Summarizing CPU and GPU Design Trends with Product Data
arXiv:1911.11313
Abstract
Moore's Law and Dennard Scaling have guided the semiconductor industry for the past few decades. Recently, both laws have faced validity challenges as transistor sizes approach the practical limits of physics. We are interested in testing the validity of these laws and reflect on the reasons responsible. In this work, we collect data of more than 4000 publicly-available CPU and GPU products. We find that transistor scaling remains critical in keeping the laws valid. However, architectural solutions have become increasingly important and will play a larger role in the future. We observe that GPUs consistently deliver higher performance than CPUs. GPU performance continues to rise because of increases in GPU frequency, improvements in the thermal design power (TDP), and growth in die size. But we also see the ratio of GPU to CPU performance moving closer to parity, thanks to new SIMD extensions on CPUs and increased CPU core counts.
arXiv commentFix flops/watt error
Cited by in corpus (10)
- GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
- Synthesis and structural analysis of Mo/B periodical multilayer X-ray mirrors for beyond extreme ultraviolet optics
- AstroPhot: Fitting Everything Everywhere All at Once in Astronomical Images
- 10,000 km Straight-line Transmission using a Real-time Software-defined GPU-Based Receiver
- Revisiting the Sample Adaptive Offset post-filter of VVC with Neural-Networks
- Socio-Technological Challenges and Opportunities: Paths Forward
- Real-time Transmission of Geometrically-shaped Signals using a Software-defined GPU-based Optical Receiver
- Large-scale Sustainable Search on Unconventional Computing Hardware
- Beyond multi-view deconvolution for inherently-aligned fluorescence tomography
- Real-time 10,000 km Straight-line Transmission using a Software-defined GPU-Based Receiver