Indirect jumps improve instruction sequence performance
J. A. Bergstra, C. A. Middelburg

TL;DR
This paper demonstrates that replacing indirect jumps with direct jumps in instruction sequences can lead to unbounded increases in internal delays if the sequence length is not limited, highlighting a trade-off in instruction sequence optimization.
Contribution
It provides a formal analysis showing the impact of eliminating indirect jumps on internal delays and sequence length in unbounded instruction sequences.
Findings
Elimination of indirect jumps can cause unbounded internal delays.
The increase in internal delays is not linearly bounded when removing indirect jumps.
Trade-offs exist between instruction sequence length and execution delay.
Abstract
Instruction sequences with direct and indirect jump instructions are as expressive as instruction sequences with direct jump instructions only. We show that, in the case where the number of instructions is not bounded, we are faced with increases of the maximal internal delays of instruction sequences on execution that are not bounded by a linear function if we strive for acceptable increases of the lengths of instruction sequences on elimination of indirect jump instructions.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
