Recently, multi-core architectures with alternative memory subsystem designs have emerged. Instead of using hardwaremanaged cache hierarchies, they employ software-managed embedde...
Modulo scheduling is an e cient technique for exploiting instruction level parallelism in a variety of loops, resulting in high performance code but increased register requirement...
Alexandre E. Eichenberger, Edward S. Davidson, San...
The interconnect mechanisms (shared bus or crossbar) used in current chip-multiprocessors (CMPs) are expected to become a bottleneck that prevents these architectures from scaling...
level of abstraction, compared with the program representation for scalar optimizations. For example, loop unrolling and loop unrolland-jam transformations exploit the large regist...
Rakesh Krishnaiyer, Dattatraya Kulkarni, Daniel M....
Abstract. Traditional parallel programming methodologies for improving performance assume cache-based parallel systems. However, new architectures, like the IBM Cyclops-64 (C64), b...
Elkin Garcia, Ioannis E. Venetis, Rishi Khan, Guan...