Do you want to write multi-GPU libraries, but don't know where to start or how to write message-passing interface code? We'll introduce the world of general-purpose, task-based runtime systems. These runtime systems will help you write programs transparently, scaling to any number of GPUs without any explicit communication and coordination that are difficult to do by hand.We'll also show you how to make your newly written code interoperate seamlessly with the existing domain libraries within the same program.
Speaker: Manolis Papadakis, Software Engineering Manager, Legate Framework, NVIDIA
CUDA Toolkit:
Watch more NVIDIA GTC sessions on demand:
Replay of NVIDIA GTC 2025 session: S72579
Topic: Models / Libraries / Frameworks - Accelerated Computing Libraries
NVIDIA technology: #CUDA, #CUDA-X
#cuda #gtc25 #nvidia #gtc
Музыка
Фильмы
ТВ Шоу
Категории видео
