性能
We present a thorough analysis of the use of modern heterogeneous systems interconnected by various cachecoherent links, including CXL, NVLink-C2C, and Infinity Fabric. We studied a wide range of server systems that combined CPUs from…
Health Indicators (HIs) are essential for predicting system failures in predictive maintenance. While methods like RaPP (Reconstruction along Projected Pathways) improve traditional HI approaches by leveraging autoencoder latent spaces,…
Diagnosing performance bottlenecks in modern software is essential yet challenging, particularly as applications become more complex and rely on custom resource management policies. While traditional profilers effectively identify execution…
The recently proposed affine frequency division multiplexing (AFDM) modulation has been considered as a promising technology for narrowband doubly-dispersive channels. However, the time-scaling effects, i.e., pulse widening and pulse…
Two popular server control policies are available for reducing energy consumption while maintaining acceptable performance levels: server speed scaling and the ability to turn servers off (and on). In this work, we explore the question of…
Energy-centric design is paramount in the current embedded computing era: use cases require increasingly high performance at an affordable power budget, often under real-time constraints. Hardware heterogeneity and parallelism help address…
Redundancy elimination is a key optimization direction, and loop nests are the main optimization target in modern compilers. Previous work on redundancy elimination of array computations in loop nests lacks universality. These approaches…
Over the lifetime of a computing task, determining the maximum usage of random-access memory (RAM) on both the motherboard and on a graphical processing unit (GPU), as well as the utilization percentage of the central processing unit (CPU)…
Efficient IO techniques are crucial in high-performance graph processing frameworks like Gunrock and Hornet, as fast graph loading can help minimize processing time and reduce system/cloud usage charges. This research study presents…
Processors with dynamic power management provide a variety of settings to control energy efficiency. However, tuning these settings does not achieve optimal energy savings. We highlight how existing power capping mechanisms can address…
To handle the high volume of requests, large-scale services are comprised of thousands of instances deployed in clouds. These services utilize diverse programming languages and are distributed across various nodes as encapsulated…
CXLMemSim is a fast, lightweight simulation framework that enables performance characterization of memory systems based on Compute Express Link (CXL) .mem technology. CXL.mem allows disaggregation and pooling of memory to mitigate memory…
Since the release of ChatGPT in November 2022, large language models (LLMs) have seen considerable success, including in the open-source community, with many open-weight models available. However, the requirements to deploy such a service…
The emerging pinching antenna (PA) technology has high flexibility to reconfigure wireless channels and combat line-of-sight blockage, thus holding transformative potential for indoor immersive applications in 6G. This paper investigates…
We characterize the impact of scheduling policies on the mean response time in nested systems with cancel-on-complete redundancy. We consider not only redundancy-oblivious policies, such as FCFS and ROS, but also redundancy-aware policies…
Recently, as a green wireless technology, active reconfigurable intelligent surface (RIS) attracts numerous research activities due to its amplifying ability to combat the double-fading effect compared to passive one. How about its energy…
Artificial Intelligence (AI) algorithms, such as Deep Neural Networks (DNNs), have become an important tool for a wide range of applications, from computer vision to natural language processing. However, the computational complexity of DNN…
Statistical models are widely used to estimate the performance of commercial off-the-shelf (COTS) AI hardware accelerators. However, training of statistical performance models often requires vast amounts of data, leading to a significant…
We consider a discrete-time parallel service system consisting of $n$ heterogeneous single server queues with infinite capacity. Jobs arrive to the system as an i.i.d. process with rate proportional to $n$, and must be immediately…
Efficient thermal and power management in modern multiprocessor systems-on-chip (MPSoCs) demands accurate power consumption estimation. One of the state-of-the-art approaches, Alternative Blind Power Identification (ABPI), theoretically…