About this document

Revisiting The Vertex Cache: Understanding and Optimizing Vertex Processing On The Modern GPU by E24106610許翰翔 is a document available to read on EtoBox.

This paper challenges the assumption that modern GPUs utilize a post-transform cache for vertex processing, demonstrating through experiments that current hardware relies on a batch-based approach instead. The authors evaluate existing mesh optimization algorithms in light of these findings and propose a new algorithm tailored for batch-based vertex reuse, which outperforms traditional methods when the batching strategy is known. Their extensive analysis reveals that modern GPUs do not exhibit the expected

Author

E24106610許翰翔

Language

EN