NVIDIA | Investor Presentation Deck | 12 slides

NVIDIA · 2021-09
arc beats above · slides in the middle · loops below · scroll → 0 LOOPS
SETUP TENSION ANALYSIS EVIDENCE RESOLUTION APPENDIX
HOVER FOR DETAILS · CLICK A SLIDE FOR FULLSCREEN · STEP 1
No image bound to this slide. Wire up imgproxy to display the rendered slide JPEG.

Deck intelligence map

3
coverage by narrative range · generated from this deck JSON

Slide inventory

12
every slide · same image gating as the playbook
01
Slide 1
front_matter
03
The chart shows a log-scale growth in PetaFLOP-days over time, with a specific callout to the compute requirements for GPT-3.establish_context
Open slide detailBeat · Problem
04
The slide uses a bulleted list to contrast the high cost of training with the utility of few-shot learning, supported by a concrete translation example.frame_problem
Open slide detailBeat · Problem
05
The chart demonstrates near-linear scaling of performance (PetaFLOP/s) against GPU count.analyze_data
Open slide detailBeat · Solution
06
The diagram shows a feedback loop where a supercomputer provides weights (Δw) to a neural network that processes 1440p inputs into 4K outputs, compared against present_solution
Open slide detailBeat · Solution
07
The slide demonstrates the performance uplift of DLSS technology, showing an increase from 108 FPS to 141 FPS.present_solution
Open slide detailBeat · Solution
08
The slide uses a visual comparison to demonstrate performance and fidelity gains.present_solution
Open slide detailBeat · Solution
09
illustrate_case
Open slide detailBeat · Solution
10
The diagram shows a flywheel-like process where data and models flow between the Data Factory, Perception AI Training, Driving AI Training, HD Map generation, Spresent_solution
Open slide detailBeat · Solution
11
summarize
12
This is a branding/cover slide.front_matter