Architectural Support for Online Program Instrumentation

For advanced profile-guided optimizations to be e ective in online environments, fine-grained and accurate pro- file information must be available at low cost. In this paper, we propose a generic framework that makes it possible for instrumentation based profilers to collect profile data e ciently, a task that has traditionally been associated with high overheads. The essence of the scheme is to make the underlying hardware aware of instrumentation using a special set of profile instructions and tuned micro-architecture. This not only allows the hardware to provide the runtime with mechanisms to control the profiling activity, but also makes it possible for the hardware itself to optimize the process of profiling in a manner transparent to the runtime. We propose selective instruction dispatch as one possible controlling mechanism that can be used by the runtime to manage the execution of profile instructions and keep profiling overheads under check. We propose profile flag prediction, a hardware optimization that complements the selective dispatch mechanism by not fetching profile instructions when the runtime has turned profiling o . The framework is light-weight and flexible. It eliminates the need for expensive book-keeping, additional recompilation or code duplication. Our simulations with benchmarks from the SPEC CPU2000 suite show that overheads for call-graph and basic block profiling can be reduced by 72.7% and 52.4% respectively with a negligible loss in accuracy