causal

Systolic arrays trade extra compute for fixed communication

A systolic array bakes two levels of the matrix-multiply loop into hardware so that the weight matrix is stored locally in registers and reused across many input vectors; this provides x×y as much compute while keeping input/output communication at only x, solving the data-movement problem that plagued CUDA cores and making it the most efficient known circuit for matrix multiplication.

causalpending

Speaker

Reiner Pope

Evidence Quote

“we want to aim for having only x times as much communication. The intention is to get this advantage term going as y.”

Source

Dwarkesh Patel Podcast - Reiner Pope – Chip design from the bottom up— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:33:43 AM

Your notes

Loading notes...