Future Scaling of Memory Hierarchy for Tensor Cores and Eliminating Redundant Shared Memory Traffic Using Inter-Warp Multicasting.
Sunjung LeeSeunghwan HwangMichael Jaemin KimJaewan ChoiJung Ho AhnPublished in: IEEE Trans. Computers (2022)
Keyphrases
- shared memory
- address space
- eliminating redundant
- memory access
- memory hierarchy
- multi core systems
- interprocess communication
- parallel algorithm
- message passing
- parallel architectures
- parallel computing
- distributed memory
- operating system
- higher order
- computer architecture
- parallel programming
- parallel execution
- parallel machines
- parallel computers
- main memory
- computing power
- multi core processors
- ip addresses
- data storage