High-Performance GPU-to-CPU Transpilation and Optimization via High-Level Parallel Constructs
2023pp. 119–134
Citations Over TimeTop 10% of 2023 papers
Abstract
While parallelism remains the main source of performance, architectural implementations and programming models change with each new hardware generation, often leading to costly application re-engineering. Most tools for performance portability require manual and costly application porting to yet another programming model.
Related Papers
- → Porting CUDA-Based Molecular Dynamics Algorithms to AMD ROCm Platform Using HIP Framework: Performance Analysis(2019)17 cited
- → Evaluating CUDA Portability with HIPCL and DPCT(2021)10 cited
- → Porting scientific libraries to PGAS in XSEDE resources(2015)4 cited
- → Innovative approach for porting existing CPU program to its CUDA program(2015)
- → CUDA GPU Programming Applied to HSI Exploitation(2017)