Bachana Jangebashvili, B.Sc.

Student Assistant

Research Topics

  • GPU database systems
  • Runtime compilation of CUDA kernels
  • Kernel fusion strategies
  • GPU-friendly data layouts

Publications

Full list on dblp.

  • Maha Alwahibi, Bachana Jangebashvili, Maximilian E. Schüle: Into the CUDA Multiverse of Runtime Compilation: Exploring Kernel Fusion Strategies for GPU Database Systems (52nd International Conference on Very Large Databases (VLDB 2026))

Bio

Bachana Jangebashvili is a student assistant in the Data Engineering group at the University of Bamberg, where he is completing his master's degree in Applied Computer Science. He works on a GPU database project: his research focuses on running database queries efficiently on GPUs – compiling CUDA kernels at query time, fusing kernels, and choosing data layouts that suit the GPU's memory access. He co-authored the demonstration paper on kernel fusion strategies for GPU database systems presented at VLDB 2026 in Boston. He received his bachelor's degree in Computer Science from Caucasus University in Tbilisi, Georgia. Before coming to Bamberg, he spent over a year building real-time applications in C++ and Unreal Engine, as a game developer at ProxyMeta and as a game development lecturer at re:school.