Implementing atomic actions on decentralized data
ACM Transactions on Computer Systems (TOCS)
Time, clocks, and the ordering of events in a distributed system
Communications of the ACM
The notions of consistency and predicate locks in a database system
Communications of the ACM
On the criteria to be used in decomposing systems into modules
Communications of the ACM
Letters to the editor: go to statement considered harmful
Communications of the ACM
The structure of the “THE”-multiprogramming system
Communications of the ACM
NAMING AND SYNCHRONIZATION IN A DECENTRALIZED COMPUTER SYSTEM
NAMING AND SYNCHRONIZATION IN A DECENTRALIZED COMPUTER SYSTEM
Computation: finite and infinite machines
Computation: finite and infinite machines
Runtime support for multicore Haskell
Proceedings of the 14th ACM SIGPLAN international conference on Functional programming
The multikernel: a new OS architecture for scalable multicore systems
Proceedings of the ACM SIGOPS 22nd symposium on Operating systems principles
| Hi-index | 0.00 |
The dominant view of computing is based on sequential processing as the "normal" case, with parallelism considered to be optional "acceleration." In this position paper, we argue that parallel is becoming the norm, so we must re-examine the primacy of serialized computations in time, simultaneous action-at-a-distance, and total ordering in our thinking and our engineering practices. We focus in this paper on some of these problematic ideas, design, and implementation structures that must be deprecated, and cleaner modularity concepts supported, if we in the systems part of the computing community are to unshackle parallel computing from its misplaced entanglement to a sequential model of computing. In the end, ours is a call to action, not revolutionary action that discards the past, but rapid evolutionary change, abandoning obsolete ideas.