Running Unit Test on Top of Serverless Service
Explore serverless architecture for unit testing, including parallelization approaches, implementation insights, and cost-benefit analysis for improved developer productivity.
Optimizing Your CI Pipelines
Discover techniques to enhance CI pipelines: parallelization, caching, early failure detection, and conditional runs for faster, more efficient builds and improved development workflows.
Designing for Azure Data Warehouse Performance - Cloud
Learn Azure Data Warehouse design principles for optimal performance, covering architecture, data modeling, and practical considerations to balance current and future needs.
User-Level Threads with Threads
Explore efficient multi-threaded programming using user-level threads, covering new kernel interfaces and primitives for cooperative threading with sub-200ns context-switch times across various languages.
Open Source GPU Compute Stack - Not Dancing the CUDA Dance
Exploring open-source alternatives to CUDA for GPU compute acceleration, discussing potential for a vendor-neutral reference stack using SYCL/OpenCL/Vulkan and Mesa.
Heterogeneous Memory Management
Explore heterogeneous computing challenges, focusing on unified address spaces, memory management, and data placement across CPUs and parallel devices like GPUs.
Malloc for Everyone and Beyond NUMA
Exploring memory management in heterogeneous computing, addressing challenges beyond NUMA, and proposing a unified API for diverse memory types in modern systems.
DWARF Extensions for Optimized SIMT - SIMD - GPU Debugging
Explore DWARF extensions for GPU debugging, addressing challenges in heterogeneous computing and optimizing variable location tracking in SIMT/SIMD environments.
Speed Up - Incremental Compilation with Nx
Explore Nx's incremental compilation feature for faster builds in large-scale Angular projects. Learn about dependency graphs, parallelization, and computation caching to enhance development speed and productivity.
Is Sharing GPU to Multiple Containers Feasible?
Explore GPU sharing for ML workloads in Kubernetes, maximizing utilization and cost-efficiency. Learn to extend Nvidia device plugin for multi-workload scheduling on a single GPU.
Production Multi-node Jobs with Gang Scheduling, K8s, GPUs and RDMA
Explore distributed execution of DL/ML jobs in Kubernetes, covering gang scheduling, GPU acceleration, and high-speed networking for improved performance and scalability.
Bring Batch Capability Into Kubernetes, Using AI and Big Data as an Example
Explore advanced scheduling features for batch workloads in Kubernetes, focusing on AI and big data applications using frameworks like TensorFlow and Spark. Learn about fair-share scheduling and the Volcano project.
Argo and Tekton - Pushing the Boundaries of the Possible on Kubernetes
Explore how Argo and Tekton push Kubernetes' boundaries for unconventional workloads, managing data, parallelism, and special lifecycle requirements beyond vanilla deployments.
C++ Workflow - Task-based Parallel Computing and Asynchronous Networking Engine
基于任务的并行计算和异步网络引擎,支持高并发请求处理。整合通信、计算、IO等异步资源,提供任务流概念实现复杂业务逻辑。跨平台、多协议,具备服务管理和负载均衡能力。
Beyond CUDA - GPU Accelerated Computing on Cross-Vendor Graphics Cards with Vulkan Kompute - AMD, Qualcomm, NVIDIA & Friends
Explore cross-vendor GPU computing with Vulkan and Kompute. Learn to write GPU-accelerated machine learning algorithms using Python and C++, applicable to various GPUs including AMD, Qualcomm, and NVIDIA.
Compiling Like a Boss
Explore techniques to optimize Scala compilation times, from compiler options and anti-patterns to utilizing multi-core processing with Triplequote Hydra, for faster and more efficient development.
Akka Streams for High Throughput Data Processing
Explore high-throughput data processing with Akka Streams, comparing it to Akka Actors. Learn best practices, optimization techniques, and when to switch to Streams for improved performance in large-scale data transfer systems.
Supercharge Your Performance - Optimus Cirrus Platform
Discover how Optimus Cirrus platform revolutionizes code compilation, reducing build times from hours to seconds through advanced caching and parallelization techniques, enhancing developer productivity at Morgan Stanley.
Building Production Applications Using Go & SQLite
Explore building scalable applications using Go and SQLite, focusing on recent advancements, configuration tips, and strategies for improving data durability and performance.
Parallel Computing in ReactJS - Provide a Pleasant User Experience
Learn to leverage modern APIs like Web Workers, WebAssembly, and Service Workers for parallel computing in React, enhancing performance and user experience in complex applications.
River Trail - Parallel Computing in JavaScript
Explore parallel computing in JavaScript with River Trail, unlocking new possibilities for high-performance web applications and efficient data processing.