A successful deep learning and AI strategy is the new heart of modern business operations. Read our guide on how businesses can navigate the challenges and opportunities of evolving their AI capabilities, and how Intel® AI Technology can help.
Benchmarks Validate CPUs for Deep Learning Inference
Learn About Intel® Deep Learning Boost (Intel® DL Boost)
Learn About Intel® Select Solution for BigDL
Notices and Disclaimers:
Software and workloads used in performance tests may have been optimized for performance only on Intel® microprocessors. Performance tests, such as SYSmark* and MobileMark*, are measured using specific computer systems, components, software, operations, and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more complete information visit http://www.intel.com/benchmarks.
Performance results are based on testing as of the date indicated in the configuration details and may not reflect all publicly available security updates. See configuration disclosure for details. No product or component can be absolutely secure.
Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel® microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel® microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel® microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice. Notice Revision #20110804.
Cost reduction scenarios described are intended as examples of how a given Intel®-based product, in the specified circumstances and configurations, may affect future costs and provide cost savings. Circumstances will vary. Intel does not guarantee any costs or cost reduction.
Intel® Advanced Vector Extensions (Intel® AVX) provides higher throughput to certain processor operations. Due to varying processor power characteristics, utilizing AVX instructions may cause a) some parts to operate at less than the rated frequency and b) some parts with Intel® Turbo Boost Technology 2.0 to not achieve any or maximum turbo frequencies. Performance varies depending on hardware, software, and system configuration and you can learn more at http://www.intel.com/go/turbo.
Intel does not control or audit third-party benchmark data or the web sites referenced in this document. You should visit the referenced web site and confirm whether referenced data are accurate.
Infos sur le produit et ses performances
Amélioration multipliée par 30 du débit d'inférence sur le processeur Intel® Xeon® Platinum 9282 avec la technologie Intel® Deep Learning Boost (Intel® DL Boost) : test réalisé par Intel le 26 février 2019. Plate-forme : processeur Intel® Xeon® Platinum 9282 2 sockets Dragon rock (56 cœurs par socket), technologie Hyper Threading ACTIVÉE, technologie Turbo ACTIVÉE, 768 Go de mémoire totale (24 emplacements / 32 Go / 2 933 MHz), BIOS : SE5C620.86B.0D.01.0241.112020180249, noyau CentOS 7 3.10.0-957.5.1.el7.x86_64, structure de Deep Learning : optimisation Intel® pour version Caffe* : https://github.com/intel/caffe d554cbf1, ICC 2019.2.187, MKL DNN version : v0.17 (hachage de validation : 830a10059a018cd2634d94195140cf2d8790a75a), modèle : https://github.com/intel/caffe/blob/master/models/intel_optimized_models/int8/resnet50_int8_full_conv.prototxt, BS=64, Aucune couche de données syntheticData : 3x224x224, 56 instances/2 sockets, type de données : INT8 ; vs. Testé par Intel en date du 11 juillet 2017 : processeur Intel® Xeon® Platinum 8180 2 sockets à 2,50 GHz (28 cœurs), technologie Hyper Threading désactivée, technologie turbo désactivée, mode d'échelonnage réglé sur « performances » via le pilote intel_pstate, RAM ECC DDR4-2666 384 Go. CentOS Linux* version 7.3.1611 (Core), noyau Linux* 3.10.0-514.10.2.el7.x86_64. Unité de stockage SSD Intel® série S3700 pour les centres de données (800 Go, 2,5 pouces, SATA 6 Gbit/s, 25 nm, MLC). Performances mesurées avec les variables environnementales : KMP_AFFINITY='granularity=fine, compact‘, OMP_NUM_THREADS=56, fréquence du processeur réglée avec les performances cpupower frequency-set -d 2.5G -u 3.8G -g. Caffe : (http://github.com/intel/caffe/), révision f96b759f71b2281835f690af267158b82b150b5c. Inférence mesurée avec la commande « caffe time --forward_only », formation mesurée avec la commande « caffe time ». Un ensemble de données synthétique a été utilisé pour les topologies « ConvNet ». Pour les autres topologies, les données ont été stockées localement et mises en mémoire avant la formation. Spécifications des topologies sur https://github.com/intel/caffe/tree/master/models/intel_optimized_models(ResNet-50). Compilateur C++ Intel® ver. 17.0.2 20170213, Intel® Math Kernel Library (Intel® MKL) small libraries version 2018.0.20170425. Caffe exécuté avec « numactl -l ».