News Intel Partners With Baidu on Neural Network Processor for Training

JayNor

Commendable
May 31, 2019
312
44
1,710
0
"Cascade Lake’s DL Boost, Intel’s new instructions to double or triple the performance of FP16 or INT8 AVX-512 vector code."

DLBoost doesn't do anything for fp16. The Cooper Lake chip is supposed to be the one that adds the bfloat16 avx512 vector operations.

The DLBoost/VNNI AVX512 additions are all fused multiply-add for int8 or int16. The DLBoost intrinsics are all described here, pretty clearly.

https://software.intel.com/sites/landingpage/IntrinsicsGuide/#expand=1651,2196,2195,2197,2204,2195,2196,2197,2204,2205,2206,2213,2214,2215,2222,2223&avx512techs=AVX512_VNNI
 
Reactions: bit_user

ASK THE COMMUNITY