what's new in metal
Generated on 8/5/2024
2 searches
What's New in Metal
General Improvements
Metal has seen several advancements aimed at improving both machine learning and gaming experiences on Apple platforms. Here are some of the key updates:
-
Machine Learning Enhancements:
- JAX Metal Backend: The JAX Metal plugin has received updates such as improved advanced array indexing, adoption of the CI runner workflow, and support for mixed precision. The Pfloat 16 data type is now supported, which is beneficial for mixed precision training (Train your machine learning and AI models on Apple GPUs).
- TensorFlow and PyTorch: The Metal backend for TensorFlow and PyTorch supports features like distributed training, custom operations, and profiling (Train your machine learning and AI models on Apple GPUs).
- MPS Graph: Enhancements to MPS and MPS Graph focus on improving the efficiency of transformer models and accelerating FFT-based ML models (Accelerate machine learning with Metal).
-
Gaming Enhancements:
- Metal Shader Converter: This tool supports all shader stages, including ray tracing and mesh shaders, and helps port shaders to Metal, significantly reducing development time (Port advanced games to Apple platforms).
- Resource Residency: Metal now supports resource residency, simplifying the adoption of ray tracing by allowing all ray-traced scene resources to be marked as resident (Port advanced games to Apple platforms).
- MetalfX: This feature improves game performance by scaling lower resolution images up, enhancing the visual quality without a significant performance hit (Port advanced games to Apple platforms).
Sessions Mentioned
- Train your machine learning and AI models on Apple GPUs
- Accelerate machine learning with Metal
- Port advanced games to Apple platforms
These updates highlight Apple's commitment to enhancing both machine learning and gaming experiences on their platforms through continuous improvements in Metal.
Port advanced games to Apple platforms
Discover how simple it can be to reach players on Apple platforms worldwide. We’ll show you how to evaluate your Windows executable on Apple silicon, start your game port with code samples, convert your shader code to Metal, and bring your game to Mac, iPhone, and iPad. Explore enhanced Metal tools that understand HLSL shaders to validate, debug, and profile your ported shaders on Metal.
Platforms State of the Union
Discover the newest advancements on Apple platforms.
Train your machine learning and AI models on Apple GPUs
Learn how to train your models on Apple Silicon with Metal for PyTorch, JAX and TensorFlow. Take advantage of new attention operations and quantization support for improved transformer model performance on your devices.
Accelerate machine learning with Metal
Learn how to accelerate your machine learning transformer models with new features in Metal Performance Shaders Graph. We’ll also cover how to improve your model’s compute bandwidth and quality, and visualize it in the all new MPSGraph viewer.