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

Home

Lecture

GPU Memory Hierarchy and Optimization

About
Privacy
Disclaimer

Graph Chatbot

Related lectures (52)

Multi-threaded Processors Log in to Mediaspace to watch this video

Covers the basics of multi-threaded processors, including design, performance impact, and pipeline utilization.

Architecture Essentials: Understanding Computer Systems Log in to Mediaspace to watch this video

Provides an overview of computer architecture, focusing on the von Neumann architecture and its components, including the CPU and memory management units.

Data-Parallel Programming: Vector & SIMD Processors Log in to Mediaspace to watch this video

Explores data-parallel programming with vector processors and SIMD, and introduces MapReduce, Pregel, and TensorFlow.

Untitled Log in to Mediaspace to watch this video

Rescuing Data Center Processors Log in to Mediaspace to watch this video

Explores challenges and solutions for data center processors, focusing on efficiency, cache issues, branch prediction, and architectural optimizations.

Multithreading Basics: Design, Performance, and Impact Log in to Mediaspace to watch this video

Covers the basics of multithreading, including design, performance impact, and GPU utilization.

Threads: Concurrency and Parallelism in Computer Systems Log in to Mediaspace to watch this video

Covers the thread abstraction in computer systems, focusing on concurrency, parallelism, and the management of threads using the POSIX API.

Memory Consistency Models: Performance Impact and Parallel Computing Log in to Mediaspace to watch this video

Covers memory consistency models, parallel computing, atomic subroutines, GPU architecture, and multithreading.

Optimizing Software: Software Optimizations & Work Distribution Log in to Mediaspace to watch this video

Covers software optimization, cache efficiency, parallel scheduling, and work distribution strategies for fast parallel programs.

Optimizing Software: Locality & Scheduling Log in to Mediaspace to watch this video

Explores software optimizations for cache efficiency, parallel execution, and load balancing.

Device Management in Operating Systems: Chaperones and Persistence Log in to Mediaspace to watch this video

Discusses device management in operating systems, focusing on device drivers, persistence, and performance optimization techniques.

Fast Interconnects: Scalable Co-processing with GPUs Log in to Mediaspace to watch this video

Explores the use of fast interconnects for scalable co-processing with GPUs in databases, emphasizing the importance of overcoming the transfer bottleneck and reevaluating assumptions for performance improvements.

Virtual Memory Log in to Mediaspace to watch this video

Covers the concept of virtual memory and the isolation of processes through address spaces, discussing segmentation, paging, and memory implementation details.

Introduction to Multiprocessor Architecture Log in to Mediaspace to watch this video

Introduces the fundamentals of multiprocessor architecture, covering post-Moore servers, sustainable datacenters, parallel programming, and GPU utilization.

Understanding Simultaneous Multithreading in Modern Processors Log in to Mediaspace to watch this video

Covers simultaneous multithreading, its implementation, and its impact on processor performance.

Virtual memory applications Log in to Mediaspace to watch this video

Explores virtual memory applications, including isolation benefits and memory-mapped files.

Virtual Memory: Principles and Mechanisms Log in to Mediaspace to watch this video

Covers the principles and mechanisms of virtual memory in computer systems, focusing on isolation, efficiency, and the role of the Memory Management Unit.

Accelerated Data Management Systems Log in to Mediaspace to watch this video

Explores accelerated data management systems through real-time specialization on heterogeneous hardware and GPU accessing fresh data from CPU memory.

Micro-architectural Analysis of OLAP: Limitations and Opportunities Log in to Mediaspace to watch this video

Explores the limitations and opportunities of OLAP workloads in terms of CPU cycles usage and processor architectures.

Cache Coherence: MESI Protocol and Data Transfers Log in to Mediaspace to watch this video

Explores the MESI protocol for cache coherence and discusses the impact of cache-to-cache communication.

Page 2 of 3