Optimized parallel prefix sum algorithm on optoelectronic biswapped-torus architecture

The former also has architectural bene¯t of nodesymmetry that leads to advantages such as easy embedding, mapping and designing of routing algorithms. Compared to symmetrical counter-part of biswapped family named BiswappedHyper Hexa-Cell, Biswapped-Torus is cost-e±cient, but requires comparatively more communication moves for mapping prefix sum.
Nội dung trích xuất từ tài liệu:
Optimized parallel prefix sum algorithm on optoelectronic biswapped-torus architecture