AMD Radeon VII: High-End 7nm Vega Video Card • Hacker News Board

Re: AMD Radeon VII: High-End 7nm Vega Video Card

#11

Post by nradov » Wed, Jan 09, 2019, 8:25 PM UTC

doctorpangloss wrote: post #10

dragontamer wrote: post #2

Its an interesting design for sure. 4x Stacks of HBM2 means 1TBps memory bandwidth at 16GB. Only 60-compute units enabled (maybe 4-CUs are expected to break during manufacturing? Its a weird number for sure...). Since it shares dies with the MI50, the Radeon VII will have 1/2 speed double-precision, making this the cheapest high-performance double-precision card in existance. ------ FP16 compute is supported at doubl…

> Deep learning enthusiasts probably will stick to NVIDIA cards We've been building the wrong hardware for ML for a while now. A TPU doesn't delivery supremacy for problems over GPU hardware. It's a Google senior engineering retention and PR project. Exceedingly few problems resemble image recognition. You wouldn't be able to tell from the research, because due to the tools it's sort of the only affordable thing to d…

What is the right hardware for ML?

Re: AMD Radeon VII: High-End 7nm Vega Video Card

#12

Post by nsxwolf » Wed, Jan 09, 2019, 8:27 PM UTC

dragontamer wrote: post #2

Its an interesting design for sure. 4x Stacks of HBM2 means 1TBps memory bandwidth at 16GB. Only 60-compute units enabled (maybe 4-CUs are expected to break during manufacturing? Its a weird number for sure...). Since it shares dies with the MI50, the Radeon VII will have 1/2 speed double-precision, making this the cheapest high-performance double-precision card in existance. ------ FP16 compute is supported at doubl…

If it could somehow actually sell for the MSRP (which of course it won't), it is a better gaming card than the RTX 2080. The 2080 costs more, and it's flagship feature is something you'll almost certainly want to turn off for gaming since it kills your frame rate and doesn't provide anything most people will notice while playing a game. Screen space reflections and cubemaps are convincing enough when you're zipping around a game world.

Re: AMD Radeon VII: High-End 7nm Vega Video Card

#13

Post by dogma1138 » Wed, Jan 09, 2019, 8:29 PM UTC

DCKing wrote: post #9

In July 2015 AMD released a 28nm chip with more GCN compute units than this card at a lower price - the Radeon R9 Fury X had the full 64 CUs / 4096 shaders enabled for $649. And it was considered a bit of a dud as a product. This Radeon VII is 2.5 process nodes better, but launches with 60 CUs / 3840 shaders enabled. All still on essentially the GCN architecture. And it launches at $699, more than three and a half ye…

Depends on how you define competitive, in gaming which this card at least partially is aimed at its about as fast as a 1080ti a card launched 2 years ago for $700.

Re: AMD Radeon VII: High-End 7nm Vega Video Card

#14

Post by dragontamer » Wed, Jan 09, 2019, 8:30 PM UTC

DCKing wrote: post #9

In July 2015 AMD released a 28nm chip with more GCN compute units than this card at a lower price - the Radeon R9 Fury X had the full 64 CUs / 4096 shaders enabled for $649. And it was considered a bit of a dud as a product. This Radeon VII is 2.5 process nodes better, but launches with 60 CUs / 3840 shaders enabled. All still on essentially the GCN architecture. And it launches at $699, more than three and a half ye…

Vega II is 60CUs at 1.8 GHz. AMD Fury is 64CUs at 1GHz.

60 CUs at 1.8GHz is way faster than AMD Fury ever was. Not only do you get the GHz advantage, but more L2 cache, more HBM2 Bandwidth, and architectural advancements (various instruction set improvements like double-speed FP16 support)

EDIT: AMD Fury's main advantage was that 1GHz clock made all of the nanosecond-level timings super easy to understand. 10-clock cycles was 10-nano seconds. Hurrah!

Re: AMD Radeon VII: High-End 7nm Vega Video Card

#15

Post by walterbell » Wed, Jan 09, 2019, 8:32 PM UTC

doctorpangloss wrote: post #10

dragontamer wrote: post #2

Its an interesting design for sure. 4x Stacks of HBM2 means 1TBps memory bandwidth at 16GB. Only 60-compute units enabled (maybe 4-CUs are expected to break during manufacturing? Its a weird number for sure...). Since it shares dies with the MI50, the Radeon VII will have 1/2 speed double-precision, making this the cheapest high-performance double-precision card in existance. ------ FP16 compute is supported at doubl…

> Deep learning enthusiasts probably will stick to NVIDIA cards We've been building the wrong hardware for ML for a while now. A TPU doesn't delivery supremacy for problems over GPU hardware. It's a Google senior engineering retention and PR project. Exceedingly few problems resemble image recognition. You wouldn't be able to tell from the research, because due to the tools it's sort of the only affordable thing to d…

> talking about the Kinect as an example here, in that it was really hyped and not much came of it

The underlying technology was acquired by Apple and is used on iPhones for FaceID, https://www.theverge.com/circuitbreaker/2017/9/17/16315510/i...

> PrimeSense was never solely responsible for the technology in Microsoft’s Kinect — as evidenced by the huge improvements Microsoft made to Kinect 2.0 on its own — and it’s also obvious that Apple is doing plenty of new software and processing work on top of this hardware. But the basic idea of the Kinect is unchanged. And now it’s in a tiny notch on the front of a $999 iPhone.

Re: AMD Radeon VII: High-End 7nm Vega Video Card

#16

Post by philjohn » Wed, Jan 09, 2019, 8:34 PM UTC

DCKing wrote: post #9

In July 2015 AMD released a 28nm chip with more GCN compute units than this card at a lower price - the Radeon R9 Fury X had the full 64 CUs / 4096 shaders enabled for $649. And it was considered a bit of a dud as a product. This Radeon VII is 2.5 process nodes better, but launches with 60 CUs / 3840 shaders enabled. All still on essentially the GCN architecture. And it launches at $699, more than three and a half ye…

I think it shows that GCN is reaching the end of its usable life. It's not been a bad microarchitecture - but hopefully Navi does something different so they aren't hamstrung in the same way.

Re: AMD Radeon VII: High-End 7nm Vega Video Card

#17

Post by CoolGuySteve » Wed, Jan 09, 2019, 8:35 PM UTC

dogma1138 wrote: post #13

DCKing wrote: post #9

In July 2015 AMD released a 28nm chip with more GCN compute units than this card at a lower price - the Radeon R9 Fury X had the full 64 CUs / 4096 shaders enabled for $649. And it was considered a bit of a dud as a product. This Radeon VII is 2.5 process nodes better, but launches with 60 CUs / 3840 shaders enabled. All still on essentially the GCN architecture. And it launches at $699, more than three and a half ye…

Depends on how you define competitive, in gaming which this card at least partially is aimed at its about as fast as a 1080ti a card launched 2 years ago for $700.

I'm hoping a 8gb or 12 gb version comes out for $500 or so.

16gb seems like overkill for the next couple years of game releases.

Re: AMD Radeon VII: High-End 7nm Vega Video Card

#18

Post by doctorpangloss » Wed, Jan 09, 2019, 8:36 PM UTC

nradov wrote: post #11

doctorpangloss wrote: post #10

Earlier quoted context omitted.

> Deep learning enthusiasts probably will stick to NVIDIA cards We've been building the wrong hardware for ML for a while now. A TPU doesn't delivery supremacy for problems over GPU hardware. It's a Google senior engineering retention and PR project. Exceedingly few problems resemble image recognition. You wouldn't be able to tell from the research, because due to the tools it's sort of the only affordable thing to d…

What is the right hardware for ML?

Probably Larabee. Too early and too expensive for its time.

Re: AMD Radeon VII: High-End 7nm Vega Video Card

#19

Post by opencl » Wed, Jan 09, 2019, 8:38 PM UTC

dragontamer wrote: post #2

Its an interesting design for sure. 4x Stacks of HBM2 means 1TBps memory bandwidth at 16GB. Only 60-compute units enabled (maybe 4-CUs are expected to break during manufacturing? Its a weird number for sure...). Since it shares dies with the MI50, the Radeon VII will have 1/2 speed double-precision, making this the cheapest high-performance double-precision card in existance. ------ FP16 compute is supported at doubl…

There's no guarantee this won't have gimped FP64, Hawaii for example had 1/2 rate FP64 but the consumer cards were 1/8 speed. But even 1/8 would leave the 1/32 NVIDIA cards in the dust.

If they don't gimp FP64 it won't leave a whole lot of reason to buy the MI50 for probably 10x the price.

Re: AMD Radeon VII: High-End 7nm Vega Video Card

#20

Post by dogma1138 » Wed, Jan 09, 2019, 8:39 PM UTC

CoolGuySteve wrote: post #17

dogma1138 wrote: post #13

Earlier quoted context omitted.

Depends on how you define competitive, in gaming which this card at least partially is aimed at its about as fast as a 1080ti a card launched 2 years ago for $700.

I'm hoping a 8gb or 12 gb version comes out for $500 or so. 16gb seems like overkill for the next couple years of game releases.

They can’t do 8 GB there are no 2GB HBM2 modules apparently and they can’t cut the amount of modules without cutting the CUs in half.

It’s essentially just to keep up some production volume this is their HPC die sold to the consumer market its the Titan V equivalent die of AMD minus the Tensor Cores just for much much cheaper.

It’s likely going to be a flop gaming wise, 2x8 pin power connectors put it at 300W TDP with performance only matching that of a 1089ti/2080 in the best case scenarios AMD currently has.

The 1080ti can be had for under $600 if you can find it the 2080 is around $700 but you get RTX and DLSS which while isn’t that useful yet is going to be more useful for gaming than 16GB of memory.