The AMD Vega GPU Architecture Teaser: Higher IPC, Tiling, & More, Coming in H1’2017
by Ryan Smith on January 5, 2017 9:00 AM ESTFirst Thoughts: A Peek At What’s To Come
Wrapping things up, while today’s reveal from AMD is only a teaser of what they have been working on over the last few years with Vega, it’s none the less an important one. Based on what we know so far, Vega stands to be the biggest change to AMD’s GPU architecture since GCN 1.0 was released 5 years ago, and the changes to the ALUs, the ROPs, the memory structure, and other aspects of Vega reinforce this notion. To be sure, Vega is not a wholly new architecture – it is clearly a further refinement of GCN – but then this is exactly why GCN was designed to be able to evolve through refinements over a very long period of time.
What we have for now then is a quick look at what’s to come from AMD. There are still many things we don’t know, not the least of which is the actual GPU configurations. But for a teaser it’s enough to show that AMD has been hard at work. It sets the stage for the hardware and marketing ramp-up to come over the next few months.
But for now, let’s close with an image. As I mentioned before, the first Vega has taped out, and Radeon Technology Group’s frontman and Chief Architect, Raja Koduri, has one. The chip was just a few weeks old as of December, and while trying to discern die size may be a little too error-prone, we can see one important detail: 2 HBM2 packages.
Raja and AMD will not tell us what chip we’re looking at – like Polaris, two Vega chips have been confirmed – but either way we are looking at one of them in all its alpha silicon glory. Bearing in mind HBM2’s much greater bandwidth per pin, we could very well be looking at a design for a Fiji-like 512GB/sec of memory bandwidth in the chip Raja holds. And for AMD, that is one more teaser for today to keep attention focused right where they want it: on Vega ahead of its H1’17 launch.
Facebook
Twitter
RSS
155 Comments
View All Comments
zodiacfml - Saturday, January 7, 2017 - link
Not impressed. Vega will just compete with Nvidia's current high-end.Alexvrb - Saturday, January 7, 2017 - link
Zodiac: "I don't have any solid data, no benchmarks, and no pricing information... but it says AMD so I'm not allowed to express anything but disdain."andrewaggb - Monday, January 9, 2017 - link
Well the only reference we have gaming-wise is that it's between 1080 and titan levels in doom at 4k. So like 1080ti. It's not particularly exciting. I want to find out it's actually way faster than a 1080 in many games or other apps, but I think zodiac is right to be skeptical. Doom runs well on AMD cards, so it's possible Vega might only be 1080 levels overall and that a 1080ti would be faster and easy for nvidia to counter vega with.I feel the same way about Zen. The benchmarks we've seen or heard so far make it sound fine, but at best as fast as intel. That's concerning if the cherry picked examples are as good, in my mind that suggests it could be 20% slower overall.
Ro_Ja - Sunday, January 8, 2017 - link
Micheal Bay was put by AnandTech to trolloranos - Sunday, January 8, 2017 - link
these graphs mean absolutely nothing without a comparison to the competitionsupdawgwtfd - Monday, January 9, 2017 - link
What's the bet this is all the info Anandtech will post?The teaser then never follow up with a review like so many other things they never get back to...
milkod2001 - Tuesday, January 10, 2017 - link
Anandtech has turned from: The Most Trusted in Tech Since 1997 to Very late late tech previews, plus this pure Purch BS from the web...Gunbuster - Tuesday, January 10, 2017 - link
Support for the HDMI 2.1 or will it be a repeat of the "screw off and wait for a 3rd party dongle 11 months in the making"?watzupken - Wednesday, January 11, 2017 - link
The fact that AMD is very late into the high end graphics with 14nm, means the expectation for them will be higher. I am not sure Vega will fill that expectation at this point in time. With the limited information at this point, it does show again that it is performing well in very selective DX 12 titles against the likes of a GTX 1080, which does not bode well to me. Moreover, the power requirement for Vega 10 seems to be higher than a GTX 1080 that they are comparing with.tamalero - Wednesday, January 11, 2017 - link
I actually if VEGA will be non cut in terms of compute performance.Making it way more attractive for accelerator cards for servers and "decent" in gaming performance.
Thus making it all around performer.