Related papers: Threadle: A Memory-Efficient Network Storage and Q…

Creating and destroying threads on modern Linux systems incurs high latency, absent concurrency, and fails to scale as we increase concurrency. To address this concern we introduce a process-local cache of idle threads. Specifically,…

Due to the continuously improving capabilities of mobile edges, recommender systems start to deploy models on edges to alleviate network congestion caused by frequent mobile requests. Several studies have leveraged the proximity of…

The Compute Express Link (CXL) interconnect makes it feasible to integrate diverse types of memory into servers via its byte-addressable SerDes links. Considering the various access latency, harnessing the full potential of CXL-based…

We propose Sectored DRAM, a new, low-overhead DRAM substrate that reduces wasted energy by enabling fine-grained DRAM data transfers and DRAM row activation. Sectored DRAM leverages two key ideas to enable fine-grained data transfers and…

Thread-level parallelism in irregular applications with mutable data dependencies presents challenges because the underlying data is extensively modified during execution of the algorithm and a high degree of parallelism must be realized…

Multi-threaded programs are expected to improve responsiveness and conserve resources by dividing an application process into multiple threads for concurrent processing. However, due to scheduling and the interaction of multiple threads,…

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…

Deep networks consume a large amount of memory by their nature. A natural question arises can we reduce that memory requirement whilst maintaining performance. In particular, in this work we address the problem of memory efficient learning…

In this paper we present SADDLE, a modular framework for automated design of cluster supercomputers and data centres. In contrast with commonly used approaches that operate on logic gate level (Verilog, VHDL) or board level (such as EDA…

There has been significant recent interest in parallel graph processing due to the need to quickly analyze the large graphs available today. Many graph codes have been designed for distributed memory or external memory. However, today even…

Deep Learning Recommendation Models (DLRMs) play a crucial role in delivering personalized content across web applications such as social networking and video streaming. However, with improvements in performance, the parameter size of DLRMs…

Neural network (NN) accelerators with multi-chip-module (MCM) architectures enable integration of massive computation capability; however, they face challenges of computing resource underutilization and off-chip communication overheads.…

In this work, we propose Retentive Network (RetNet) as a foundation architecture for large language models, simultaneously achieving training parallelism, low-cost inference, and good performance. We theoretically derive the connection…

We propose doubly nested network(DNNet) where all neurons represent their own sub-models that solve the same task. Every sub-model is nested both layer-wise and channel-wise. While nesting sub-models layer-wise is straight-forward with…

Deep Learning system architects strive to design a balanced system where the computational accelerator -- FPGA, GPU, etc, is not starved for data. Feeding training data fast enough to effectively keep the accelerator utilization high is…

The number of triangles in a graph is a fundamental metric, used in social network analysis, link classification and recommendation, and more. Driven by these applications and the trend that modern graph datasets are both large and dynamic,…

Graph analysis performs many random reads and writes, thus, these workloads are typically performed in memory. Traditionally, analyzing large graphs requires a cluster of machines so the aggregate memory exceeds the graph size. We…

Software-managed heterogeneous memory (HM) provides a promising solution to increase memory capacity and cost efficiency. However, to release the performance potential of HM, we face a problem of data management. Given an application with…

Sustaining long-term interactions remains a bottleneck for Large Language Models (LLMs), as their limited context windows struggle to manage dialogue histories that extend over time. Existing memory systems often treat interactions as…

Widely popular transformer-based NLP models such as BERT and Turing-NLG have enormous capacity trending to billions of parameters. Current execution methods demand brute-force resources such as HBM devices and high speed interconnectivity…