DelayRepay - Delayed Execution for Kernel Fusion in Python
Python is a popular, dynamic language for data science and scientific computing. To ensure efficiency, significant numerical libraries are implemented in static native languages. However, performance suffers when switching between native and non-native code, especially if data has to be converted between native arrays and Python data structures. As GPU accelerators are increasingly used, this problem becomes particularly acute. Data and control has to be repeatedly transferred between the accelerator and the host.
In this talk, I'll present DelayRepay, a delayed execution framework for numeric Python programs. It avoids excessive switching and data transfer by using lazy evaluation and kernel fusion. Using DelayRepay, operations on NumPy arrays are executed lazily, allowing multiple calls to accelerator kernels to be fused together dynamically. DelayRepay is available as a drop-in replacement for existing Python libraries. This approach enables significant performance improvement over the state-of-the-art and is invisible to the application programmer. I show that our approach provides a maximum 377× speedup over NumPy - a 409% increase over the state of the art.
On this page of the site you can watch the video online DelayRepay - Delayed Execution for Kernel Fusion in Python with a duration of hours minute second in good quality, which was uploaded by the user PRiML Workshop 11 July 2021, share the link with friends and acquaintances, this video has already been watched 32 times on youtube and it was liked by 1 viewers. Enjoy your viewing!
