Dynamic Hammock Predication for Non-predicated Instruction Set Architectures

Artur Klauser, Todd Austin, Dirk Grunwald, and Brad Calder

International Conference on Parallel Architectures and Compilation Techniques, Paris, France, pages 278-285, October 1998.

Abstract:

Conventional speculative architectures use branch prediction to evaluate the most likely execution path during program execution. However, certain branches are difficult to predict. One solution to this problem is to evaluate both paths following such a conditional branch. Predicated execution can be used to implement this form of multi-path execution. Predicated architectures fetch and issue instructions that have associated predicates. These predicates indicate if the instruction should commit its result. Predicating a branch reduces the number of branches executed, eliminating the chance of branch misprediction at the cost of executing additional instructions.

In this paper, we propose a restricted form of multi-path execution called Dynamic Prediction for architectures with little or no support for predicated instructions in their instruction set. Dynamic predication dynamically predicates instruction sequences in the form of a branch hammock, concurrently executing both paths of a branch. A branch hammock is a short forward branch that spans a few instructions in the form of an if-then or if-then-else construct. We mark these and other constructs in the executable. When the decode stage detects such a sequence, it passes a predicated instruction sequence to a dynamically scheduled execution core. Our results show that dynamic predication can accrue speedups of up to 13%.