Related papers: CAWL: A Cache-aware Write Performance Model of Lin…
Traffic and channel-data rate combined with the stream oriented methodology can provide a scheme for offering optimized and guaranteed QoS. In this work a stream oriented modeled scheme is proposed based on each node's self-scheduling…
The key to speeding up applications is often understanding where the elapsed time is spent, and why. This document reviews in depth the full array of performance analysis tools and techniques available on Linux for this task, from the…
Configuration tuning for large software systems is generally challenging due to the complex configuration space and expensive performance evaluation. Most existing approaches follow a two-phase process, first learning a regression-based…
Performance benchmarking is a common practice in software engineering, particularly when building large-scale, distributed, and data-intensive systems. While cloud environments offer several advantages for running benchmarks, it is often…
Domain-specific systems-on-chip, a class of heterogeneous many-core systems, are recognized as a key approach to narrow down the performance and energy-efficiency gap between custom hardware accelerators and programmable processors.…
We present a novel characterization of how a program stresses cache. This characterization permits fast performance prediction in order to simulate and assist task scheduling on heterogeneous clusters. It is based on the estimation of stack…
While detailed resource usage monitoring is possible on the low-level using proper tools, associating such usage with higher-level abstractions in the application layer that actually cause the resource usage in the first place presents a…
In recent years, artificial intelligence (AI) technologies have found industrial applications in various fields. AI systems typically possess complex software and heterogeneous CPU/GPU hardware architecture, making it difficult to answer…
The design and operation of modern software systems exhibit a shift towards virtualization, containerization and service-based orchestration. Performance capacity engineering and resource utilization tuning become priority requirements in…
In recent years, the deployment of large-scale Internet of Things (IoT) applications has given rise to edge federations that seamlessly interconnect and leverage resources from multiple edge service providers. The requirement of supporting…
Cluster orchestrators such as Kubernetes depend on accurate estimates of node capacity and job requirements. Inaccuracies in either lead to poor placement decisions and degraded cluster performance. In this paper, we show that in densely…
Modern and future processors need to remain functionally correct in the presence of permanent faults to sustain scaling benefits and limit field returns. This paper presents a combined analytical and microarchitectural simulation-based…
Application-level caching is a form of caching that has been increasingly adopted to satisfy performance and throughput requirements. The key idea is to store the results of a computation, to improve performance by reusing instead of…
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,…
Evaluative claims about LLM infrastructure -- ``workload X is fastest on hardware Y with software Z'' -- depend on a complex configuration space spanning hardware accelerators, interconnect bandwidth, software frameworks, parallelism plans,…
Web caching is essential for the World Wide Web, saving processing power, bandwidth, and reducing latency. Many proxy caching solutions focus on buffering data from the main server, neglecting cacheable information meant for server writes.…
The performance of Deep-Learning (DL) computing frameworks rely on the performance of data ingestion and checkpointing. In fact, during the training, a considerable high number of relatively small files are first loaded and pre-processed on…
The rapid adoption of large language models (LLMs) is pushing AI accelerators toward increasingly powerful and specialized designs. Instead of further complicating software development with deeply hierarchical scratchpad memories (SPMs) and…
This paper presents a performance model tailored for warp specialization kernels, focusing on factors such as warp size, tilling size, input matrix size, memory bandwidth, and thread divergence. Our model offers accurate predictions of…
Latency and cost of Internet-based services are encouraging the use of application-level caching to continue satisfying users' demands, and improve the scalability and availability of origin servers. Despite its popularity, this level of…