This week, NVIDIA officially snapped their suspenders announcing the next in their series of GPUs sporting the latest graphics-crackin’ Ampere microarchitecture – the RTX A6000 Pro Viz GPU and the A40 Data Center GPU. They follow on the mainstream GPU availability of the unexpected, highly demanded, hard to come by RTX 3080 and RTX 3090 and, later this month, RTX 3070.
NVIDIA Ampere GPU Specs
If you love the 1st-gen RTX GPUs, the next-gen is going to make you all sorts of giddy. The Ampere cards build on the Quadro RTX capabilities and introduce the 3rd-Generation of Tensor Cores tech to speed up AI operations, 2nd-Generation RT Cores to speed up ray tracing, and 3rd-generation NVLink to speed up multiple GPU scaling.
Though new performance data is coming out daily, here’s a mish-mash of specs that are, strangely enough, spread across various sites, collected here for your convenience.
| CUDA Cores | Ampere GPU Comparison | ||||
| A40 | A6000 | RTX 3070 | RTX 3080 | RTX 3090 | |
| GPU | GA102 | GA102 | GA104 | GA102 | GA102 |
| VRAM | 48GB | 48GB | 8GB | 10GB | 24GB |
| Memory Clock | 14.5 GB GDDR6 | 16 GB GDDR6 | 16 GB GDDR6 | 19 GB GDDR6 | 19.5 GB GDDR6 |
| Memory Bandwidth | 696 Gbps | 768 Gbps | 448 Gbps | 760 Gbps | 936 Gbps |
| Memory Interface Width | 384-bit | 384-bit | 256-bit | 320-bit | 384-bit |
| CUDA Cores | 10752 | 10752 | 5888 | 8704 | 10496 |
| Tensor Cores (3rd-Gen) | 336 | 336 | 384 | 576 | 576 |
| RT Cores (2nd-Gen) | 84 | 84 | 46 | 68 | 82 |
| VRAM | 48GB | 48GB | 8GB | 10GB | 24GB |
| Tensor Performance | ? | ? | 82 TFLOPS | 119 TFLOPS | 143 TFLOPS |
| NVLinks Support | Yes | Yes | No | No | Yes |
| List Price | TBA | TBA | $499 | $699 | $1499 |
You’ll notice the A6000 and A40 sit roughly between the Geforce 30 Series RTX 3080 and RTX 3090 but with gains in VRAM akin to the Turing-era Quadro RTX 8000 but more than doubling its CUDA core count. In fact, it may be more helpful to compare it to the high-end Turing GPU, so let’s do that.
| CUDA Cores | RTX GPU Comparison | ||
| A40 | RTX A6000 | RTX 8000 | |
| GPU | GA102 | GA102 | TU102 |
| Processor Sizr | 8 nm | 8 nm | 12 nm |
| VRAM | 48GB | 48GB | 48GB |
| Memory Clock | 14.5 GB GDDR6 | 16 GB GDDR6 | 14 GB GDDR6 |
| Memory Bandwidth | 696 Gbps | 768 Gbps | 672 Gbps |
| Memory Interface Width | 384-bit | 384-bit | 384-bit |
| CUDA Cores | 10752 | 10752 | 4608 |
| Tensor Cores | 336 | 336 | 576 |
| RT Cores | 84 | 84 | 72 |
| Tensor Performance | ? | ? | 130.5 TFLOPS |
| NVLinks Support | Yes | Yes | Yes |
| List Price | TBA | TBA | $10000 |
NVIDIA Ampere GPU Design
Perhaps just as sexy as all these numbers is the new GPU design. With the sleek two-tone black/gold style, it is now an certifiable travesty to hide these GPUs inside a dust-ridden tower or rack. Just look at these beauties:
NVIDIA Ampere GPU Performance
As mentioned, new Ampere performance data is showing up daily. Techgage has published quite a few articles on the RTX 30 series already with a look at RTX 3080 performance and RTX 3090 performance. Though RTX A6000 data is yet to hit, NVIDIA did reveal some performance insight. If you use KeyShot with SOLIDWORKS, Fusion 360, PTC Creo or other modeling software, early benchmarks with the RTX A6000 are showing up to a 275% performance increase over the RTX 6000. Here’s what others are saying about the new Ampere card.
The ability to double or triple the resolution and vastly accelerate our real-time visualization of massive, complex building models in cityscapes with the NVIDIA RTX A6000 is super impressive,”
Paul Renner, visualization manager at KPF
The new NVIDIA RTX A6000 lets us completely redefine what’s possible with real-time ray tracing and machine learning.”
Darren Hendler, director of the digital human group at Digital Domain
The new NVIDIA RTX A6000 has exceeded our expectations and shown performance gains of over 2x with ray-traced exterior scenes. It’s quite impressive.”
Guillaume Shan, Computer Graphics and Visualization Solutions at Groupe Renault
Be on the lookout for RTX A6000 availability mid-December and to start showing up in workstations from Lenovo, Dell, HP, and others early next year. If you’re interested in the technical aspects of the new Ampere architecture, hit the NVIDIA Ampere overview and settle in with some biscuits and cup o’ gravy to read over the riveting whitepaper at the bottom.
One more for good measure…
