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

According to their respective product pages, the MI50 and MI60 will be available on November 18.

Source: AMD (1, 2)

Report a problem with article
Next Article

Windows 10 19H1 will apparently add support for WPA3

Previous Article

Microsoft announces new OneDrive features coming in November