Intel Tiger Lake Performance Between Windows 10 vs. Ubuntu 21.04 Linux

[phoronix]

Phoronix: Intel Tiger Lake Performance Between Windows 10 vs. Ubuntu 21.04 Linux

With having hands on with a Dell XPS 13 9310 (Dell 0DXP1F) with the Core i7 1185G7 Tiger Lake processor (compared to prior Linux tests with the i7-1165G7), here is a fresh look at the performance of Microsoft Windows 10 Pro as shipped by Dell with all available stable updates versus a clean install of Ubuntu 21.04 Linux.

https://www.phoronix.com/vr.php?view=30331

[stormcrow]

Michael, were these tests run with the default power/thermal settings for Windows & Ubuntu?

[Guest]

Not directly related, but for anyone interested, here's fresh GeekBench CPU benchmarks between openSUSE TW and Windows 10 with a Ryzen 2700X: https://browser.geekbench.com/v5/cpu...seline=8792820

I don't think I've ever seen Windows score overall higher with GeekBench with any CPU, but Linux seems to handle "different" CPU architectures (NUMA and with Ryzen, CCX stuff) better by a notable amount.

[edexiel]

Would be interested to see the difference in battery life, I often see a some significant gap in battery life from one OS to the other

[Michael]

Michael, were these tests run with the default power/thermal settings for Windows & Ubuntu?

Yes default on both

[avem]

Would be interested to see the difference in battery life, I often see a some significant gap in battery life from one OS to the other

The battery life while running benchmarks won't differ significantly but what's really interesting how it will fare in terms of light web browsing, editing spreadsheets and presentations, watching youtube (VP9/AV1 video HW acceleration works out of the box in Windows 8 and higher and in Linux it's a long and sad story) or listening to Spotify - all minor activities in terms of CPU usage where the OS power saving technologies really shine and that's where unfortunately Linux is quite far behind. Even if we compare LibreOffice with Microsoft Office, the latter is far superior in terms of being CPU efficient.

I've asked Michael to run such tests on multiple occasions but so far he hasn't been interested.