Tensor Streaming Processor architecture
GPTKB entity
Statements (13)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:architecture
|
| gptkbp:developedBy |
gptkb:NVIDIA
|
| gptkbp:enables |
deep learning inference
deep learning training |
| gptkbp:feature |
high throughput matrix operations
tensor core integration |
| https://www.w3.org/2000/01/rdf-schema#label |
Tensor Streaming Processor architecture
|
| gptkbp:introducedIn |
gptkb:NVIDIA_Volta_architecture
|
| gptkbp:purpose |
accelerate AI workloads
|
| gptkbp:supports |
mixed precision computing
|
| gptkbp:usedIn |
gptkb:NVIDIA_GPUs
|
| gptkbp:bfsParent |
gptkb:Groq
|
| gptkbp:bfsLayer |
6
|