AVX-512 Vector Neural Network Instructions
GPTKB entity
Statements (20)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:architecture
|
| gptkbp:abbreviation |
gptkb:AVX-512_VNNI
|
| gptkbp:architecture |
x86
|
| gptkbp:category |
gptkb:SIMD_instruction_set
|
| gptkbp:enables |
faster inference for neural networks
|
| gptkbp:feature |
fused multiply add
integer dot product |
| gptkbp:introduced |
gptkb:Intel
|
| gptkbp:introducedIn |
2018
|
| gptkbp:partOf |
gptkb:AVX-512
|
| gptkbp:purpose |
accelerate deep learning workloads
|
| gptkbp:relatedTo |
gptkb:Intel_Deep_Learning_Boost
AVX2 AVX-512 BF16 |
| gptkbp:supportedBy |
gptkb:Cascade_Lake
|
| gptkbp:usedIn |
gptkb:Intel_Core_i9-10900K
gptkb:Intel_Xeon_Scalable_processors |
| gptkbp:bfsParent |
gptkb:AVX-512VNNI
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
AVX-512 Vector Neural Network Instructions
|