Tag
Design-CP introduces context-parallel inference strategies for RFdiffusion 3 that enable the all-atom design of large multimeric protein nanoparticles by distributing quadratic activations across multiple GPUs, making large-assembly protein design feasible on smaller GPU clusters.
A detailed thread summarizing the book 'Programming Massively Parallel Processors', focusing on CUDA and GPU programming concepts, optimization techniques, and parallel patterns.
The author built a DIY GPU-like parallel computing cluster using 65536 low-cost RISC-V microcontrollers (CH570), achieving QVGA resolution rendering, and solved engineering challenges such as power supply, heat dissipation, and programming automation.
This article explains how GPUs work for deep learning, covering why they are ideal for parallel matrix computations, the difference between CPU and GPU, and key concepts like VRAM and Tensor Cores.
Researchers propose using sound waves and phi-bits to create neuromorphic devices that better mimic biological neurons, potentially enabling faster, more energy-efficient computing for pattern recognition and data analysis.
This paper studies parallel Continuous Local Search (CLS) for Boolean satisfiability with pseudo-Boolean constraints, revealing that redundant constraints can inhibit convergence and that CLS shows promise as a sub-solver in hybrid settings.
Explores the use of monoids for embarrassingly parallel data processing, showing that traditionally sequential algorithms like Horner rule and Boyer-Moore majority voting can be parallelized via monoid composition. Also introduces vertical monoid composition for efficient nested grouping-aggregation.
A comprehensive walkthrough on building multi-agent teams with Claude Managed Agents, covering role design, model mixing, and parallel execution to scale from one to 20 agents.
Python 3.14 introduces the ability to disable the Global Interpreter Lock (GIL), enabling true parallel execution of multi-threaded code, overcoming a long-standing limitation.
A curated list of major books on CUDA programming covering beginner to advanced topics, including C++ and Python, with focus on practical resources for NVIDIA GPU parallel computing.
Accelerate is an embedded domain-specific language in Haskell for high-performance parallel array computations, supporting online compilation to multicore CPUs and CUDA GPUs.
A hands-on introduction to the Futhark programming language through a collection of commented example programs, covering basic features and programming techniques for parallel computing.
This article introduces the Cornell Virtual Workshop's free online tutorial on basic CUDA programming using C, covering prerequisites and additional resources.