Intel® Xeon® D Processor Performance

The Intel® Xeon® D processor brings advanced intelligence and groundbreaking data center architecture into an lower-power, optimized solution, for high-density edge computing, integrating essential hardware-enhanced network, security and acceleration capabilities into a single socket, system-on-a-chip (SoC) processor for flexible and scalable specialty cloud edge solutions.1

General Purpose Compute Benchmarks

STREAM* OpenMP (OMP) measures memory bandwidth for a set of four computational kernels in GB/s.

SPEC CPU* 2006 (SPECint*_rate_base2006) measures parallel integer operations performance and contains 12 integer applications. It is compute intensive and concentrates on the CPU and memory subsystems without measuring disk or network I/O. 

Intel internal testing as of May 27, 2015

View configuration details ›

Cloud Benchmarks

Memcached* speeds up application performance by caching data and objects in RAM to reduce the number of times an external data source (i.e. a database) must be read.

Server Side Java* is a measure of server-side performance of Java* runtime environment.

Dynamic Web Serving measures the number of simultaneous users (taking user input into account) that a server can deliver content to while meeting a specified SLA (service level agreement).

Intel internal testing as of May 27, 2015

View configuration details ›

Configuration Details

General Purpose Compute Benchmarks:

Memory Bandwidth

New configuration: Intel® Xeon® processor D product family-based reference platform with one Intel® Xeon® processor D-1540 (8 cores, 2.0 GHz, 45 W), Intel® Turbo Boost Technology enabled, Intel® Hyper-Threading Technology (Intel® HT Technology) enabled, 64 GB memory (4x 16 GB DDR4-2133 RDIMM ECC), 800 GB SATA SSD, stream_omp v5.4 with Intel® Compiler version 14.0.3.174 running on 8 threads, Red Hat Enterprise Linux* 7.0, Stream Triad = 29.9 GB/s.

Base configuration: Supermicro SuperServer* 5018A-TN4 with one Intel Atom® processor C2750 (8 cores, 2.4 GHz, 20 W), Intel® Turbo Boost Technology enabled, 32 GB memory (4x 8 GB DDR3-1600 SO-DIMM ECC), 800 GB SATA SSD, stream_omp v5.4 with Intel® Compiler version 14.0.3.174 running on 8 threads, Red Hat Enterprise Linux 7.0, Stream Triad = 16.5 GB/s.

Integer Throughput

New configuration: Intel® Xeon® processor D product family-based reference platform with one Intel® Xeon® processor D-1540 (8 cores, 2.0 GHz, 45 W), Intel® Turbo Boost Technology enabled, Intel® Hyper-Threading Technology (Intel® HT Technology) enabled, 64 GB memory (4x 16 GB DDR4-2133 RDIMM ECC), 800 GB SATA SSD. SPEC CPU* 2006 v1.2, INTEL.cpu2006.1.2.ic15.29aug2014 binaries, Red Hat Enterprise Linux 7.0, estimated score: SPECint*_rate_base2006 (16 copy) = 280.

Base configuration: Supermicro SuperServer 5018A-TN4 with one Intel Atom® processor C2750 (8 cores, 2.4 GHz, 20 W), Intel® Turbo Boost Technology enabled, 32 GB memory (4x 8 GB DDR3-1600 SO-DIMM ECC), 800 GB SATA SSD. SPEC CPU 2006 v1.2, INTEL.cpu2006.1.2.ic15.29aug2014 binaries, Red Hat Enterprise Linux 7.0, estimated score: SPECint_rate_base2006 (8 copy) = 102.

Cloud Benchmarks:

Memory Caching

New configuration: Intel® Xeon® D processor based reference platform with one Intel® Xeon® processor D-1540 (8C, 2.0GHz, 45W), Intel® Turbo Boost Technology enabled, Intel® Hyper-Threading Technology (Intel® HT Technology) enabled, 64GB memory (4x16GB DDR4-2133 RDIMM ECC), 1x10GBase-T X552, 800GB SATA SSD. Memcached 1.4.15 with process affinity. MC-Blaster*—from gitHUB—modified to distribute data & transactions over multiple memcached servers & support hot and random keys, Ubuntu* 14.10 (3.16.0-23 generic), Random Key Gets = 3.38MRPS.

Base configuration: Supermicro SuperServer 5018A-TN4 with one Intel Atom® processor C2750 (8 cores, 2.4 GHz, 20 W), Intel® Turbo Boost Technology enabled, 32 GB memory (4x 8 GB DDR3-1600 SO-DIMM ECC), 1x 10GBase-T X520, 800 GB SATA SSD, memcached 1.4.15 with process affinity, MC-Blaster—from gitHUB—modified to distribute data and transactions over multiple memcached servers and support hot and random keys, Ubuntu 14.10 (3.16.0-23 generic), Random Key Gets = 1.48MRPS.

Server Side Java

New configuration: Intel® Xeon® D processor based reference platform with with one Intel® Xeon® processor D-1540 (8C, 2.0GHz, 45W), Intel® Turbo Boost Technology enabled, Intel® Hyper-Threading Technology (Intel® HT Technology) enabled, 64GB memory (4x16GB DDR4-2133 RDIMM ECC), 800GB SATA SSD, Oracle* JDK 8u31, Ubuntu 14.10 (3.16.0-23 generic), Score=18708.

Base configuration: Supermicro SuperServer 5018A-TN4 with one Intel Atom® processor C2750 (8 cores, 2.4 GHz, 20 W), Intel® Turbo Boost Technology enabled, 32 GB memory (4x 8 GB DDR3-1600 SO-DIMM ECC), 800 GB SATA SSD, Oracle JDK 8u31, Ubuntu 14.10 (3.16.0-23 generic), Score = 5396.

Dynamic Web Serving

New configuration: Intel® Xeon® D processor based reference platform with with one Intel® Xeon® processor D-1540 (8C, 2.0GHz, 45W), Intel® Turbo Boost Technology enabled, Intel® Hyper-Threading Technology (Intel® HT Technology) enabled, 64GB memory (4x16GB DDR4-2133 RDIMM ECC), 2x10GBase-T X552, 3x S3700 SATA SSD, Ubuntu 14.10 (3.16.0-23 generic), Nginx* 1.4.4,  Php-fpm* 15.4.14, memcached* 1.4.14, Simultaneous users=47152.

Base configuration: Supermicro SuperServer 5018A-TN4 with one Intel Atom® processor C2750 (8 cores, 2.4 GHz, 20 W), Intel® Turbo Boost Technology enabled, 32 GB memory (4x 8 GB DDR3-1600 SO-DIMM ECC), 1x 10GBase-T X520, 2x Intel® SSD DC S3700 SATA SSD, Ubuntu 14.10 (3.16.0-23 generic), Nginx 1.4.4, Php-fpm 15.4.14, memcached 1.4.14, Simultaneous users = 12896.

Additional information: 2 3 4 5 6

產品與效能資訊

1

陳述係依據新的 Intel® 產品與功能相較於過去的 Intel 產品與功能之結果。

2

效能標竿結果是在實施最近的軟體修補程式與韌體更新以解決「Spectre」和「Meltdown」安全漏洞之前取得的資料。實施這些更新可能會讓這些結果變得不適用於您的裝置或系統。 

效能測試中使用的軟體與工作負載可能僅針對 Intel® 微處理器進行最佳化。效能測試(例如 SYSmark* 與 MobileMark*)使用特定的電腦系統、元件、軟體、作業及功能進行評量。這些因素若有任何異動,均可能導致測得結果產生變化。建議您參考其他資訊與效能測試數據,協助您充分評估欲購買產品的性能,包括該產品在搭配其他產品運作時的效能。如需完整的資訊,請參閱 http://www.intel.com.tw/benchmarks

3

對於本文件提及的各項第三方效能標竿或網站,Intel 並不會控制或稽核其設計或執行。Intel 鼓勵所有的客戶參閱提及的網站,或是其他發佈類似評量效能標竿報告的網站,確認提及的效能標竿是否正確,並且反映出可購買系統的效能表現。

4

Intel® 處理器編號並不代表效能。處理器編號乃是用來區別屬於同一處理器系列中的不同特色,並非用來區別不同的處理器系列。如需詳細資料,請參閱 https://www.intel.com.tw/content/www/tw/zh/processors/processor-numbers.html

5

對於不是 Intel® 微處理器特有的最佳化,用於非 Intel 微處理器時,Intel 的編譯器可能會,也可能不會最佳化到同樣程度。這些最佳化包括 SSE2 與 SSE3 指令集,也包括其他最佳化。對於任何最佳化,用於並非由 Intel 製造的微處理器,Intel 不保證最佳化的可用性、功能性或效力。

在本產品中取決於微處理器的最佳化,乃是為了用於 Intel 微處理器而設計。某些最佳化並非專門針對 Intel® 微架構,而是保留給 Intel 微處理器。關於本公告所涉及的具體指令集,如需詳細資訊,請參閱適用產品的使用指南與參考指南。

公告修訂版編號 20110804

6

SPEC* 與 SPECint*、SPECfp*、SPECjbb*、SPECjEnterprise*、SPECvirt_sc*、SPECpower_ssj*、SPECompM* 及 SPECompL* 效能標竿名稱是 Standard Performance Evaluation Corporation (SPEC) 的註冊商標。