Planned Weekly Schedule     Week Part Lectures Workshops Assignments 1 Introduction Heterogeneous Computers Assignment Discussion   Initial Assessment 2 Linear Algebra Fundamentals Initial Profile 1   3 Linear Algebra in Science BLAS 1   From Serial to Parallel The Eco-System 4 Test 1 Device Management 1   CUDA Programming Model CUDA Preliminaries 5 CUDA Libraries cuBlas 1   Thrust 6 Test 2 Thrust 1   Kernels and Grids 7 Parallel Profiling A Simple Kernel   2 Study Week 8 CUDA Programming Model Test 3 Instructor Assigned   2 Memory Model 9 Warp Partitioning Reduction   2 Optimization 10 Test 4 Thread Divergence 3   Streams Floating-Point 11 Case Studies Coalesced Memory Access 3   OpenCL Programming Model OpenCL Preliminaries 12 OpenCL Memory Model CUDA to OpenCL 3   Directive Programming OpenACC 13 Conclusion Test 5 Best Practices Presentations Exam Week