The browser version you are using is not recommended for this site.
Please consider upgrading to the latest version of your browser by clicking one of the following links.

Intel® Xeon Phi™ Product Family

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

Peak Theoretical Performance

These charts represent processors' or coprocessors' theoretical peak capabilities for single precision computations, double precision computations, and memory bandwidth. The metrics provide a baseline for the raw performance capabilities of each part.

Accelerate your highly parallel applications with the Intel® Xeon Phi™ coprocessor:

  • Up to 3.6 times higher peak single precision floating point operations per second (FLOPS)
  • Up to 3.6 times higher peak double precision FLOPS
  • Up to 3.45 times higher peak memory bandwidth

vs. two Intel® Xeon® processor E5-2670

Developer starter kits >

Intel calculated as of November 2013

Host platform:

Two-socket Intel® Server Board W2600CR software development platform: two Intel® Xeon® processor E5-2670 (10 cores, 20M cache, 2.6 GHz, 8.0 GT/s Intel® QuickPath Interconnect (Intel® QPI), 115 W thermal design power (TDP)), memory at 1600 MHz

Two-socket Intel® Server Board W2600CR software development platform: two Intel Xeon processor E5-2697 v2 (12 cores, 30M cache, 2.7 GHz, 8.0 GT/s Intel QPI, 130 W TDP), memory at 1866 MHz


Coprocessor details:

Intel® Xeon Phi™ coprocessor 7120P/X/D/A: 61 cores, 1.238 GHz, 16 memory channels, 16 GB memory at 5.5 GT/s, 300 W TDP

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

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

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


Theoretical values calculations:

Peak single precision FLOPS calculations:

  • Intel Xeon processor E5-2690: 16 FLOPS/clock x 8 cores/socket x 2 sockets x 2.6 GHz = 665.6 GF/s
  • Intel Xeon processor E5-2697 v2: 16 FLOPS/clock x 12 cores/socket x 2 sockets x 2.7 GHz = 1063.8 GF/s
  • Intel Xeon Phi coprocessor 7120P/D/X/A: 32 FLOPS/clock x 61 cores x 1.238 GHz = 2416.58 GF/s
  • Intel Xeon Phi coprocessor 5120D: 32 FLOPS/clock x 60 cores x 1.053 GHz = 2021.76 GF/s
  • Intel Xeon Phi coprocessor 5110P: 32 FLOPS/clock x 60 cores x 1.053 GHz = 2021.76 GF/s
  • Intel Xeon Phi coprocessor 3120P/A: 32 FLOPS/clock x 57 cores x 1.098 GHz = 2002.75 GF/s

Peak double precision FLOPS calculations:

  • Intel Xeon processor E5-2690: 8 FLOPS/clock x 8 cores/socket x 2 sockets x 2.6 GHz = 332.8 GF/s
  • Intel Xeon processor E5-2697 v2: 8 FLOPS/clock x 12 cores/socket x 2 sockets x 2.7 GHz = 518.4 GF/s
  • Intel Xeon Phi coprocessor 7120P/D/X/A: 16 FLOPS/clock x 61 cores x 1.238 GHz = 1208.29 GF/s
  • Intel Xeon Phi  coprocessor 5120D: 16 FLOPS/clock * 60 cores * 1.053 GHz = 1010.88 GF/s
  • Intel Xeon Phi coprocessor 5110P: 16 FLOPS/clock x 60 cores x 1.053 GHz = 1010.88 GF/s
  • Intel Xeon Phi coprocessor 3120P/A: 16 FLOPS/clock x 57 cores x 1.098 GHz = 1001.38GF/s

Peak memory bandwidth calculations:

  • Intel Xeon processor E5-2690: 8 bytes/channel x 4 channels x 2 sockets x 1.6 GHz = 102.4 GB/s
  • Intel Xeon processor E5-2697 v2: 8 bytes/channel x 4 channels x 2 sockets x 1.866 GHz = 119.4 GB/s
  • Intel Xeon Phi coprocessor 7120P/D/X/A: 4 bytes/channel x 16 channels x 5.5 GT/s = 352 GB/s
  • Intel Xeon Phi coprocessor 5120P: 4 bytes/channel x 16 channels x 5.5 GT/s = 352 GB/s
  • Intel Xeon Phi coprocessor 5110P: 4 bytes/channel x 16 channels x 5.0 GT/s = 320 GB/s
  • Intel Xeon Phi coprocessor 3120P: 4 bytes/channel x 12 channels x 5.0 GT/s = 240 GB/s

Additional information: 1 2 3

Related Videos

Product and Performance Information

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 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.

3

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