By Mike McCarthy
Nvidia has announced a number of new professional graphic cards, filling out their entire Quadro line-up with models based on their newest Pascal architecture. At the absolute top end, there is the new Quadro GP100, which is a PCIe card implementation of their supercomputer chip. It has similar 32-bit (graphics) processing power to the existing Quadro P6000, but adds 16-bit (AI) and 64-bit (simulation). It is intended to combine compute and visualization capabilities into a single solution. It has 16GB of new HBM2 (High Bandwidth Memory) and two cards can be paired together with NVLink at 80GB/sec to share a total of 32GB between them.
This powerhouse is followed by the existing P6000 and P5000 announced last July. The next addition to the line-up is the single-slot VR-ready Quadro P4000. With 1,792 CUDA cores running at 1200MHz, it should outperform a previous-generation M5000 for less than half the price. It is similar to its predecessor the M4000 in having 8GB RAM, four DisplayPort connectors, and running on a single six-pin power connector. The new P2000 follows next with 1024 cores at 1076MHz and 5GB of RAM, giving it similar performance to the K5000, which is nothing to scoff at. The P1000, P600 and P400 are all low-profile cards with Mini-DisplayPort connectors.
All of these cards run on PCIe Gen3 x16, and use DisplayPort 1.4, which adds support for HDR and DSC. They all support 4Kp60 output, with the higher end cards allowing 5K and 4Kp120 displays. In regards to high-resolution displays, Nvidia continues to push forward with that, allowing up to 32 synchronized displays to be connected to a single system, provided you have enough slots for eight Quadro P4000 cards and two Quadro Sync II boards.
Nvidia also announced a number of Pascal-based mobile Quadro GPUs last month, with the mobile P4000 having roughly comparable specifications to the desktop version. But you can read the paper specs for the new cards elsewhere on the Internet. More importantly, I have had the opportunity to test out some of these new cards over the last few weeks, to get a feel for how they operate in the real world.
I was able to run tests and benchmarks with the P6000, P4000 and P2000 against my current M6000 for comparison. All of these test were done on a top-end Dell 7910 workstation, with a variety of display outputs, primarily using Adobe Premiere Pro, since I am a video editor after all.
I ran a full battery of benchmark tests on each of the cards using Premiere Pro 2017. I measured both playback performance and encoding speed, monitoring CPU and GPU use, as well as power usage throughout the tests. I had HD, 4K, and 6K source assets to pull from, and tested monitoring with an HD projector, a 4K LCD and a 6K array of TVs. I had assets that were RAW R3D files, compressed MOVs and DPX sequences. I wanted to see how each of the cards would perform at various levels of production quality and measure the differences between them to help editors and visual artists determine which option would best meet the needs of their individual workflow.
I started with the intuitive expectation that the P2000 would be sufficient for most HD work, but that a P4000 would be required to effectively handle 4K. I also assumed that a top-end card would be required to playback 6K files and split the image between my three Barco Escape formatted displays. And I was totally wrong.
Besides when using the higher-end options within Premiere’s Lumetri-based color corrector, all of the cards were fully capable of every editing task I threw at them. To be fair, the P6000 usually renders out files about 30 percent faster than the P2000, but that is a minimal difference compared to the costs. Even the P2000 was able to playback my uncompressed 6K assets onto my array of Barco Escape displays without issue. It was only when I started making heavy color changes in Lumetri that I began to observe any performance differences at all.
Color correction is an inherently parallel, graphics-related computing task, so this is where GPU processing really shines. Premiere’s Lumetri color tools are based on SpeedGrade’s original CUDA processing engine, and it can really harness the power of the higher-end cards. The P2000 can make basic corrections to 6K footage, but it is possible to max out the P6000 with HD footage if I adjust enough different parameters. Fortunately, most people aren’t looking for more stylized footage than the 300 had, so in this case, my original assumptions seem to be accurate. The P2000 can handle reasonable corrections to HD footage, the P4000 is probably a good choice for VR and 4K footage, while the P6000 is the right tool for the job if you plan to do a lot of heavy color tweaking or are working on massive frame sizes.
The other way I expected to be able to measure a difference between the cards would be in playback while rendering in Adobe Media Encoder. By default, Media Encoder pauses exports during timeline playback, but this behavior can be disabled by reopening Premiere after queuing your encode. Even with careful planning to avoid reading from the same disks as the encoder was accessing from, I was unable to get significantly better playback performance from the P6000 compared to the P2000. This says more about the software than it says about the cards.
The largest difference I was able to consistently measure across the board was power usage, with each card averaging about 30 watts more as I stepped up from the P2000 to the P4000 to the P6000. But they all are far more efficient than the previous M6000, which frequently sucked up an extra 100 watts in the same tests. While “watts” may not be a benchmark most editors worry too much about, among other things it does equate to money for electricity. Lower wattage also means less cooling is needed, which results in quieter systems that can be kept closer to the editor without being distracting from the creative process or interfering with audio editing. It also allows these new cards to be installed in smaller systems with smaller power supplies, using up fewer power connectors. My HP Z420 workstation only has one 6-pin PCIe power plug, so the P4000 is the ideal GPU solution for that system.
It appears that we have once again reached a point where hardware processing capabilities have surpassed the software capacity to use them, at least within Premiere Pro. This leads to the cards performing relatively similar to one another in most of my tests, but true 3D applications might reveal much greater differences in their performance. Further optimization of CUDA implementation in Premiere Pro might also lead to better use of these higher-end GPUs in the future.
Mike McCarthy is an online editor and workflow consultant with 10 years of experience on feature films and commercials. He has been on the forefront of pioneering new solutions for tapeless workflows, DSLR filmmaking and now multiscreen and surround video experiences. If you want to see more specific details about performance numbers and benchmark tests for these Nvidia cards, check out techwithmikefirst.com.