Halide: A Language for Fast, Portable Computation on Images and Tensors - Alex Reinking - CppCon 20
https://cppcon.org/
https://github.com/CppCon/CppCon2020/blob/main/Presentations/halide_a_language_for_fast_portable_computation_on_images_and_tensors/halide_a_language_for_fast_portable_computation_on_images_and_tensors__alex_reinking__cppcon_2020.pptx
---
Halide is an open-source, domain-specific language for optimizing image processing, machine learning, and general array processing. It is used by major companies like Google, Adobe, and Qualcomm to optimize performance-critical software. It processes every photo taken with a Pixel phone, composites layers in every Photoshop document, and handles video processing at scale at YouTube.
We will explore how Halide achieves top-tier performance in a fraction of the development time by separating the algorithm (what to compute) from the schedule (how to optimize it). Halide's schedules determine trade-offs between parallelism, vectorization, cache locality, and memory management in a simple, modular way. Programmers can easily target different CPUs and GPUs by writing multiple schedules. Halide integrates tightly with C++ and provides both a JIT and a C++ compatible ahead-of-time compiler.
---
Alex is a Ph.D. student at UC Berkeley working with Jonathan Ragan-Kelley on designing domain-specific languages for high-performance computing. He has previously worked at Microsoft Research and Facebook AI+R. He holds an MS in Computer Science from UC Berkeley and a BS in Computer Science and Mathematics from Yale.
---
Streamed & Edited by Digital Medium Ltd - events.digital-medium.co.uk
events@digital-medium.co.uk
Видео Halide: A Language for Fast, Portable Computation on Images and Tensors - Alex Reinking - CppCon 20 канала CppCon
https://github.com/CppCon/CppCon2020/blob/main/Presentations/halide_a_language_for_fast_portable_computation_on_images_and_tensors/halide_a_language_for_fast_portable_computation_on_images_and_tensors__alex_reinking__cppcon_2020.pptx
---
Halide is an open-source, domain-specific language for optimizing image processing, machine learning, and general array processing. It is used by major companies like Google, Adobe, and Qualcomm to optimize performance-critical software. It processes every photo taken with a Pixel phone, composites layers in every Photoshop document, and handles video processing at scale at YouTube.
We will explore how Halide achieves top-tier performance in a fraction of the development time by separating the algorithm (what to compute) from the schedule (how to optimize it). Halide's schedules determine trade-offs between parallelism, vectorization, cache locality, and memory management in a simple, modular way. Programmers can easily target different CPUs and GPUs by writing multiple schedules. Halide integrates tightly with C++ and provides both a JIT and a C++ compatible ahead-of-time compiler.
---
Alex is a Ph.D. student at UC Berkeley working with Jonathan Ragan-Kelley on designing domain-specific languages for high-performance computing. He has previously worked at Microsoft Research and Facebook AI+R. He holds an MS in Computer Science from UC Berkeley and a BS in Computer Science and Mathematics from Yale.
---
Streamed & Edited by Digital Medium Ltd - events.digital-medium.co.uk
events@digital-medium.co.uk
Видео Halide: A Language for Fast, Portable Computation on Images and Tensors - Alex Reinking - CppCon 20 канала CppCon
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Back to Basics: Exceptions - Klaus Iglberger - CppCon 2020](https://i.ytimg.com/vi/0ojB8c0xUd8/default.jpg)
![Empirically Measuring, & Reducing, C++’s Accidental Complexity - Herb Sutter - CppCon 2020](https://i.ytimg.com/vi/6lurOCdaj0Y/default.jpg)
![Modern C++ Safety and Security At 20 - Matthew Butler - CppCon 2020](https://i.ytimg.com/vi/uccarZGpDhk/default.jpg)
![Making Games Start Fast: A Story About Concurrency - Mathieu Ropert - CppCon 2020](https://i.ytimg.com/vi/TcuPIVKNSN0/default.jpg)
![CppCon 2019: Emery Berger “Mesh: Automatically Compacting Your C++ Application's Memory”](https://i.ytimg.com/vi/XRAP3lBivYM/default.jpg)
![Building an Intuition for Composition - Sy Brand - CppCon 2020](https://i.ytimg.com/vi/AGRWRwi7rD0/default.jpg)
![The Surprising Costs of void() (and Other Not-Quite-Innocuous Evils) - Patrice Roy - CppCon 2020](https://i.ytimg.com/vi/Wg1f9Sufyic/default.jpg)
![Get Off My Thread: Techniques for Moving Work to Background Threads - Anthony Williams - CppCon 2020](https://i.ytimg.com/vi/iUKxvEg0zdk/default.jpg)
![Halide CVPR tutorial](https://i.ytimg.com/vi/WvzlaRpmtVk/default.jpg)
![Heterogeneous Programming in C++ with SYCL 2020 - Michael Wong & Gordon Brown - CppCon 2020](https://i.ytimg.com/vi/fxCnpNVPazk/default.jpg)
![Structure and Interpretation of Computer Programs: SICP - Conor Hoekstra - CppCon 2020](https://i.ytimg.com/vi/7oV7hiAsVTI/default.jpg)
![The Hidden Secrets of Move Semantics - Nicolai Josuttis - CppCon 2020](https://i.ytimg.com/vi/TFMKjL38xAI/default.jpg)
![How to Learn Faster with the Feynman Technique (Example Included)](https://i.ytimg.com/vi/_f-qkGJBPts/default.jpg)
![Back to Basics: Concurrency - Arthur O'Dwyer - CppCon 2020](https://i.ytimg.com/vi/F6Ipn7gCOsY/default.jpg)
![CppCon 2019: Miro Knejp “Non-conforming C++: the Secrets the Committee Is Hiding From You”](https://i.ytimg.com/vi/IAdLwUXRUvg/default.jpg)
![The Science of Unit Tests - Dave Steffen - CppCon 2020](https://i.ytimg.com/vi/FjwayiHNI1w/default.jpg)
![Halide Talk](https://i.ytimg.com/vi/3uiEyEKji0M/default.jpg)
![Plenary: Performance Matters - Emery Berger - CppCon 2020](https://i.ytimg.com/vi/koTf7u0v41o/default.jpg)
![Everything and Nothing: What is Nothing? (Jim Al-Khalili) | Science Documentary | Science](https://i.ytimg.com/vi/rKPv8zApee0/default.jpg)
![OO Considered Harmful - Phil Nash - CppCon 2020](https://i.ytimg.com/vi/pH-q2m5sb04/default.jpg)