Modular: What about OpenCL and CUDA C++ alternatives? (Democratizing AI Compute, Part 5)

AI-Driven Approach for Portable GPU Kernels in High-Performance Computing

This academic paper from North Carolina State University researchers presents an approach to leveraging AI ecosystems for creating portable

CUDA-oxide: Nvidia's official Rust to CUDA compiler

CUDA-L2: AI-Optimized Matrix Multiplication Outperforms NVIDIA cuBLAS

CUDA-L2 is a system that uses large language models and reinforcement learning to automatically optimize half-precision matrix multiplicatio

AI-Generated Metal Kernels Accelerate PyTorch Inference by 87% on Apple Devices

Researchers developed AI-generated Metal kernels that accelerate PyTorch inference on Apple devices by 87% across 215 modules. The study dem

Exploring Advanced Matrix Multiplication Engines for AI Applications

The article discusses the importance of matrix multiplication in modern computing, particularly in AI applications like neural networks and

Rethinking Graphics API Complexity: A Call for Simplifying GPU Programming

This technical blog post critiques the growing complexity of modern graphics APIs and shader frameworks, arguing that the current state of G