Subject: Processors | September 25, 2017 - 09:36 PM | Tim Verry
Tagged: skylake-x, overclocking, Intel Skylake-X, Intel, Cinebench, 7980xe, 3dmark, 14nm
Renowned overclocker der8auer got his hands on the new 18-core Intel Core i9-7980XE and managed to break a few records with more than a bit of LN2 and thermal paste. Following a delid, der8auer slathered the bare die and surrounding PCB with a polymer-based (Kryonaut) TIM and reattached the HIS to prepare for the extreme overclock. He even attempted to mill out the middle of the IHS to achieve a balance between direct die cooling and using the IHS to prevent bending the PCB and spread out the pressure from the LN2 cooler block, but ran into inconsistent results between runs and opted not to proceed with that method.
Using an Asus Rampage VI Apex X299 motherboard and the Core i9-7980XE at an Asus ROG event in Taiwan der8auer used liquid nitrogen to push all eighteen cores (plus Hyper-Threading) to 6.1 GHz for a CPU-Z validation. To get those clockspeeds he needed to crank up the voltage to 1.55V (1.8V VCCIN) which is a lot for the 14nm Skylake X processor. Der8auer noted that overclocking was temperature limited beyond this point as at 6.1 GHz he was seeing positive temperatures on the CPU cores despite the surface of the LN2 block being as low as -100 °C! Perhaps even more incredible is the power draw of the processor as it runs at these clockspeeds with the system drawing as much as 1,000 watts (~83 amps) on the +12V rail with the CPU being responsible for almost all of that number! That is a lot of power running through the motherboard VRMs and the on-processor FIVR!
For comparison, at 5.5 GHz he measured 70 amps on the +12V rail (840W) with the chip using 1.45V vcore under load.
For Cinebench R15, the extreme overclocker opted for a tamer 5.7 GHz where the i9-7980XE achieved a multithreaded score of 5,635 points. He compared that to his AMD Threadripper overclock of 5.4 GHz where he achieved a Cinebench score of 4,514 (granted the Intel part was using four more threads and clocked higher).
To push things (especially his power supply heh) further, the overclocker added a LN2 cooled NVIDIA Titan Xp to the mix and managed to overclock the graphics card to 2455 MHz at 1.4V. With the 3840 Pascal cores at 2.455 GHz he managed to break three single card world records by scoring 45,705 in 3DMark 11, 35,782 in 3DMark Fire Strike, and 120,425 in 3DMark Vantage!
Der8auer also made a couple interesting statements regarding overclocking at these levels including the issues of cold bugs not allowing the CPU and/or GPU to boot up if the cooler plate is too cold. On the other side of things, once the chip is running the power consumption can jump drastically with more voltage and higher clocks such that even LN2 can’t maintain sub-zero core temperatures! The massive temperature delta can also create condensation issues that need to be dealt with. He mentions that while for 24/7 overclocking liquid metal TIMs are popular choices, when extreme overclocking the alloy actually works against them because the sub-zero temperatures reduce the effectiveness and thermal conductivity of the interface material which is why polymer-based TIMs are used when cooling with liquid nitrogen, liquid helium, or TECs. Also, while most people apply a thin layer of thermal paste to the direct die or HIS, when extreme overclocking he “drowns” the processor die and PCB in the TIM to get as much contact as possible with the cooler as every bit of heat transfer helps even the small amount he can transfer through the PCB. Further, FIVR has advantages such as per-core voltage fine tuning, but it also can hold back further overclocking from cold bugs that will see the processor shut down past -100 to -110 °C temperature limiting overclocks whereas with an external VRM setup they could possibly push the processor further.
For the full scoop, check out his overclocking video. Interesting stuff!
- The Intel Core i9-7980XE and 7960X Review: Skylake-X at $1999 and 18-cores
- Delidded Ryzen 7 1700 Confirms AMD Is Using Solder With IHS On Ryzen Processors
- The AMD Ryzen Threadripper 1950X and 1920X Review
- Overclocking the AMD Ryzen 7 1700 - The Real Winner?
- Overclockers Push Ryzen 7 1800X to 5.2 GHz On LN2, Break Cinebench Record
Subject: Graphics Cards | March 28, 2017 - 04:32 PM | Scott Michaud
Tagged: vulkan, DirectX 12, Futuremark, 3dmark
The latest update to 3DMark adds Vulkan support to its API Overhead test, which attempts to render as many simple objects as possible while keeping above 30 FPS. This branch of game performance allows developers to add more objects into a scene, and design these art assets in a more simple, straight-forward way. This is, now, one of the first tests that can directly compare DirectX 12 and Vulkan, which we expect to be roughly equivalent, but we couldn’t tell for sure.
While I wasn’t able to run the tests myself, Luca Rocchi of Ocaholic gave it a shot on their Core i7-5820K and GTX 980. Apparently, Vulkan was just under 10% faster than DirectX 12 in their results, reaching 22.6 million draw calls in Vulkan, but 20.6 million in DirectX 12. Again, this is one test, done by a third-party, for a single system, and a single GPU driver, on a single 3D engine, and one that is designed to stress a specific portion of the API at that; take it with a grain of salt. Still, this suggests that Vulkan can keep pace with the slightly-older DirectX 12 API, and maybe even beat it.
This update also removed Mantle support. I just thought I’d mention that.
Subject: General Tech | July 21, 2016 - 12:21 PM | Ryan Shrout
Tagged: Wraith, Volta, video, time spy, softbank, riotoro, retroarch, podcast, nvidia, new, kaby lake, Intel, gtx 1060, geforce, asynchronous compute, async compute, arm, apollo lake, amd, 3dmark, 10nm, 1070m, 1060m
PC Perspective Podcast #409 - 07/21/2016
Join us this week as we discuss the GTX 1060 review, controversy surrounding the async compute of 3DMark Time Spy and more!!
The URL for the podcast is: http://pcper.com/podcast - Share with your friends!
- iTunes - Subscribe to the podcast directly through the Store (audio only)
- Google Play - Subscribe to our audio podcast directly through Google Play!
- RSS - Subscribe through your regular RSS reader (audio only)
- MP3 - Direct download link to the MP3 file
This episode of the PC Perspective Podcast is sponsored by Casper!
Hosts: Ryan Shrout, Allyn Malventano, Jeremy Hellstrom, and Josh Walrath
Yes, We're Writing About a Forum Post
Update - July 19th @ 7:15pm EDT: Well that was fast. Futuremark published their statement today. I haven't read it through yet, but there's no reason to wait to link it until I do.
Update 2 - July 20th @ 6:50pm EDT: We interviewed Jani Joki, Futuremark's Director of Engineering, on our YouTube page. The interview is embed just below this update.
Original post below
The comments of a previous post notified us of an Overclock.net thread, whose author claims that 3DMark's implementation of asynchronous compute is designed to show NVIDIA in the best possible light. At the end of the linked post, they note that asynchronous compute is a general blanket, and that we should better understand what is actually going on.
So, before we address the controversy, let's actually explain what asynchronous compute is. The main problem is that it actually is a broad term. Asynchronous compute could describe any optimization that allows tasks to execute when it is most convenient, rather than just blindly doing them in a row.
This is asynchronous computing.
Subject: General Tech | June 23, 2016 - 06:37 PM | Jeremy Hellstrom
Tagged: Futuremark. Time Spy, 3dmark
A new version of DirectX hitting the market means we need a new benchmark and once again Futuremark has delivered, with the Time Spy benchmark. Right now 3D Mark is 80% off on Steam and if you pick it up you will get access to the new Time Spy Basic benchmark when it is released.
Time Spy uses the new DirectX 12 API and supports new features like asynchronous compute, explicit multi-adapter, and multi-threading. It will have reviewers digging out hardware they thought they had already tested to provide you with new benchmark data points that will apply to the currently available DX12 games as well as those which will be released.
This is also a great opportunity to pick up the full version of the benchmark for your own usage, even if you have yet to upgrade to DX12 hardware. You should check out the teaser trailer if you are familiar with past 3D Mark versions as you will see a few glimpses at benchmark screens that caused you mental raster burn in years past.
Subject: Graphics Cards | May 27, 2016 - 02:58 PM | Allyn Malventano
Tagged: sli, review, led, HB, gtx, evga, Bridge, ACX 3.0, 3dmark, 1080
...so the time where we manage to get multiple GTX 1080's in the office here would, of course, be when Ryan is on the other side of the planet. We are also missing some other semi-required items, like the new 'SLI HB 'bridge, but we should be able to test on an older LED bridge at 2560x1440 (under the resolution where the newer style is absolutely necessary to avoid a sub-optimal experience). That said, surely the storage guy can squeeze out a quick run of 3DMark to check out the SLI scaling, right?
For this testing, I spent just a few minutes with EVGA's OC Scanner to take advantage of GPU Boost 3.0. I cranked the power limits and fans on both cards, ending up at a stable overclock hovering at right around 2 GHz on the pair. I'm leaving out the details of the second GPU we got in for testing as it may be under NDA and I can't confirm that as all of the people to ask are in an opposite time zone, so I'm leaving out that for now (pfft - it has an aftermarket cooler). Then I simply ran Firestrike (25x14) with SLI disabled:
...and then with it enabled:
That works out to a 92% gain in 3DMark score, with the FPS figures jumping by almost exactly 2x. Now remember, this is by no means a controlled test, and the boss will be cranking out a much more detailed piece with frame rated results galore in the future, but for now I just wanted to get some quick figures out to the masses for consumption and confirmation that 1080 SLI is a doable thing, even on an older bridge.
*edit* here's another teaser:
Aftermarket coolers are a good thing as evidenced by the 47c of that second GPU, but the Founders Edition blower-style cooler is still able to get past 2GHz just fine. Both cards had their fans at max speed in this example.
I was able to confirm we are not under NDA on the additional card we received. Behold:
This is the EVGA Superclocked edition with their ACX 3.0 cooler.
More to follow (yes, again)!
Subject: General Tech | April 2, 2015 - 01:16 PM | Ken Addison
Tagged: podcast, video, dx12, 3dmark, freesync, g-sync, Intel, 3d nand, 20nm, 28nm, micron, nvidia, shield, Tegra X1, raptr, 850 EVO, msata, M.2
Join us this week as we discuss DX12 Performance, Dissecting G-SYNC and FreeSync, Intel 3D NAND and more!
The URL for the podcast is: http://pcper.com/podcast - Share with your friends!
- iTunes - Subscribe to the podcast directly through the Store
- RSS - Subscribe through your regular RSS reader
- MP3 - Direct download link to the MP3 file
Hosts:Ryan Shrout, Jeremy Hellstrom, Josh Walrath, and Allyn Malventano
Program length: 1:27:10
Week in Review:
News item of interest:
Hardware/Software Picks of the Week:
Jeremy: Just pretend it is Half Life 3
Our first DX12 Performance Results
Late last week, Microsoft approached me to see if I would be interested in working with them and with Futuremark on the release of the new 3DMark API Overhead Feature Test. Of course I jumped at the chance, with DirectX 12 being one of the hottest discussion topics among gamers, PC enthusiasts and developers in recent history. Microsoft set us up with the latest iteration of 3DMark and the latest DX12-ready drivers from AMD, NVIDIA and Intel. From there, off we went.
First we need to discuss exactly what the 3DMark API Overhead Feature Test is (and also what it is not). The feature test will be a part of the next revision of 3DMark, which will likely ship in time with the full Windows 10 release. Futuremark claims that it is the "world's first independent" test that allows you to compare the performance of three different APIs: DX12, DX11 and even Mantle.
It was almost one year ago that Microsoft officially unveiled the plans for DirectX 12: a move to a more efficient API that can better utilize the CPU and platform capabilities of future, and most importantly current, systems. Josh wrote up a solid editorial on what we believe DX12 means for the future of gaming, and in particular for PC gaming, that you should check out if you want more background on the direction DX12 has set.
One of DX12 keys for becoming more efficient is the ability for developers to get closer to the metal, which is a phrase to indicate that game and engine coders can access more power of the system (CPU and GPU) without having to have its hand held by the API itself. The most direct benefit of this, as we saw with AMD's Mantle implementation over the past couple of years, is improved quantity of draw calls that a given hardware system can utilize in a game engine.
Subject: Graphics Cards, Processors | March 4, 2015 - 08:46 PM | Ryan Shrout
Tagged: GDC, gdc 15, API, dx12, DirectX 12, dx11, Mantle, 3dmark, Futuremark
It's probably not a surprise to most that Futuremark is working on a new version of 3DMark around the release of DirectX 12. What might be new for you is that this version will include an API overhead test, used to evaluate a hardware configuration's ability to affect performance in Mantle, DX11 and DX12 APIs.
While we don't have any results quite yet (those are pending and should be very soon), Intel was showing the feature test running at an event at GDC tonight. In what looks like a simple cityscape being rendered over and over, the goal is to see how many draw calls, or how fast the CPU can react to a game engine, the API and hardware can be.
The test was being showcased on an Intel-powered notebook using a 5th Generation Core processor, code named Broadwell. Obviously this points to the upcoming support for DX12 (though obviously not Mantle) that Intel's integrated GPUs will provide.
It should be very interesting to see how much of an advantage DX12 offers over DX11, even on Intel's wide ranges of consumer and enthusiast processors.
Subject: General Tech, Graphics Cards | May 28, 2014 - 01:49 PM | Jeremy Hellstrom
Tagged: benchmarking, 3dmark
HELSINKI, FINLAND – May 28, 2014 – Futuremark today announced 3DMark Sky Diver, a new DirectX 11 benchmark test for gaming laptops and mid-range PCs. 3DMark Sky Diver is the ideal test for benchmarking systems with mainstream DirectX 11 graphics cards, mobile GPUs, or integrated graphics. A preview trailer for the new benchmark shows a wingsuited woman skydiving into a mysterious, uncharted location. The scene is brought to life with tessellation, particles and advanced post-processing effects. Sky Diver will be shown in full at Computex from June 3-7, or find out more on the Futuremark website.
Jukka Mäkinen, Futuremark CEO said, "Some people think that 3DMark is only for high-end hardware and extreme overclocking. Yet millions of PC gamers rely on 3DMark to choose systems that best balance performance, efficiency and affordability. 3DMark Sky Diver complements our other tests by providing the ideal benchmark for gaming laptops and mainstream PCs."
3DMark - The Gamer's Benchmark for all your hardware
3DMark is the only benchmark that offers a range of tests for different classes of hardware:
- Fire Strike, for high performance gaming PCs (DirectX 11, feature level 11)
- Sky Diver, for gaming laptops and mid-range PCs (DirectX 11, feature level 11)
- Cloud Gate, for notebooks and typical home PCs (DirectX 11 feature level 10)
- Ice Storm, for tablets and entry level PCs (DirectX 11 feature level 9)
With 3DMark, you can benchmark the full performance range of modern DirectX 11 graphics hardware. Where Fire Strike is like a modern game on ultra high settings, Sky Diver is closer to a DirectX 11 game played on normal settings. This makes Sky Diver the best choice for benchmarking entry level to mid-range systems and Fire Strike the perfect benchmark for high performance gaming PCs.
See 3DMark Sky Diver in full at Computex
3DMark Sky Diver will be on display on the ASUS, MSI, GIGABYTE, Galaxy, Inno3D, and G-Skill booths at Computex, June 3-7.
S.Y. Shian, ASUS Vice President & General Manager of Notebook Business Unit said,
"We are proud to partner with Futuremark to show 3DMark Sky Diver at Computex. Sky Diver helps PC gamers choose systems that offer great performance and great value. We invite everyone to visit our stand to experience 3DMark Sky Diver on a range of new ASUS products."
Sky Diver will be released as an update for all editions of 3DMark, including the free 3DMark Basic Edition.