This morning AMD is taking the wraps off of a brand new high-end video card aimed on the workstation market, the Radeon Pro VII. True to its namesake, this can be a skilled model of the Radeon VII, which was first launched final 12 months, incorporating AMD’s Vega 20 GPU and its full suite of pro-grade options. Taking the place on the prime of AMD’s Radeon Pro stack of video playing cards, the Radeon Pro VII is geared toward AMD’s greatest workload prospects within the CAD/CAM, media, and HPC workstation industries, who’re prepared to pay a premium for AMD’s quickest workstation card but.
Like its namesake, the Radeon Pro VII relies on the corporate’s Vega 20 GPU, which when it launched in late 2018 was AMD’s first 7nm GPU. And although AMD is now on to their newer Navi structure for graphics workloads, Vega 20 stays AMD’s single strongest GPU so far. This is especially evident in blended graphics/compute or pure-compute workloads, the place Vega 20’s distinctive options like quick double precision assist, excessive reminiscence bandwidth, and exterior Infinity Fabric hyperlinks should not matched by some other card, and have turn out to be the spine of AMD’s compute-focused Radeon Instinct MI50 and MI60 playing cards.
All instructed, AMD hasn’t produced a card just like the Radeon Pro VII in fairly a while. There have been quite a few Radeon Pro playing cards over the previous few years, however all of those had been primarily based on AMD’s extra broad-market client and workstation GPUs. The Radeon Pro VII, in contrast, is AMD’s first skilled card since 2014 that ticks all of the packing containers for each graphics and compute, providing vital rendering capabilities paired with the widest array of GPU compute options that AMD affords. In quick, that is the cardboard for workstation customers who want all of it, they usually want all of it in a single product.
| AMD Workstation Card Specification Comparison | ||||||
| Radeon Pro VII |
Radeon VII | Radeon Pro W5700 |
Radeon Pro WX 9100 |
|||
| CUs | 60 | 60 | 36 | 64 | ||
| ROPs | 64 | 64 | 64 | 64 | ||
| Boost Clock | ~1700MHz | 1750MHz | ~1930MHz | 1500MHz | ||
| Memory Clock | 2.0Gbps HBM2 | 2.0Gbps HBM2 | 14 Gbps GDDR6 | 1.89Gbps HBM2 | ||
| Memory Bus Width | 4096-bit | 4096-bit | 256-bit | 2048-bit | ||
| Single Precision | 13.1 TFLOPs | 13.Eight TFLOPs | 8.89 TFLOPs | 12.Three TFLOPs | ||
| Double Precision | 6.5 TFLOPs (half of charge) |
3.5 TFLOPS (1/four charge) |
556 GFLOPs (1/16 charge) |
769 GFLOPs (1/16 charge) |
||
| VRAM | 16GB | 16GB | 8GB | 16GB | ||
| ECC | Yes | Yes | No | Yes (DRAM) | ||
| TDP | 250W | 300W | 205W | <250W | ||
| GPU | Vega 20 | Vega 20 | Navi 10 | Vega 10 | ||
| Architecture | Vega (GCN 5) |
Vega (GCN 5) |
RDNA (1) | Vega (GCN 5) |
||
| Infinity Fabric Link | Yes (2x) | No | No | No | ||
| Manufacturing Process | TSMC 7nm | TSMC 7nm | TSMC 7nm | GloFo 14nm | ||
| Launch Date | 06/2020 | 02/2019 | 11/2019 | 10/2017 | ||
| Launch Price (MSRP) | $1899 | $699 | $799 | $2199 | ||
By the numbers, the Radeon Pro VII is a succesful substitute for the Radeon Pro WX 9100 in AMD’s product stack. Similar to what we’ve seen there, AMD is swapping out older Vega 10 playing cards for newer and extra highly effective Vega 20 playing cards. The outcomes from a efficiency perspective make the Radeon Pro VII essentially the most highly effective professional card in AMD’s arsenal, although the positive aspects over the WX 9100 are a blended bag.
With 60 energetic CUs and a lift clockspeed of roughly 1700MHz, on paper the Radeon Pro VII is just not terribly sooner in FP32 compute/graphics workloads than the WX 9100 it replaces; the clockspeed enhance afforded by 7nm has been tempered considerably by the decrease CU depend. Instead, what makes the Radeon Pro VII stand out is all the things it could try this the WX 9100 couldn’t, beginning with…
