Search for: All records

Summary This paper presents an extended version of our previous work on using compiler technology to automatically convert sequential C++ data abstractions, for example, queues, stacks, maps, and trees, to concurrent lock‐free implementations. A key difference between our work and existing research in software transactional memory (STM) is that our compiler‐based approach automatically selects the best state‐of‐the‐practice nonblocking synchronization method for the underlying sequential implementation of the data structure. The extended material includes a broader collection of the state‐of‐the‐practice lock‐free synchronization techniques, additional formal correctness proofs of the overall integration of the different synchronizations in our system, and a more comprehensive experimental study of the integrated techniques. We evaluate our compiler‐generated nonblocking data structures both by using a collection of micro‐benchmarks, including the Synchrobench suite, and by using a multi‐threaded application Dedup from PARSEC. Our automatically synchronized code attains performance competitive to that of concurrent data structures manually‐written by experts and much better performance than heavier‐weight support by STM. 

Transactional data structures allow data structures to support transactional execution, in which a sequence of operations appears to execute atomically. We consider a paradigm in which a transaction commits its changes to the data structure only if all of its operations succeed; if one operation fails, then the transaction aborts. In this work, we introduce an optimization technique called Check-Wait-Pounce that increases performance by avoiding aborts that occur due to failed operations. Check-Wait-Pounce improves upon existing methodologies by delaying the execution of transactions until they are expected to succeed, using a thread-unsafe representation of the data structure as a heuristic. Our evaluation reveals that Check-Wait-Pounce reduces the number of aborts by an average of 49.0%. Because of this reduction in aborts, the tested transactional linked lists achieve average gains in throughput of 2.5x, while some achieve gains as high as 4x.