ffwd: delegation is (much) faster than you think

We revisit the question of delegation vs. synchronized access to shared memory, and show through analysis and demonstration that delegation can be much faster than locking under a range of common circumstances. Starting from first principles, we propose fast, fly-weight delegation (ffwd). The highly optimized design of ffwd allows it to significantly outperform prior work on delegation, while retaining the scalability advantage. In experiments with 6 benchmark applications, and 6 shared data structures, running on four different multi-socket systems with up to 128 hardware threads, we compare ffwd to a selection of lock, combining, lock-free, software transactional memory and delegation designs. Overall, we find that ffwd often offers a simple and highly competitive alternative to existing work. By definition, the performance of a fully delegated data structure is limited by the single-thread throughput of said data structure. However, due to cache effects, many data structures offer their best performance when confined to a single thread. With an efficient delegation mechanism, we approach this single-threaded performance in a multi-threaded setting. In application-level benchmarks, we see improvements up to 100% over the next best solution tested (RCL), and multiple micro-benchmarks show improvements in the 5-10x range.