Meeting 0x12 - Parallel Mergesort with Cuda
This months C++ meeting will be presented by Fabian.
GPUs allow programmers to launch thousands of threads and run software in a massively parallel fashion. During this talk, we will discuss both the software interface and hardware architecture of CUDA cards. Based on this discussion, we investigate how to re-write the time-honored mergesort algorithm.
Agenda
17:30 – 17:45 | Meet & Greet |
17:45 – 18:30 | Presentation |
18:30 – 19:00 | Meet & eat |
19:00 – 20:00 | Q&A |