Hot Chips 2020 Posters
| Autor: | Yaotian Feng, Ethan Lyons, Lingjun Zhu, Fares Elsabbagh, Da Eun Shim, Priyadarshini Roshan, Apurve Chawda, Will Gulian, Blaise Tine, Hyesoon Kim, Sung Kyu Lim |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Exploit
business.industry Data parallelism Computer science 0211 other engineering and technologies 021107 urban & regional planning 02 engineering and technology Modular design computer.software_genre 03 medical and health sciences 0302 clinical medicine Software Computer architecture Scalability Benchmark (computing) 030212 general & internal medicine Compiler General-purpose computing on graphics processing units business computer |
| Zdroj: | 2020 IEEE Hot Chips 32 Symposium (HCS). |
| DOI: | 10.1109/hcs49909.2020.9250188 |
| Popis: | The emergence of data parallel architectures have enabled new opportunities to address the power limitations and scalability of multi-core processors, allowing new ways to exploit the abundant data parallelism present in emerging big-data and machine learning applications. This transition is getting a significant boost with the advent of RISC-V with its unique modular and extensible ISA, allowing a widerange of low-cost processor designs. In this work, we present Vortex, a full-stack RISC-V GPGPU processor with OpenCL support. The Vortex platform is highly customizable and scalable with a complete open-source compiler, driver, and runtime software stack to enable research in GPU architectures. We evaluated this design using 15 nm technology. We also show the preliminary performance and energy numbers of running them with a subset of benchmarks from the Rodinia Benchmark suite. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|