Entry № 041-3 / V-2699 · 0:00 synced

Who REALLY Runs Hotter? AMD vs Intel

Linus Tech Tips@LinusTechTips2.2M viewsSep 16, 201919:15
Source
YT
Views
2.2M
Subscribers
16.8M
Critic
?
Audience
?

0 up · 0 down · 0 ratings

Promos

We have two 8-core CPUs: One at 105W, the other at 95W – But those numbers are completely arbitrary. Let’s test them and see for ourselves which will heat up faster! Buy a Core i9-9900K: On Amazon: geni.us On Newegg: lmg.gg Buy a Ryzen 7 3800X: On Amazon: geni.us On Newegg: lmg.gg Purchases made through some store links may provide some compensation to Linus Media Group. Discuss on the forum: linustechtips.com Our Affiliates, Referral Programs, and Sponsors: linustechtips.com Get Private Internet Access today at geni.us Displate metal posters: lmg.gg Linus Tech Tips merchandise at lttstore.com Linus Tech Tips posters at crowdmade.com Our Test Benches on Amazon: amazon.com Our production gear: geni.us Twitter - twitter.com Facebook - @LinusTech Instagram - @linustech Twitch - twitch.tv Intro Screen Music Credit: Title: Laszlo - Supernova Video Link: youtube.com iTunes Download Link: itunes.apple.com Artist Link: soundcloud.com Outro Screen Music Credit: Approaching Nirvana - Sugar High youtube.com

Start
AI OverviewDefault language

This video dives into a practical experiment to answer a common question in PC hardware: which processor actually runs hotter, an Intel Core i9-9900K or an AMD Ryzen 7 3800X? The hosts challenge the conventional interpretation of TDP ratings by highlighting that there is no universal industry standard for reporting CPU power draw, and that third party measurements are essential for a fair comparison. The setup includes two identical test benches with equal memory configurations and fresh OS installs, paired with a custom heat capture system using a thermal mass and thermochromic dye to visually track heat transfer. The discussion emphasizes that simply attaching the same cooler and running a stress test can misrepresent real heat outputs due to die size, soldering, IHS, and software reporting differences. The team then explains their methodology for a fair comparison by measuring the heat absorbed by a thermal mass rather than relying solely on CPU temperatures, and outlines the practical challenges of mounting and insulating both CPUs for an accurate reading. The core of the video shows the execution of the experiment. They assemble a sealed coolant loop with a thermal mass and a dye that changes color at high temperature to visualize heat transfer, while avoiding external heat losses as much as possible. The initial runs reveal several issues, including heat throttling and mounting contact problems, which the crew iterates on by adjusting cooling paths and re-seating components. They also explore how pump heat, coolant volume, and convection affect the measured heat, noting that the presence of thermal throttling can mask true power output. A key moment occurs when they implement a more direct reservoir setup and begin formal graphing of coolant temperature versus time, which enables a clearer view of which CPU delivers heat more quickly under load. As the measurements progress, the hosts compare stock behavior, multi-core enhancement settings, and RAM speed to understand how these factors influence heat output. They observe that despite Intel’s higher nominal power envelope in some configurations, AMD’s Ryzen system can heat more slowly in certain scenarios, while other runs show the opposite depending on boost behavior and cooling efficiency. The discussion then turns to the broader implications: Intel and AMD measure TDP differently, which complicates apples-to-apples comparisons, and there is no industry-wide standard yet. The video concludes with a recommendation to rely on independent reviews for performance and thermal data and to ignore branded TDP numbers when making direct comparisons, since real-world cooling and turbo behavior can vary significantly. Overall, the video emphasizes empirical testing and critical interpretation of manufacturer specifications over simple at-a-glance wattage figures, offering viewers a practical framework for evaluating heat and performance in modern CPUs.

Topics · technology · hardware · science · consumer_electronics

Questions answered

What is the main reason there is no universal TDP standard across CPUs?
There is no universal standard because manufacturers measure power draw and thermal output using different definitions and testing assumptions, such as base frequency versus turbo behavior, which makes apples-to-apples comparisons difficult.
How do the hosts ensure a fair comparison between AMD and Intel CPUs?
They control variables like memory speed and OS state, use identical test benches, and measure heat transfer into a thermal mass rather than relying on CPU temperatures alone, while discussing the impact of boosting and cooling on the results.
Why do the hosts use thermochromic ink in the experiment?
Thermochromic ink visually marks when coolant reaches a high temperature, allowing them to see which CPU is contributing more heat based on color change rather than relying solely on sensor data.
What is the final takeaway regarding TDP ratings and buying decisions?
The takeaway is to ignore simple TDP numbers for direct comparison and instead rely on independent reviews and real-world thermal data, since TDP is not standardized and may not reflect actual sustained heat output.