Even when Samsung releases the update that will allow users to prioritize performance to have a "normal" experience, all of the Galaxy S22, S21, S20, and S10 devices will still remain delisted. The point of performing these comparisons is to have an indicator of relative performance across devices.Currently, Geekbench policy is that once a device is delisted from its device browser, there's no coming back. While modern smartphones have limited thermal capacities and require maximum boost clocks speeds only for short burst of time, the entire point of benchmarking a smartphone isn’t just to test performance values of a sub- component like the CPU, GPU, or AI co-processor. The point of this sort of cheating is to give customers an inaccurate picture of device performance. The company claims in its response that “We believe that showcasing the full capabilities of a chipset in benchmarking tests is in line with the practices of other companies and gives consumers an accurate picture of device performance.” While the first part of this statement holds merit, but the second part of it isn't true at all. In my opinion, MediaTek’s response isn't rubbish, but it isn't entirely true either. SEE ALSO: 192 MP Camera Sensors May Soon Be A Reality If Leaks Are Anything To Go By This means that a user will see different levels of performance from different apps as the chipset dynamically manages the CPU, GPU and memory resources according to the power and performance that is required for a great user experience," the company added. "If someone is running a compute-intensive program like a demanding game, the chipset will intelligently adapt to computing patterns to deliver sustained performance. Their argument? It's regular practice across the industry to optimise the performance for benchmarking tests. MediaTek, however, via a blog post, defended its approach towards benchmarking scores. Since this cheat allows the SoC to go full throttle, there’s also the risk of faster battery degradation and overheating, with no visible gain in performance numbers. What's disturbing is that this appear's to have been happening since 2016 and impacts a wide variety of tests including more recent AI tests, and applications we haven’t seen companies cheating in before. He also corroborates evidence that these files are indeed coming from MediaTek and integrated into the chip's BSP (Board Support Package), defined as “the layer of software containing hardware-specific drivers and other routines.” Image: AnandTech ![]() In a scathing article published on AnandTech, Andrei Frumusanu details the discovery of MediaTek’s alleged benchmark cheating mechanism, how it affects performance, and the company’s contradictory response.įrumusanu’s investigation found multiple devices from multiple manufacturers, each with a similar Power_Whitelist_CFG.xml file with the same applications loaded in it. The latest culprit appears to be a SoC vendor - MediaTek, a company which makes the processors that power a wide array of phones, from companies including Oppo, Xiaomi, Vivo, and even Sony. ![]() Well, there's been another revelation thanks to an investigation, but the latest culprit in question isn't a smartphone maker. Cheating on benchmarks aren't a new occurence and smartphone brands have been caught trying to game benchmark scores a number of times in the past.
0 Comments
Leave a Reply. |