AMD CDNA2 later this year
During JPMorgan’s 49th Annual Global Technology, Media and Communications Conference, AMD CEO and President Dr. Lisa Su has briefly mentioned CDNA2 architecture.
Lisa Su has confirmed that AMD has plans to launch next-generation CDNA later this year. The next-generation CDNA is obviously the CDNA2 architecture which has appeared in both official roadmaps and substantial leaks over the past few months.
Last year, we talked about our first generation CDNA architecture. This year, as I said, we’re putting together our next generation CDNA architecture. This is actually a key component that enabled us to win the largest supercomputer bids in the US around the Frontier Oak Ridge National Labs installment as well as the Lawrence Livermore National Labs installment with El Capitan and many others. But it’s a coherent interconnect between CPUs and GPUs that allow us to fully optimize for HPC and for AI and ML applications. And we will be launching the next generation of that architecture, actually, later this year. We’re very excited about it. I think it’s progressed extremely well. It’s the next big step in sort of innovation around the data center architectures.
— AMD CEO, Dr. Lisa Su
First and so far the only AMD CDNA2 GPU is Aldebaran, which is to feature ‘advanced node’. This implies that the chip should feature chiplets based on different nodes on a single package. Aldebaran is rumored to be a heterogeneous design, which computes tiles being the first to feature CDNA2 architecture. We have already seen leaks suggesting that Aldebaran is a dual-die design.
AMD has so far not revealed any details on CDNA2 architecture but it has confirmed it will feature 3rd generation Infinity Architecture and it will extend to exascale. It is rumored that Aldebaran could feature on-package HBM2e memory, which is a similar approach to Intel’s Ponte Vecchio.
AMD CDNA Roadmap, Source: AMD
| AMD Instinct Accelerators | |||
|---|---|---|---|
| Accelerator Name | AMD Radeon Instinct MI60 | AMD Instinct MI100 | AMD Instinct MI200 |
| Architecture | 7nm GCN5 | 7nm CDNA1 (GFX908) | CDNA2 (GFX90A) |
| GPU | Vega 20 | Arcturus | Aldebaran (MCM) |
| GPU Cores | 4096 | 7680 | TBC |
| GPU Clock Speed | 1800 MHz | ~1500 MHz | TBC |
| FP16 Compute | 29.5 TFLOPs | 185 TFLOPs | TBC |
| FP32 Compute | 14.7 TFLOPs | 23.1 TFLOPs | TBC |
| FP64 Compute | 7.4 TFLOPs | 11.5 TFLOPs | TBC |
| VRAM | 32 GB HBM2 | 32 GB HBM2 | HBM2E |
| Memory Clock | 1000 MHz | 1200 MHz | TBC |
| Memory Bus | 4096-bit bus | 4096-bit bus | TBC |
| Memory Bandwidth | 1 TB/s | 1.23 TB/s | TBC |
| Form Factor | Dual Slot, Full Length | Dual Slot, Full Length | OAM |
| Cooling | Passive Cooling | Passive Cooling | TBC |
| TDP | 300W | 300W | TBC |
Source: Seeking Alpha via ComputerBase
