Guest User

AVX512/AVX2/SSE i7 7800X@4.5GHz

a guest
Jul 4th, 2018
168
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 16.67 KB | None | 0 0
  1. AVX512
  2. Subroutine/MSps | 1 2 4 8 16 32 64 128 256 512 1024 2048 4096 8192 16384 32768 |
  3. ---------------------------------+----------------------------------------------------------------------------------------------------------------------------------|
  4. srslte_vec_xor_bbb | 102.4 204.8 372.4 682.7 744.7 2978.9 2849.4 21845.3 37449.1 65536.0 104857.6 139810.1 123361.9 125203.1 47662.5 48984.6 |
  5. srslte_vec_acc_ff | 35.3 81.9 146.3 248.2 655.4 4681.1 8192.0 13107.2 17476.3 21845.3 23831.3 23045.6 20164.9 19065.0 18497.5 18226.2 |
  6. srslte_vec_dot_prod_sss | 44.5 89.0 157.5 256.0 390.1 5461.3 10922.7 18724.6 29127.1 32768.0 38836.1 46603.4 49344.8 51463.9 49636.7 50306.5 |
  7. srslte_vec_sum_sss | 56.9 107.8 195.0 341.3 512.0 8192.0 16384.0 26214.4 43690.7 52428.8 69905.1 61680.9 63550.1 24892.0 25040.6 25134.4 |
  8. srslte_vec_sub_sss | 53.9 102.4 195.0 356.2 512.0 8192.0 13107.2 26214.4 52428.8 52428.8 69905.1 61680.9 62601.6 24892.0 25040.6 25078.1 |
  9. srslte_vec_prod_sss | 53.9 107.8 186.2 356.2 528.5 8192.0 16384.0 26214.4 52428.8 47662.5 69905.1 61680.9 61680.9 24892.0 24818.4 25153.2 |
  10. srslte_vec_acc_cc | 34.1 68.3 128.0 282.5 546.1 4096.0 7281.8 10922.7 11915.6 9892.2 11037.6 9939.1 9404.3 9218.3 9005.5 9039.4 |
  11. srslte_vec_sum_fff | 53.9 97.5 178.1 327.7 1092.3 8192.0 13107.2 16384.0 23831.3 34952.5 30840.5 31775.0 12483.0 12175.0 11475.5 12223.8 |
  12. srslte_vec_sub_fff | 56.9 102.4 186.2 341.3 1170.3 8192.0 13107.2 18724.6 26214.4 37449.1 30840.5 31300.8 12483.0 12539.0 12183.9 12381.7 |
  13. srslte_vec_dot_prod_ccc | 16.0 22.5 28.4 32.6 303.4 1927.5 3120.8 4096.0 5698.8 7281.8 8594.9 9238.6 8577.3 9068.8 8710.9 9046.8 |
  14. srslte_vec_dot_prod_conj_ccc | 15.8 22.3 28.2 32.1 297.9 1927.5 3276.8 4369.1 5957.8 7825.2 9039.4 9799.8 8848.7 9754.2 10034.2 9863.1 |
  15. srslte_vec_convert_fi | 68.3 120.5 215.6 327.7 455.1 10922.7 16384.0 26214.4 32768.0 29127.1 37449.1 38130.0 39199.1 22982.5 23141.0 22354.7 |
  16. srslte_vec_convert_if | 73.1 128.0 292.6 455.1 655.4 3276.8 2978.9 3744.9 3912.6 3942.0 3898.1 3883.6 3956.9 3960.6 3916.3 3973.3 |
  17. srslte_vec_prod_fff | 53.9 102.4 178.1 341.3 1170.3 8192.0 13107.2 26214.4 26214.4 34952.5 30840.5 31300.8 12446.0 12409.2 12492.3 11975.2 |
  18. srslte_vec_prod_cfc | 48.8 93.1 157.5 248.2 1024.0 5461.3 9362.3 13107.2 13797.1 15887.5 16384.0 6765.0 6909.9 6610.4 6684.1 5808.3 |
  19. srslte_vec_prod_ccc | 26.3 32.5 36.9 39.6 862.3 5461.3 7281.8 7710.1 9039.4 9892.2 10280.2 5405.0 5592.4 5773.3 5884.7 4318.5 |
  20. srslte_vec_prod_ccc_split | 22.8 40.2 71.9 110.7 780.2 5461.3 8192.0 10922.7 13797.1 17476.3 17476.3 5940.9 5256.0 5886.7 5945.2 4382.2 |
  21. srslte_vec_prod_conj_ccc | 25.6 27.3 33.0 34.0 862.3 5461.3 7281.8 7281.8 9039.4 9709.0 10280.2 5475.6 5874.4 5996.1 5994.0 4335.2 |
  22. srslte_vec_sc_prod_ccc | 13.3 20.5 28.1 143.7 268.6 1927.5 3449.3 5698.8 7943.8 9709.0 11781.8 12192.7 7752.9 7884.0 7735.0 7613.9 |
  23. srslte_vec_sc_prod_fff | 64.0 120.5 215.6 409.6 1092.3 10922.7 16384.0 43690.7 52428.8 58254.2 49932.2 49932.2 54471.5 16320.2 16336.1 15723.7 |
  24. srslte_vec_abs_cf | 68.3 97.5 81.9 98.7 712.3 5461.3 5957.8 6241.5 6096.4 6026.3 5991.9 6009.0 6000.4 5991.9 5974.8 5973.7 |
  25. srslte_vec_abs_square_cf | 56.9 107.8 178.1 315.1 1489.5 8192.0 16384.0 18724.6 21845.3 23831.3 24966.1 25890.8 11881.9 11949.6 11865.1 11642.8 |
  26. srslte_vec_sc_prod_cfc | 60.2 107.8 186.2 819.2 1820.4 8192.0 16384.0 21845.3 29127.1 24966.1 24966.1 26886.6 8176.0 8184.0 8012.0 7921.3 |
  27. srslte_vec_div_ccc | 25.6 32.0 36.2 37.9 819.2 4096.0 4681.1 5041.2 5461.3 4899.9 4993.2 4194.3 4510.0 4483.5 4479.9 3757.1 |
  28. srslte_vec_div_cfc | 53.9 102.4 163.8 199.8 963.8 5461.3 9362.3 8738.1 11397.6 12787.5 13797.1 6990.5 6668.2 6836.7 6684.1 6598.7 |
  29. srslte_vec_div_fff | 53.9 102.4 178.1 327.7 1092.3 6553.6 13107.2 18724.6 21845.3 27594.1 28339.9 29537.4 12483.0 12464.5 12446.0 11966.6 |
  30. srslte_vec_max_fi | 28.4 56.9 105.0 174.3 481.9 3640.9 6553.6 10082.5 13797.1 15887.5 16644.1 17050.0 17476.3 17260.5 17439.9 17503.6 |
  31. srslte_vec_max_abs_fi | 27.7 56.9 113.8 190.5 512.0 3640.9 6553.6 10082.5 13107.2 15420.2 15650.4 16777.2 17260.5 17154.6 17242.8 17296.1 |
  32. srslte_vec_max_abs_ci | 26.9 55.4 105.0 174.3 442.8 2978.9 4681.1 7281.8 8456.3 9039.4 9446.6 9709.0 9754.2 9754.2 9771.2 9819.9 |
  33. srslte_vec_apply_cfo | 3.6 7.1 10.4 13.2 7.9 60.1 119.2 233.2 445.8 810.3 1452.3 2287.0 3292.2 4209.0 4860.1 5301.7 |
  34. srslte_cfo_correct | 4.4 7.1 10.3 13.4 8.1 60.1 118.3 233.2 448.1 821.8 1452.3 2287.0 3297.4 4165.1 4833.5 5284.2 |
  35. srslte_cfo_correct_change | 4.3 7.1 10.3 13.3 10.6 60.1 119.2 233.2 448.1 832.2 1452.3 2279.5 3297.4 4194.3 4855.9 5284.2 |
  36.  
  37.  
  38. AVX2
  39. Subroutine/MSps | 1 2 4 8 16 32 64 128 256 512 1024 2048 4096 8192 16384 32768 |
  40. ---------------------------------+----------------------------------------------------------------------------------------------------------------------------------|
  41. srslte_vec_xor_bbb | 93.1 204.8 341.3 744.7 2730.7 2978.9 2849.4 21845.3 37449.1 65536.0 95325.1 123361.9 119837.3 119837.3 50081.2 49200.0 |
  42. srslte_vec_acc_ff | 64.0 128.0 204.8 512.0 4096.0 6553.6 10922.7 14563.6 16384.0 13443.3 12483.0 10433.6 9754.2 9310.3 9162.9 9071.2 |
  43. srslte_vec_dot_prod_sss | 48.8 89.0 163.8 273.1 2730.7 6553.6 10922.7 18724.6 29127.1 32768.0 40329.8 42799.0 44150.6 45343.8 32832.1 33026.0 |
  44. srslte_vec_sum_sss | 53.9 102.4 186.2 356.2 2730.7 8192.0 13107.2 21845.3 32768.0 37449.1 43690.7 34952.5 35246.3 20213.5 18137.5 18167.0 |
  45. srslte_vec_sub_sss | 53.9 107.8 186.2 356.2 3276.8 6553.6 13107.2 16384.0 32768.0 37449.1 45590.3 34952.5 35544.9 20262.3 19350.9 19152.1 |
  46. srslte_vec_prod_sss | 53.9 102.4 195.0 356.2 2730.7 6553.6 13107.2 26214.4 32768.0 37449.1 43690.7 31775.0 35544.9 20020.5 19350.9 18517.9 |
  47. srslte_vec_acc_cc | 42.7 85.3 146.3 292.6 1638.4 4681.1 7281.8 7710.1 7281.8 4946.1 5065.6 4766.3 4624.4 4554.1 4524.6 4510.6 |
  48. srslte_vec_sum_fff | 56.9 102.4 178.1 585.1 2340.6 6553.6 13107.2 18724.6 18724.6 22795.1 17772.5 17772.5 9962.7 9697.8 9351.8 9152.9 |
  49. srslte_vec_sub_fff | 53.9 102.4 186.2 546.1 2340.6 6553.6 10922.7 16384.0 18724.6 21845.3 16131.9 17924.4 10106.8 9675.4 9362.3 9167.9 |
  50. srslte_vec_dot_prod_ccc | 17.1 23.5 29.5 234.1 910.2 2048.0 2427.3 2978.9 3276.8 3404.5 3506.9 3542.5 3569.6 3584.9 3591.0 3592.2 |
  51. srslte_vec_dot_prod_conj_ccc | 17.1 19.7 29.3 234.1 1489.5 1927.5 2621.4 3276.8 3799.2 4128.3 4297.4 4396.5 4369.1 4466.8 4483.5 4484.7 |
  52. srslte_vec_convert_fi | 68.3 120.5 215.6 327.7 5461.3 10922.7 13107.2 16384.0 20164.9 21845.3 21399.5 22075.3 22192.1 17367.7 17367.7 17050.0 |
  53. srslte_vec_convert_if | 68.3 128.0 292.6 481.9 2730.7 3276.8 3640.9 3744.9 3855.1 3971.9 3927.3 3934.6 3979.4 3929.1 3977.5 3969.1 |
  54. srslte_vec_prod_fff | 53.9 102.4 178.1 585.1 4096.0 8192.0 13107.2 18724.6 18724.6 21845.3 17772.5 17772.5 10106.8 10022.2 10180.3 9098.3 |
  55. srslte_vec_prod_cfc | 51.2 97.5 163.8 546.1 2730.7 3640.9 3855.1 3971.9 4033.0 4002.2 4002.2 3971.9 3971.9 3979.4 3965.3 3898.1 |
  56. srslte_vec_prod_ccc | 26.3 33.6 37.2 431.2 2730.7 2730.7 2978.9 2978.9 3013.1 2978.9 2987.4 2957.9 2981.0 2978.9 2980.0 2752.6 |
  57. srslte_vec_prod_ccc_split | 22.3 41.0 57.7 409.6 2730.7 4681.1 7281.8 8192.0 10082.5 11155.1 10922.7 3758.3 3725.0 3723.3 3739.9 3167.0 |
  58. srslte_vec_prod_conj_ccc | 26.3 27.7 33.9 455.1 2730.7 2184.5 2978.9 3048.2 3013.1 2978.9 2995.9 2970.5 2983.1 2982.1 2981.6 2754.9 |
  59. srslte_vec_sc_prod_ccc | 13.3 20.5 78.8 151.7 1092.3 2048.0 3449.3 5242.9 7085.0 7598.4 7884.0 8192.0 6700.2 6770.5 6594.8 6521.8 |
  60. srslte_vec_sc_prod_fff | 64.0 128.0 215.6 744.7 4096.0 8192.0 16384.0 21845.3 29127.1 32768.0 32768.0 33288.1 30174.8 16194.2 15842.5 14939.6 |
  61. srslte_vec_abs_cf | 73.1 97.5 99.9 682.7 5461.3 5461.3 5957.8 6241.5 6096.4 6026.3 5858.0 5991.9 5932.5 5979.1 5976.9 5926.3 |
  62. srslte_vec_abs_square_cf | 56.9 107.8 178.1 819.2 5461.3 8192.0 8192.0 8738.1 9039.4 9039.4 8886.2 8962.2 8559.8 8603.7 8447.7 8449.9 |
  63. srslte_vec_sc_prod_cfc | 56.9 107.8 409.6 819.2 5461.3 8192.0 10922.7 14563.6 16384.0 16912.5 12192.7 15196.8 7869.2 7869.2 7601.8 7430.1 |
  64. srslte_vec_div_ccc | 25.0 32.0 35.9 409.6 2048.0 2048.0 2730.7 2849.4 2912.7 2834.0 2788.8 2671.5 2748.6 2769.4 2713.0 2497.2 |
  65. srslte_vec_div_cfc | 51.2 97.5 157.5 512.0 2730.7 3276.8 4096.0 3971.9 3971.9 4002.2 4002.2 3869.3 3964.4 3981.3 3957.8 3912.6 |
  66. srslte_vec_div_fff | 53.9 102.4 178.1 630.2 4096.0 6553.6 10922.7 14563.6 17476.3 20164.9 14768.7 17623.1 9059.0 9020.0 9015.2 8955.0 |
  67. srslte_vec_max_fi | 41.0 78.8 157.5 356.2 2340.6 4096.0 5461.3 5698.8 5140.1 5090.2 4946.1 4934.5 4911.4 4894.2 4885.6 4889.9 |
  68. srslte_vec_max_abs_fi | 41.0 78.8 151.7 341.3 2340.6 4096.0 5461.3 5461.3 5140.1 4946.1 4832.1 4799.0 4771.7 4750.1 4748.7 4748.7 |
  69. srslte_vec_max_abs_ci | 39.4 81.9 141.2 327.7 1638.4 2730.7 3276.8 3855.1 3971.9 4064.2 4112.1 4128.3 4100.0 4116.1 4124.2 4128.8 |
  70. srslte_vec_apply_cfo | 4.1 7.1 10.3 7.3 53.9 106.4 207.4 392.4 714.3 1202.5 1826.8 2473.1 3019.7 3394.8 3568.9 3702.4 |
  71. srslte_cfo_correct | 4.4 7.1 10.1 7.2 54.1 106.4 201.6 392.4 708.5 1186.2 1780.3 2478.9 2981.0 3396.2 3578.8 3697.5 |
  72. srslte_cfo_correct_change | 4.4 7.1 10.3 9.5 53.7 106.4 206.7 392.4 712.3 1199.7 1830.0 2481.8 2966.3 3398.9 3578.0 3714.6 |
  73.  
  74. SSE
  75. Subroutine/MSps | 1 2 4 8 16 32 64 128 256 512 1024 2048 4096 8192 16384 32768 |
  76. ---------------------------------+----------------------------------------------------------------------------------------------------------------------------------|
  77. srslte_vec_xor_bbb | 102.4 204.8 341.3 682.7 1820.4 2048.0 2114.1 16384.0 29127.1 65536.0 95325.1 123361.9 116508.4 118149.4 49932.2 50081.2 |
  78. srslte_vec_acc_ff | 85.3 170.7 409.6 744.7 3276.8 6553.6 8192.0 7710.1 5825.4 6636.6 5377.3 4899.9 4707.4 4583.9 4541.7 4519.7 |
  79. srslte_vec_dot_prod_sss | 51.2 97.5 170.7 481.9 2730.7 4681.1 7281.8 11915.6 13107.2 22795.1 22795.1 23045.6 23173.0 22857.2 19508.4 19395.6 |
  80. srslte_vec_sum_sss | 56.9 113.8 195.0 630.2 2730.7 4681.1 9362.3 13107.2 14563.6 22795.1 23301.7 15307.7 15363.8 12018.1 11765.2 11744.6 |
  81. srslte_vec_sub_sss | 56.9 113.8 195.0 585.1 3276.8 5461.3 9362.3 11915.6 14563.6 21845.3 22795.1 15768.1 15592.2 12318.1 11765.2 11590.5 |
  82. srslte_vec_prod_sss | 56.9 107.8 195.0 546.1 3276.8 4681.1 8192.0 11915.6 14563.6 22795.1 22795.1 17772.5 17924.4 12192.7 11715.9 11744.6 |
  83. srslte_vec_acc_cc | 46.5 89.0 170.7 327.7 1820.4 3276.8 3449.3 2788.8 2279.5 2647.9 2432.9 2338.0 2292.0 2270.3 2258.6 2253.5 |
  84. srslte_vec_sum_fff | 41.0 107.8 292.6 585.1 2730.7 4096.0 5957.8 7281.8 7943.8 11650.8 8665.9 8594.9 6035.0 5928.3 5884.7 5861.0 |
  85. srslte_vec_sub_fff | 56.9 113.8 292.6 585.1 2730.7 4681.1 6553.6 7281.8 7943.8 11397.6 8594.9 8630.3 6168.1 5895.0 5905.4 5868.2 |
  86. srslte_vec_dot_prod_ccc | 18.6 22.3 141.2 248.2 1170.3 1310.7 1820.4 2184.5 2427.3 3216.5 3554.5 3672.8 3393.4 3375.7 3605.7 3427.8 |
  87. srslte_vec_dot_prod_conj_ccc | 18.0 21.8 141.2 240.9 1170.3 1638.4 1820.4 2221.6 2449.9 3666.3 3771.9 3751.6 3472.1 3457.8 3479.3 3482.9 |
  88. srslte_vec_convert_fi | 73.1 136.5 227.6 682.7 4096.0 6553.6 7281.8 8738.1 9362.3 13797.1 14169.9 14169.9 14315.0 13774.4 13606.8 13590.3 |
  89. srslte_vec_convert_if | 68.3 128.0 292.6 481.9 1820.4 2184.5 2520.6 2621.4 2730.7 3942.0 3731.6 3890.8 3909.0 3966.2 3917.2 3923.1 |
  90. srslte_vec_prod_fff | 56.9 107.8 292.6 585.1 2730.7 4681.1 5957.8 7281.8 7943.8 11650.8 8594.9 8594.9 6250.8 5849.8 5819.4 5878.5 |
  91. srslte_vec_prod_cfc | 51.2 102.4 292.6 512.0 2048.0 2730.7 3276.8 3196.9 3196.9 4481.1 4462.0 3718.4 3731.6 3773.6 3734.1 3711.8 |
  92. srslte_vec_prod_ccc | 28.4 34.1 341.3 546.1 2048.0 2048.0 2184.5 2114.1 2097.2 2962.1 2945.4 2461.4 2452.8 2444.2 2446.0 2392.1 |
  93. srslte_vec_prod_ccc_split | 22.8 41.0 204.8 372.4 1489.5 2340.6 2849.4 3196.9 3591.0 5090.2 4877.1 2654.6 2730.7 2868.9 2977.3 2816.4 |
  94. srslte_vec_prod_conj_ccc | 28.4 31.5 372.4 546.1 1820.4 2184.5 2114.1 2114.1 2114.1 2896.6 2920.8 2455.7 2455.7 2410.5 2426.6 2406.7 |
  95. srslte_vec_sc_prod_ccc | 13.7 42.7 83.6 106.4 744.7 1260.3 1985.9 2621.4 3196.9 4161.0 4211.1 4245.2 3775.3 3907.1 3808.7 3804.8 |
  96. srslte_vec_sc_prod_fff | 68.3 136.5 409.6 744.7 3276.8 6553.6 8192.0 10082.5 11915.6 16912.5 16644.1 16131.9 14820.9 10838.0 9886.4 9401.6 |
  97. srslte_vec_abs_cf | 85.3 102.4 372.4 744.7 2730.7 3640.9 3855.1 3971.9 4096.0 5637.5 5729.9 5745.6 5468.5 5493.5 5482.8 5439.2 |
  98. srslte_vec_abs_square_cf | 56.9 107.8 341.3 682.7 2730.7 4096.0 4369.1 5041.2 5349.9 7598.4 7598.4 7626.0 6657.6 6721.6 6665.6 6673.5 |
  99. srslte_vec_sc_prod_cfc | 60.2 136.5 273.1 512.0 2730.7 3640.9 4681.1 5461.3 5825.4 8066.0 8256.5 7681.9 5329.5 4908.5 4544.2 4525.8 |
  100. srslte_vec_div_ccc | 27.7 32.5 315.1 455.1 1365.3 1310.7 1394.4 1409.4 1417.0 1736.1 1576.8 1574.4 1578.0 1565.3 1570.6 1569.4 |
  101. srslte_vec_div_cfc | 51.2 97.5 292.6 512.0 2048.0 2730.7 3120.8 3120.8 3158.4 4443.1 4350.9 3813.0 3721.7 3753.3 3730.8 3715.5 |
  102. srslte_vec_div_fff | 56.9 113.8 292.6 585.1 2340.6 4096.0 5041.2 6241.5 7281.8 9532.5 8738.1 8924.1 6177.2 5745.6 5765.4 5627.1 |
  103. srslte_vec_max_fi | 33.0 64.0 117.0 221.4 1092.3 1560.4 1724.6 1618.2 1569.7 2157.6 2148.7 2140.0 2131.3 2119.4 2134.8 2129.6 |
  104. srslte_vec_max_abs_fi | 33.0 64.0 113.8 221.4 1092.3 1489.5 1680.4 1598.4 1533.0 2105.6 2093.0 2086.7 2082.6 2085.7 2079.5 2084.3 |
  105. srslte_vec_max_abs_ci | 33.0 60.2 113.8 199.8 963.8 1310.7 1456.4 1440.4 1424.7 1978.4 1971.0 1925.8 1954.5 1948.1 1954.0 1957.6 |
  106. srslte_vec_apply_cfo | 3.3 5.7 5.9 23.7 59.6 113.0 206.1 346.8 538.3 1038.2 1274.1 1420.8 1526.3 1570.9 1617.9 1635.9 |
  107. srslte_cfo_correct | 3.5 5.7 4.5 23.6 45.9 86.2 164.3 288.1 650.5 934.6 1195.6 1368.0 1506.0 1550.6 1609.9 1630.4 |
  108. srslte_cfo_correct_change | 3.5 5.6 4.5 23.6 46.0 88.3 164.7 288.1 650.5 934.6 1191.6 1365.3 1508.2 1576.5 1610.3 1630.3 |
Add Comment
Please, Sign In to add comment