacks, and systems using specialized RDMA adapters. It also scales up to 84 Mrps with 8 threads on 4 CPU cores, while maintaining state-of-the-art us-scale tail latency. We also demonstrate that large third-party applications, like memcached and MICA KVS, can be easily ported on Dagger with minimal changes to their codebase, bringing their median and tail KVS access latency down to 2.8 - 3.5us and 5.4 - 7.8us, respectively. Finally, we show that Dagger is beneficial for multi-tier end-to-end microservices with different threading models by evaluating it using an 8-tier application implementing a flight check-in service.

cs.AR↗

arXiv2021

OverQ: Opportunistic Outlier Quantization for Neural Network Accelerators

Outliers in weights and activations pose a key challenge for fixed-point quantization of neural networks. While they can be addressed by fine-tuning, this is not practical for ML service providers (e.g., Google or Microsoft) who often receive customer models without training data. Specialized hardware for handling activation outliers can enable low-precision neural networks, but at the cost of nontrivial area overhead. We instead propose overwrite quantization (OverQ), a lightweight hardware technique that opportunistically increases bitwidth for activation outliers by overwriting nearby zeros. It has two major modes of operation: range overwrite and precision overwrite. Range overwrite reallocates bits to increase the range of outliers, while precision overwrite reuses zeros to increase the precision of non-outlier values. Combining range overwrite with a simple cascading logic, we handle the vast majority of outliers to significantly improve model accuracy at low bitwidth. Our experiments show that with modest cascading, we can consistently handle over 90% of outliers and achieve +5% ImageNet Top-1 accuracy on a quantized ResNet-50 at 4 bits. Our ASIC prototype shows OverQ can be implemented efficiently on top of existing weight-stationary systolic arrays with small area increases per processing element. We imagine this technique can complement modern DNN accelerator designs to provide small increases in accuracy with insignificant area overhead.

cs.LG↗

arXiv2021

Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design

Artificial intelligence (AI) technologies have dramatically advanced in recent years, resulting in revolutionary changes in people's lives. Empowered by edge computing, AI workloads are migrating from centralized cloud architectures to distributed edge systems, introducing a new paradigm called edge AI. While edge AI has the promise of bringing significant increases in autonomy and intelligence into everyday lives through common edge devices, it also raises new challenges, especially for the development of its algorithms and the deployment of its services, which call for novel design methodologies catered to these unique challenges. In this paper, we provide a comprehensive survey of the latest enabling design methodologies that span the entire edge AI development stack. We suggest that the key methodologies for effective edge AI development are single-layer specialization and cross-layer co-design. We discuss representative methodologies in each category in detail, including on-device training methods, specialized software design, dedicated hardware design, benchmarking and design automation, software/hardware co-design, software/compiler co-design, and compiler/hardware co-design. Moreover, we attempt to reveal hidden cross-layer design opportunities that can further boost the solution quality of future edge AI and provide insights into future directions and emerging areas that require increased research focus.

cs.AR↗

arXiv2020

FracBNN: Accurate and FPGA-Efficient Binary Neural Networks with Fractional Activations

Binary neural networks (BNNs) have 1-bit weights and activations. Such networks are well suited for FPGAs, as their dominant computations are bitwise arithmetic and the memory requirement is also significantly reduced. However, compared to start-of-the-art compact convolutional neural network (CNN) models, BNNs tend to produce a much lower accuracy on realistic datasets such as ImageNet. In addition, the input layer of BNNs has gradually become a major compute bottleneck, because it is conventionally excluded from binarization to avoid a large accuracy loss. This work proposes FracBNN, which exploits fractional activations to substantially improve the accuracy of BNNs. Specifically, our approach employs a dual-precision activation scheme to compute features with up to two bits, using an additional sparse binary convolution. We further binarize the input layer using a novel thermometer encoding. Overall, FracBNN preserves the key benefits of conventional BNNs, where all convolutional layers are computed in pure binary MAC operations (BMACs). We design an efficient FPGA-based accelerator for our novel BNN model that supports the fractional activations. To evaluate the performance of FracBNN under a resource-constrained scenario, we implement the entire optimized network architecture on an embedded FPGA (Xilinx Ultra96v2). Our experiments on ImageNet show that FracBNN achieves an accuracy comparable to MobileNetV2, surpassing the best-known BNN design on FPGAs with an increase of 28.9% in top-1 accuracy and a 2.5x reduction in model size. FracBNN also outperforms a recently introduced BNN model with an increase of 2.4% in top-1 accuracy while using the same model size. On the embedded FPGA device, FracBNN demonstrates the ability of real-time image classification.

cs.LG↗

arXiv2020

Logic Synthesis Meets Machine Learning: Trading Exactness for Generalization

Logic synthesis is a fundamental step in hardware design whose goal is to find structural representations of Boolean functions while minimizing delay and area. If the function is completely-specified, the implementation accurately represents the function. If the function is incompletely-specified, the implementation has to be true only on the care set. While most of the algorithms in logic synthesis rely on SAT and Boolean methods to exactly implement the care set, we investigate learning in logic synthesis, attempting to trade exactness for generalization. This work is directly related to machine learning where the care set is the training set and the implementation is expected to generalize on a validation set. We present learning incompletely-specified functions based on the results of a competition conducted at IWLS 2020. The goal of the competition was to implement 100 functions given by a set of care minterms for training, while testing the implementation using a set of validation minterms sampled from the same function. We make this benchmark suite available and offer a detailed comparative analysis of the different approaches to learning

cs.LG↗

arXiv2020

FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems

Graph neural networks (GNNs) are gaining increasing popularity as a promising approach to machine learning on graphs. Unlike traditional graph workloads where each vertex/edge is associated with a scalar, GNNs attach a feature tensor to each vertex/edge. This additional feature dimension, along with consequently more complex vertex- and edge-wise computations, has enormous implications on locality and parallelism, which existing graph processing systems fail to exploit. This paper proposes FeatGraph to accelerate GNN workloads by co-optimizing graph traversal and feature dimension computation. FeatGraph provides a flexible programming interface to express diverse GNN models by composing coarse-grained sparse templates with fine-grained user-defined functions (UDFs) on each vertex/edge. FeatGraph incorporates optimizations for graph traversal into the sparse templates and allows users to specify optimizations for UDFs with a feature dimension schedule (FDS). FeatGraph speeds up end-to-end GNN training and inference by up to 32x on CPU and 7x on GPU.

cs.LG↗

arXiv2020

Dagger: Towards Efficient RPCs in Cloud Microservices with Near-Memory Reconfigurable NICs

Cloud applications are increasingly relying on hundreds of loosely-coupled microservices to complete user requests that meet an applications end-to-end QoS requirements. Communication time between services accounts for a large fraction of the end-to-end latency and can introduce performance unpredictability and QoS violations. This work presents our early work on Dagger, a hardware acceleration platform for networking, designed specifically with the unique qualities of microservices in mind. The Dagger architecture relies on an FPGA-based NIC, closely coupled with the processor over a configurable memory interconnect, designed to offload and accelerate RPC stacks. Unlike the traditional cloud systems that use PCIe links as the NIC I/O interface, we leverage memory-interconnected FPGAs as networking devices to provide the efficiency, transparency, and programmability needed for fine-grained microservices. We show that this considerably improves CPU utilization and performance for cloud RPCs.

cs.AR↗