Implementing and evaluating nested parallel transactions in software transactional memory

Abstract

Transactional Memory (TM) is a promising technique that simplifies parallel programming for shared-memory applications. To date, most TM systems have been designed to efficiently support single-level parallelism. To achieve widespread use and maximize performance gains, TM must support nested parallelism available in many applications and supported by several programming models.We present NesTM, a software TM (STM) system that supports closed-nested parallel transactions. NesTM is based on a highperformance, blocking STM that uses eager version management and word-granularity conflict detection. Its algorithm targets the state and runtime overheads of nested parallel transactions. We also describe several subtle correctness issues in supporting nested parallel transactions in NesTM and discuss their performance impact.Through our evaluation, we quantitatively analyze the performance of NesTM using STAMP applications and microbenchmarks based on concurrent data structures. First, we show that the performance overhead of NesTM is reasonable when single-level parallelism is used. Second, we quantify the incremental overhead of NesTM when the parallelism is exploited in deeper nesting levels and draw conclusions that can be useful in designing a nestingaware TM runtime environment. Finally, we demonstrate a usecase where nested parallelism improves the performance of a transactional microbenchmark.

Making nested parallel transactions practical using lightweight hardware support

“…We discuss only a few concepts for concurrent nesting [3]. We refer readers to [2,14] for additional discussions.…”

“…We use NesTM [3] as a proxy for a timestamp-based STM with support for concurrent nesting. While it is an open research issue to formally check the correctness and liveness guarantees of timestamp-based nested STMs, we use NesTM to investigate performance differences between software and hybrid nested TMs.…”

“…While it is an open research issue to formally check the correctness and liveness guarantees of timestamp-based nested STMs, we use NesTM to investigate performance differences between software and hybrid nested TMs. We only provide a brief description and refer to [3] for additional information on NesTM.…”

“…NesTM [3] extends an eager variant of TL2 [8] to support concurrent nesting. NesTM uses a global version clock to establish serializability.…”

“…While compatible with existing multicore chips, most STM implementations already suffer from excessive runtime overheads of TM barriers even for single-level parallelism [6]. To make the problem worse, supporting nested parallelism solely in software may introduce additional performance overheads due to the use of complicated data structures [2,4] or the use of an algorithm whose time complexity is proportional to the nesting depth [3]. For example, as shown in our performance evaluation, a singlethreaded, transactional version of the red-black tree microbenchmark runs 6.2× slower with single-level transactions and 17.0× slower with nested transactions than a non-transactional, sequential version.…”