Ananya Desavali @ananyades1234

RocPorter addresses one of AMD's biggest software ecosystem challenges: the difficulty of migrating existing CUDA applications to the ROCm platform. Although many organizations want to adopt AMD GPUs, manually porting CUDA code to HIP is time-consuming and requires deep knowledge of ROCm libraries and compatibility differences. RocPorter simplifies this process by automatically translating CUDA source code into HIP while simultaneously performing static analysis of the source. It identifies CUDA runtime APIs, GPU libraries, kernel launches, shared memory usage, cooperative groups, warp-level intrinsics, and unsupported or unknown symbols. Based on this analysis, RocPorter generates a comprehensive migration report that includes ROCm readiness, migration difficulty, estimated engineering effort, automatic vs. manual changes, compatibility checks, fix-up recommendations, and a prioritized migration roadmap. Designed as an engineering productivity tool rather than a simple code converter, RocPorter helps developers understand not only how to migrate CUDA applications, but also the effort and risks involved before beginning a port to AMD hardware.

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.