Created
March 19, 2019 11:59
-
-
Save kadirmalak/954ff179d7a96d266eaea49f0855ae5e to your computer and use it in GitHub Desktop.
export OMP_NUM_THREADS=6; export OMP_PROC_BIND="CLOSE"; export GOMP_CPU_AFFINITY="0 1 2 3 4 5"
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
> export OMP_NUM_THREADS=6 | |
> export OMP_PROC_BIND="CLOSE" | |
> export GOMP_CPU_AFFINITY="0 1 2 3 4 5" | |
> ./runtests --gtest_filter="PlaygroundTests.FastScalar" | |
Note: Google Test filter = PlaygroundTests.FastScalar | |
[==========] Running 1 test from 1 test case. | |
[----------] Global test environment set-up. | |
[----------] 1 test from PlaygroundTests | |
[ RUN ] PlaygroundTests.FastScalar | |
Scalar Addition - x.add(3.14159265359) | |
TestName OpNum Warmup NumIter DataType Inplace Shape Strides Axis Orders avg (us) median (us) min (us) max (us) stdev (us) | |
sAdd 0 10 1000 FLOAT false [16] [1]/[1] N/A c/c 0 0 0 6 0.19 | |
sAdd 0 10 1000 FLOAT true [16] [1]/[1] N/A c/c 0 0 0 5 0.16 | |
sAdd 0 10 1000 FLOAT false [64] [1]/[1] N/A c/c 0 0 0 4 0.13 | |
sAdd 0 10 1000 FLOAT true [64] [1]/[1] N/A c/c 0 0 0 5 0.16 | |
sAdd 0 10 1000 FLOAT false [256] [1]/[1] N/A c/c 0 0 0 4 0.13 | |
sAdd 0 10 1000 FLOAT true [256] [1]/[1] N/A c/c 0 0 0 4 0.13 | |
sAdd 0 10 1000 FLOAT false [1024] [1]/[1] N/A c/c 0 0 0 1 0.03 | |
sAdd 0 10 1000 FLOAT true [1024] [1]/[1] N/A c/c 0 0 0 4 0.13 | |
sAdd 0 10 1000 FLOAT false [4096] [1]/[1] N/A c/c 4 2 2 2291 72.35 | |
sAdd 0 10 1000 FLOAT true [4096] [1]/[1] N/A c/c 2 2 2 8 0.45 | |
sAdd 0 10 1000 FLOAT false [16384] [1]/[1] N/A c/c 3 3 3 228 7.11 | |
sAdd 0 10 1000 FLOAT true [16384] [1]/[1] N/A c/c 3 3 3 7 0.18 | |
sAdd 0 10 1000 FLOAT false [65536] [1]/[1] N/A c/c 4 5 3 17 0.93 | |
sAdd 0 10 1000 FLOAT true [65536] [1]/[1] N/A c/c 3 3 3 7 0.42 | |
sAdd 0 10 1000 FLOAT false [262144] [1]/[1] N/A c/c 7 7 7 15 0.41 | |
sAdd 0 10 1000 FLOAT true [262144] [1]/[1] N/A c/c 7 7 6 14 0.34 | |
sAdd 0 10 1000 FLOAT false [1048576] [1]/[1] N/A c/c 29 30 29 41 0.89 | |
sAdd 0 10 1000 FLOAT true [1048576] [1]/[1] N/A c/c 22 22 22 32 0.79 | |
sAdd 0 10 1000 FLOAT false [4194304] [1]/[1] N/A c/c 3126 3126 2947 3403 15.99 | |
sAdd 0 10 1000 FLOAT true [4194304] [1]/[1] N/A c/c 234 231 220 275 9.31 | |
sAdd 0 10 1000 FLOAT false [16777216] [1]/[1] N/A c/c 12380 12379 12357 12682 14.79 | |
sAdd 0 10 1000 FLOAT true [16777216] [1]/[1] N/A c/c 8502 8503 8444 8582 18.84 | |
sAdd 0 10 1000 FLOAT false [67108864] [1]/[1] N/A c/c 49702 49701 49650 49817 20.19 | |
sAdd 0 10 1000 FLOAT true [67108864] [1]/[1] N/A c/c 33957 33953 33871 34133 35.72 | |
sAdd 0 10 1000 FLOAT false [268435456] [1]/[1] N/A c/c 198437 198436 198289 198681 47.15 | |
sAdd 0 10 1000 FLOAT true [268435456] [1]/[1] N/A c/c 135656 135645 135524 135965 59.14 | |
sAdd 0 10 1000 FLOAT false [1073741824] [1]/[1] N/A c/c 794002 794000 793571 795473 172.00 | |
sAdd 0 10 1000 FLOAT true [1073741824] [1]/[1] N/A c/c 542388 542367 542051 543108 159.63 | |
Scalar Subtraction - x.sub(3.14159265359) | |
TestName OpNum Warmup NumIter DataType Inplace Shape Strides Axis Orders avg (us) median (us) min (us) max (us) stdev (us) | |
sSub 1 10 1000 FLOAT false [16] [1]/[1] N/A c/c 0 0 0 9 0.29 | |
sSub 1 10 1000 FLOAT true [16] [1]/[1] N/A c/c 0 0 0 8 0.25 | |
sSub 1 10 1000 FLOAT false [64] [1]/[1] N/A c/c 0 0 0 7 0.22 | |
sSub 1 10 1000 FLOAT true [64] [1]/[1] N/A c/c 0 0 0 5 0.16 | |
sSub 1 10 1000 FLOAT false [256] [1]/[1] N/A c/c 0 0 0 6 0.19 | |
sSub 1 10 1000 FLOAT true [256] [1]/[1] N/A c/c 0 0 0 8 0.25 | |
sSub 1 10 1000 FLOAT false [1024] [1]/[1] N/A c/c 0 0 0 0 0.00 | |
sSub 1 10 1000 FLOAT true [1024] [1]/[1] N/A c/c 0 0 0 4 0.13 | |
sSub 1 10 1000 FLOAT false [4096] [1]/[1] N/A c/c 2 2 2 16 0.46 | |
sSub 1 10 1000 FLOAT true [4096] [1]/[1] N/A c/c 1 2 1 6 0.30 | |
sSub 1 10 1000 FLOAT false [16384] [1]/[1] N/A c/c 2 3 2 14 0.61 | |
sSub 1 10 1000 FLOAT true [16384] [1]/[1] N/A c/c 3 3 3 9 0.30 | |
sSub 1 10 1000 FLOAT false [65536] [1]/[1] N/A c/c 5 6 4 17 1.33 | |
sSub 1 10 1000 FLOAT true [65536] [1]/[1] N/A c/c 4 4 4 8 0.21 | |
sSub 1 10 1000 FLOAT false [262144] [1]/[1] N/A c/c 10 10 10 18 0.46 | |
sSub 1 10 1000 FLOAT true [262144] [1]/[1] N/A c/c 10 10 10 17 0.37 | |
sSub 1 10 1000 FLOAT false [1048576] [1]/[1] N/A c/c 35 35 34 42 0.92 | |
sSub 1 10 1000 FLOAT true [1048576] [1]/[1] N/A c/c 34 34 33 42 0.80 | |
sSub 1 10 1000 FLOAT false [4194304] [1]/[1] N/A c/c 3099 3098 3081 3353 11.27 | |
sSub 1 10 1000 FLOAT true [4194304] [1]/[1] N/A c/c 165 160 155 268 17.04 | |
sSub 1 10 1000 FLOAT false [16777216] [1]/[1] N/A c/c 12389 12388 12361 12705 14.34 | |
sSub 1 10 1000 FLOAT true [16777216] [1]/[1] N/A c/c 8498 8498 8438 8577 19.00 | |
sSub 1 10 1000 FLOAT false [67108864] [1]/[1] N/A c/c 49647 49646 49597 49757 20.47 | |
sSub 1 10 1000 FLOAT true [67108864] [1]/[1] N/A c/c 33900 33896 33805 34102 33.93 | |
sSub 1 10 1000 FLOAT false [268435456] [1]/[1] N/A c/c 198424 198421 198291 198693 52.77 | |
sSub 1 10 1000 FLOAT true [268435456] [1]/[1] N/A c/c 135547 135540 135364 136058 74.17 | |
sSub 1 10 1000 FLOAT false [1073741824] [1]/[1] N/A c/c 793128 793118 792668 793852 159.70 | |
sSub 1 10 1000 FLOAT true [1073741824] [1]/[1] N/A c/c 541863 541848 541411 542707 177.09 | |
Scalar Multiplication - x.mul(3.14159265359) | |
TestName OpNum Warmup NumIter DataType Inplace Shape Strides Axis Orders avg (us) median (us) min (us) max (us) stdev (us) | |
sMul 2 10 1000 FLOAT false [16] [1]/[1] N/A c/c 0 0 0 8 0.26 | |
sMul 2 10 1000 FLOAT true [16] [1]/[1] N/A c/c 0 0 0 8 0.25 | |
sMul 2 10 1000 FLOAT false [64] [1]/[1] N/A c/c 0 0 0 5 0.16 | |
sMul 2 10 1000 FLOAT true [64] [1]/[1] N/A c/c 0 0 0 6 0.19 | |
sMul 2 10 1000 FLOAT false [256] [1]/[1] N/A c/c 0 0 0 5 0.16 | |
sMul 2 10 1000 FLOAT true [256] [1]/[1] N/A c/c 0 0 0 1 0.03 | |
sMul 2 10 1000 FLOAT false [1024] [1]/[1] N/A c/c 0 0 0 5 0.16 | |
sMul 2 10 1000 FLOAT true [1024] [1]/[1] N/A c/c 0 0 0 4 0.13 | |
sMul 2 10 1000 FLOAT false [4096] [1]/[1] N/A c/c 2 2 2 11 0.35 | |
sMul 2 10 1000 FLOAT true [4096] [1]/[1] N/A c/c 2 2 2 6 0.16 | |
sMul 2 10 1000 FLOAT false [16384] [1]/[1] N/A c/c 2 2 2 13 0.73 | |
sMul 2 10 1000 FLOAT true [16384] [1]/[1] N/A c/c 3 3 3 8 0.23 | |
sMul 2 10 1000 FLOAT false [65536] [1]/[1] N/A c/c 5 6 4 17 1.02 | |
sMul 2 10 1000 FLOAT true [65536] [1]/[1] N/A c/c 3 4 3 11 0.56 | |
sMul 2 10 1000 FLOAT false [262144] [1]/[1] N/A c/c 9 9 8 16 0.41 | |
sMul 2 10 1000 FLOAT true [262144] [1]/[1] N/A c/c 7 7 7 15 0.58 | |
sMul 2 10 1000 FLOAT false [1048576] [1]/[1] N/A c/c 34 34 33 44 1.31 | |
sMul 2 10 1000 FLOAT true [1048576] [1]/[1] N/A c/c 22 22 22 29 0.63 | |
sMul 2 10 1000 FLOAT false [4194304] [1]/[1] N/A c/c 3102 3101 3082 3189 7.70 | |
sMul 2 10 1000 FLOAT true [4194304] [1]/[1] N/A c/c 129 128 122 164 5.60 | |
sMul 2 10 1000 FLOAT false [16777216] [1]/[1] N/A c/c 12369 12368 12337 12745 18.62 | |
sMul 2 10 1000 FLOAT true [16777216] [1]/[1] N/A c/c 8499 8499 8453 8725 18.73 | |
sMul 2 10 1000 FLOAT false [67108864] [1]/[1] N/A c/c 49635 49635 49575 49749 21.65 | |
sMul 2 10 1000 FLOAT true [67108864] [1]/[1] N/A c/c 33940 33936 33851 34089 32.57 | |
sMul 2 10 1000 FLOAT false [268435456] [1]/[1] N/A c/c 198404 198403 198267 198591 45.87 | |
sMul 2 10 1000 FLOAT true [268435456] [1]/[1] N/A c/c 135654 135647 135529 135884 53.57 | |
sMul 2 10 1000 FLOAT false [1073741824] [1]/[1] N/A c/c 794082 794072 793560 795066 149.69 | |
sMul 2 10 1000 FLOAT true [1073741824] [1]/[1] N/A c/c 542314 542296 541939 542950 165.17 | |
Scalar Division - x.div(3.14159265359) | |
TestName OpNum Warmup NumIter DataType Inplace Shape Strides Axis Orders avg (us) median (us) min (us) max (us) stdev (us) | |
sDiv 3 10 1000 FLOAT false [16] [1]/[1] N/A c/c 0 0 0 1 0.03 | |
sDiv 3 10 1000 FLOAT true [16] [1]/[1] N/A c/c 0 0 0 12 0.38 | |
sDiv 3 10 1000 FLOAT false [64] [1]/[1] N/A c/c 0 0 0 5 0.16 | |
sDiv 3 10 1000 FLOAT true [64] [1]/[1] N/A c/c 0 0 0 0 0.00 | |
sDiv 3 10 1000 FLOAT false [256] [1]/[1] N/A c/c 0 0 0 5 0.16 | |
sDiv 3 10 1000 FLOAT true [256] [1]/[1] N/A c/c 0 0 0 5 0.16 | |
sDiv 3 10 1000 FLOAT false [1024] [1]/[1] N/A c/c 0 0 0 0 0.00 | |
sDiv 3 10 1000 FLOAT true [1024] [1]/[1] N/A c/c 0 0 0 4 0.13 | |
sDiv 3 10 1000 FLOAT false [4096] [1]/[1] N/A c/c 1 2 1 13 0.41 | |
sDiv 3 10 1000 FLOAT true [4096] [1]/[1] N/A c/c 2 2 2 7 0.21 | |
sDiv 3 10 1000 FLOAT false [16384] [1]/[1] N/A c/c 3 3 3 11 0.45 | |
sDiv 3 10 1000 FLOAT true [16384] [1]/[1] N/A c/c 3 3 3 8 0.19 | |
sDiv 3 10 1000 FLOAT false [65536] [1]/[1] N/A c/c 5 6 4 16 1.04 | |
sDiv 3 10 1000 FLOAT true [65536] [1]/[1] N/A c/c 3 3 3 7 0.50 | |
sDiv 3 10 1000 FLOAT false [262144] [1]/[1] N/A c/c 8 9 8 17 0.47 | |
sDiv 3 10 1000 FLOAT true [262144] [1]/[1] N/A c/c 7 7 7 14 0.34 | |
sDiv 3 10 1000 FLOAT false [1048576] [1]/[1] N/A c/c 33 33 33 41 1.10 | |
sDiv 3 10 1000 FLOAT true [1048576] [1]/[1] N/A c/c 22 22 22 29 0.61 | |
sDiv 3 10 1000 FLOAT false [4194304] [1]/[1] N/A c/c 3109 3108 3093 3146 7.11 | |
sDiv 3 10 1000 FLOAT true [4194304] [1]/[1] N/A c/c 137 133 128 221 12.75 | |
sDiv 3 10 1000 FLOAT false [16777216] [1]/[1] N/A c/c 12389 12388 12365 12584 11.53 | |
sDiv 3 10 1000 FLOAT true [16777216] [1]/[1] N/A c/c 8503 8503 8457 8699 18.62 | |
sDiv 3 10 1000 FLOAT false [67108864] [1]/[1] N/A c/c 49657 49656 49601 49752 20.30 | |
sDiv 3 10 1000 FLOAT true [67108864] [1]/[1] N/A c/c 33934 33931 33866 34125 32.36 | |
sDiv 3 10 1000 FLOAT false [268435456] [1]/[1] N/A c/c 198555 198553 198430 198711 41.72 | |
sDiv 3 10 1000 FLOAT true [268435456] [1]/[1] N/A c/c 135606 135597 135480 135881 61.33 | |
sDiv 3 10 1000 FLOAT false [1073741824] [1]/[1] N/A c/c 793924 793922 793544 794391 138.94 | |
sDiv 3 10 1000 FLOAT true [1073741824] [1]/[1] N/A c/c 542327 542318 541987 542847 150.03 | |
Scalar Power - x.pow(3.14159265359) | |
TestName OpNum Warmup NumIter DataType Inplace Shape Strides Axis Orders avg (us) median (us) min (us) max (us) stdev (us) | |
sPow 31 10 1000 FLOAT false [16] [1]/[1] N/A c/c 0 0 0 1 0.03 | |
sPow 31 10 1000 FLOAT true [16] [1]/[1] N/A c/c 0 0 0 9 0.28 | |
sPow 31 10 1000 FLOAT false [64] [1]/[1] N/A c/c 1 1 1 5 0.13 | |
sPow 31 10 1000 FLOAT true [64] [1]/[1] N/A c/c 1 1 1 5 0.13 | |
sPow 31 10 1000 FLOAT false [256] [1]/[1] N/A c/c 2 2 2 6 0.13 | |
sPow 31 10 1000 FLOAT true [256] [1]/[1] N/A c/c 2 2 2 6 0.18 | |
sPow 31 10 1000 FLOAT false [1024] [1]/[1] N/A c/c 6 6 6 11 0.23 | |
sPow 31 10 1000 FLOAT true [1024] [1]/[1] N/A c/c 6 6 6 10 0.21 | |
sPow 31 10 1000 FLOAT false [4096] [1]/[1] N/A c/c 7 7 7 20 0.57 | |
sPow 31 10 1000 FLOAT true [4096] [1]/[1] N/A c/c 7 7 7 11 0.39 | |
sPow 31 10 1000 FLOAT false [16384] [1]/[1] N/A c/c 17 17 17 39 3.10 | |
sPow 31 10 1000 FLOAT true [16384] [1]/[1] N/A c/c 17 17 17 25 0.56 | |
sPow 31 10 1000 FLOAT false [65536] [1]/[1] N/A c/c 61 61 61 69 1.01 | |
sPow 31 10 1000 FLOAT true [65536] [1]/[1] N/A c/c 61 61 61 68 0.96 | |
sPow 31 10 1000 FLOAT false [262144] [1]/[1] N/A c/c 239 239 236 247 1.53 | |
sPow 31 10 1000 FLOAT true [262144] [1]/[1] N/A c/c 237 237 236 246 1.52 | |
sPow 31 10 1000 FLOAT false [1048576] [1]/[1] N/A c/c 946 946 943 957 1.65 | |
sPow 31 10 1000 FLOAT true [1048576] [1]/[1] N/A c/c 944 944 939 1044 3.57 | |
sPow 31 10 1000 FLOAT false [4194304] [1]/[1] N/A c/c 3800 3797 3781 4519 25.39 | |
sPow 31 10 1000 FLOAT true [4194304] [1]/[1] N/A c/c 3766 3764 3758 4417 22.43 | |
sPow 31 10 1000 FLOAT false [16777216] [1]/[1] N/A c/c 15194 15192 15149 16031 35.73 | |
sPow 31 10 1000 FLOAT true [16777216] [1]/[1] N/A c/c 15192 15192 15159 15896 31.31 | |
sPow 31 10 1000 FLOAT false [67108864] [1]/[1] N/A c/c 60404 60402 60379 60796 25.41 | |
sPow 31 10 1000 FLOAT true [67108864] [1]/[1] N/A c/c 60961 60735 60683 65050 946.87 | |
sPow 31 10 1000 FLOAT false [268435456] [1]/[1] N/A c/c 241609 241594 241508 243712 103.62 | |
sPow 31 10 1000 FLOAT true [268435456] [1]/[1] N/A c/c 242968 242962 242861 243705 51.78 | |
sPow 31 10 1000 FLOAT false [1073741824] [1]/[1] N/A c/c 966731 966243 965923 972188 1267.25 | |
sPow 31 10 1000 FLOAT true [1073741824] [1]/[1] N/A c/c 971808 971836 971330 972683 214.29 | |
[ OK ] PlaygroundTests.FastScalar (9813258 ms) | |
[----------] 1 test from PlaygroundTests (9813258 ms total) | |
[----------] Global test environment tear-down | |
[==========] 1 test from 1 test case ran. (9813258 ms total) | |
[ PASSED ] 1 test. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment