Related papers: Shared Virtual Memory: Its Design and Performance …
Cloud providers offer a variety of execution platforms in form of bare-metal, VM, and containers. However, due to the pros and cons of each execution platform, choosing the appropriate platform for a specific cloud-based application has…
Developing kernels for Processing-In-Memory (PIM) platforms poses unique challenges in data management and parallel programming on limited processing units. Although software development kits (SDKs) for PIM, such as the UPMEM SDK, provide…
Several manufacturers have already started to commercialize near-bank Processing-In-Memory (PIM) architectures. Near-bank PIM architectures place simple cores close to DRAM banks and can yield significant performance and energy improvements…
Modern GPU applications, such as machine learning (ML), can only partially utilize GPUs, leading to GPU underutilization in cloud environments. Sharing GPUs across multiple applications from different tenants can improve resource…
Background: Virtual Machine (VM) consolidation is an effective technique to improve resource utilization and reduce energy footprint in cloud data centers. It can be implemented in a centralized or a distributed fashion. Distributed VM…
Serverless computing is an emerging cloud paradigm that offers an elastic and scalable allocation of computing resources with pay-as-you-go billing. In the Function-as-a-Service (FaaS) programming model, applications comprise short-lived…
Mobile virtual reality (VR) delivery is gaining increasing attention from both industry and academia due to its ability to provide an immersive experience. However, achieving mobile VR delivery requires ultra-high transmission rate, deemed…
Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through GPU resource sharing. However, cold-start latency, especially the model loading…
Modern LLM serving systems confront inefficient GPU utilization due to the fundamental mismatch between compute-intensive prefill and memory-bound decode phases. While current practices attempt to address this by organizing these phases…
This work studies the behavior of state-of-the-art memory controller designs when executing scale-out workloads. It considers memory scheduling techniques, memory page management policies, the number of memory channels, and the address…
In this paper, we evaluate the performance of various parallel optimization methods for Kernel Support Vector Machines on multicore CPUs and GPUs. In particular, we provide the first comparison of algorithms with explicit and implicit…
In the last decade, specific-purpose computing and storage devices, such as GPUs, TPUs, or high-speed storage, have been incorporated into server nodes of Supercomputers and Data centers. The development of high-bandwidth memory (HBM)…
Compute and memory are tightly coupled within each server in traditional datacenters. Large-scale datacenter operators have identified this coupling as a root cause behind fleet-wide resource underutilization and increasing Total Cost of…
Solid-state storage architectures based on NAND or emerging memory devices (SSD), are fundamentally architected and optimized for both reliability and performance. Achieving these simultaneous goals requires co-design of memory components…
Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…
With the emergence of Non-Volatile Memories (NVMs) and their shortcomings such as limited endurance and high power consumption in write requests, several studies have suggested hybrid memory architecture employing both Dynamic Random Access…
Modern computing systems are embracing hybrid memory comprising of DRAM and non-volatile memory (NVM) to combine the best properties of both memory technologies, achieving low latency, high reliability, and high density. A prominent…
Large language models (LLMs) based on transformers have made significant strides in recent years, the success of which is driven by scaling up their model size. Despite their high algorithmic performance, the computational and memory…
Leadership supercomputers feature a diversity of storage, from node-local persistent memory and NVMe SSDs to network-interconnected flash memory and HDD. Memory mapping files on different tiers of storage provides a uniform interface in…
Memory management is necessary with the increasing number of multi-connected AI devices and data bandwidth issues. For this purpose, high-speed multi-port memory is used. The traditional multi-port memory solutions are hard-bounded to a…