AMD Instinct MI200 ‘Aldebaran’ GPU seemingly confirmed to be dual-die

AMD Aldebaran might be dual-die MCM GPU

AMD MI200 had only just appeared in Linux patches, but due to the extensivity of the data, we are still learning new details hidden within the code. A patch from February 24th appears to confirm that Aldebaran will be a dual-die GPU. This was discovered by Coelacanth’s Dream . The patch clearly refers to alde_die_0 and alde_die_1 , indicating that the chip is dual-die. In this case, “Alde” refers to Aldebaran, the upcoming compute accelerator for Instinct MI200, not Intel Alder Lake.

AMD Aldebaran in Linux patch, Source: Freedesktop

Aldebaran will compete with Intel Xe-HP(C) and NVIDIA Hopper as the first multi-chip module graphics processors, or more precisely compute accelerators. The same patches have already indicated that the MI200 will have an updated variant of High-Bandwidth-Memory called HBM2E. This means that AMD does not need to increase the number of stacks, but rather add more DRAM layers to increase capacity.

The multi-chip module will require new chiplets to be added to the package, such as the I/O module, which could theoretically be infused into each GPU module (like we had with the first-gen EPYC), but that seems rather unlikely.

Monolithic vs MCM design, Source: VideoCardz

AMD continues to claim that CDNA2-based GPU will be manufactured using “Advanced Node”. This likely means that each chiplets will be using different nodes, such as 7nm and 5nm within the same package. MCM GPUs such as Aldebaran will shape the future of graphics accelerators. It may take a while to see MCM in gaming GPUs though.

AMD CDNA Roadmap, Source: AMD

AMD Instinct Accelerators
Accelerator NameAMD Radeon Instinct MI60AMD Instinct MI100AMD Instinct MI200
Architecture7nm GCN57nm CDNA1 (GFX908) CDNA2 (GFX90A)
GPUVega 20Arcturus Aldebaran (MCM)
GPU Cores40967680 TBC
GPU Clock Speed1800 MHz~1500 MHz TBC
FP16 Compute29.5 TFLOPs185 TFLOPs TBC
FP32 Compute14.7 TFLOPs23.1 TFLOPs TBC
FP64 Compute7.4 TFLOPs11.5 TFLOPs TBC
VRAM32 GB HBM232 GB HBM2 HBM2E
Memory Clock1000 MHz1200 MHz TBC
Memory Bus4096-bit bus4096-bit bus TBC
Memory Bandwidth1 TB/s1.23 TB/s TBC
Form FactorDual Slot, Full LengthDual Slot, Full Length OAM
CoolingPassive CoolingPassive Cooling TBC
TDP300W300W TBC

Source: Freedesktop via Coelacanth’s Dream