This site may earn affiliate commissions from the links on this page. Terms of use.

CoffeeLakeFeature

Intel's Java Lake Core i7-8700K has launched, earning our top CPU recommendation at its price betoken. But there's i issue worth existence aware of going frontward: Intel has declared that information technology will no longer officially disembalm its per-core Turbo frequencies. When we queried Intel why this was being changed, the company told us the following:

[Westward]e're no longer disclosing this level of detail every bit its proprietary to Intel. Intel only specifies processor frequencies for base and unmarried-core Turbo in our processor marketing and technical collateral, such as ARK, and not the multi-core Turbo frequencies. We're adjustment communications to be consequent. All Turbo frequencies are opportunistic given their dependency on system configuration and workloads.

There are several reasons to view this alter as a negative. First, not all Intel CPUs are equally aggressive when it comes to their Turbo scaling, even if they have the same or similar Turbo ranges. This is one reason why the gap betwixt chips tin be wider than they'd otherwise be. The Cadre i7-8700K, for instance, has a peak all-core frequency of 4.3GHz on half-dozen cores, which is adequately shut to its summit frequency of 4.7GHz for unmarried-cadre.

Equally a general dominion, Intel's higher-stop CPUs will boost more aggressively than their lower-end cores, simply even this isn't absolute. You can't assume that a CPU with a high single-cadre heave frequency too has an aggressive multi-core boost frequency, and you tin can't presume that ii CPUs with the aforementioned or very similar Turbo ranges have the same multi-core boost frequency distribution–though this is typically more of an consequence when comparing betwixt two unlike production generations as opposed to inside the aforementioned family. We'd expect more variance between the 6700K and 7700K, for example, than betwixt the Core i7-7700 and the Core i7-7700K.

cfl_turbo_v2

Anandtech was able to put this tabular array together anyway.

Second, and arguably more importantly, a lot of motherboards don't implement Turbo Heave well. We've seen motherboards literally opposite the way Turbo Boost is supposed to part, and downclock the CPU when running lightly threaded workloads as opposed to boosting it. Nosotros've seen boards either push the Turbo frequencies higher than default or lower than expected, even when explicitly ordered to utilize Intel'southward default scaling.

Fifty-fifty more than frustrating, this behavior can vary depending on which CPU y'all're testing. Our Asus Prime X299-A motherboard displayed very different behavior when nosotros tested the Core i9-7900X as opposed to the Core i9-7980XE. When nosotros tested Broadwell-E on a Gigabyte motherboard earlier this yr, nosotros had to manually punch in multipliers, only to notice that the 35x multiplier–and only the 35x multiplier–would produce random clock drops unless every criterion application was whitelisted in Intel's Turbo Boost 3.0 app. This didn't actually implement Turbo Boost 3.0-style scaling; information technology simply kept the CPU clock from flipping back and forth between two unlike clock speeds while benchmarking. The 34x and 36x multipliers were unaffected.

Finally, motherboard manufacturers have permission from Intel to really boost clock speeds, if you lot're loading XMP profiles. One problem we had with the 7980XE is that multiple attempts nosotros fabricated to set Intel stock Turbo settings would instead ready an all-cadre heave frequency of 4.2GHz, vastly higher than Intel's intended frequency of iii.4GHz. Intel has allowed motherboard manufacturers to make these aggressive changes when XMP is enabled for a number of years. But not every chip can handle them, and enthusiasts can stop up destabilizing their own systems every bit a result if they don't take notation of the different clocking scheme that'southward enabled when XMP is activated.

Some of these problems come with the territory. Pre-release hardware is called "pre-release" for a reason, and we almost ever get through a UEFI revision or two during the testing procedure. Motherboard vendors are also pretty responsive to feedback on how Turbo modes are implemented, and are willing to assistance with gathering data and making sure problems get resolved. But it's precisely considering Turbo modes are opportunistic and clocks can vary depending on the workload or even the SIMD ready the application uses that this information is and so valuable to have. If you lot don't know what the per-core clock frequencies or AVX offsets are supposed to be, information technology's not possible to make up one's mind whether you're seeing appropriate frequencies at any given point. And Intel's Turbo Heave clocks take ever been opportunistic and have ever depended on available cooling and thermal headroom. That'due south not a justification for keeping the information secret when it'due south literally how Turbo Boost has worked since the beginning.

This data tin withal be gathered via transmission testing (assuming none of the issues to a higher place apply), and testing multiple motherboards would be the simplest way to make sure in that location are no problems affecting one specific model. Ultimately, Intel'south conclusion to restrict this information seems pointless. It makes it harder for end-users to determine whether their platforms are configured properly without actually preventing the specific information from beingness discovered. It's a lose-lose for everyone, and information technology's a policy nosotros hope Intel reconsiders.