Automatic pool allocation

Abstract

This paper describes Automatic Pool Allocation, a transformation framework that segregates distinct instances of heap-based data structures into seperate memory pools and allows heuristics to be used to partially control the internal layout of those data structures. The primary goal of this work is performance improvement, not automatic memory management, and the paper makes several new contributions. The key contribution is a new compiler algorithm for partitioning heap objects in imperative programs based on a context-sensitive pointer analysis, including a novel strategy for correct handling of indirect (and potentially unsafe) function calls. The transformation does not require type safe programs and works for the full generality of C and C++. Second, the paper describes several optimizations that exploit data structure partitioning to further improve program performance. Third, the paper evaluates how memory hierarchy behavior and overall program performance are impacted by the new transformations. Using a number of benchmarks and a few applications, we find that compilation times are extremely low, and overall running times for heap intensive programs speed up by 10-25% in many cases, about 2x in two cases, and more than 10x in two small benchmarks. Overall, we believe this work provides a new framework for optimizing pointer intensive programs by segregating and controlling the layout of heapbased data structures.

Unification-based Pointer Analysis without Oversharing

“…2(a), as computed by a DSA-like PTA. This performance issue was already observed in [7], but only a workaround that loses context-sensitivity for global objects was implemented.…”

“…The main idea is to distinguish local aliasing created at different call sites. Data Structure Analysis (DSA) [7] is an example of a contextsensitive Steensgaard PTA. The results of a context-sensitive Steensgaard PTA on P 1 are shown in Fig.…”

“…In unification-based analyses, this is usually achieved by calculating a separate F − → relation for each function F in the analyzed program. DSA is an example of such an analysis [7]. Although not formally specified in [7], it is defined by adding rules to Γ STEENS ,…”

“…State-of-the-art implementations of unification-based, context-sensitive PTA (e.g., DSA [7] and SEADSA [8]) perform the analysis in phases. First, each function is analyzed in an intra-procedural manner (LOCAL).…”

FreeGuard

“…FreeGuard maintains four bump pointers for each size class of each per-thread heap, which always point to the rst neverallocated object [14,21]. Objects will be allocated in a sequential order.…”