4.2 Teraflops of Performance? As part of an ongoing effort to raise the performance of open source math libraries, AMD added offline kernel compilation to clBLAS. Find out what the results were in this new blog.
clRNG 1.0 is an OpenCL library that generates uniform random numbers. This library is now available as open-source. Since it’s in beta, we’re looking for feedback. Check it out, use it, and let us know your feedback.
You can use OpenCL™ 2.0’s features and GPU compute to get real performance improvements in your code. Curious whether those performance gains are worth the effort? See what we did with hashing algorithms.
Questions about HSA development? See what other developers have asked, and get answers in the HSA forum on DevGurus.
Developing for DX12 or Vulkan can offer significant performance boosts but sometimes requires a new approach to graphics programming. Come see us at GDC Europe August 3-4 for a presentation that will show you how to work with the new APIs.
Heterogeneous Computing with OpenCL 2.0 teaches OpenCL and parallel programming for complex systems that may include a variety of device architectures: multi-core CPUs, GPUs, and fully-integrated Accelerated Processing Units (APUs). This fully-revised edition includes the latest enhancements in OpenCL 2.0 and much more. Best of all, it’s out of pre-order status and available now!
Over the past year or two AMD’s Mantle introduced the efficiency of low-level APIs to the PC gaming developer community. That sparked a trend leading to significant developments in graphics APIs like Vulkan™ and DirectX® 12. Why is concurrency the greatest feature of those new graphics APIs? Find out in this new blog post.
Microsoft® DirectX® 12 is designed to substantially increase a PC’s ability to run visually complex games at playable framerates. This blog post looks at the major rendering features of DirectX® 12, early performance profiles of AMD products, and collaborating with developers to ensure peak performance and top-notch image quality in upcoming games.
Power Profiling, Shader Analysis & More with AMD CodeXL 1.7
No comments:
Post a Comment