Related papers: ZipFlow: a Compiler-based Framework to Unleash Com…
In scientific simulations, observations, and experiments, the cost of transferring data to and from disk and across networks has become a significant bottleneck that particularly impacts subsequent data analysis and visualization. To…
Huffman compression is a statistical, lossless, data compression algorithm that compresses data by assigning variable length codes to symbols, with the more frequently appearing symbols given shorter codes than the less. This work is a…
GPUs offer orders-of-magnitude higher memory bandwidth than traditional CPU-only systems. However, GPU device memory tends to be relatively small and the memory capacity can not be increased by the user. This paper describes Buddy…
Extract-Transform-Load (ETL) handles large amount of data and manages workload through dataflows. ETL dataflows are widely regarded as complex and expensive operations in terms of time and system resources. In order to minimize the time and…
Deploying pretrained visual models in real-world environments often suffers from significant performance degradation due to the diversity of testing scenarios. Continuous adaptation of learning models on edge devices via unlabeled data…
Over the past decade, machine learning model complexity has grown at an extraordinary rate, as has the scale of the systems training such large models. However there is an alarmingly low hardware utilization (5-20%) in large scale AI…
This work presents DCFlow, a novel unsupervised cross-modal flow estimation framework that integrates a decoupled optimization strategy and a cross-modal consistency constraint. Unlike previous approaches that implicitly learn flow…
Modern GPU systems are constantly evolving to meet the needs of computing-intensive applications in scientific and machine learning domains. However, there is typically a gap between the hardware capacity and the achievable application…
State-of-the-art deep learning systems such as TensorFlow and PyTorch tightly couple the model with the underlying hardware. This coupling requires the user to modify application logic in order to run the same job across a different set of…
We present a massively parallel solver that accelerates DC loadflow computations for power grid topology optimization tasks. Our approach leverages low-rank updates of the Power Transfer Distribution Factors (PTDFs) to represent substation…
Intra-device parallelism addresses resource under-utilization in ML inference and training by overlapping the execution of operators with different resource usage. However, its wide adoption is hindered by a fundamental conflict with the…
Large-scale GPU clusters are widely-used to speed up both latency-critical (online) and best-effort (offline) deep learning (DL) workloads. However, most DL clusters either dedicate each GPU to one workload or share workloads in time,…
The high memory and computation demand of large language models (LLMs) makes them challenging to be deployed on consumer devices due to limited GPU memory. Offloading can mitigate the memory constraint but often suffers from low GPU…
Due to ongoing accrual over long durations, a defining characteristic of real-world data streams is the requirement for rolling, often real-time, mechanisms to coarsen or summarize stream history. One common data structure for this purpose…
Serverless computing that runs functions with auto-scaling is a popular task execution pattern in the cloud-native era. By connecting serverless functions into workflows, tenants can achieve complex functionality. Prior researches adopt the…
Processing large graphs with memory-limited GPU needs to resolve issues of host-GPU data transfer, which is a key performance bottleneck. Existing GPU-accelerated graph processing frameworks reduce the data transfers by managing the active…
Multimodal Large Language Models (MLLMs) have achieved remarkable advances by integrating text, image, and audio understanding within a unified architecture. However, existing distributed training frameworks remain fundamentally data-blind:…
GPUs have been widely used to accelerate computations exhibiting simple patterns of parallelism - such as flat or two-level parallelism - and a degree of parallelism that can be statically determined based on the size of the input dataset.…
As inference workloads for large language models (LLMs) scale to meet growing user demand, pipeline parallelism (PP) has become a widely adopted strategy for multi-GPU deployment, particularly in cross-node setups, to improve key-value (KV)…
The JPEG compression format has been the standard for lossy image compression for over multiple decades, offering high compression rates at minor perceptual loss in image quality. For GPU-accelerated computer vision and deep learning tasks,…