Subject: Systems | January 24, 2017 - 10:30 PM | Scott Michaud
Tagged: xbox one, xbox, Project Scorpio, microsoft
Digital Foundry received an Xbox Project Scorpio whitepaper from an anonymous source, although they were able to validate its authenticity. Basically, they sent it to their own, off-the-record sources who would have access to the same info, and those individuals confirmed it’s an official document that they’ve seen before. Of course, the trust bottlenecks through Digital Foundry, but they’re about as reputable as you can get in this industry, so that works.
Anywho, disclaimer aside, the whitepaper unveils a few interesting details about how Project Scorpio is expecting to provide higher performance. The most interesting change is what’s missing: the small, on-chip RAM (ESRAM). Microsoft claims that the higher global memory bandwidth removes the need to have it on Project Scorpio.
Digital Foundry is still a bit concerned that, while the 320 GB/s bandwidth might be enough, the latency might be a concern for compatibility. Personally, I’m not too concerned. Modern GPUs do a huge amount of latency-hiding tricks, such as parking whole shaders at global memory accesses and running other tasks while the GPU fetches the memory the original shader needs, swapping it back and finishing when it arrives. Also, the increased GPU performance will mean that the game has more room to be wasteful of GPU resources, since it only needs to perform at least as good as a regular Xbox One. I expect that there wouldn’t be enough round-trips to ESRAM for it to be a major slowdown when running on Project Scorpio (and its not-ESRAM).
Seriously, Wall-E with a Freddie Mercury 'stache.
Microsoft does suggest that developers make use of ESRAM on Xbox One and Xbox One S, though. Yes, don’t deliberately throw away performance on the slower machines just because that accelerator isn’t available on higher-end devices, like Project Scorpio or a gaming PC (heh heh heh).
Another point that Digital Foundry highlighted was that the actual number of rendered fragments (pixels that may or may not make it to screen) didn’t scale up by a factor-of-four (going from 1080p to 4K) in all cases. A first-party developer noticed a case where it was only a 3.5x scaling between the two resolutions. (This metric was actually rendered pixels, not even just GPU load, which would include resolution-independent tasks, like physics simulations.) I’m not exactly sure how the number of fragments decreased, but it could be due to some rendering tricks, like when Halo renders the background at a lower resolution. (Yes, I’m using Khronos verbiage; it’s less ambiguous.)
They also assume that Project Scorpio will use pre-Zen AMD CPU cores. I agree. It seems like Zen wouldn’t be around early enough to make production, especially when you consider the pre-release units that are circulating around Microsoft, and probably third-party developers, too.
Project Scorpio launches this holiday season (2017).
Subject: General Tech | September 7, 2016 - 09:18 PM | Scott Michaud
Tagged: sony, ps4, ps4 pro, microsoft, Project Scorpio, xbox
At today's media briefing event, Sony announced two new versions of their PlayStation 4 console. The first is not even given a new name; they are just referring to it as the “new slimmer and lighter PS4” in their marketing material. It replaces the current version with one that is about 30% smaller, 16% lighter, and 28% more power efficient, according to a press release provided by AMD.
This update will be sold for $299.99 USD ($379.99 CDN) starting on September 15th.
The main topic of discussion was the PlayStation 4 Pro, though. Like Microsoft is doing with Project Scorpio, Sony wants the PS4 Pro to be compatible with the same catalog of titles, but do so at higher resolution and color depths. Sony claims that this generation is basically maxing out what can be done with 1080p. PC developers do not seem to have a problem using performance for new features, but the point that development costs are quickly becoming the limiting factor is valid to some extent.
In terms of specifications, while the CPU got an unspecified speed bump, the main upgrade is a new GPU, which is rated at 4.2 TFLOPs. This is about 30% slower than Microsoft's announced Project Scorpio (6 TFLOPs) but it also will arrive a year sooner. Will this lead time matter, though? The software catalog is already being built up by both companies, and it has been since each console launched in 2013.
Did they ever explain the extra ring on the case?
Also, because Microsoft started with a weaker console, scaling up to 4K resolution should be easier for their game developers. Project Scorpio is about 4.6x faster than the Xbox One, and it intends to draw four times the number of pixels. The gap between the PS4 and the PS4 Pro is just 2.3x. That could be a problem for them. (Meanwhile, us PC gamers can strap multiple 10+ TFLOP GPUs together for true 4K at decent frame rates, but that's another discussion.)
Granted, theoretical is different than real-world. We'll need to re-evaluate the industry in a couple of years, once an appropriate amount of hindsight is available. Also, Sony claims that PlayStation VR will still be available for both consoles, and that it will be a good experience whatever you choose. This is clearly aimed at Microsoft requiring Project Scorpio for their upcoming VR initiative, although likely to prevent confusion in their own fan base, rather than prodding their competitor.
Again, the PlayStation 4 Pro is launching this year, November 10th, and is expected to retail for $399.99 USD ($499.99 CDN). It's not a big jump in performance, but it's also not a big jump in price, either. In fact, I would consider it priced low enough to question the value of the regular PS4, even at $299.
What are your thoughts? Is this actually priced too low for pro?
Subject: General Tech | April 10, 2013 - 12:31 PM | Jeremy Hellstrom
Tagged: Project Scorpio, Intel, idf 2013, idf, Avonton
Intel talked about their Project Scorpio at IDF, similar to HP's Project Moonshot which has just become available. Instead of a new Atom server being a complete system installed in a rack there will be a housing into which self contained server modules can be added and will communicate with the other modules via fabric switch. That way you can pick how many modules you need based on your usage and purchase only that many, with upgrades being as easy as sliding in another module and configuring it. Lego for admins!
They also showed off information on the new Avonton Atom as well as some information on the next family of Xeon processors which you can read more about at The Tech Report.
"Intel kicked off IDF Beijing with a keynote address that revealed a number of new server processors in the Atom and Xeon families. The chip maker also discussed its rack scale architecture, which aims to make next-generation servers more flexible and efficient through modular components."
Here is some more Tech News from around the web:
- Mm.. you like RAID? Ooh, you want flash. Try this super-Hadooper @ The Register
- Intel hints at server processor plans for the rest of this year @ The Register
- Intel Xeon 2013 update - A bit later, but a bit better too @ VR-Zone
- Free Anti-Virus Comparison Review @ OCC