⋮    ⋮  

AMD Confirms Radeon Instinct MI100 ‘Arcturus’ Discrete GPU Accelerator With CDNA Architecture In 2H 2020


During Dell's EMC presentation, AMD's CTO, Mark Papermaster, confirmed that they will be introducing the next-generation CDNA architecture-based Radeon Instinct MI100 accelerator during the second half of 2020.

AMD's Radeon Instinct MI100 CDNA Architecture Based Discrete GPU Accelerator Arriving in 2H 2020

The AMD Radeon Instinct MI100 which is internally referred to as 'Arcturus' will be a next-gen HPC part that will feature an enhanced version of the 7nm Vega architecture. The accelerator has never been mentioned by AMD officially until now. The GPU seems to be the top HPC part for 2020 in the AMD first-generation CDNA portfolio. Mark confirmed that the Discrete GPU will be introduced in the second half of 2020.

AMD Grows Revenue In Sixth Straight Quarter Reveal Q3 2021 Results

Following is the quote from Mark during the Q/A session:

Like our multi-generational commitment to the Zen roadmap in x86 CPU, we have done the same with our DNA architectures for GPU - rDNA for gaming and visualization, and cDNA for compute & AI. The rDNA is driving gain in AMD share for graphics and deployed in the upcoming Sony and Microsoft new game consoles, and for cDNA you will see the MI100 discrete GPU both 2nd half of 2020.

The ROCm software stack creates an alternative for GPU compute with easy portability and enabling competition. - AMD CTO, Mark Papermaster

Based on what we have learned from various prototype leaks, the Radeon Instinct MI100 'Arcturus' GPU will feature several variants. The flagship variant goes in the D34303 SKU which makes use of the XL variant. The info for this part is based on a test board so it is likely that final specifications would not be the same but here are the key points:

  • Based on Arcturus XL GPU
  • Test Board has a TDP of 200W
  • Up To 32 GB HBM2 Memory
  • HBM2 Memory Clocks Reported Between 1000-1200 MHz

Apple’s M1 Max GPU With 32 Cores Beats a $6000 AMD Radeon Pro W6900X in the Affinity Benchmark

The Radeon Instinct MI100 test board has a TDP of 200W and is based on the XL variant of AMD's Arcturus GPU. The card also features 32 GB of HBM2 memory with pin speeds of 1.0 - 1.2 GHz. The MI60 in comparison has 64 CUs with a TDP of 300W while clock speeds are reported at 1200 MHz (Base Clock) while the memory operates at 1.0 GHz along with a 4096-bit bus interface, pumping out 1 TB/s bandwidth. There's a big chance that the final design of the Arcturus GPU could be featuring Samsung's latest HBM2E 'Flashbolt' memory which offers 3.2 Gbps speeds for up to 1.5 Tb/s of bandwidth.

AMD Radeon Instinct Accelerators 2020

Accelerator NameAMD Instinct MI300AMD Instinct MI250XAMD Instinct MI250AMD Instinct MI100AMD Radeon Instinct MI60AMD Radeon Instinct MI50AMD Radeon Instinct MI25AMD Radeon Instinct MI8AMD Radeon Instinct MI6
GPU ArchitectureTBA (CDNA 3)Aldebaran (CDNA 2)Aldebaran (CDNA 2)Arcturus (CDNA 1)Vega 20Vega 20Vega 10Fiji XTPolaris 10
GPU Process NodeAdvanced Process NodeAdvanced Process NodeAdvanced Process Node7nm FinFET7nm FinFET7nm FinFET14nm FinFET28nm14nm FinFET
GPU Dies4 (MCM)?2 (MCM)2 (MCM)1 (Monolithic)1 (Monolithic)1 (Monolithic)1 (Monolithic)1 (Monolithic)1 (Monolithic)
GPU Cores28,160?14,08014,080?768040963840409640962304
GPU Clock SpeedTBA1700 MHz~1700 MHz~1500 MHz1800 MHz1725 MHz1500 MHz1000 MHz1237 MHz
FP16 ComputeTBA383 TOPsTBA185 TFLOPs29.5 TFLOPs26.5 TFLOPs24.6 TFLOPs8.2 TFLOPs5.7 TFLOPs
FP32 ComputeTBA95.8 TFLOPsTBA23.1 TFLOPs14.7 TFLOPs13.3 TFLOPs12.3 TFLOPs8.2 TFLOPs5.7 TFLOPs
FP64 ComputeTBA47.9 TFLOPsTBA11.5 TFLOPs7.4 TFLOPs6.6 TFLOPs768 GFLOPs512 GFLOPs384 GFLOPs
Memory ClockTBATBATBA1200 MHz1000 MHz1000 MHz945 MHz500 MHz1750 MHz
Memory BusTBA8192-bit8192-bit4096-bit bus4096-bit bus4096-bit bus2048-bit bus4096-bit bus256-bit bus
Memory BandwidthTBA~2 TB/s?~2 TB/s?1.23 TB/s1 TB/s1 TB/s484 GB/s512 GB/s224 GB/s
Form FactorTBADual Slot, Full Length / OAMDual Slot, Full Length / OAMDual Slot, Full LengthDual Slot, Full LengthDual Slot, Full LengthDual Slot, Full LengthDual Slot, Half LengthSingle Slot, Full Length
CoolingTBAPassive CoolingPassive CoolingPassive CoolingPassive CoolingPassive CoolingPassive CoolingPassive CoolingPassive Cooling

So far, AMD has unveiled that the main focus of CDNA would be performance, efficiency, features, scalability in the data center market. Currently, AMD's GCN architecture has served this segment but with CDNA, AMD will be creating GPUs specifically optimized for high-performance Compute, Machine Learning, and HPC. The 1st Gen CDNA GPUs will feature a 2nd Gen Infinity Architecture and would utilize the ROCm (Radeon Open Compute Platform) to power the data center with key optimizations and enhanced scalability. The 2nd Gen Infinity Architecture will allow for 4-8 Way GPU connectivity in a singular node, allowing the new Radeon Instinct boards to run in harmony.

AMD has proved that they can offer more FLOPs at a competitive price so maybe that is where Arcturus would be targetting. With 2H 2020 now set for the Radeon Instinct MI100, we will soon know how AMD's latest CDNA architecture competes against NVIDIA's Ampere based A100 GPU accelerator in the HPC segment.