Graphics Processing Unit had been developed to render graphics faster and since then, it ha found applications in Machine Learning inference. We have explored the key ideas that are used in Graphics Processing Unit to make it so fast.
Read this article to understand the key ideas that makes GPU faster than CPU
Key ideas include:
- Use many “slimmed down cores,” run them in parallel
- Pack cores full of ALUs (by sharing instruction stream overhead across groups of fragments)
- Avoid latency stalls by interleaving execution of many groups of fragments
Have a doubt or thought? Join the discussion now
This is a companion discussion topic for the original entry at http://iq.opengenus.org/key-ideas-that-makes-graphics-processing-unit-gpu-so-fast/