NVIDIA's next-generation Ampere GPU architecture should be announced in the coming months, and was meant to be unveiled at its GPU Technology Conference -- which was made all-digital, then canceled altogether.
But now, we have a juicy new rumor on Ampere and some delicious specs to salivate over. NVIDIA is reportedly using TSMC's fresh 7nm node for its HPC (High Performance Computing) products (think Tesla GPUs) while the GA10x GPUs will be made on Samsung's new 10nm node.
KittyCorgi on Twitter has tweeted that there will be 5 different Ampere GPUs on offer, with the GA102 sitting at the top of the heap -- the GA102 will succeed the Turing-based GA102 GPU that powers the GeForce RTX 2080 Ti and TITAN RTX. Following that is the GA103 (which doesn't succeed any Turing GPU), then GA104, and then GA106 and GA107.
All of these Ampere GA102/103/106/107 GPUs will be made on Samsung's new 10nm (8LPP) process node, with ray tracing (RTX) abilities on all GPUs -- including the lower-end GA107 part.
I think we'll see the full-fat GA102 with its insane 5376 CUDA cores for an Ampere-powered TITAN RTX successor, while a slightly cut-down GA102 used for the GeForce RTX 3080 Ti. NVIDIA would probably keep the same 24GB of GDDR6 framebuffer on the Ampere-based TITAN RTX, giving the GeForce RTX 3080 Ti anything between 11/12/16GB of RAM.
NVIDIA Ampere GPUs
- GA102 - 84 SMs / 5376 CUDA cores / 12GB GDDR6 / 384-bit bus - 40% faster than RTX 2080 Ti
- GA103 - 60 SMs / 3840 CUDA cores / 10GB GDDR6 / 320-bit bus - 10% faster than RTX 2080 Ti
- GA104 - 48 SMs / 3072 CUDA cores / 8GB GDDR6 / 256-bit bus - 5% slower than RTX 2080 Ti
NVIDIA Ampere GA100 Specs
- 8192 CUDA cores @ 2GHz (2.2GHz boost)
- 1024 Tensor Cores
- 130 RT Cores
- 48GB of HBM2e memory @ 1.2GHz
- 300W TDP
- TSMC 7nm+
- 36 TFLOPs peak output
I've already written about rumors that NVIDIA's next-gen Ampere GPU architecture would be up to 75% faster than current-gen GPUs such as the Turing architecture, right after rumors that Ampere would offer 50% more performance at half the power of Turing. This is pretty crazy stuff right there.
Not only that, but we've got some rumored specs on the purported GeForce RTX 3080 and GeForce RTX 3070 graphics cards, which will both be powered by NVIDIA's new Ampere GPU architecture.
We've already heard that Ampere would offer 50% more performance at half the power of Turing, which sent the hairs on my neck standing up. Better yet, you can read about the leaked specs on the purported Ampere-based GeForce RTX 3080 and GeForce RTX 3070 right here.
GA103 (GeForce RTX 3080)
- 10/20GB GDDR6
- 320-bit memory interface
- 60 SMs
- 3480 CUDA cores
GA104 (GeForce RTX 3070)
- 8/16GB GDDR6
- 256-bit memory interface
- 48 SMs
- 3072 CUDA cores
AMD also just revealed its next-gen RDNA 2 / Navi 2X plans, something we referred to as Big Navi until just recently. Those specs are monstrous, but they pale in comparison to what NVIDIA has planned for its flagship HPC destined Ampere GA100 beast.
AMD RDNA 2 / Navi 2X / Big Navi Specs
- 7nm node (confirmed)
- RDNA 2 architecture (confirmed)
- 80 compute units
- 5120 stream processors
- 17.5 TFLOPs compute performance
- Hardware ray tracing support (confirmed)