GPU-Based Hardware Platforms
GPU, SIMD, single-package platforms, multi-package platforms GPU-based hardware platforms are platforms that usually use GPUs in conjunction with CPUs to accelerate specific tasks. GPUs have evolved as a powerful accelerator for processing huge amounts of data in parallel.
This chapter details the architectural design and internal working of GPU-based hardware platforms. For this, we broadly classify GPU-based hardware platforms into two categories: single-package and multi-package. We then detail the architectural differences as well as the advantages and limitations of each category.
Graphics processing units (GPUs) were initially designed to accelerate the rendering of images for video editing and gaming. However, more recently, GPUs have evolved as a powerful accelerator for processing huge amounts of data in parallel. Similar to CPUs, GPUs also contains processing cores, registers, multiple levels of cache, and a global memory unit. However, GPUs differ...
- AMD (2017a) AMD Ryzen mobile. http://www.amd.com/en/products/ryzen-processors-laptop
- AMD (2017b) AMD Vega 64. https://gaming.radeon.com/en/product/vega/radeon-rx-vega-64/
- AnandTech (2017) Intel to create 8th generation CPUs with AMD Radeon graphics. https://www.anandtech. com/show/12003/intel-to-create-new-8th-generation-cp us-with-amd-radeon-graphics-with-hbm2-using-emib
- Bergstra J, Bastien F, Breuleux O, Lamblin P, Pascanu R, Delalleau O, Desjardins G, Warde-Farley D, Goodfellow IJ, Bergeron A, Bengio Y (2011) Theano: deep learning on GPUs with python. In: Big learn workshop, NIPS’11Google Scholar
- Chetlur S, Woolley C, Vandermersch P, Cohen J, Tran J, Catanzaro B, Shelhamer E (2014) cuDNN: efficient primitives for deep learning. CoRR. http://arxiv.org/abs/1410.0759. https://dblp.org/rec/bib/journals/corr/ChetlurWVCTCS14
- Kruger J, Westermann R (2003) Acceleration techniques for GPU-based volume rendering. In: Proceedings of the 14th IEEE visualization 2003 (VIS’03), IEEE computer society, Washington, DC, p 38. https://doi.org/10.1109/VIS.2003.10001
- Liu Y, Liu X, Wu E (2004) Real-time 3d fluid simulation on GPU with complex obstacles. In: Proceedings of the 12th Pacific conference on computer graphics and applications, PG 2004, pp 247–256. https://doi.org/10.1109/PCCGA.2004.1348355
- NVIDIA (2015) NVIDIA Tegra X1. http://www.nvidia.com/object/tegra-x1-processor.html
- NVIDIA (2016) NVIDIA Tesla P100. https://images. nvidia.com/content/pdf/tesla/whitepaper/pascal-archite cture-whitepaper.pdf
- Qualcomm (2017) Snapdragon 835 Mobile Platform. https://www.qualcomm.com/products/snapdragon/proc essors/835
- Shimokawabe T, Aoki T, Muroi C, Ishida J, Kawano K, Endo T, Nukada A, Maruyama N, Matsuoka S (2010) An 80-fold speedup, 15.0 tflops full GPU acceleration of non-hydrostatic weather model asuca production code. In: Proceedings of the 2010 ACM/IEEE international conference for high performance computing, networking, storage and analysis (SC’10). IEEE computer society, Washington, DC, pp 1–11. https://doi.org/10.1109/SC.2010.9Google Scholar
- Wikipedia (2011) Semiconductor package. https://en.wikipedia.org/wiki/Semiconductor_package
- Wikepedia (2017) Apple mobile application processors. https://en.wikipedia.org/wiki/Apple_mobile_application_processors?oldid=752966303