AMD announces world's first 7nm compute cards, the Radeon Instinct MI50 and MI60

At its Next Horizon event, alongside the Zen 2 architecture preview, AMD took the time to share a few details about its 7nm accelerator cards aimed at high performance computing workloads.

Based on the Vega20 architecture, the Radeon Instinct MI50 and MI60 GPUs are in essence AMD's equivalent for Nvidia's Tesla lineup. Geared towards deep learning and AI, these two deliver up to 6.7 TFLOPS and 7.4 TFLOPS respectively of peak dual precision performance. This is a massive increase in comparison to the previous top-of-the-line Instinct GPU - the MI25 - with its peak dual precision performance of 768 GFLOPS.

Despite keeping the same 300W TDP, Vega20's shrinking of the die has brought with it some improvements too, like an increased bandwidth of up to 1TB/s compared to the MI25's 484GB/s. A few of the specification highlights are present in the table below:

	Radeon Instinct MI50	Radeon Instinct MI60
Architecture	Vega20	Vega20
Process	7nm	7nm
Compute units	60	64
Stream processors	3840	4096
Memory	16GB	32GB
Memory clock	1GHz	1GHz
Full Chip ECC RAS support	Yes	Yes
Bandwidth	Up to 1TB/s	Up to 1TB/s
Memory type	HBM2	HBM2
Memory interface	4096-bit	4096-bit
Bus interface	PCIe Gen 3, PCIe Gen 4	PCIe Gen 3, PCIe Gen 4
Infinity Fabric	2 links, 100GB/s peak bandwidth	2 links, 100GB/s peak bandwidth
Peak half precision performance (FP16)	Up to 26.8 TFLOPS	Up to 29.5 TFLOPS
Peak single precision performance (FP32)	Up to 13.4 TFLOPS	Up to 14.7 TFLOPS
Peak dual precision performance (FP64)	Up to 6.7 TFLOPS	Up to 7.4 TFLOPS
TDP	300W	300W
Card type	Double slot, full height	Double slot, full height
Cooling	Passive	Passive