While profile guided optimizations (PGO) and link time optimiza-tions (LTO) have been widely adopted, post link optimizations (PLO)have languished until recently when researchers demonstrated that late injection of profiles can yield significant performance improvements. However, the disassembly-driven, monolithic design of post link optimizers face scaling challenges with large binaries andis at odds with distributed build systems. To reconcile and enable post link optimizations within a distributed build environment, we propose Propeller, a relinking optimizer for warehouse scale work-loads. To enable flexible code layout optimizations, we introduce basic block sections, a novel linker abstraction. Propeller uses basic block sections to enable a new approach to PLO without disassembly. Propeller achieves scalability by relinking the binary using precise profiles instead of rewriting the binary. The overhead of relinking is lowered by caching and leveraging distributed compiler actions during code generation. Propeller has been deployed to production at Google with over tens of millions of cores executing Propeller optimized code at any time. An evaluation of internal warehouse-scale applications show Propeller improves performance by 1.1% to 8% beyond PGO and ThinLTO. Compiler tools such as Clang improve by 7% while MySQL improves by 1%. Compared to the state of the art binary optimizer, Propeller achieves comparable performance while lowering memory overheads by 30%-70% on large benchmarks.

Modern software executes a large amount of code. Previous techniques of code layout optimization were developed one or two decades ago and have become inadequate to cope with the scale and complexity of new types of applications such as compilers, browsers, interpreters, language VMs and shared libraries.

Cache in multicore machines is often shared, and the cache performance depends on how memory accesses belonging to different programs interleave with one another. The full range of performance possibilities includes all possible interleavings, which are too numerous to be studied by experiments for any mix of non-trivial programs.

A program can benefit from improved cache block utilization when contemporaneously accessed data elements are placed in the same memory block. This can reduce the program's memory block working set and thereby, reduce the capacity miss rate. We formally define the problem of data packing for arbitrary number of blocks in the cache and packing factor (the number of data objects fitting in a cache block) and study how well the optimal solution can be approximated for two dual problems. On the one hand, we show that the cache hit maximization problem is approximable within a constant factor, for every fixed number of blocks in the cache. On the other hand, we show that unless P=NP, the cache miss minimization problem cannot be efficiently approximated.