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
Space Jam - Thursday, January 5, 2017 - link
What's the status of the RX 480/470/460 reviews? A teaser was given, but nothing more. And the GTX 1050 (Ti) got an announcement thread which noted the fab differences but has yet to see a review.MajGenRelativity - Thursday, January 5, 2017 - link
I'm also interested in knowing the answer to these questions :)Notmyusualid - Thursday, January 5, 2017 - link
I'm growing tired of the details.Show me the basic power requirements, price, and some well-known benchmarks, then I'll make my purchasing decision.
I guess I've had a long day.
Jtaylor1986 - Thursday, January 5, 2017 - link
You get tired pretty quickly then since these are essentially the first details that have been officially release other than the vague roadmapwebdoctors - Thursday, January 5, 2017 - link
I agree, an announcement that a product 6 months out will be faster than today's isn't that exciting. If it also beamed light into my eyes directly or purified the air with the cooling fan, that would be a neat twist but right now its a pretty bland announcement.tuxRoller - Thursday, January 5, 2017 - link
I'm not sure we can say that the ISA has changed since it has long supported i8.http://gpuopen.com/compute-product/amd-gcn3-isa-ar...
extide - Friday, January 6, 2017 - link
Yeah, why reinvent the wheel? I bet it has additional instructions, but is largely extended rather than totally new.tuxRoller - Friday, January 6, 2017 - link
Yup. Gcn hasn't been given enough credit for how forward looking its been, but instead all people talk about is how old it is.https://gcc.gnu.org/wiki/cauldron2016?action=
AttachFile&do=get&target=Porting+GCC+to+GCN.pdf
So this fellow has been working on adding a gcn target to gcc, and you can see from his presentation how general is the ISA.
tuxRoller - Friday, January 6, 2017 - link
Sorry about that link. I had to split it over two lines in order to get past the AT ai's spam protection:)Threska - Friday, January 6, 2017 - link
TinyURLhttp://preview.tinyurl.com/gtjlxrn