PyTorchKR Papers

최신 논문

총 2,230편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2208.08711공식 코드 · Papers with Code

L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training

The training process of deep neural networks (DNNs) is usually pipelined with stages for data preparation on CPUs followed by gradient computation on accelerators like GPUs. In an ideal pipeline, the end-to-end training throughput is eventually limited by the throughput of the accelerator, not by that of data preparation. In the past, the DNN training pipeline achieved a near-optimal throughput by utilizing datasets encoded with a lightweight, lossy image format like JPEG. However, as high-resolution, losslessly-encoded datasets become more popular for applications requiring high accuracy, a performance problem arises in the data preparation stage due to low-throughput image decoding on the CPU. Thus, we propose L3, a custom lightweight, lossless image format for high-resolution, high-throughput DNN training. The decoding process of L3 is effectively parallelized on the accelerator, thus minimizing CPU intervention for data preparation during DNN training. L3 achieves a 9.29x higher data preparation throughput than PNG, the most popular lossless image format, for the Cityscapes dataset on NVIDIA A100 GPU, which leads to 1.71x higher end-to-end training throughput. Compared to JPEG and WebP, two popular lossy image formats, L3 provides up to 1.77x and 2.87x higher end-to-end training throughput for ImageNet, respectively, at equivalent metric performance.

arXiv:2208.08706공식 코드 · Papers with Code

Musika! Fast Infinite Waveform Music Generation

Fast and user-controllable music generation could enable novel ways of composing or performing music. However, state-of-the-art music generation systems require large amounts of data and computational resources for training, and are slow at inference. This makes them impractical for real-time interactive use. In this work, we introduce Musika, a music generation system that can be trained on hundreds of hours of music using a single consumer GPU, and that allows for much faster than real-time generation of music of arbitrary length on a consumer CPU. We achieve this by first learning a compact invertible representation of spectrogram magnitudes and phases with adversarial autoencoders, then training a Generative Adversarial Network (GAN) on this representation for a particular music domain. A latent coordinate system enables generating arbitrarily long sequences of excerpts in parallel, while a global context vector allows the music to remain stylistically coherent through time. We perform quantitative evaluations to assess the quality of the generated samples and showcase options for user control in piano and techno music generation. We release the source code and pretrained autoencoder weights at github.com/marcoppasini/musika, such that a GAN can be trained on a new music domain with a single GPU in a matter of hours.

arXiv:2208.07339공식 코드 · Papers with Code

LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

Large language models have been widely adopted but require significant GPU memory for inference. We develop a procedure for Int8 matrix multiplication for feed-forward and attention projection layers in transformers, which cut the memory needed for inference by half while retaining full precision performance. With our method, a 175B parameter 16/32-bit checkpoint can be loaded, converted to Int8, and used immediately without performance degradation. This is made possible by understanding and working around properties of highly systematic emergent features in transformer language models that dominate attention and transformer predictive performance. To cope with these features, we develop a two-part quantization procedure, LLM.int8(). We first use vector-wise quantization with separate normalization constants for each inner product in the matrix multiplication, to quantize most of the features. However, for the emergent outliers, we also include a new mixed-precision decomposition scheme, which isolates the outlier feature dimensions into a 16-bit matrix multiplication while still more than 99.9% of values are multiplied in 8-bit. Using LLM.int8(), we show empirically it is possible to perform inference in LLMs with up to 175B parameters without any performance degradation. This result makes such models much more accessible, for example making it possible to use OPT-175B/BLOOM on a single server with consumer GPUs. We open-source our software.

arXiv:2208.07204공식 코드 · Papers with Code

USB: A Unified Semi-supervised Learning Benchmark for Classification

Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural networks from scratch, which is time-consuming and environmentally unfriendly. To address the above issues, we construct a Unified SSL Benchmark (USB) for classification by selecting 15 diverse, challenging, and comprehensive tasks from CV, natural language processing (NLP), and audio processing (Audio), on which we systematically evaluate the dominant SSL methods, and also open-source a modular and extensible codebase for fair evaluation of these SSL methods. We further provide the pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning. USB enables the evaluation of a single SSL algorithm on more tasks from multiple domains but with less cost. Specifically, on a single NVIDIA V100, only 39 GPU days are required to evaluate FixMatch on 15 tasks in USB while 335 GPU days (279 GPU days on 4 CV datasets except for ImageNet) are needed on 5 CV tasks with TorchSSL.

arXiv:2208.06555공식 코드 · Papers with Code

BenchPress: A Deep Active Benchmark Generator

We develop BenchPress, the first ML benchmark generator for compilers that is steerable within feature space representations of source code. BenchPress synthesizes compiling functions by adding new code in any part of an empty or existing sequence by jointly observing its left and right context, achieving excellent compilation rate. BenchPress steers benchmark generation towards desired target features that has been impossible for state of the art synthesizers (or indeed humans) to reach. It performs better in targeting the features of Rodinia benchmarks in 3 different feature spaces compared with (a) CLgen - a state of the art ML synthesizer, (b) CLSmith fuzzer, (c) SRCIROR mutator or even (d) human-written code from GitHub. BenchPress is the first generator to search the feature space with active learning in order to generate benchmarks that will improve a downstream task. We show how using BenchPress, Grewe's et al. CPU vs GPU heuristic model can obtain a higher speedup when trained on BenchPress's benchmarks compared to other techniques. BenchPress is a powerful code generator: Its generated samples compile at a rate of 86%, compared to CLgen's 2.33%. Starting from an empty fixed input, BenchPress produces 10x more unique, compiling OpenCL benchmarks than CLgen, which are significantly larger and more feature diverse.

arXiv:2208.06102공식 코드 · Papers with Code

Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training

Training deep neural networks (DNNs) is becoming increasingly more resource- and energy-intensive every year. Unfortunately, existing works primarily focus on optimizing DNN training for faster completion, often without considering the impact on energy efficiency. In this paper, we observe that common practices to improve training performance can often lead to inefficient energy usage. More importantly, we demonstrate that there is a tradeoff between energy consumption and performance optimization. To this end, we propose Zeus, an optimization framework to navigate this tradeoff by automatically finding optimal job- and GPU-level configurations for recurring DNN training jobs. Zeus uses an online exploration-exploitation approach in conjunction with just-in-time energy profiling, averting the need for expensive offline measurements, while adapting to data drifts over time. Our evaluation shows that Zeus can improve the energy efficiency of DNN training by 15.3%-75.8% for diverse workloads.

arXiv:2208.05740공식 코드 · Papers with Code

General Cutting Planes for Bound-Propagation-Based Neural Network Verification

Bound propagation methods, when combined with branch and bound, are among the most effective methods to formally verify properties of deep neural networks such as correctness, robustness, and safety. However, existing works cannot handle the general form of cutting plane constraints widely accepted in traditional solvers, which are crucial for strengthening verifiers with tightened convex relaxations. In this paper, we generalize the bound propagation procedure to allow the addition of arbitrary cutting plane constraints, including those involving relaxed integer variables that do not appear in existing bound propagation formulations. Our generalized bound propagation method, GCP-CROWN, opens up the opportunity to apply general cutting plane methods for neural network verification while benefiting from the efficiency and GPU acceleration of bound propagation methods. As a case study, we investigate the use of cutting planes generated by off-the-shelf mixed integer programming (MIP) solver. We find that MIP solvers can generate high-quality cutting planes for strengthening bound-propagation-based verifiers using our new formulation. Since the branching-focused bound propagation procedure and the cutting-plane-focused MIP solver can run in parallel utilizing different types of hardware (GPUs and CPUs), their combination can quickly explore a large number of branches with strong cutting planes, leading to strong verification performance. Experiments demonstrate that our method is the first verifier that can completely solve the oval20 benchmark and verify twice as many instances on the oval21 benchmark compared to the best tool in VNN-COMP 2021, and also noticeably outperforms state-of-the-art verifiers on a wide range of benchmarks. GCP-CROWN is part of the $\alpha,\!\beta$-CROWN verifier, the VNN-COMP 2022 winner. Code is available at http://PaperCode.cc/GCP-CROWN

arXiv:2208.05321공식 코드 · Papers with Code

A Frequency-aware Software Cache for Large Recommendation System Embeddings

Deep learning recommendation models (DLRMs) have been widely applied in Internet companies. The embedding tables of DLRMs are too large to fit on GPU memory entirely. We propose a GPU-based software cache approaches to dynamically manage the embedding table in the CPU and GPU memory space by leveraging the id's frequency statistics of the target dataset. Our proposed software cache is efficient in training entire DLRMs on GPU in a synchronized update manner. It is also scaled to multiple GPUs in combination with the widely used hybrid parallel training approaches. Evaluating our prototype system shows that we can keep only 1.5% of the embedding parameters in the GPU to obtain a decent end-to-end training speed.

arXiv:2208.05004공식 코드 · Papers with Code

CoViT: Real-time phylogenetics for the SARS-CoV-2 pandemic using Vision Transformers

Real-time viral genome detection, taxonomic classification and phylogenetic analysis are critical for efficient tracking and control of viral pandemics such as Covid-19. However, the unprecedented and still growing amounts of viral genome data create a computational bottleneck, which effectively prevents the real-time pandemic tracking. For genomic tracing to work effectively, each new viral genome sequence must be placed in its pangenomic context. Re-inferring the full phylogeny of SARS-CoV-2, with datasets containing millions of samples, is prohibitively slow even using powerful computational resources. We are attempting to alleviate the computational bottleneck by modifying and applying Vision Transformer, a recently developed neural network model for image recognition, to taxonomic classification and placement of viral genomes, such as SARS-CoV-2. Our solution, CoViT, places SARS-CoV-2 genome accessions onto SARS-CoV-2 phylogenetic tree with the accuracy of 94.2%. Since CoViT is a classification neural network, it provides more than one likely placement. Specifically, one of the two most likely placements suggested by CoViT is correct with the probability of 97.9%. The probability of the correct placement to be found among the five most likely placements generated by CoViT is 99.8%. The placement time is 0.055s per individual genome running on NVIDIAs GeForce RTX 2080 Ti GPU. We make CoViT available to research community through GitHub: https://github.com/zuherJahshan/covit.

arXiv:2208.04101공식 코드 · Papers with Code

FRA-RIR: Fast Random Approximation of the Image-source Method

The training of modern speech processing systems often requires a large amount of simulated room impulse response (RIR) data in order to allow the systems to generalize well in real-world, reverberant environments. However, simulating realistic RIR data typically requires accurate physical modeling, and the acceleration of such simulation process typically requires certain computational platforms such as a graphics processing unit (GPU). In this paper, we propose FRA-RIR, a fast random approximation method of the widely-used image-source method (ISM), to efficiently generate realistic RIR data without specific computational devices. FRA-RIR replaces the physical simulation in the standard ISM by a series of random approximations, which significantly speeds up the simulation process and enables its application in on-the-fly data generation pipelines. Experiments show that FRA-RIR can not only be significantly faster than other existing ISM-based RIR simulation tools on standard computational platforms, but also improves the performance of speech denoising systems evaluated on real-world RIR when trained with simulated RIR. A Python implementation of FRA-RIR is available online\footnote{\url{https://github.com/yluo42/FRA-RIR}}.

arXiv:2208.01641공식 코드 · Papers with Code

Streaming-capable High-performance Architecture of Learned Image Compression Codecs

Learned image compression allows achieving state-of-the-art accuracy and compression ratios, but their relatively slow runtime performance limits their usage. While previous attempts on optimizing learned image codecs focused more on the neural model and entropy coding, we present an alternative method to improving the runtime performance of various learned image compression models. We introduce multi-threaded pipelining and an optimized memory model to enable GPU and CPU workloads asynchronous execution, fully taking advantage of computational resources. Our architecture alone already produces excellent performance without any change to the neural model itself. We also demonstrate that combining our architecture with previous tweaks to the neural models can further improve runtime performance. We show that our implementations excel in throughput and latency compared to the baseline and demonstrate the performance of our implementations by creating a real-time video streaming encoder-decoder sample application, with the encoder running on an embedded device.

arXiv:2208.01313공식 코드 · Papers with Code

Unified Normalization for Accelerating and Stabilizing Transformers

Solid results from Transformers have made them prevailing architectures in various natural language and vision tasks. As a default component in Transformers, Layer Normalization (LN) normalizes activations within each token to boost the robustness. However, LN requires on-the-fly statistics calculation in inference as well as division and square root operations, leading to inefficiency on hardware. What is more, replacing LN with other hardware-efficient normalization schemes (e.g., Batch Normalization) results in inferior performance, even collapse in training. We find that this dilemma is caused by abnormal behaviors of activation statistics, including large fluctuations over iterations and extreme outliers across layers. To tackle these issues, we propose Unified Normalization (UN), which can speed up the inference by being fused with other linear operations and achieve comparable performance on par with LN. UN strives to boost performance by calibrating the activation and gradient statistics with a tailored fluctuation smoothing strategy. Meanwhile, an adaptive outlier filtration strategy is applied to avoid collapse in training whose effectiveness is theoretically proved and experimentally verified in this paper. We demonstrate that UN can be an efficient drop-in alternative to LN by conducting extensive experiments on language and vision tasks. Besides, we evaluate the efficiency of our method on GPU. Transformers equipped with UN enjoy about 31% inference speedup and nearly 18% memory reduction. Code will be released at https://github.com/hikvision-research/Unified-Normalization.

arXiv:2208.00001공식 코드 · Papers with Code

FastGeodis: Fast Generalised Geodesic Distance Transform

The FastGeodis package provides an efficient implementation for computing Geodesic and Euclidean distance transforms (or a mixture of both), targeting efficient utilisation of CPU and GPU hardware. In particular, it implements the paralellisable raster scan method from Criminisi et al. (2009), where elements in a row (2D) or plane (3D) can be computed with parallel threads. This package is able to handle 2D as well as 3D data, where it achieves up to a 20x speedup on a CPU and up to a 74x speedup on a GPU as compared to an existing open-source library (Wang, 2020) that uses a non-parallelisable single-thread CPU implementation. The performance speedups reported here were evaluated using 3D volume data on an Nvidia GeForce Titan X (12 GB) with a 6-Core Intel Xeon E5-1650 CPU. Further in-depth comparison of performance improvements are discussed in the FastGeodis documentation: https://fastgeodis.readthedocs.io

arXiv:2208.00716공식 코드 · Papers with Code

Graph Neural Network with Local Frame for Molecular Potential Energy Surface

Modeling molecular potential energy surface is of pivotal importance in science. Graph Neural Networks have shown great success in this field. However, their message passing schemes need special designs to capture geometric information and fulfill symmetry requirement like rotation equivariance, leading to complicated architectures. To avoid these designs, we introduce a novel local frame method to molecule representation learning and analyze its expressivity. Projected onto a frame, equivariant features like 3D coordinates are converted to invariant features, so that we can capture geometric information with these projections and decouple the symmetry requirement from GNN design. Theoretically, we prove that given non-degenerate frames, even ordinary GNNs can encode molecules injectively and reach maximum expressivity with coordinate projection and frame-frame projection. In experiments, our model uses a simple ordinary GNN architecture yet achieves state-of-the-art accuracy. The simpler architecture also leads to higher scalability. Our model only takes about 30% inference time and 10% GPU memory compared to the most efficient baselines.

arXiv:2207.14696공식 코드 · Papers with Code

BiFeat: Supercharge GNN Training via Graph Feature Quantization

Graph Neural Networks (GNNs) is a promising approach for applications with nonEuclidean data. However, training GNNs on large scale graphs with hundreds of millions nodes is both resource and time consuming. Different from DNNs, GNNs usually have larger memory footprints, and thus the GPU memory capacity and PCIe bandwidth are the main resource bottlenecks in GNN training. To address this problem, we present BiFeat: a graph feature quantization methodology to accelerate GNN training by significantly reducing the memory footprint and PCIe bandwidth requirement so that GNNs can take full advantage of GPU computing capabilities. Our key insight is that unlike DNN, GNN is less prone to the information loss of input features caused by quantization. We identify the main accuracy impact factors in graph feature quantization and theoretically prove that BiFeat training converges to a network where the loss is within $\epsilon$ of the optimal loss of uncompressed network. We perform extensive evaluation of BiFeat using several popular GNN models and datasets, including GraphSAGE on MAG240M, the largest public graph dataset. The results demonstrate that BiFeat achieves a compression ratio of more than 30 and improves GNN training speed by 200%-320% with marginal accuracy loss. In particular, BiFeat achieves a record by training GraphSAGE on MAG240M within one hour using only four GPUs.

arXiv:2207.14507공식 코드 · Papers with Code

GPU-accelerated SIFT-aided source identification of stabilized videos

Video stabilization is an in-camera processing commonly applied by modern acquisition devices. While significantly improving the visual quality of the resulting videos, it has been shown that such operation typically hinders the forensic analysis of video signals. In fact, the correct identification of the acquisition source usually based on Photo Response non-Uniformity (PRNU) is subject to the estimation of the transformation applied to each frame in the stabilization phase. A number of techniques have been proposed for dealing with this problem, which however typically suffer from a high computational burden due to the grid search in the space of inversion parameters. Our work attempts to alleviate these shortcomings by exploiting the parallelization capabilities of Graphics Processing Units (GPUs), typically used for deep learning applications, in the framework of stabilised frames inversion. Moreover, we propose to exploit SIFT features {to estimate the camera momentum and} %to identify less stabilized temporal segments, thus enabling a more accurate identification analysis, and to efficiently initialize the frame-wise parameter search of consecutive frames. Experiments on a consolidated benchmark dataset confirm the effectiveness of the proposed approach in reducing the required computational time and improving the source identification accuracy. {The code is available at \url{https://github.com/AMontiB/GPU-PRNU-SIFT}}.

arXiv:2207.14200공식 코드 · Papers with Code

CrAM: A Compression-Aware Minimizer

Deep neural networks (DNNs) often have to be compressed, via pruning and/or quantization, before they can be deployed in practical settings. In this work we propose a new compression-aware minimizer dubbed CrAM that modifies the optimization step in a principled way, in order to produce models whose local loss behavior is stable under compression operations such as pruning. Thus, dense models trained via CrAM should be compressible post-training, in a single step, without significant accuracy loss. Experimental results on standard benchmarks, such as residual networks for ImageNet classification and BERT models for language modelling, show that CrAM produces dense models that can be more accurate than the standard SGD/Adam-based baselines, but which are stable under weight pruning: specifically, we can prune models in one-shot to 70-80% sparsity with almost no accuracy loss, and to 90% with reasonable ($\sim 1\%$) accuracy loss, which is competitive with gradual compression methods. Additionally, CrAM can produce sparse models which perform well for transfer learning, and it also works for semi-structured 2:4 pruning patterns supported by GPU hardware. The code for reproducing the results is available at https://github.com/IST-DASLab/CrAM .

arXiv:2207.12547공식 코드 · Papers with Code

The BUTTER Zone: An Empirical Study of Training Dynamics in Fully Connected Neural Networks

We present an empirical dataset surveying the deep learning phenomenon on fully-connected feed-forward multilayer perceptron neural networks. The dataset, which is now freely available online, records the per-epoch training and generalization performance of 483 thousand distinct hyperparameter choices of architectures, tasks, depths, network sizes (number of parameters), learning rates, batch sizes, and regularization penalties. Repeating each experiment an average of 24 times resulted in 11 million total training runs and 40 billion epochs recorded. Accumulating this 1.7 TB dataset utilized 11 thousand CPU core-years, 72.3 GPU-years, and 163 node-years. In surveying the dataset, we observe durable patterns persisting across tasks and topologies. We aim to spark scientific study of machine learning techniques as a catalyst for the theoretical discoveries needed to progress the field beyond energy-intensive and heuristic practices.

arXiv:2207.12577공식 코드 · Papers with Code

Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution

Deep learning-based super-resolution (SR) has gained tremendous popularity in recent years because of its high image quality performance and wide application scenarios. However, prior methods typically suffer from large amounts of computations and huge power consumption, causing difficulties for real-time inference, especially on resource-limited platforms such as mobile devices. To mitigate this, we propose a compiler-aware SR neural architecture search (NAS) framework that conducts depth search and per-layer width search with adaptive SR blocks. The inference speed is directly taken into the optimization along with the SR loss to derive SR models with high image quality while satisfying the real-time inference requirement. Instead of measuring the speed on mobile devices at each iteration during the search process, a speed model incorporated with compiler optimizations is leveraged to predict the inference latency of the SR block with various width configurations for faster convergence. With the proposed framework, we achieve real-time SR inference for implementing 720p resolution with competitive SR performance (in terms of PSNR and SSIM) on GPU/DSP of mobile platforms (Samsung Galaxy S21).

arXiv:2207.12000공식 코드 · Papers with Code

GNN Transformation Framework for Improving Efficiency and Scalability

We propose a framework that automatically transforms non-scalable GNNs into precomputation-based GNNs which are efficient and scalable for large-scale graphs. The advantages of our framework are two-fold; 1) it transforms various non-scalable GNNs to scale well to large-scale graphs by separating local feature aggregation from weight learning in their graph convolution, 2) it efficiently executes precomputation on GPU for large-scale graphs by decomposing their edges into small disjoint and balanced sets. Through extensive experiments with large-scale graphs, we demonstrate that the transformed GNNs run faster in training time than existing GNNs while achieving competitive accuracy to the state-of-the-art GNNs. Consequently, our transformation framework provides simple and efficient baselines for future research on scalable GNNs.