Skip to Main content Skip to Navigation
Journal articles

Thread scheduling and memory coalescing for dynamic vectorization of SPMD workloads

Abstract : Simultaneous Multi-Threading (SMT) is a hardware model in which different threads share the same processing unit. This model is a compromise between high parallelism and low hardware cost. Minimal Multi-Threading (MMT) is one architecture recently proposed that shares instruction decoding and execution between threads running the same program in an SMT processor, thereby generalizing the approach followed by Graphics Processing Units to general-purpose processors. In this paper we propose new ways to expose redundancies in the MMT execution model. First, we propose and evaluate a new thread reconvergence heuristic that handles function calls better than previous approaches. Our heuristic only inspects the program counter and the stack frame to reconverge threads; hence, it is amenable to efficient and inexpensive hardware implementation. Second, we demonstrate that this heuristic is able to reveal the existence of substantial regularity in inter-thread memory access patterns. We validate our results on data-parallel applications from the PARSEC and SPLASH suites. Our new reconvergence heuristic increases the throughput of our MMT model by 7%, when compared to a previous, and substantially more complex approach, due to Long et al. Moreover, it gives us an effective way to increase regularity in memory accesses. We have observed that over 70% of simultaneous memory accesses are either the same for all the threads, or are affine expressions of the thread identifier. This observation motivates the design of newly proposed hardware that benefits from regularity in inter-thread memory accesses.
Document type :
Journal articles
Complete list of metadata
Contributor : Caroline Collange Connect in order to contact the contributor
Submitted on : Friday, February 11, 2022 - 1:53:50 PM
Last modification on : Friday, February 11, 2022 - 2:37:24 PM
Long-term archiving on: : Thursday, May 12, 2022 - 6:42:53 PM


Files produced by the author(s)



Teo Milanez, Caroline Collange, Fernando Magno Quintão Pereira, Wagner Meira, Renato A. Ferreira. Thread scheduling and memory coalescing for dynamic vectorization of SPMD workloads. Parallel Computing, Elsevier, 2014, 40 (9), pp.548-558. ⟨10.1016/j.parco.2014.03.006⟩. ⟨hal-01087054⟩



Record views


Files downloads