Solution Performance

Discover the Benefits

  • Significantly improved deep learning inference throughput, without impacting latency

  • Delivering better user experience



Hisign is one of the key biometric companies in China. They provide biometric authentication solutions, including fingerprint, voice and face recognition - for Foreign Affairs and Public Security. Their solutions are used  for national ID card systems, e-passports, and for access control systems in enterprise.  Hisign Face Recognition software uses customized Resnet32 to accurately identify the human face.

Visit ›


Deploying facial recognition solutions often faces two bottlenecks: network bandwidth and computing capabilities, that negatively impact deep learning inference throughput and latency, thereby resulting in less than optimal user experiences.  Additionally, achieving improvement in throughput often requires scaling out, resulting in added deployment costs & complexity.


For facial recognition, a customized Resnet32 model was optimized on Intel Caffe. Compared to FP32, Intel® DL Boost (delivered by Vector Neural Network Instructions (VNNI)/INT8) optimizations helped increase deep learning inference throughput by 2.18X  (see chart)12, while meeting the partner-specified latency of less than 10ms.



Significantly improved deep learning inference throughput, without impacting latency, thus delivering better user experience.


Product and Performance Information


HiSign Face Recognition* (self-defined workload); OS: Red Hat Enterprise Linux* 7.5 Kernel 4.19.3-1.el7.elrepo.x86_64. Testing by Intel and HiSign completed on Dec 15, 2018. Security Mitigations for Variants 1, 2, 3 and L1TF in place. 

TEST SYSTEM CONFIG: 2nd Gen Intel® Xeon® Platinum processor 8260L, 2.3 GHz, 24 cores, turbo, and HT on, BIOS 1.0180, 768GB total memory, 12 slots / 64GB / 2666 MT/s / DDR4 LRDIMM, 1 x 480GB / Intel® SSD Data Center (Intel® SSD DC) S4500; Intel® Optimization for Caffe*.


Performance varies by use, configuration and other factors. Learn more at