Optimizing Dynamic Memory Management in a Multithreaded Application Executing on a Multiprocessor
ICPP '98 Proceedings of the 1998 International Conference on Parallel Processing
Dynamic Storage Allocation: A Survey and Critical Review
IWMM '95 Proceedings of the International Workshop on Memory Management
Scalable lock-free dynamic memory allocation
Proceedings of the ACM SIGPLAN 2004 conference on Programming language design and implementation
McRT-Malloc: a scalable transactional memory allocator
Proceedings of the 5th international symposium on Memory management
Modern Operating Systems
XMalloc: A Scalable Lock-free Dynamic Memory Allocator for Many-core Machines
CIT '10 Proceedings of the 2010 10th IEEE International Conference on Computer and Information Technology
KMA: A Dynamic Memory Manager for OpenCL
Proceedings of Workshop on General Purpose Processing Using GPUs
| Hi-index | 0.00 |
Dynamic memory allocation in massively parallel systems often suffers from drastic performance decreases due to the required global synchronization. This is especially true when many allocation or deallocation requests occur in parallel. We propose a method to alleviate this problem by making use of the SIMD parallelism found in most current massively parallel hardware. More specifically, we propose a hybrid dynamic memory allocator operating at the SIMD parallel warp level. Using additional constraints that can be fulfilled for a large class of practically relevant algorithms and hardware systems, we are able to significantly speed-up the dynamic allocation. We present and evaluate a prototypical implementation for modern CUDA-enabled graphics cards, achieving an overall speedup of up to several orders of magnitude.