The Manchester prototype dataflow computer
Communications of the ACM - Special section on computer architecture
Data flow graph optimization in ifi
Proc. of a conference on Functional programming languages and computer architecture
Stored data structures on the Manchester dataflow machine
ISCA '86 Proceedings of the 13th annual international symposium on Computer architecture
Control of parallelism in the Manchester Dataflow Machine
Proc. of a conference on Functional programming languages and computer architecture
Parallel structure storage in a dataflow machine
Parallel structure storage in a dataflow machine
Manchester data-flow: a progress report
ICS '92 Proceedings of the 6th international conference on Supercomputing
A model for dataflow based vector execution
ICS '94 Proceedings of the 8th international conference on Supercomputing
Two issues in parallel language design
ACM Transactions on Programming Languages and Systems (TOPLAS)
Self-regulation of workload in the Manchester Data-Flow computer
Proceedings of the 28th annual international symposium on Microarchitecture
An evaluation of bottom-up and top-down thread generation techniques
MICRO 26 Proceedings of the 26th annual international symposium on Microarchitecture
Asynchrony in parallel computing: from dataflow to multithreading
Progress in computer research
Asynchrony in parallel computing: from dataflow to multithreading
Progress in computer research
Iterative Instructions in the Manchester Dataflow Computer
IEEE Transactions on Parallel and Distributed Systems
A Hybrid Scheme for Processing Data Structures in a Dataflow Environment
IEEE Transactions on Parallel and Distributed Systems
The Initial Performance of a Bottom-Up Clustering Algorithm for Dataflow Graphs
PACT '93 Proceedings of the IFIP WG10.3. Working Conference on Architectures and Compilation Techniques for Fine and Medium Grain Parallelism
Hi-index | 14.98 |
The efficiency of dataflow code generated from a high-level language can be considerably improved by both conventional and dataflow-specific optimizations. Such techniques are used in implementing the single-assignment language SISAL on the Manchester Dataflow Machine. The quality of code generated for numeric applications can be measured in terms of the ratio of total number of instructions executed to floating-point operations: the MIPS/MFLOPS ratio. Relevant features of the general-purpose single-assignment language SISAL and the Manchester Dataflow Machine are introduced. An assessment of the initial SISAL implementation shows it to be very expensive. A range of optimizations is then described.