Informasi Produk dan Performa

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

Klaim berdasarkan kapabilitas kinerja presisi ganda puncak teoritis yang dihitung untuk satu koprosesor. 16 DP FLOPS/clock/core * 61 core * 1,238 GHz = 1,208 TeraFLOPS.

3

Hasil telah diperkirakan berdasarkan analisis internal Intel dan diberikan hanya untuk tujuan informasi. Perbedaan apa pun dalam rancangan maupun konfigurasi perangkat keras atau perangkat lunak dapat mempengaruhi performa yang sebenarnya.

4

FLOPS presisi ganda puncak teoritis terhitung (2 x prosesor Intel® Xeon® E5-2697v2 (12 core, 2.7 GHz) versus 1 x koprosesor Intel® Xeon Phi™ 7120P (61 core, 1.238 GHz) (518 GF/dtk vs. 1208 GF/dtk)

5

Server prosesor Intel® Xeon® E5-2697v2 2 soket vs. koprosesor Intel® Xeon Phi™ 5120D tunggal (skor perf/watt DGEMM yang diukur Intel 548 GF/dtk @ 451 W vs. 837 GF/dtk @ 225 W)

6

Server rangkaian produk prosesor Intel® Xeon® E5-2600 2 soket versus koprosesor Intel® Xeon Phi™ (7,04x: Diukur oleh Intel pada Desember 2013. E5-2697v2 2 soket (12 core, 2.7 GHz) vs. 1 koprosesor Intel® Xeon Phi™ 7120P (61 core, 1.238GHz) pada Simulasi Monte Carlo Presisi Tunggal.  78,44 Koption/dtk vs. 552,41 Koption/dtk )