Other formats:
BibTeX
LaTeX
RIS
@article{1314761, author = {Vinkler, Marek and Havran, Vlastimil}, article_number = {8}, doi = {http://dx.doi.org/10.1111/cgf.12666}, keywords = {dynamic memory allocation; many-core architecture; GPU; CUDA}, language = {eng}, issn = {0167-7055}, journal = {Computer Graphics Forum}, title = {Register Efficient Dynamic Memory Allocator for GPUs}, volume = {34}, year = {2015} }
TY - JOUR ID - 1314761 AU - Vinkler, Marek - Havran, Vlastimil PY - 2015 TI - Register Efficient Dynamic Memory Allocator for GPUs JF - Computer Graphics Forum VL - 34 IS - 8 SP - 143-154 EP - 143-154 PB - Wiley SN - 01677055 KW - dynamic memory allocation KW - many-core architecture KW - GPU KW - CUDA N2 - We compare five existing dynamic memory allocators optimized for GPUs and show their strengths and weaknesses. In the measurements, we use three generic evaluation tests proposed in the past and we add one with a real workload, where dynamic memory allocation is used in building the k-d tree data structure. Following the performance analysis we propose a new dynamic memory allocator and its variants that address the limitations of the existing dynamic memory allocators. The new dynamic memory allocator uses few resources and is targeted towards large and variably sized memory allocations on massively parallel hardware architectures. ER -
VINKLER, Marek and Vlastimil HAVRAN. Register Efficient Dynamic Memory Allocator for GPUs. \textit{Computer Graphics Forum}. Wiley, 2015, vol.~34, No~8, p.~143-154. ISSN~0167-7055. Available from: https://dx.doi.org/10.1111/cgf.12666.
|