相关论文: Dynamic Warp Resizing in High-Performance SIMT

Though Remote Direct Memory Access (RDMA) promises to reduce datacenter network latencies significantly compared to TCP (e.g., 10x), end-to-end congestion control in the presence of incasts is a challenge. Targeting the full generality of…

We present an adaptive scheduler for a single differencing engine (SmartDiff) with two execution modes: (i) in-memory threads and (ii) Dask based parallelism. The scheduler continuously tunes batch size and worker/thread count within fixed…

The goal of dynamic time warping is to transform or warp time in order to approximately align two signals together. We pose the choice of warping function as an optimization problem with several terms in the objective. The first term…

Dynamic distribution network reconfiguration (DNR) algorithms perform hourly status changes of remotely controllable switches to improve distribution system performance. The problem is typically solved by physical model-based control…

Round Robin (RR) Algorithm is considered as optimal in time shared environment because the static time is equally shared among the processes. If the time quantum taken is static then it undergoes degradation of the CPU performance and leads…

Hardware/Software (HW/SW) co-designed processors provide a promising solution to the power and complexity problems of the modern microprocessors by keeping their hardware simple. Moreover, they employ several runtime optimizations to…

Modern Automatic Speech Recognition (ASR) systems rely on distributed deep learning to for quick training completion. To enable efficient distributed training, it is imperative that the training algorithms can converge with a large…

Sparse deep learning has reduced computation significantly, but its irregular non-zero data distribution complicates the data flow and hinders data reuse, increasing on-chip SRAM access and thus power consumption of the chip. This paper…

As deep learning models continue to increase in size, the memory requirements for training have surged. While high-level techniques like offloading, recomputation, and compression can alleviate memory pressure, they also introduce…

To meet strict Service-Level Objectives (SLOs),contemporary Large Language Models (LLMs) decouple the prefill and decoding stages and place them on separate GPUs to mitigate the distinct bottlenecks inherent to each phase. However, the…

Processing-using-DRAM has been proposed for a limited set of basic operations (i.e., logic operations, addition). However, in order to enable the full adoption of processing-using-DRAM, it is necessary to provide support for more complex…

Weight decay is often used to ensure good generalization in the training practice of deep neural networks with batch normalization (BN-DNNs), where some convolution layers are invariant to weight rescaling due to the normalization. In this…

The use of Dynamic Random Access Memory (DRAM) for storing Machine Learning (ML) models plays a critical role in accelerating ML inference tasks in the next generation of communication systems. However, periodic refreshment of DRAM results…

Multi-core processors are becoming more and more popular in embedded and real-time systems. While fixed-priority scheduling with task-splitting in real-time systems are widely applied, current approaches have not taken into consideration…

This work presents dyGRASS, an efficient dynamic algorithm for spectral sparsification of large undirected graphs that undergo streaming edge insertions and deletions. At its core, dyGRASS employs a random-walk-based method to efficiently…

Recent advances demonstrate that irregularly wired neural networks from Neural Architecture Search (NAS) and Random Wiring can not only automate the design of deep neural networks but also emit models that outperform previous manual…

Generating long-range, geometrically consistent video presents a fundamental dilemma: while consistency demands strict adherence to 3D geometry in pixel space, state-of-the-art generative models operate most effectively in a…

GPU architectures have continued to grow in complexity, with recent incarnations introducing increasingly powerful fixed-function units for matrix multiplication and data movement to accompany highly parallel general-purpose cores. To fully…

Dynamic scaling is critical to stream processing engines, as their long-running nature demands adaptive resource management. Existing scaling approaches easily cause performance degradation due to coarse-grained synchronization and…

Based on our observations of infrared targets, serious scale variation along within sequence frames has high-frequently occurred. In this paper, we propose a dynamic re-parameterization network (DRPN) to deal with the scale variation and…