facebook rss twitter

Some AMD Ryzen CPUs don't run as hot as is reported

by Mark Tyson on 14 March 2017, 10:01

Tags: AMD (NYSE:AMD)

Quick Link: HEXUS.net/qadfa2

Add to My Vault: x

AMD has uploaded a blog post to its gaming community website. The post, by AMD exec Robert Hallock, comes about a fortnight since the AMD Ryzen 7 processor family launch and seeks to clear up a few grey areas that have become apparent through both pro reviews and user testing. Topics addressed are; Temperature reporting, Thread scheduling, Power plans, and Simultaneous Multi-Threading (SMT).

AMD Ryzen 7 CPU temperatures

AMD Ryzen processor temperatures are reported to the system via a sensor called 'T Control,' or tCTL for short. This temperature might be offset in certain models to create "a consistent fan policy," throughout the range, explains AMD. Please check over the chart below for an example of a scenario where a Ryzen 7 CPU is running at 38°C. You will see that the Ryzen 7 1700X and 1800X offset the temperature sensor read by 20°C.

Temperature monitor software is expected to get refined to understand tCTL offsets and report correct temperatures in the future.

Thread scheduling

There have been some tech press reports of AMD Ryzen performing poorly on Windows 10 - compared to Windows 7 systems. AMD has investigated to see if there is any truth in this and have concluded that "the Windows 10 thread scheduler is operating properly for Zen."

AMD's Hallock explains that and outdated version of the Sysinternals Coreinfo utility produced incorrect topology data "that has been widely reported in the media". There are many applications that already make good use of the cores and threads in Ryzen. However there are indeed a number of apps and games that would benefit from Ryzen with some targeted optimisations. This is why AMD is distributing 300+ AMD Ryzen dev kit systems worldwide.

Power Plans, SMT paradox

Elsewhere in the AMD blog post Hallock explains why AMD recommends the high Performance power plan within Windows 10. In a nutshell this is because it turns core parking off, and allows for fast frequency changes.

Users have been perturbed by instances where SMT has reduced performance in some games while the expectation would be to see neutral/positive benefit from SMT. Indeed that is the case in a wide range of titles AMD has tested. However, the admitted 'outliers' to this rule could improve with "some simple changes," to the game code. A status update will be provided by AMD when this information is ready to share.



HEXUS Forums :: 28 Comments

Login with Forum Account

Don't have an account? Register today!
What?

So they've set a 20 deg C arbitrary buffer onto measured temps to get fans to work overtime, for reasons only they know. Thread scheduling is “fine” even though the CPU performs noticeably better on an older operating system that likely doesn't support all of Ryzen's features, PLUS no explanation as to why this is.

Balanced power plan still hasn't received any Ryzen related modifications (though this is likely all Microsoft) and AMD refuse to accept that negative SMT scaling is in any way systematic or meaningful, despite the community saying otherwise, and believes “simple” changes are all that is required. So simple that they haven't arrived anywhere for anyone yet.

Why did they bother?

Edit: though to be fair Intel has had a very long time to get HT working properly on their side and while negative scaling isn't as bad, they have far from alleviated it, so maybe it's just the fundamental concept of increasing threads for lower single thread throughput that causes it. It could therefore be that Ryzen suffers more on single thread IPC when it deploys SMT threads to systemwide processes during gameplay. I don't know, someone with a bigger brain can explain it.
Problems, what problems?
Well, the 20°C offset only seems to apply to ‘X’ models.
And the ‘X’ models are meant to feature a more aggressive XFR boosting depending on temps. So is a faster fan meant to allow a higher boost? Or if the CPU relies on this erroneous offset does this mean the boost is actually lower?
I remember watching Tiny Ton Logans review of the 1800x and he said that there was something amiss as there was nowhere near enough heat being displaced from the case to account for the temperature reading of the cpu.

Bit half bakes I guess but haven't AMD cpu's always been funny with how they report temperatures?
Very odd. It's almost like they want to keep efficiency high by having the fans work harder than normal. Worst case would be that they can only cope with a lower tjMax, but I don't see why they wouldn't just lower it in that case - perhaps they thought about it and concluded it didn't fit well with existing fan profiles :/