DeepAI AI Chat
Log In Sign Up

Adaptive Data Path Selection for Durable Transaction in GPU Persistent Memory

by   Xinjian Long, et al.
Beijing University of Posts and Telecommunications

The new non-volatile memory technology relies on data recoverability to achieve the promise of byte-addressable persistence in computer applications. The durable transaction (e.g. logging) is one of the major persistency programming models to provide recoverable data structures. To achieve performant failure-atomic transactional updates to PM, multi-data-path architectures that separate the data paths for persists are recently explored for CPUs. Considering the importance of GPU as a key computing platform for many application domains, we investigate the multi-data-path architecture for durable transactions to PM in GPU. Our solution, AGPM, exploits an adaptative data-path-selection strategy for the log updates to PM. AGPM reduces the GPU kernels' execution time by at least 24.37 state-of-the-art designs.


page 1

page 2

page 3

page 4


Blizzard: Adding True Persistence to Main Memory Data Structures

Persistent memory (PMEM) devices present an opportunity to retain the fl...

Transactional Composition of Nonblocking Data Structures

This paper introduces nonblocking transaction composition (NBTC), a new ...

Enabling Atomic Durability for Persistent Memory with Transiently Persistent CPU Cache

Persistent memory (pmem) products bring the persistence domain up to the...

MOD: Minimally Ordered Durable Datastructures for Persistent Memory

Persistent Memory (PM) makes possible recoverable applications that can ...

GPU-Accelerated Computation of Vietoris-Rips Persistence Barcodes

The computation of Vietoris-Rips persistence barcodes is both execution-...

Transactions on Red-black and AVL trees in NVRAM

Byte-addressable non-volatile memory (NVRAM) supports persistent storage...

Accelerating Distributed-Memory Autotuning via Statistical Analysis of Execution Paths

The prohibitive expense of automatic performance tuning at scale has lar...