Cascade lake-advanced-performance-press-deck
0 likes132 views
Lisa Spelman announced new Intel Xeon Scalable processors including Cascade Lake Advanced Performance processors with up to 48 cores, up to 2666 MHz DDR4 memory, and improved performance on HPC, AI and cloud workloads. Intel Software Guard Extensions provide advanced security capabilities to the new processors. Intel Optane persistent memory delivers affordable high capacity memory and high performance storage to support large scale analytics and database workloads.
Cascade lake-advanced-performance-press-deck
- 1. Lisa Spelman VICE PRESIDENT & GENERAL MANAGER INTEL® XEON® PRODUCTS AND DATA CENTER MARKETING
- 6. Security MitigationsLeadership Performance Higher Frequencies Optimized Cache Hierarchy Intel Deep Learning Boost (VNNI) Optimized Frameworks & Libraries NEXT GEN INTEL® XEON® SCALABLE PROCESSOR
- 7. NEW CLASS OF INTEL® XEON® SCALABLE PROCESSORS ANNOUNCING DDR4 12 channels CASCADE LAKE ADVANCED PERFORMANCE 2-SOCKET SERVER CASCADE LAKE MCP 48 CORES CASCADE LAKE MCP 48 CORES DDR4 12 channels LINPACK STREAM TRIAD vs AMD EPYC 7601 Up to Up to DL INFERENCE IMAGES PER SECOND vs Intel® Xeon® Platinum Processor at launch Up to ARCHITECTED FOR DEMANDING HPC, AI & IAAS WORKLOADS MORE MEMORY CHANNELS THAN ANY OTHER CPU HIGH SPEED INTERCONNECT
- 8. UP TO PERFORMANCE IMPROVEMENT 4-YEARREFRESH1 UP TO UP TO 2666 M H Z DDR4 PERFORMANCEANDVISUALSWITH EXPANDABILITY,RELIABILITY,Security PERFORMANCE IMPROVEMENT GEN-ON-GEN2 UP TO TURBOBoost WITHINTEL® TECHNOLOGY2.0 AVAILABLE IN SINGLE-SOCKET CONFIGURATION ONLY INTEL®SOFTWAREGUARDEXTENSIONS DELIVERSADVANCEDSECURITYCAPABILITIES ENHANCED UP TO
- 9. INTEL® SOFTWARE GUARD EXTENSIONS PROVIDE A MORE SECURE PROCESSING ENVIRONMENT EVEN IF ATTACKER HAS CONTROL OF THE PLATFORM Fortanix provides Runtime Encryption® software to protect keys, data, and x86 applications IBM Cloud Data Shield powered by Fortanix protects run time data at scale on Kubernetes Service Azure Confidential Computing protects customer’s most sensitive data while it’s processed in the cloud R3 Corda’s approach to privacy and security shares data only with those who need to see it, enabling strict confidentiality for enterprise blockchain applications
- 11. VS. DRAM AT 2.6TB DATA SCALE more performance SPARK SQL DS VS. COMPARABLE SERVER SYSTEM WITH DRAM & NAND NVME DRIVES Moreread transactions Moreusers Persystem APACHE CASSANDRA VALUE OF PERSISTENCE minutes to S T A R T T I M E Three9S to A V A I L A B I L I T Y STORAGE MEMORY PERSISTENT MEMORY Improving memorycapacity DRAM HOT TIER HDD / TAPE COLD TIER SSD WARM TIER Delivering efficientstorage Intel®3DNandSSD Improving SSDperformance www.intel.com/benchmarks
- 13. PERSISTENT PERFORMANCE & MAXIMUM CAPACITY APPLICATION VOLATILE MEMORY POOL OPTANE PERSISTENT MEMORY DRAM AS CACHE AFFORDABLE MEMORY CAPACITY FOR MANY APPLICATIONS APPLICATION OPTANE PERSISTENT MEMORY DRAM
- 17. ConfigurationDetails LINPACK: AMD EPYC 7601: Supermicro AS-2023US-TR4 with 2 AMD EPYC 7601 (2.2GHz, 32 core) processors, SMT OFF, Turbo ON, BIOS ver 1.1a, 4/26/2018, microcode: 0x8001227, 16x32GB DDR4-2666, 1 SSD, Ubuntu 18.04.1 LTS (4.17.0-041700-generic Retpoline), High Performance Linpack v2.2, compiled with Intel(R) Parallel Studio XE 2018 for Linux, Intel MPI version 18.0.0.128, AMD BLIS ver 0.4.0, Benchmark Config: Nb=232, N=168960, P=4, Q=4, Score = 1095GFs, tested by Intel as of July 31, 2018. compared to 1-node, 2-socket 48- core Cascade Lake Advanced Performance processor projections by Intel as of 10/3/2018. Stream Triad: 1-node, 2-socket AMD EPYC 7601, http://www.amd.com/system/files/2017-06/AMD-EPYC-SoC-Delivers-Exceptional-Results.pdf tested by AMD as of June 2017 compared to 1-node, 2-socket 48-core Cascade Lake Advanced Performance processor projections by Intel as of 10/3/2018. DL Inference: Platform: 2S Intel® Xeon® Platinum 8180 CPU @ 2.50GHz (28 cores), HT disabled, turbo disabled, scaling governor set to “performance” via intel_pstate driver, 384GB DDR4- 2666 ECC RAM. CentOS Linux release 7.3.1611 (Core), Linux kernel 3.10.0-514.10.2.el7.x86_64. SSD: Intel® SSD DC S3700 Series (800GB, 2.5in SATA 6Gb/s, 25nm, MLC).Performance measured with: Environment variables: KMP_AFFINITY='granularity=fine, compact‘, OMP_NUM_THREADS=56, CPU Freq set with cpupower frequency-set -d 2.5G -u 3.8G -g performance. Caffe: (http://github.com/intel/caffe/), revision f96b759f71b2281835f690af267158b82b150b5c. Inference measured with “caffe time --forward_only” command, training measured with “caffe time” command. For “ConvNet” topologies, dummy dataset was used. For other topologies, data was stored on local storage and cached in memory before training. Topology specs from https://github.com/intel/caffe/tree/master/models/intel_optimized_models (ResNet-50),and https://github.com/soumith/convnet-benchmarks/tree/master/caffe/imagenet_winners (ConvNet benchmarks; files were updated to use newer Caffe prototxt format but are functionally equivalent). Intel C++ compiler ver. 17.0.2 20170213, Intel MKL small libraries version 2018.0.20170425. Caffe run with “numactl -l“. Tested by Intel as of July 11th 2017 -. compared to 1-node, 2-socket 48-core Cascade Lake Advanced Performance processor projections by Intel as of 10/7/2018.