Content deleted Content added
→Description: removed bits about similarity to hyperthreading as SIMT is not like it at all. Tags: Mobile edit Mobile web edit Advanced mobile edit |
→Vortex GPU: add Jeff busy nyuzi Tags: Mobile edit Mobile web edit Advanced mobile edit |
||
Line 73:
The Vortex GPU is an Open Source [[GPGPU]] project by [[Georgia Tech University]] that runs [[OpenCL]]. Technical details:<ref>{{Cite web | title=vortex/docs/microarchitecture.md at master · vortexgpgpu/vortex · GitHub | url=https://github.com/vortexgpgpu/vortex/blob/master/docs/microarchitecture.md | access-date=2025-07-30 | website=github.com}}</ref>
Note a key defining characteristics of SIMT: the ''PC is shared''. However note also that time-multiplexing is used, giving the impression that it has more Array Processing Elements than there actually are.
=== Nyuzi GPGPU ===
Nyuzi is not SIMT: it is worth listing for comparison. Nyuzi implemented a [[barrel processor]] strategy over a SIMT one.<ref>http://www.cs.binghamton.edu/~millerti/nyami-ispass2015.pdf</ref> The project is noteworthy for learning and adapting as it progressed, providing comprehensive documentation and research papers.<ref>https://github.com/jbush001/NyuziProcessor/wiki</ref> The floating-point pipelines are Predicated [[SIMD]].
== See also ==
| |||