This week’s news recap talks Microsoft’s hardware-accelerated GPU scheduling (something we’ve since benchmarked, written and run after this news piece), alongside discussion of technical documents for Alder Lake and the new LGA1700 socket. We’ll also be talking about a “new” GTX 1650 Ultra, some interesting marketing from T-Force, and the return of data caps.
At GN, we continue to expand our thermal analysis with thermal pads, as we looked at the Thermal Grizzly Carbonaut Pad Vs. IC Diamond Thermal Pad and compared them to pastes. We also looked at how AMD’s silicon has matured, comparing Old vs Original AMD Ryzen 5 3600 CPUs.
News video embed and article below, as usual.
Hardware-accelerated GPU scheduling is a feature new to Microsoft’s May 2020 update, Windows 10 version 2004, and has now been supported by both NVIDIA and AMD via driver updates. This feature is not to be confused with DirectX 12 Ultimate, which was delivered in the same Windows update. Hardware-accelerated GPU scheduling is supported on Pascal and Turing cards from NVIDIA, as well as AMD’s 5600 and 5700 series of cards. In today’s content, we’ll first walk through what exactly this feature does and what it’s supposed to mean, then we’ll show some performance testing for how it behaviorally affects change.
Enabling hardware-accelerated GPU scheduling requires Windows 10 2004, a supported GPU, and the latest drivers for that GPU (NVIDIA version 451.48, AMD version 20.5.1 Beta). With those requirements satisfied, a switch labelled “Hardware-accelerated GPU Scheduling” should appear in the Windows 10 “Graphics Settings” menu, off by default. Enabling the feature requires a reboot. This switch is the only visible sign of the new feature.
This week's hardware news recap teases some of our upcoming content pieces, including a potential test on Dragonball FighterZ, along with pending-publication interviews of key Spectre & Meltdown researchers. In addition to that, as usual, we discuss major hardware news for the past few days. The headline item is the most notable, and pertains to Samsung's GDDR6 memory entering mass production, nearing readiness for deployment in future products. This will almost certainly include GPU products, alongside the expected mobile device deployments. We also talk AMD's new-hires and RTG restructure, its retiring of the implicit primitive discard accelerator for Vega, and SilverStone's new low-profile air cooler.
Show notes are below the embedded video.
Intel has released its own internal testing of architectures dated from Skylake to Coffee Lake, using Windows 10 and Windows 7, in A/B testing between the Meltdown kernel patch. We’ve done some of our own testing (but need to do more), but not with the applications Intel has tested. As usual, exercise grain-of-salt-mining for first-party numbers, but it’s a starting point.
Intel claims that it’s found its CPUs largely retain 95-100% of their original performance (from pre-patch, with some worst-case scenarios showing 79% of original performance – Skylake in SYSMark 2014 SE Responsiveness, namely. On average, it would appear that Intel is retaining roughly 96% of its performance, based on its own internal, first-party data.
Here’s the full chart from the company:
This content piece was highly requested by the audience, although there is presently limited point to its findings. Following the confluence of the Meltdown and Spectre exploits last week, Microsoft pushed a Windows security software update that sought to fill some of the security gaps, something which has been speculated as causing a performance dip between 5% and 30%. As of now, today, Intel has not yet released its microcode update, which means that it is largely folly to undertake the benchmarks we’re undertaking in this content piece – that said, there is merit to it, but the task must be looked at from the right perspective.
From the perspective of advancing knowledge and building a baseline for the next round of tests – those which will, unlike today’s, factor-in microcode patches – we must eventually run the tests being run today. This will give us a baseline for performance, and will grant us two critical opportunities: (1) We may benchmark baseline, per-Windows-patch performance, and (2) we can benchmark post-patch performance, pre-microcode. Both will allow us to see the isolated impact from Intel’s firmware update versus Microsoft’s software update. This is important, and alone makes the endeavor worthwhile – particularly because our CPU suite is automated, anyway, so no big time loss, despite CES looming.
Speaking of, we only had time to run one CPU through the suite, and only with a few games, as, again, CES is looming. This is enough for now, though, and should sate some demand and interest.
The Windows 10 Fall Creators Update (FCU) has reportedly provided performance uplift under specific usage scenarios, most of which center around GPU-bound scenarios with Vega 56 or similar GPUs. We know with relative certainty that FCU has improved performance stability and frametime consistency with adaptive synchronization technologies – Gsync and FreeSync, mostly – and that there may be general GPU-bound performance uplift. Some of this could come down to driver hooks and implementation in Windows, some of it could be GPU or arch-specific. What we haven’t seen much of is CPU-bound tests, attempting to isolate the CPU as the DUT for benchmarking.
These tests look at AMD Ryzen R7 1700 (stock) performance in Windows 10 Creator’s Update (build 1703, ending in 608) versus Windows 10 Fall Creators Update. Our testing can only speak for our testing, as always, and we cannot reasonably draw conclusions across the hardware stack with these benchmarks. The tests are representative of the R7 1700 in CPU-bound scenarios, created by using a GTX 1080 Ti FTW3. Because this is a 1080 Ti FTW3, we have two additional considerations for possible performance uplift (neither of which will be represented herein):
- - As an nVidia GPU, it is possible that driver/OS behavior will be different than with an AMD GPU
- - As a 1080 Ti FTW3, it is possible and likely that GPU-bound performance – which we aren’t testing – would exhibit uplift where this testing does not
Our results are not conclusive of the entirety of FCU, and cannot be used to draw wide-reaching conclusions about multiple hardware configurations. Our objective is to start pinpointing performance uplift, and from what combination of components that uplift can be derived. Most reports we have seen have spotted uplift with 1070 or Vega 56 GPUs, which would indicate GPU-bound performance increases (particularly because said reports show bigger gains at higher resolutions). We also cannot yet speak to performance change on Intel CPUs.
This issue has been driving us crazy for weeks. All of our test machines connect to shared drives on central terminal (which has Windows 10 installed). As tests are completed, we launch a Windows Explorer tab (file explorer) and navigate to \\COMPUTER-NAME\data to drop our results into the system. This setup is used for rapid file sharing across gigabit internal lines, rather than going through cumbersome USB keys or bloating our NAS with small test files.
Unfortunately, updating our primary test benches to Windows 10 Anniversary Edition broke this functionality. We’d normally enter \\COMPUTER-NAME\data to access the shared drive over the network, but that started returning an “incorrect username or password” error (despite using the correct username and password) after said Win10 update. The issue was worked around for a few weeks, but it finally became annoying enough to require some quick research.
Steam's hardware survey reports a +1.57% increase month-over-month in Windows 10 64-bit adoption, marking a growth trend favoring the move to DirectX 12. Presently, the major Dx12-ready titles include Rise of the Tomb Raider, Hitman, Ashes of the Singularity, and forthcoming Total War: Warhammer; you can learn about Warhammer's unique game engine technology over here.
In Steam's survey, Windows 7 is broken into just “Windows 7” and “Windows 7 64-bit,” the two totaling 41.43% of the users responding to the optional survey. The survey also breaks Windows 10 into a “64-bit” and an unspecified version, totaling 41.4% (or 40.01% for the specific 64-bit line-item).
Tabulated results are below:
Good news! The Gears of War Ultimate Edition is coming to PC. Windows made this surprise announcement just today -- but for some reason this announcement comes with a little deja vu. Why does it feel so familiar?
Here’s one reason: It was almost 10 years ago… Halo 2 was finally, after three long years, coming to PC; but what we weren’t prepared for was:
Windows 10 was officially released yesterday. With Windows 10 comes DirectX12 and some other changes, such as Xbox Live for the PC. Of course, Windows 10 (and Dx12) also requires new drivers. Both AMD and nVidia have released drivers within the last week to support Windows 10. Because Windows 7 and 8.1 users can upgrade to Windows 10 for free within a year, these drivers are significant to migration as a potentially large portion of users will be shifting simultaneously.
We’ll first cover AMD’s newest 15.7.1 driver, then nVidia’s 353.62 driver.
We moderate comments on a ~24~48 hour cycle. There will be some delay after submitting a comment.