Introduction to Massively Parallel GPU Computing with CUDA
od
wtorek, 25 marca 2025 (15:00)
do
wtorek, 1 kwietnia 2025 (18:00)
poniedziałek, 24 marca 2025
wtorek, 25 marca 2025
15:00
Overview of CUDA architecture and programming model
Overview of CUDA architecture and programming model
15:00 - 16:00
– GPU evolution – CUDA GPU architecture
16:00
Basic CUDA programming
Basic CUDA programming
16:00 - 17:00
– Brief revise of CUDA programming model – Key principles – Introduction to the concept of threads & blocks – Host-device data transfer
17:00
Hands-on exercises on writing simple CUDA programs
Hands-on exercises on writing simple CUDA programs
17:00 - 18:00
– Using CUDA on HPC cluster – Simple programs with C/C++
środa, 26 marca 2025
czwartek, 27 marca 2025
piątek, 28 marca 2025
sobota, 29 marca 2025
niedziela, 30 marca 2025
poniedziałek, 31 marca 2025
wtorek, 1 kwietnia 2025
15:00
Overview of CUDA memory hierarchy
Overview of CUDA memory hierarchy
15:00 - 16:00
– An overview of memory levels – Global memory – Registers, constant memory, texture memory – Shared memory and synchronization
16:00
Introduction to CUDA Deep Neural Network library (cuDNN)
Introduction to CUDA Deep Neural Network library (cuDNN)
16:00 - 17:00
– Using cuDNN for deep neural networks – Convolutional neural networks in cuDNN – Integration with other CUDA libraries (cuBLAS, cuSOLVER, cuRAND, cuTENSOR, TensorRT)
17:00
Exercises on CUDA techniques: image processing and neural networks
Exercises on CUDA techniques: image processing and neural networks
17:00 - 18:00
– Image convolution filtering – Implementation of neural network from scratch with C/C++ – Implementation of neural network using cuDNN