• <More on Intel.com

Intel® Xeon Phi™ Product Family

Highly parallel processing to power your breakthrough innovations

Intel® Xeon Phi™ brand badge

Power your breakthrough innovations with the highly parallel processing of the Intel® Xeon Phi™ coprocessor. We’ve packed over a teraFLOPS of double-precision peak performance into every chip.

Performance per Watt with Linpack*

The Linpack* benchmark performs dual precision vector and matrix operations. Linpack is often used by the high performance computing (HPC) community to measure the floating point operations per second (FLOPS) of a processor or coprocessor.

Intel Measured as of December 2013

Performance per Watt with SGEMM* and DGEMM*

The SGEMM* and DGEMM* benchmarks demonstrate the processor's or coprocessor's ability to do a multiplication of two matrices using either single precision calculations (SGEMM) our double precision calculations (DGEMM). Different matrix sizes were tested and produced varying results. The matrix size that produced the best result was chosen.

Intel Measured as of December 2013

 

Configuration Details

 

Intel® Xeon® processor perf/watt = performance of 2x Intel Xeon processor platform/total system power

Intel® Xeon Phi™ coprocessor perf/watt = coprocessor performance/coprocessor power

 

Intel® Xeon® Processor Platform:

Two-socket Intel® Server Board S2600CP software development platform: 2x Intel® Xeon® processor E5-2670 (20M cache, 2.6 GHz, 8.0 GT/s Intel® QPI, 115W TDP), 64 GB memory @ 1600 MHz, Red Hat Enterprise Linux* (RHEL) 6.3, Intel® Turbo Boost Technology on, Intel® Hyper-Threading Technology (Intel® HT Technology) off, Enhanced Intel SpeedStep® Technology enabled, HW & ACL prefetch on, C-state enabled: Performance mode Intel® Compiler 14.0, Intel® Math Kernel Library (Intel® MKL) 11.1.1 (Intel Xeon processor results only).

Two-socket Intel Server Board S2600CP software development platform: 2x Intel Xeon processor E5-2697 v2 (30M cache, 2.7 GHz, 8.0 GT/s Intel QPI, 130W TDP), 64 GB memory @ 1866 MHz, RHEL 6.3, Intel Turbo Boost Technology on, Intel HT Technology off, Enhanced Intel SpeedStep Technology enabled, HW & ACL prefetch on, C-state enabled: Performance mode Intel Compiler 14.0, Intel MKL 11.1.1  (Intel Xeon processor results only).

 

Platform Hosting the Coprocessor: 

Two-socket Intel® Server Board W2600CR software development platform: 2x Intel Xeon processor E5-2697 v2 (12C, 30M cache, 2.7 GHz, 8.0 GT/s Intel QPI, 130W TDP), 32 GB memory @ 1600 MHz, RHEL 6.3

Intel® Xeon Phi™ coprocessor 7120P/X: 61 cores, 1.238 GHz, 16 memory channels, 16 GB memory @ 5.5 GT/s, 300W TDP C-step (Intel Turbo Boost Technology on)

Intel Xeon Phi coprocessor 5120D: 60 cores, 1.053 GHz, 16 memory channels, 8 GB memory @ 5.5 GT/s, 245W TDP C-step

Intel Xeon Phi coprocessor 5110P: 60 cores, 1.053 GHz, 16 memory channels, 8 GB memory @ 5.0 GT/s, 225W TDP B1-step

Intel Xeon Phi coprocessor 3120P/A: 57 cores, 1.098 GHz, 12 memory channels, 6 GB memory @ 5.0 GT/s, 300W TDP C-step

 

Matrix Sizes:

 

SGEMM*

DGEMM*

Linpack*

7120P:

30720 x 30720

15360 x 15360

43072 x 43072

5120D:

15360 x 15360

15360 x 15360

28672 x 28672

5110P:

15360 x 15360

15360 x 15360

28672 x 28672

3120P:

15360 x 15360

15360 x 15360

22528 x 22528

2S E5-2670

38912 x 38912

18944 x 18944

69632 x 69632

2S E5-2697 v2

38400 x 38400

20480 x 20480

75776 x 75776

 

Score:

 

SGEMM (GF/s)

DGEMM

Linpack

7120P:

2221.41@293W

1066.76@302W

999.01@313W

5120D:

1742.25@125W

837.43@225W

766.61@230W

5110P:

1741.34@217W

836.55@229W

769.46@235W

3120P:

1721.85@223W

817.76@222W

714.51@279W

2S E5-2670

670.25@383W

332.42@390W

334.38@392W

2S E5-2697v2

1058.91@435W

548.13@451W

542.6@459W

Software Stack (Intel® Xeon Phi™ Coprocessor):

MPSS 3.1:  (Flash: 2.1.03.0386; SMC firmware: 1.15.4830, coprocessor OS: 2.6.38.8+mpss3.1; SMC Flash 1.15.4830), Intel® C++ Composer XE for Linux 2013 SP1 Update 1  (Intel® C++ Compiler 14.0.1, Intel® MKL: 11.1.1, Intel® IPP 8.0.1, Intel® TBB 4.2.1)

Data Source:

Intel® Xeon Phi™ coprocessor: Intel Internal Testing TR2039C

Intel® Xeon® Processor: Intel Internal Testing TR1390

Additional information: 1 2 3 4 5

Product and Performance Information

open

1. 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 information, go to www.intel.com/performance.

2. Intel does not control or audit the design or implementation of third party benchmarks or websites referenced in this document. Intel encourages all of its customers to visit the referenced websites or others where similar performance benchmarks are reported and confirm whether the referenced benchmarks are accurate and reflect performance of systems available for purchase.

3. Intel processor numbers are not a measure of performance. Processor numbers differentiate features within each processor family, not across different processor families. See www.intel.com/content/www/us/en/processors/processor-numbers.html for details.

4. 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 and SSE3 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

5. Different hardware architectures may require different source code. Results are based on Intel’s best efforts to use code optimized to run on all architectures and perform the same work. Future code optimizations may result in different results. 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