The g-machine: a fast, graph-reduction evaluator
Proc. of a conference on Functional programming languages and computer architecture
Architecture of high performance computers: vol. 1
Architecture of high performance computers: vol. 1
Reduced instruction set computers
Communications of the ACM - Special section on computer architecture
Cache evaluation and the impact of workload choice
ISCA '85 Proceedings of the 12th annual international symposium on Computer architecture
The Manchester Mark I and atlas: a historical perspective
Communications of the ACM - Special issue on computer architecture
Communications of the ACM
Efficient compilation of lazy evaluation
SIGPLAN '84 Proceedings of the 1984 SIGPLAN symposium on Compiler construction
Architecture of a VLSI instruction cache for a RISC
ISCA '83 Proceedings of the 10th annual international symposium on Computer architecture
ASPLOS I Proceedings of the first international symposium on Architectural support for programming languages and operating systems
A study of branch prediction strategies
ISCA '81 Proceedings of the 8th annual symposium on Computer Architecture
MU6-G. a new design to achieve mainframe performance from a mini-sized computer
ISCA '80 Proceedings of the 7th annual symposium on Computer Architecture
LFP '84 Proceedings of the 1984 ACM Symposium on LISP and functional programming
Keeping jump instructions out of the pipeline of a RISC-like computer
ACM SIGARCH Computer Architecture News
S-1 architecture manual
Reduced Instruction Set Computer Architectures for VLSI
Reduced Instruction Set Computer Architectures for VLSI
Hi-index | 0.00 |
The G-machine provides architecture support for the evaluation of functional programming languages by graph reduction. This paper describes an instruction fetch unit for such an architecture that provides a high throughput of instructions, low latency and adequate elasticity in the instruction pipeline. This performance is achieved by a hybrid instruction set and a decoupled RISC architecture. The hybrid instruction set consists of complex instructions that reflect the abstract architecture and simple instructions that reflect the hardware implementation. The instruction fetch unit performs translation from complex instruction to a sequence of simple instructions which can be executed rapidly. A suitable mix of techniques, including cache, buffers and the translation scheme, provide the memory bandwidth required to feed a RISC execution unit. The simulation results identify the performance gains, maximum throughput and minimum latency achieved by various techniques. Results achieved here are in general applicable to von Neumann architectures.