An automatic mapping technique for OpenACC kernel code based on deeply fused and heterogeneous many-core architecture.
Libo ZhangXingquan MaoHongtao YouLong GuXiaocheng JiangPublished in: CCF Trans. High Perform. Comput. (2020)
Keyphrases
- loosely coupled
- fully automatic
- real time
- heterogeneous environments
- management system
- source code
- network architecture
- data fusion
- kernel methods
- texas instruments
- high dimensional feature space
- software architecture
- semi automatic
- kernel function
- data flow
- kernel matrix
- multiple kernel learning
- software development
- open source
- feature space
- code generation
- heterogeneous systems
- feature fusion
- industry standard
- dot product
- support vector