Paralleles Rechnen Seminar

Requirements / organisational issues

• ?E-Mail your 2 preferred topics to Prof. Schmidt by 3rd February 2107
  
• I will then assign a topic to you
  
• You are welcome to suggestion your own topic
  

• ?GPU Sparse Matrix Multiplication
  
• GPU Multisplit
  
• In-place matrix transposition on GPUs
  
• In-place data sliding on GPUs
  
• Optimizing CUDA dynamic parallelism
  
• Deep Learning on GPU clusters
  
• Library for k-mer indexing of biological sequences
  
• HIPAcc: A DSL and compiler for image processing
  
• Gerbil: fast k-mer counting on GPUs
  
• Big data analytics on the cloud: Spark vs MPI
  
• Self-suggested topic (requires approval by Prof. Schmidt)