SPDK Accelerator Framework: Evolution from Copy Framework to Modern Hardware Acceleration
Explore the evolution of SPDK's Accelerator Framework, from basic IOAT support to a robust system with 8 operations and 7 accelerators, including the new Intel® Data Streaming Accelerator.
Custom Chips Needed for Efficient High-Performance Computing
Explore the future of computing power through custom hardware solutions, from manycore systems to silicon development, addressing latency and energy efficiency challenges in high-performance computing.
SmartNICs and SmartSSDs: Impact on Data Center Technology and Future Acceleration
Explore the evolution of SmartNICs and SmartSSDs in data centers, their market impact, and how emerging technologies like PCIe 5 and CXL are shaping the future of smart acceleration.
The CFU: Custom Hardware with RISC-V and Zephyr
Explore custom hardware integration using RISC-V's Custom Function Unit and Zephyr RTOS on FPGAs, enhancing embedded system performance and flexibility.
FlexibleIP - IPv6 Stack for Low-Power Devices Paper Presentation
Explore IPv6 stack optimization for low-power devices, covering cross-layer design, hardware acceleration, header compression, and implementation examples with performance analysis.
Project Sumatra - GPU Acceleration for Java
Explore GPU workloads, AMD's Accelerated Processing Unit, and the Sumatra prototype for Java optimization using Stream API and HSAIL technologies.
Optimizing Data-Flow in Binary Neural Networks
Explore optimizing data flow in Binary Neural Networks, focusing on hardware efficiency, quantization techniques, and accuracy improvements for embedded systems.
Embedded Machine Learning in the Real World
Explore embedded ML applications, challenges, and opportunities in real-world scenarios, focusing on tiny models, accelerated hardware, and practical tooling.
TinyML Talks - SRAM Based In-Memory Computing for Energy-Efficient AI Inference
Explore SRAM-based in-memory computing for energy-efficient AI inference, covering bitcell circuits, architectures, and design optimization for improved performance in low-power processors.
hls4ml: An Open-Source Co-Design Workflow for Scientific Low-Power Machine Learning Devices
Explore hls4ml, an open-source workflow for implementing machine learning algorithms on FPGAs and ASICs, enabling real-time processing for scientific applications and accelerating discoveries.
Smartphone Impostor Detection with Behavioral Data Privacy and Minimalist Hardware Support
Innovative smartphone security: Deep Learning for quick impostor detection, preserving user privacy with on-device processing and minimal hardware support.
Many Shades of Acceleration - An Open TinyML Platform Perspective
Explore extreme edge AI, energy efficiency, and acceleration techniques for TinyML applications with insights from the PULP platform and RISC-V processors.
Containerizing Hardware Accelerated Applications Using GPUs and FPGAs
Explore containerizing hardware-accelerated applications, focusing on GPU-accelerated media processing. Learn benefits, challenges, and performance implications of this approach.
Hardware Friendly Vhost vDPA: Towards an Efficient and Migratable Device Model
Simplified vhost-vdpa device model for efficient live migration of hardware-backed vDPA devices, addressing challenges and proposing new interfaces for state management and migration.
Current State of Graphics Virtualization Upstream
Explore the latest developments in Linux graphics virtualization, focusing on open-source solutions for containerized and virtualized workloads in modern hardware environments.
State of Art for Enabling Performance Sensitive Workloads and Future Needs
Experts discuss cutting-edge techniques for optimizing performance-sensitive workloads, exploring current challenges and future directions in system optimization and resource management.
Stateless HEVC Decoding in Mainline Linux - The Rocky Road to Becoming a Stable API
Explore the journey of implementing stateless HEVC decoding in Linux, covering API design challenges, hardware requirements, and the path to stability in the mainline kernel.
Container CXL Memory Interface
Explore the Container CXL Memory Interface with Hongjian Fan, gaining insights into this advanced technology and its applications in modern computing systems.
Container CXL Memory Interface
Explore the Container CXL Memory Interface with Hongjian Fan, delving into its architecture, implementation, and impact on system performance and resource management.
Linux Stateless Video Decoder Support
Explore stateless video decoder support in Linux, focusing on implementation, benefits, and future developments for efficient multimedia processing.
Live Migration with Hardware Acceleration
Explore hardware-accelerated live migration techniques for improved efficiency and performance in virtualized environments.