LECTURES A GRATIS GLOBAL SERVICE
⌕ SEARCH GRATIS GLOBAL ↗
LECTURES
Why Parallelism? Why Efficiency?
SOURCE: YOUTUBE · NO TRACKING UNTIL YOU PRESS PLAY · TROUBLE PLAYING? WATCH AT THE SOURCE ↗

Why Parallelism? Why Efficiency?

72 MIN · EN · STATUS: [ STREAMING ]
RATE THIS
STANFORD

Stanford's CS149 Parallel Computing opens with Kayvon Fatahalian laying out why modern chips stopped getting faster by simply raising clock speed and started adding cores instead. He walks through the basic challenges of parallelizing code, from dividing work across processors to the overhead of coordinating them, and explains why raw efficiency, not just parallelism, matters for real workloads. The lecture covers processor fundamentals, including how instruction-level parallelism, multi-core design, and vector units fit together, setting up the vocabulary the rest of the course will build on. Kunle Olukotun joins as co-instructor on the course. The talk is pitched at students who already know how a single processor works and need the motivating argument for why parallel thinking is now unavoidable in systems design, from graphics chips to data centers. It runs as a standard lecture hall session with slides and direct address to the class.

At a glance

Lecture facts

Runtime compared with the other 387 Computer Science lectures
Runtime1 h 12 m
Compared with Computer ScienceLonger than 55%
Source channelStanford Online (YouTube)