Targeting heterogeneous computing platforms

This chapter covers code retargeting for heterogeneous platforms, including the use of directives and DSLs specific to GPUs as well as FPGA-based accelerators. This chapter highlights important aspects when mapping computations described in C/C++ programming language to GPUs and FPGAs using OpenCL and high-level synthesis tools, respectively. We complement this chapter by revisiting the roofline model and explain its importance when targeting heterogeneous architectures. This chapter also presents performance models and program analysis methodologies to support developers in deciding when to offload computation to GPU- and FPGA-based accelerators.