[HN Gopher] A PCIe Coral TPU Finally Works on Raspberry Pi 5
       ___________________________________________________________________
        
       A PCIe Coral TPU Finally Works on Raspberry Pi 5
        
       Author : mikece
       Score  : 52 points
       Date   : 2023-11-17 19:16 UTC (3 hours ago)
        
 (HTM) web link (www.jeffgeerling.com)
 (TXT) w3m dump (www.jeffgeerling.com)
        
       | jauntywundrkind wrote:
       | Coral is 4 years old, and it's both shocking & not that there
       | aren't many competitors out there today.
       | 
       | Also a bit sad PyCoral requires python 3.9! Yikes!
        
         | filterfiber wrote:
         | Especially since it only has like 8 MB of memory I think?
        
           | geerlingguy wrote:
           | Some SoCs even have competent built in NPUs, too, but
           | software support is severely lacking.
           | 
           | PyCoral and Coral hardware development seems glacial lately
           | :(
           | 
           | They have enjoyed a lot of momentum... I wish they could
           | release a follow-up version and get some longstanding
           | software issues resolved.
        
         | gymbeaux wrote:
         | I think companies prefer to develop AI stuff and then sell it,
         | rather than sell the hardware.
        
           | nmstoker wrote:
           | However keeping the Python version up to date shouldn't be
           | that hard though, should it?
        
       | westurner wrote:
       | An HBM3E HAT would or would not yet make TPUs more useful with a
       | Raspberry Pi 5?
       | 
       | Jetson Nano (~$149)
       | 
       | Orin Nano (~$499, 32 tensor cores, 40 TOPS)
       | 
       | AGX Orin (200-275 TOPS)
       | 
       | NVIDIA Jetson > Origins:
       | https://en.wikipedia.org/wiki/Nvidia_Jetson#Versions
       | 
       | TOPS for NVIDIA [Orin] Nano [AGX]
       | https://connecttech.com/jetson/jetson-module-comparison/
       | 
       | Coral Mini-PCIe ($25; ? tensor cores, 4 TOPS (int8); 2 TOPS per
       | watt)
       | 
       | TPUv5 (393 TOPS)
       | 
       | Tensor Processing Unit (TPU)
       | https://en.wikipedia.org/wiki/Tensor_Processing_Unit
       | 
       | AI Accelerator > Nomenclature:
       | https://en.wikipedia.org/wiki/AI_accelerator
       | 
       | NVIDIA DLSS > Architecture:
       | https://en.wikipedia.org/wiki/Deep_learning_super_sampling#A... :
       | 
       | > _DLSS is only available on GeForce RTX 20, GeForce RTX 30,
       | GeForce RTX 40, and Quadro RTX series of video cards, using
       | dedicated AI accelerators called Tensor Cores. [23][28] Tensor
       | Cores are available since the Nvidia Volta GPU microarchitecture,
       | which was first used on the_ Tesla _V100 line of products.[29]
       | They are used for doing fused multiply-add (FMA) operations that
       | are used extensively in neural network calculations for applying
       | a large series of multiplications on weights, followed by the
       | addition of a bias. Tensor cores can operate on FP16, INT8, INT4,
       | and INT1 data types._
       | 
       | Vision processing unit:
       | https://en.wikipedia.org/wiki/Vision_processing_unit
       | 
       | Versatile Processor Unit (VPU)
        
       ___________________________________________________________________
       (page generated 2023-11-17 23:00 UTC)