Related papers: Reuse Cache for Heterogeneous CPU-GPU Systems

We propose a CPU-GPU heterogeneous computing method for solving time-evolution partial differential equation problems many times with guaranteed accuracy, in short time-to-solution and low energy-to-solution. On a single-GH200 node, the…

In cloud storage systems with a large number of servers, files are typically not stored in single servers. Instead, they are split, replicated (to ensure reliability in case of server malfunction) and stored in different servers. We analyze…

Given its high integration density, high speed, byte addressability, and low standby power, non-volatile or persistent memory is expected to supplement/replace DRAM as main memory. Through persistency programming models (which define…

At the edge, there is a high level of similarity in computing. One approach that has been proposed to enhance the efficiency of edge computing is computation reuse, which eliminates redundant computations. Edge computing is integrated with…

With the emergence of social networks and improvements in computational photography, billions of JPEG images are shared and viewed on a daily basis. Desktops, tablets and smartphones constitute the vast majority of hardware platforms used…

LLMs are increasingly used world-wide from daily tasks to agentic systems and data analytics, requiring significant GPU resources. LLM inference systems, however, are slow compared to database systems, and inference performance and…

Retrieval-augmented generation (RAG) has become a common strategy for updating large language model (LLM) responses with current, external information. However, models may still rely on memorized training data, bypass the retrieved…

Random linear network coding (RLNC) in theory achieves the max-flow capacity of multicast networks, at the cost of high decoding complexity. To improve the performance-complexity tradeoff, we consider the design of sparse network codes. A…

Linear Programs (LPs) appear in a large number of applications and offloading them to a GPU is viable to gain performance. Existing work on offloading and solving an LP on a GPU suggests that there is performance gain generally on large…

Caching techniques are widely used in the era of cloud computing from applications, such as Web caches to infrastructures, Memcached and memory caches in computer architectures. Prediction of cached data can greatly help improve cache…

The explosive growth of electric vehicles (EVs) is leading to a surge in retired EV batteries, which are typically recycled despite having nearly 80% available capacity. Repurposing automotive batteries for second-use battery energy storage…

The Preconditioned Conjugate Gradient (PCG) method is widely used for solving linear systems of equations with sparse matrices. A recent version of PCG, Pipelined PCG, eliminates the dependencies in the computations of the PCG algorithm so…

GPUs are now used for a wide range of problems within HPC. However, making efficient use of the computational power available with multiple GPUs is challenging. The main challenges in achieving good performance are memory layout, affecting…

The performance of discrete general purpose graphics processing units (GPGPUs) has been improving at a rapid pace. The PCIe interconnect that controls the communication of data between the system host memory and the GPU has not improved as…

Modern AI clusters, which host diverse workloads like data pre-processing, training and inference, often store the large-volume data in cloud storage and employ caching frameworks to facilitate remote data access. To avoid code-intrusion…

Production garbage collectors make substantial compromises in pursuit of reduced pause times. They require far more CPU cycles and memory than prior simpler collectors. concurrent copying collectors (C4, ZGC, and Shenandoah) suffer from the…

Linear Programs (LPs) appear in a large number of applications and offloading them to the GPU is viable to gain performance. Existing work on offloading and solving an LP on GPU suggests that performance is gained from large sized LPs…

The ability to reuse previous policies is an important aspect of human intelligence. To achieve efficient policy reuse, a Deep Reinforcement Learning (DRL) agent needs to decide when to reuse and which source policies to reuse. Previous…

The growing complexity of LLM usage today, e.g., multi-round conversation and retrieval-augmented generation (RAG), makes contextual states (i.e., KV cache) reusable across user requests. Given the capacity constraints of GPU memory, only a…

In long-context Large Language Model (LLM) inference, the Time-To-First-Token (TTFT) latency incurred by the prefill stage has become the foremost bottleneck limiting interactive performance and deployment cost. KV Cache reuse offers a…