AMD Announces The Radeon Pro VII

[coder]

The Radeon VII was announced in January 2019 and the first two items are due to improved yields on 7nm

Do you know that, or are you just guessing? Because I think you've got it backwards: the Radeon VII is the one which clocks higher, which I assume is the main reason it uses more power.

Keep in mind that Vega 20 was already on the market for nearly 6 months (i.e. in the form of the Instinct series), by the time Radeon VII shipped. And if yields are now so good, why is this new card still limited to 60 CU? And why did AMD kill off the MI60, which had 64 CU?

[qarium]

[---]

Your exclusive contract with apple over the VEGA20 chips with full 4096 shader is really bad.
i maybe can understand if you do not allow the 4096 on a radeon7 700€ desktop card.

but limit your 1900 dollar VII / 7 PRO to 3840 shader cores is pure madness

just tell me how much does apple pay to AMD to Castrate the 4096 shader chips to only 3840 shader cores ?

is there a date when the contract tuns out? can we have radeon 7 and radeon 7 pro with full 4096 shader cores after the expiring date of the exclusive contract with apple?

AMD really should release the 4096 shader version after the contract ends.

[moriel5]

Try asking on a forum specific to that product, or at least focused on professional video editing.

Thanks, that would probably be the right thing, though I had posted here, since I prefer to get information that is more of the engineering kind (I like to learn about how it works, after all).

[pipe13]

A few differences I noticed:
1. TDP: 295W->250W, likely due to the improvements from TSMC
2. FP64: 3.5TFLOPS -> 6.5 TFLOPS, although I'm not sure FP64 is still a thing for GPU computing...
3. Infinity fabric for GPU P2P.

FP64 is very definitely still a thing. In my current image processing application I too thought it wouldn't be. But I was wrong. A key iterative algorithm converges much more uniformly in double precision than single. Color me surprised. My parallelization is done via TBB, with optional CUDA kernels and NVBLAS. I've a consumer-grade GTX-960 upon which NVBLAS speeds FP32 GEMM considerably -- I'm recalling about 40% -- and the CUDA kernels maybe another 5. I've a *lot* more profiling to do before investing more development time in CUDA or OpenACC, but the GEMM results alone prompt me to seriously consider an FP64 GPU should I ever upgrade my hardware and take this thing to production.

OTOH, there's a limit to how far parallelization can take this sort of algorithm. CPU's are considerably easier to program, and I might be better off investing in more CPU cores.

[wizard69]

A few differences I noticed:
1. TDP: 295W->250W, likely due to the improvements from TSMC
2. FP64: 3.5TFLOPS -> 6.5 TFLOPS, although I'm not sure FP64 is still a thing for GPU computing...
3. Infinity fabric for GPU P2P.

Kinda looks like a transitional product to eventually become CDNA. I'm actually surprised that they have included I/O ports.

[bridgman]

We released the V340 last year IIRC.

Thanks... I thought we had released a dual GPU card more recently but I was having trouble remembering the name.

[agd5f]

It would have been very nice if there was one SR-IOV BIOS that you can select via the BIOS switch, and SR-IOV would have been the redeeming feature of the Radeon VII, but AMD tries to keep their cool technology away from enthusiasts, developers, and semi-professional users unfortunately.

The Radeon Pro V340 does have a port that resembles a mini-DisplayPort. What is its function then?

I think it was leftover from bringup for debugging. I don't think it was productised.

[chithanh]

I wonder if it supports SRI-OV...

It would have been very nice if there was one SR-IOV BIOS that you can select via the BIOS switch, and SR-IOV would have been the redeeming feature of the Radeon VII, but AMD tries to keep their cool technology away from enthusiasts, developers, and semi-professional users unfortunately.

All of the SR-IOV cards are headless server cards. We released the V340 last year IIRC.

The Radeon Pro V340 does have a port that resembles a mini-DisplayPort. What is its function then?

[ms178]

Radeon VII:

• is 300 W (this is 250)
• runs at higher clocks (boosts to 1750 MHz instead of 1700 MHz)
• has only PCIe 3.0 (instead of 4.0)
• has half of the fp64 performance
• has no over-the-top Infinity Link connector for direct card-to-card communication.
• costs $700 (this lists for $1900)

The Radeon VII was announced in January 2019 and the first two items are due to improved yields on 7nm and the next two items are artificial limitations due to market segmentation (physically the chip was already capable of this from the start). So why does AMD release such a card 14 months after the Radeon VII? It could have been on the market for two or three quarters already...

[agd5f]

Wait, none of them? So AMD hasn't released a card with SR_IOV for 4 years?

All of the SR-IOV cards are headless server cards. We released the V340 last year IIRC.