Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Fast Interconnects: Scalable Co-processing with GPUs

Description

This lecture discusses the use of fast interconnects to enable scalable co-processing with GPUs in databases. The instructor presents the motivation behind leveraging GPUs in the database market, the research problem related to memory capacity and interconnect bandwidth, and the game-changing impact of fast interconnects. Various contributions and the benefits for databases are highlighted, along with detailed explanations of probe-side and build-side scaling. Lessons learned, future work on k-Means, and the evaluation of GPU+CPU cooperation are also covered, emphasizing the importance of overcoming the transfer bottleneck and reevaluating assumptions for performance improvements.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Official source

Ontological neighbourhood

Computer engineering

Hardware engineering: Microprocessors

Related concepts (31)

General-purpose computing on graphics processing units

General-purpose computing on graphics processing units (GPGPU, or less often GPGP) is the use of a graphics processing unit (GPU), which typically handles computation only for computer graphics, to perform computation in applications traditionally handled by the central processing unit (CPU). The use of multiple video cards in one computer, or large numbers of graphics chips, further parallelizes the already parallel nature of graphics processing.

Graphics processing unit

A graphics processing unit (GPU) is a specialized electronic circuit initially designed to accelerate computer graphics and (either on a video card or embedded on the motherboards, mobile phones, personal computers, workstations, and game consoles). After their initial design, GPUs were found to be useful for non-graphic calculations involving embarrassingly parallel problems due to their parallel structure. Other non-graphical uses include the training of neural networks and cryptocurrency mining.

HyperTransport

HyperTransport (HT), formerly known as Lightning Data Transport, is a technology for interconnection of computer processors. It is a bidirectional serial/parallel high-bandwidth, low-latency point-to-point link that was introduced on April 2, 2001. The HyperTransport Consortium is in charge of promoting and developing HyperTransport technology. HyperTransport is best known as the system bus architecture of AMD central processing units (CPUs) from Athlon 64 through AMD FX and the associated motherboard chipsets.

PCI Express

PCI Express (Peripheral Component Interconnect Express), officially abbreviated as PCIe or PCI-e, is a high-speed serial computer expansion bus standard, designed to replace the older PCI, PCI-X and AGP bus standards. It is the common motherboard interface for personal computers' graphics cards, sound cards, hard disk drive host adapters, SSDs, Wi-Fi and Ethernet hardware connections.

Hopper (microarchitecture)

Hopper is a graphics processing unit (GPU) microarchitecture developed by Nvidia. It is designed for datacenters and is parallel to Ada Lovelace. Named for computer scientist and United States Navy rear admiral Grace Hopper, the Hopper architecture was leaked in November 2019 and officially revealed in March 2022. It improves upon its predecessors, the Turing and Ampere microarchitectures, featuring a new streaming multiprocessor and a faster memory subsystem. The Nvidia Hopper H100 GPU is implemented using the TSMC 4N process with 80 billion transistors.

Related lectures (53)

Accelerator-centric OS Architecture

By the instructor Mark Silberstein explores accelerator-centric OS architecture and the role of CPUs in modern computers.

Memory Cache Principles

Explores memory cache principles, emphasizing spatial locality, latency impact, and cache efficiency strategies.

Data Wrangling with Hadoop

Covers data wrangling techniques using Hadoop, focusing on row versus column-oriented databases, popular storage formats, and HBase-Hive integration.

Cache Memory

Explores cache memory design, hits, misses, and eviction policies in computer systems, emphasizing spatial and temporal locality.

Big Data Best Practices and Guidelines