• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

AMD VEGA confirmed for 2017 H1

Status
Not open for further replies.
TNA said:
And if they are overclockers dream, the WC version should be very nice if priced well :D
Click to expand...

The shader units must have more transistors as estimates for the die size are around 500mm2 or thereabouts,so it will be interesting to see if AMD had to regress IPC(for want of a better word) or has increased it.

It seems that the Ryzen APU uses a Vega based IGP,so it does make me wonder whether we will see lower end Vega based cards as time progresses??
 
nashathedog said:
Rubbish, That's exactly what he said, There's no getting out of it, AMD CTO Joe Macri said. “This is an overclocker's dream.” He hammers the point home so it beggars belief that someone could seriously claim otherwise.

Watch the video from 13m 28s
Click to expand...
he talked about the cooling dissipation capability, he talked about pcb build and with robust power phases, all of it about the package, they never claimed the chip itself will overclock, ppl assume what they want to assume, marketing hammers stuff in for it to stick, doesn't mean you should say what they dont have the courage to say, if they said all that and yet they didn't touch on the chip overclockability, that's a give away already, so don't fill in the blank then come complain about something you said, that's your own conclusion, blame yourself.
ps: when i say you, i mean everyone in general.
 
AlamoX said:
he talked about the cooling dissipation capability, he talked about pcb build and with robust power phases, all of it about the package, they never claimed the chip itself will overclock, ppl assume what they want to assume, marketing hammers stuff in for it to stick, doesn't mean you should say what they dont have the courage to say, if they said all that and yet they didn't touch on the chip overclockability, that's a give away already, so don't fill in the blank then come complain about something you said, that's your own conclusion, blame yourself.
ps: when i say you, i mean everyone in general.
Click to expand...

His words exactly "you are going to be able to overclock this thing like no tomorrow" - you are reaching at straws.

There was some posts on this about 6-8 months ago or maybe a bit longer where I posted a couple of videos including a later one by Raja where he acknowledged it and kind said they weren't going to make that mistake in the future heh.
 
Sargatanas2511 said:
They have said that IPC is increased previously so with a much higher clock too, it's looking good.
Click to expand...

Good to hear,since that will help with the APUs too,since they have to operate at a lower clockspeed range due to TDP limitations.
AlamoX said:
yes if vega doesn't bring any architectural improvements over FuryX, vega would still be a good 20% faster than a 1080.
Click to expand...

It will be interesting to see what efficiency improvements they made over Polaris too.
 
Last edited:
Shaz12 said:
Dont want to read through these pages. What's new?
Click to expand...

Well we know Vega has the same shader configuration as Fiji but seems to run at 1500MHZ~1600MHZ,and that it uses two stacks of HBM2 with upto 16GB VRAM and slightly lower bandwidth than Fiji.

The cards showed off used one six pin and one eight pin PCI-E power connector.
 
TNA said:
Hahaha :D
Click to expand...

The funny thing its EXACTLY the same argument last year in this same thread and had has much relevance now as then. This is why that chap brought it up.

TNA said:
Nothing to get wet about.

Come back 1st June.
Click to expand...

We do have some tidbits - the rumour of much higher clockspeeds and the same amount of shaders as Fiji are true.

Having said that with a 500MM2 die,it makes me wonder what else is under the hood. Its only around 100MM2 smaller than Fiji on a much denser process node.
 
D.P. said:
This, AIBs have no choice in VRAm capacity or speeds with HBM This also has other issues such as AMD is then 100% responsible for sourcing all memory and has to suck up the memory costs, interposer costs and any failure. With GDDR that cost and responsibility lies with the AIB. OF course withe IHV has to ensure sufficient quantities of GDDR is available at the right speeds but as we have seen in the past, some AIBs might choose samsung while other choose Micron etc.
Click to expand...

The cost of faulty dies, interposers and memory will just be amortised into the unit cost available to AIBs. The AIBs have far lower risk and less to test on each card during production as a result.

Totally agree with the issue of not having multiple sources of HBM though. Although it is analogous to AMD being the only supplier of radeon GPUs.
 
CAT-THE-FIFTH said:
The funny thing its EXACTLY the same argument last year in this same thread and had has much relevance now as then. This is why that chap brought it up.



We do have some tidbits - the rumour of much higher clockspeeds and the same amount of shaders as Fiji are true.

Having said that with a 500MM2 die,it makes me wonder what else is under the hood. Its only around 100MM2 smaller than Fiji on a much denser process node.
Click to expand...
I still think as I always have that Vega will be better than what people think. My worry is the price. If they over price it, it will make me wait 6 month's until Volta is out, which will force AMD to lower price and then buy Vega then. lol. Kind of like what others do, but the opposite way around :p
 
Status
Not open for further replies.
Back
Top Bottom