F# Tensor 0.4.9

Hostname:MINT2WIN
CPU:Intel(R) Xeon(R) CPU E5-1650 v2 @ 3.50GHz
GPU:nVidia Quadro K2200
OS:Microsoft Windows 10.0.17134
Runtime:.NET SDK 2.1.300-preview2-008533
Time:2018-05-01 00:00:00Z

NumPy 1.14.0

Hostname:MINT2WIN
CPU:Intel(R) Xeon(R) CPU E5-1650 v2 @ 3.50GHz
GPU:nVidia Quadro K2200
OS:Microsoft Windows 10.0.17134
Runtime:Anaconda3 5.1.0
Time:2018-05-01 00:00:00Z

FunctionShapeTypeDeviceMeanStdDevMeanStdDev
zeros1000x1000boolHost0.08 ms±0.01 ms——
int32Host0.17 ms±0.00 ms0.27 ms±0.01 ms
Cuda0.60 ms±0.02 ms——
int64Host0.41 ms±0.00 ms0.56 ms±0.01 ms
Cuda0.67 ms±0.04 ms——
singleHost0.16 ms±0.01 ms0.27 ms±0.00 ms
Cuda0.61 ms±0.02 ms——
doubleHost0.42 ms±0.00 ms0.58 ms±0.01 ms
Cuda0.72 ms±0.09 ms——
2000x2000boolHost0.17 ms±0.00 ms——
int32Host1.07 ms±0.05 ms1.59 ms±0.02 ms
Cuda1.13 ms±0.03 ms——
int64Host2.62 ms±0.05 ms3.56 ms±0.04 ms
Cuda2.46 ms±0.74 ms——
singleHost1.13 ms±0.03 ms1.59 ms±0.02 ms
Cuda1.14 ms±0.02 ms——
doubleHost2.69 ms±0.24 ms3.56 ms±0.04 ms
Cuda2.35 ms±0.64 ms——
4000x4000boolHost1.09 ms±0.02 ms——
int32Host2.35 ms±0.09 ms0.01 ms±0.00 ms
Cuda3.79 ms±1.60 ms——
int64Host4.64 ms±0.15 ms0.01 ms±0.00 ms
Cuda9.13 ms±1.35 ms——
singleHost2.46 ms±0.06 ms0.01 ms±0.00 ms
Cuda5.06 ms±0.93 ms——
doubleHost5.15 ms±0.14 ms0.01 ms±0.00 ms
Cuda8.41 ms±3.11 ms——
ones1000x1000int32Host2.05 ms±0.02 ms0.28 ms±0.00 ms
Cuda0.86 ms±0.04 ms——
int64Host4.26 ms±0.07 ms0.66 ms±0.01 ms
Cuda0.65 ms±0.01 ms——
singleHost2.14 ms±0.05 ms0.28 ms±0.00 ms
Cuda0.64 ms±0.04 ms——
doubleHost4.18 ms±0.07 ms0.66 ms±0.01 ms
Cuda0.84 ms±0.03 ms——
2000x2000int32Host8.87 ms±0.13 ms1.60 ms±0.02 ms
Cuda1.12 ms±0.02 ms——
int64Host18.44 ms±0.54 ms3.54 ms±0.01 ms
Cuda2.32 ms±0.40 ms——
singleHost8.81 ms±0.04 ms1.61 ms±0.02 ms
Cuda1.11 ms±0.02 ms——
doubleHost18.91 ms±0.32 ms3.54 ms±0.01 ms
Cuda2.23 ms±0.07 ms——
4000x4000int32Host30.20 ms±0.03 ms28.85 ms±0.03 ms
Cuda5.52 ms±1.47 ms——
int64Host61.23 ms±0.14 ms61.94 ms±0.06 ms
Cuda10.67 ms±0.68 ms——
singleHost31.15 ms±0.07 ms28.86 ms±0.02 ms
Cuda3.86 ms±1.24 ms——
doubleHost60.22 ms±0.12 ms61.97 ms±0.06 ms
Cuda8.29 ms±2.86 ms——
arange1000x1000int32Host9.23 ms±0.40 ms——
Cuda0.64 ms±0.04 ms——
int64Host11.70 ms±0.32 ms——
Cuda0.64 ms±0.03 ms——
singleHost9.71 ms±0.06 ms——
Cuda0.56 ms±0.01 ms——
doubleHost11.40 ms±0.21 ms——
Cuda0.80 ms±0.02 ms——
2000x2000int32Host35.72 ms±1.65 ms——
Cuda1.21 ms±0.05 ms——
int64Host43.38 ms±1.18 ms——
Cuda2.29 ms±0.03 ms——
singleHost37.54 ms±0.38 ms——
Cuda1.15 ms±0.04 ms——
doubleHost43.32 ms±0.02 ms——
Cuda2.33 ms±0.06 ms——
4000x4000int32Host149.09 ms±3.17 ms——
Cuda3.65 ms±0.98 ms——
int64Host169.28 ms±0.17 ms——
Cuda10.61 ms±0.45 ms——
singleHost148.52 ms±0.11 ms——
Cuda3.13 ms±2.01 ms——
doubleHost165.32 ms±0.27 ms——
Cuda10.82 ms±0.34 ms——
copy1000x1000boolHost0.29 ms±0.01 ms——
Cuda0.74 ms±0.05 ms——
int32Host2.38 ms±0.04 ms0.38 ms±0.01 ms
Cuda0.87 ms±0.03 ms——
int64Host5.19 ms±0.11 ms0.79 ms±0.01 ms
Cuda1.02 ms±0.04 ms——
singleHost2.37 ms±0.05 ms0.38 ms±0.01 ms
Cuda0.76 ms±0.02 ms——
doubleHost5.26 ms±0.28 ms0.80 ms±0.01 ms
Cuda0.96 ms±0.05 ms——
2000x2000boolHost2.46 ms±0.07 ms——
Cuda1.21 ms±0.04 ms——
int32Host10.34 ms±0.18 ms1.77 ms±0.01 ms
Cuda1.26 ms±0.04 ms——
int64Host18.47 ms±0.10 ms3.60 ms±0.01 ms
Cuda2.01 ms±0.11 ms——
singleHost10.58 ms±0.30 ms1.82 ms±0.03 ms
Cuda1.33 ms±0.05 ms——
doubleHost18.35 ms±0.04 ms3.65 ms±0.01 ms
Cuda2.08 ms±0.10 ms——
4000x4000boolHost10.86 ms±0.49 ms——
Cuda4.01 ms±1.23 ms——
int32Host37.76 ms±0.02 ms40.94 ms±0.02 ms
Cuda5.53 ms±1.02 ms——
int64Host75.04 ms±0.22 ms82.02 ms±0.04 ms
Cuda10.66 ms±0.65 ms——
singleHost37.39 ms±0.07 ms40.95 ms±0.04 ms
Cuda3.55 ms±0.21 ms——
doubleHost75.84 ms±0.21 ms82.04 ms±0.02 ms
Cuda10.85 ms±0.35 ms——
negate1000x1000boolCuda0.87 ms±0.04 ms——
int32Host2.36 ms±0.05 ms0.46 ms±0.01 ms
Cuda0.97 ms±0.05 ms——
int64Host5.09 ms±0.19 ms1.27 ms±0.01 ms
Cuda1.04 ms±0.04 ms——
singleHost2.32 ms±0.03 ms0.45 ms±0.01 ms
Cuda0.90 ms±0.04 ms——
doubleHost4.96 ms±0.31 ms1.28 ms±0.01 ms
Cuda0.95 ms±0.05 ms——
2000x2000boolCuda1.51 ms±0.06 ms——
int32Host10.39 ms±0.54 ms2.78 ms±0.01 ms
Cuda1.52 ms±0.03 ms——
int64Host17.69 ms±0.16 ms5.85 ms±0.76 ms
Cuda2.11 ms±0.16 ms——
singleHost9.86 ms±0.29 ms2.88 ms±0.02 ms
Cuda1.55 ms±0.07 ms——
doubleHost17.61 ms±0.07 ms5.65 ms±0.01 ms
Cuda2.48 ms±0.16 ms——
4000x4000boolCuda4.21 ms±0.14 ms——
int32Host35.61 ms±0.10 ms33.18 ms±0.10 ms
Cuda4.30 ms±0.12 ms——
int64Host71.59 ms±0.95 ms65.78 ms±0.04 ms
Cuda10.94 ms±0.36 ms——
singleHost36.18 ms±0.24 ms33.74 ms±0.07 ms
Cuda4.88 ms±0.23 ms——
doubleHost71.45 ms±1.32 ms66.81 ms±0.06 ms
Cuda11.16 ms±0.62 ms——
add1000x1000boolCuda1.02 ms±0.06 ms——
int32Host2.61 ms±0.08 ms0.78 ms±0.01 ms
Cuda1.01 ms±0.04 ms——
int64Host6.03 ms±0.37 ms1.97 ms±0.11 ms
Cuda1.15 ms±0.04 ms——
singleHost2.61 ms±0.07 ms0.79 ms±0.01 ms
Cuda1.02 ms±0.04 ms——
doubleHost5.83 ms±0.18 ms1.93 ms±0.01 ms
Cuda1.15 ms±0.05 ms——
2000x2000boolCuda1.82 ms±0.07 ms——
int32Host11.11 ms±0.42 ms3.89 ms±0.01 ms
Cuda1.81 ms±0.11 ms——
int64Host19.92 ms±0.21 ms8.27 ms±0.81 ms
Cuda2.58 ms±0.06 ms——
singleHost11.06 ms±0.33 ms3.88 ms±0.01 ms
Cuda1.80 ms±0.05 ms——
doubleHost19.54 ms±0.32 ms7.81 ms±0.01 ms
Cuda2.54 ms±0.09 ms——
4000x4000boolCuda5.11 ms±0.12 ms——
int32Host39.14 ms±0.10 ms36.95 ms±0.08 ms
Cuda5.06 ms±0.04 ms——
int64Host82.45 ms±4.69 ms73.74 ms±0.02 ms
Cuda9.79 ms±1.28 ms——
singleHost39.32 ms±0.23 ms37.40 ms±0.08 ms
Cuda4.95 ms±0.07 ms——
doubleHost76.73 ms±2.82 ms74.86 ms±0.02 ms
Cuda11.85 ms±3.39 ms——
subtract1000x1000boolCuda1.01 ms±0.05 ms——
int32Host2.81 ms±0.16 ms0.78 ms±0.01 ms
Cuda0.98 ms±0.03 ms——
int64Host5.74 ms±0.22 ms1.95 ms±0.11 ms
Cuda1.12 ms±0.04 ms——
singleHost2.54 ms±0.02 ms0.79 ms±0.01 ms
Cuda0.98 ms±0.01 ms——
doubleHost5.91 ms±0.23 ms1.92 ms±0.01 ms
Cuda1.14 ms±0.05 ms——
2000x2000boolCuda1.78 ms±0.04 ms——
int32Host10.88 ms±0.32 ms3.91 ms±0.02 ms
Cuda1.78 ms±0.09 ms——
int64Host19.54 ms±0.30 ms8.27 ms±0.81 ms
Cuda2.56 ms±0.03 ms——
singleHost10.81 ms±0.23 ms3.90 ms±0.01 ms
Cuda1.79 ms±0.07 ms——
doubleHost19.31 ms±0.04 ms7.81 ms±0.01 ms
Cuda2.57 ms±0.06 ms——
4000x4000boolCuda5.08 ms±0.07 ms——
int32Host40.09 ms±0.37 ms36.97 ms±0.08 ms
Cuda4.97 ms±0.05 ms——
int64Host76.80 ms±0.22 ms73.91 ms±0.01 ms
Cuda8.69 ms±0.30 ms——
singleHost39.44 ms±0.03 ms37.43 ms±0.08 ms
Cuda5.05 ms±0.12 ms——
doubleHost78.04 ms±1.11 ms74.93 ms±0.03 ms
Cuda14.08 ms±0.14 ms——
multiply1000x1000boolCuda0.93 ms±0.02 ms——
int32Host2.66 ms±0.11 ms0.78 ms±0.01 ms
Cuda0.99 ms±0.03 ms——
int64Host12.78 ms±0.65 ms1.91 ms±0.12 ms
Cuda1.13 ms±0.04 ms——
singleHost2.78 ms±0.08 ms0.78 ms±0.01 ms
Cuda1.00 ms±0.03 ms——
doubleHost5.75 ms±0.11 ms1.93 ms±0.01 ms
Cuda1.14 ms±0.03 ms——
2000x2000boolCuda1.75 ms±0.02 ms——
int32Host11.41 ms±0.39 ms3.91 ms±0.02 ms
Cuda1.83 ms±0.08 ms——
int64Host45.04 ms±0.58 ms7.90 ms±0.88 ms
Cuda2.55 ms±0.10 ms——
singleHost11.29 ms±0.18 ms3.88 ms±0.01 ms
Cuda1.79 ms±0.05 ms——
doubleHost19.92 ms±0.14 ms7.83 ms±0.03 ms
Cuda2.59 ms±0.04 ms——
4000x4000boolCuda5.02 ms±0.11 ms——
int32Host39.89 ms±0.21 ms37.25 ms±0.08 ms
Cuda5.11 ms±0.15 ms——
int64Host187.02 ms±10.77 ms77.64 ms±0.01 ms
Cuda10.28 ms±0.68 ms——
singleHost39.47 ms±0.01 ms37.36 ms±0.06 ms
Cuda5.02 ms±0.05 ms——
doubleHost78.73 ms±1.30 ms74.78 ms±0.02 ms
Cuda8.60 ms±0.30 ms——
divide1000x1000boolCuda1.08 ms±0.02 ms——
int32Host——4.74 ms±0.01 ms
Cuda1.06 ms±0.05 ms——
int64Host——5.58 ms±0.01 ms
Cuda1.40 ms±0.05 ms——
singleHost2.58 ms±0.03 ms0.90 ms±0.01 ms
Cuda1.11 ms±0.03 ms——
doubleHost5.98 ms±0.23 ms3.54 ms±0.01 ms
Cuda1.18 ms±0.03 ms——
2000x2000boolCuda1.97 ms±0.06 ms——
int32Host——18.89 ms±0.01 ms
Cuda1.98 ms±0.05 ms——
int64Host——22.76 ms±0.10 ms
Cuda3.26 ms±0.05 ms——
singleHost11.04 ms±0.21 ms3.87 ms±0.01 ms
Cuda1.94 ms±0.11 ms——
doubleHost21.78 ms±0.16 ms14.22 ms±0.02 ms
Cuda2.66 ms±0.05 ms——
4000x4000boolCuda5.78 ms±0.09 ms——
int32Host——130.69 ms±0.02 ms
Cuda5.90 ms±0.08 ms——
int64Host——142.73 ms±0.04 ms
Cuda11.17 ms±0.12 ms——
singleHost40.92 ms±0.93 ms43.09 ms±0.02 ms
Cuda5.55 ms±0.11 ms——
doubleHost87.25 ms±1.90 ms112.29 ms±0.03 ms
Cuda9.89 ms±0.30 ms——
power1000x1000singleHost23.07 ms±0.57 ms83.52 ms±0.03 ms
Cuda1.21 ms±0.05 ms——
doubleHost23.60 ms±0.59 ms67.25 ms±0.03 ms
Cuda4.98 ms±0.13 ms——
2000x2000singleHost85.71 ms±0.98 ms333.76 ms±0.08 ms
Cuda2.53 ms±0.06 ms——
doubleHost89.66 ms±3.49 ms267.09 ms±0.09 ms
Cuda16.55 ms±0.06 ms——
4000x4000singleHost334.92 ms±1.75 ms1365.24 ms±0.32 ms
Cuda7.72 ms±0.09 ms——
doubleHost348.07 ms±4.73 ms1135.26 ms±0.19 ms
Cuda63.69 ms±0.57 ms——
modulo1000x1000int32Host——16.17 ms±0.01 ms
Cuda1.03 ms±0.05 ms——
int64Host——27.20 ms±0.01 ms
Cuda1.42 ms±0.06 ms——
singleHost8.16 ms±0.23 ms38.89 ms±0.06 ms
Cuda1.30 ms±0.02 ms——
doubleHost8.99 ms±0.57 ms38.64 ms±0.03 ms
Cuda1.25 ms±0.04 ms——
2000x2000int32Host——64.71 ms±0.03 ms
Cuda2.02 ms±0.06 ms——
int64Host——108.82 ms±0.03 ms
Cuda3.20 ms±0.04 ms——
singleHost28.89 ms±0.80 ms155.63 ms±0.09 ms
Cuda2.80 ms±0.03 ms——
doubleHost29.32 ms±0.58 ms154.72 ms±0.05 ms
Cuda2.86 ms±0.06 ms——
4000x4000int32Host——287.69 ms±0.11 ms
Cuda5.83 ms±0.03 ms——
int64Host——492.06 ms±0.25 ms
Cuda11.10 ms±0.13 ms——
singleHost108.78 ms±1.37 ms651.76 ms±0.22 ms
Cuda9.16 ms±0.08 ms——
doubleHost110.98 ms±1.32 ms678.19 ms±0.15 ms
Cuda9.30 ms±0.09 ms——
dot1000x1000int32Host——473.22 ms±0.07 ms
int64Host——1353.18 ms±0.17 ms
singleHost21.14 ms±0.17 ms10.13 ms±0.01 ms
Cuda3.32 ms±0.10 ms——
doubleHost38.60 ms±1.16 ms20.17 ms±0.44 ms
Cuda52.04 ms±0.27 ms——
2000x2000int32Host——4041.68 ms±0.42 ms
int64Host——11000.01 ms±22.24 ms
singleHost104.04 ms±21.00 ms75.56 ms±1.29 ms
Cuda15.93 ms±0.07 ms——
doubleHost202.81 ms±44.84 ms147.94 ms±1.54 ms
Cuda403.79 ms±1.22 ms——
4000x4000int32Host——33160.89 ms±2.34 ms
int64Host——86242.90 ms±2.01 ms
singleHost605.88 ms±64.61 ms590.84 ms±2.47 ms
Cuda117.63 ms±3.59 ms——
doubleHost——1177.82 ms±2.07 ms
sgn1000x1000boolCuda0.92 ms±0.03 ms——
int32Host5.74 ms±0.34 ms0.56 ms±0.01 ms
Cuda0.98 ms±0.04 ms——
int64Host6.76 ms±0.24 ms6.89 ms±0.11 ms
Cuda0.92 ms±0.04 ms——
singleHost6.43 ms±0.11 ms7.98 ms±0.12 ms
Cuda0.92 ms±0.02 ms——
doubleHost6.94 ms±0.34 ms8.25 ms±0.11 ms
Cuda1.03 ms±0.05 ms——
2000x2000boolCuda1.55 ms±0.07 ms——
int32Host18.84 ms±0.54 ms2.91 ms±0.08 ms
Cuda1.56 ms±0.02 ms——
int64Host21.68 ms±0.37 ms27.67 ms±0.28 ms
Cuda2.50 ms±0.09 ms——
singleHost20.16 ms±0.33 ms32.08 ms±0.31 ms
Cuda1.62 ms±0.08 ms——
doubleHost22.54 ms±0.61 ms33.00 ms±0.04 ms
Cuda2.02 ms±0.08 ms——
4000x4000boolCuda5.00 ms±0.08 ms——
int32Host70.85 ms±1.88 ms37.13 ms±0.43 ms
Cuda5.14 ms±0.26 ms——
int64Host79.25 ms±1.05 ms165.27 ms±0.71 ms
Cuda8.92 ms±1.79 ms——
singleHost77.25 ms±0.66 ms156.19 ms±0.81 ms
Cuda4.46 ms±0.06 ms——
doubleHost84.58 ms±0.57 ms187.36 ms±0.81 ms
Cuda10.73 ms±0.25 ms——
log1000x1000int32Host——32.64 ms±0.47 ms
int64Host——33.00 ms±0.49 ms
singleHost12.74 ms±0.43 ms23.53 ms±4.29 ms
Cuda0.98 ms±0.05 ms——
doubleHost13.13 ms±0.25 ms31.81 ms±0.48 ms
Cuda2.16 ms±0.06 ms——
2000x2000int32Host——130.48 ms±0.91 ms
int64Host——132.12 ms±0.91 ms
singleHost46.65 ms±1.03 ms82.64 ms±0.92 ms
Cuda1.74 ms±0.05 ms——
doubleHost47.91 ms±0.79 ms127.23 ms±0.98 ms
Cuda6.27 ms±0.01 ms——
4000x4000int32Host——580.22 ms±1.26 ms
int64Host——655.68 ms±47.15 ms
singleHost179.25 ms±1.62 ms361.09 ms±1.52 ms
Cuda4.91 ms±0.12 ms——
doubleHost183.58 ms±0.84 ms566.88 ms±1.28 ms
Cuda23.17 ms±0.04 ms——
log101000x1000int32Host——34.15 ms±0.53 ms
int64Host——34.59 ms±0.55 ms
singleHost12.79 ms±0.23 ms25.56 ms±0.40 ms
Cuda0.95 ms±0.02 ms——
doubleHost13.27 ms±0.39 ms34.88 ms±0.57 ms
Cuda2.24 ms±0.02 ms——
2000x2000int32Host——136.53 ms±1.12 ms
int64Host——138.04 ms±1.03 ms
singleHost49.18 ms±1.68 ms102.44 ms±1.11 ms
Cuda1.76 ms±0.08 ms——
doubleHost47.70 ms±1.15 ms139.56 ms±1.09 ms
Cuda6.79 ms±0.05 ms——
4000x4000int32Host——604.82 ms±1.64 ms
int64Host——610.75 ms±1.76 ms
singleHost179.04 ms±2.06 ms440.81 ms±1.90 ms
Cuda4.80 ms±0.08 ms——
doubleHost182.97 ms±3.08 ms616.02 ms±0.36 ms
Cuda25.00 ms±0.18 ms——
exp1000x1000int32Host——27.33 ms±0.00 ms
int64Host——29.07 ms±3.99 ms
singleHost7.45 ms±0.11 ms16.57 ms±0.02 ms
Cuda0.98 ms±0.05 ms——
doubleHost8.13 ms±0.22 ms26.94 ms±0.01 ms
Cuda1.51 ms±0.04 ms——
2000x2000int32Host——109.37 ms±0.01 ms
int64Host——111.06 ms±0.01 ms
singleHost24.26 ms±0.76 ms66.35 ms±0.01 ms
Cuda1.67 ms±0.03 ms——
doubleHost25.63 ms±0.52 ms107.68 ms±0.01 ms
Cuda3.90 ms±0.11 ms——
4000x4000int32Host——575.90 ms±103.34 ms
int64Host——576.50 ms±110.41 ms
singleHost94.02 ms±1.68 ms293.30 ms±0.07 ms
Cuda4.65 ms±0.07 ms——
doubleHost97.30 ms±1.56 ms487.84 ms±0.37 ms
Cuda13.43 ms±0.03 ms——
sin1000x1000int32Host——54.91 ms±0.09 ms
int64Host——55.34 ms±0.09 ms
singleHost7.86 ms±0.53 ms21.02 ms±0.03 ms
Cuda0.96 ms±0.06 ms——
doubleHost9.21 ms±0.68 ms60.76 ms±0.02 ms
Cuda1.66 ms±0.03 ms——
2000x2000int32Host——219.60 ms±0.09 ms
int64Host——221.39 ms±0.10 ms
singleHost27.79 ms±0.94 ms84.46 ms±0.02 ms
Cuda1.74 ms±0.09 ms——
doubleHost28.69 ms±0.37 ms242.90 ms±0.05 ms
Cuda4.46 ms±0.06 ms——
4000x4000int32Host——939.10 ms±0.35 ms
int64Host——944.28 ms±0.40 ms
singleHost109.36 ms±2.68 ms369.04 ms±0.05 ms
Cuda4.97 ms±0.08 ms——
doubleHost109.69 ms±2.07 ms1053.12 ms±37.89 ms
Cuda15.28 ms±0.05 ms——
cos1000x1000int32Host——86.90 ms±0.04 ms
int64Host——87.34 ms±0.05 ms
singleHost8.57 ms±0.57 ms41.42 ms±0.02 ms
Cuda0.94 ms±0.04 ms——
doubleHost8.80 ms±0.41 ms82.03 ms±0.10 ms
Cuda1.72 ms±0.10 ms——
2000x2000int32Host——348.03 ms±0.06 ms
int64Host——349.48 ms±0.11 ms
singleHost27.14 ms±0.53 ms166.05 ms±0.04 ms
Cuda1.85 ms±0.02 ms——
doubleHost28.08 ms±0.64 ms328.65 ms±0.40 ms
Cuda4.41 ms±0.10 ms——
4000x4000int32Host——1461.91 ms±29.70 ms
int64Host——1455.08 ms±0.25 ms
singleHost103.46 ms±1.39 ms692.74 ms±0.12 ms
Cuda4.93 ms±0.06 ms——
doubleHost105.98 ms±1.33 ms1373.27 ms±1.03 ms
Cuda15.37 ms±0.20 ms——
tan1000x1000singleHost9.26 ms±0.38 ms——
Cuda0.83 ms±0.01 ms——
doubleHost9.68 ms±0.12 ms——
Cuda2.36 ms±0.03 ms——
2000x2000singleHost32.65 ms±0.48 ms——
Cuda2.11 ms±0.06 ms——
doubleHost33.76 ms±0.34 ms——
Cuda6.76 ms±0.17 ms——
4000x4000singleHost127.05 ms±1.63 ms——
Cuda6.06 ms±0.10 ms——
doubleHost129.43 ms±1.10 ms——
Cuda24.58 ms±0.02 ms——
asin1000x1000int32Host——11.11 ms±0.01 ms
int64Host——11.50 ms±0.01 ms
singleHost16.15 ms±0.43 ms11.96 ms±0.00 ms
Cuda0.81 ms±0.04 ms——
doubleHost17.38 ms±0.44 ms10.38 ms±0.01 ms
Cuda2.26 ms±0.07 ms——
2000x2000int32Host——44.41 ms±0.01 ms
int64Host——47.40 ms±4.59 ms
singleHost61.59 ms±0.59 ms47.89 ms±0.02 ms
Cuda1.88 ms±0.07 ms——
doubleHost64.00 ms±1.46 ms41.60 ms±0.02 ms
Cuda6.85 ms±0.04 ms——
4000x4000int32Host——239.15 ms±9.48 ms
int64Host——237.64 ms±0.04 ms
singleHost243.50 ms±3.46 ms219.26 ms±0.04 ms
Cuda5.38 ms±0.05 ms——
doubleHost248.15 ms±2.13 ms220.14 ms±0.03 ms
Cuda25.13 ms±0.18 ms——
acos1000x1000int32Host——12.10 ms±0.01 ms
int64Host——12.48 ms±0.01 ms
singleHost16.14 ms±0.30 ms11.54 ms±0.01 ms
Cuda1.00 ms±0.04 ms——
doubleHost17.13 ms±0.20 ms11.37 ms±0.01 ms
Cuda1.87 ms±0.08 ms——
2000x2000int32Host——48.36 ms±0.03 ms
int64Host——49.96 ms±0.01 ms
singleHost61.06 ms±0.32 ms46.28 ms±0.02 ms
Cuda1.86 ms±0.05 ms——
doubleHost62.61 ms±0.74 ms45.48 ms±0.02 ms
Cuda5.30 ms±0.03 ms——
4000x4000int32Host——304.26 ms±32.94 ms
int64Host——253.44 ms±0.06 ms
singleHost243.49 ms±5.10 ms212.83 ms±0.03 ms
Cuda5.46 ms±0.07 ms——
doubleHost244.80 ms±1.37 ms235.34 ms±0.03 ms
Cuda18.92 ms±0.02 ms——
atan1000x1000int32Host——38.09 ms±0.02 ms
int64Host——38.50 ms±0.03 ms
singleHost8.51 ms±0.13 ms18.98 ms±0.02 ms
Cuda1.06 ms±0.05 ms——
doubleHost9.30 ms±0.22 ms39.43 ms±0.02 ms
Cuda2.09 ms±0.09 ms——
2000x2000int32Host——152.32 ms±0.06 ms
int64Host——169.61 ms±24.22 ms
singleHost29.27 ms±1.00 ms76.03 ms±0.02 ms
Cuda1.86 ms±0.04 ms——
doubleHost29.66 ms±0.41 ms157.75 ms±0.03 ms
Cuda6.50 ms±0.06 ms——
4000x4000int32Host——668.09 ms±0.16 ms
int64Host——673.69 ms±0.18 ms
singleHost112.47 ms±0.08 ms334.32 ms±0.11 ms
Cuda5.57 ms±0.10 ms——
doubleHost114.61 ms±0.85 ms757.55 ms±103.61 ms
Cuda23.62 ms±0.01 ms——
sinh1000x1000int32Host——63.06 ms±7.39 ms
int64Host——49.02 ms±0.02 ms
singleHost8.72 ms±0.21 ms38.09 ms±0.01 ms
Cuda0.96 ms±0.02 ms——
doubleHost9.72 ms±0.31 ms48.73 ms±0.01 ms
Cuda2.47 ms±0.08 ms——
2000x2000int32Host——241.74 ms±36.77 ms
int64Host——196.19 ms±0.03 ms
singleHost31.37 ms±0.77 ms152.72 ms±0.03 ms
Cuda1.82 ms±0.08 ms——
doubleHost32.05 ms±0.29 ms194.96 ms±0.03 ms
Cuda6.98 ms±0.12 ms——
4000x4000int32Host——905.57 ms±122.32 ms
int64Host——844.33 ms±0.24 ms
singleHost118.98 ms±0.55 ms639.87 ms±0.09 ms
Cuda5.23 ms±0.11 ms——
doubleHost123.36 ms±0.82 ms839.24 ms±0.20 ms
Cuda25.66 ms±0.17 ms——
cosh1000x1000int32Host——35.42 ms±0.03 ms
int64Host——35.87 ms±0.01 ms
singleHost9.09 ms±0.11 ms22.92 ms±0.03 ms
Cuda0.93 ms±0.03 ms——
doubleHost9.82 ms±0.01 ms35.28 ms±0.01 ms
Cuda1.75 ms±0.12 ms——
2000x2000int32Host——141.86 ms±0.14 ms
int64Host——159.11 ms±26.40 ms
singleHost32.15 ms±1.38 ms91.70 ms±0.09 ms
Cuda1.72 ms±0.04 ms——
doubleHost32.51 ms±0.50 ms141.36 ms±0.04 ms
Cuda4.70 ms±0.08 ms——
4000x4000int32Host——626.83 ms±0.35 ms
int64Host——632.70 ms±0.39 ms
singleHost123.85 ms±3.35 ms431.62 ms±72.79 ms
Cuda4.69 ms±0.06 ms——
doubleHost125.60 ms±0.39 ms625.80 ms±0.13 ms
Cuda16.64 ms±0.17 ms——
tanh1000x1000int32Host——28.31 ms±0.01 ms
int64Host——28.69 ms±0.02 ms
singleHost8.36 ms±0.40 ms32.42 ms±5.54 ms
Cuda0.92 ms±0.04 ms——
doubleHost8.84 ms±0.14 ms28.56 ms±0.02 ms
Cuda2.14 ms±0.04 ms——
2000x2000int32Host——115.52 ms±6.88 ms
int64Host——114.78 ms±0.03 ms
singleHost27.77 ms±0.56 ms111.03 ms±0.09 ms
Cuda1.84 ms±0.07 ms——
doubleHost29.40 ms±0.60 ms114.38 ms±0.03 ms
Cuda6.23 ms±0.10 ms——
4000x4000int32Host——511.16 ms±0.12 ms
int64Host——516.73 ms±0.17 ms
singleHost110.60 ms±2.60 ms552.64 ms±77.32 ms
Cuda5.04 ms±0.05 ms——
doubleHost113.75 ms±1.79 ms621.19 ms±77.36 ms
Cuda22.50 ms±0.02 ms——
sqrt1000x1000int32Host6.63 ms±0.50 ms3.73 ms±0.01 ms
int64Host11.66 ms±0.81 ms4.09 ms±0.01 ms
singleHost2.44 ms±0.04 ms0.92 ms±0.00 ms
Cuda1.01 ms±0.06 ms——
doubleHost6.51 ms±0.52 ms3.21 ms±0.01 ms
Cuda1.25 ms±0.03 ms——
2000x2000int32Host23.78 ms±0.04 ms14.92 ms±0.01 ms
int64Host41.70 ms±0.46 ms16.47 ms±0.01 ms
singleHost10.54 ms±0.21 ms3.72 ms±0.02 ms
Cuda1.85 ms±0.04 ms——
doubleHost20.13 ms±0.08 ms12.82 ms±0.01 ms
Cuda2.88 ms±0.06 ms——
4000x4000int32Host95.80 ms±0.73 ms115.76 ms±1.60 ms
int64Host163.14 ms±0.06 ms119.99 ms±0.04 ms
singleHost35.85 ms±0.12 ms42.34 ms±0.02 ms
Cuda5.35 ms±0.10 ms——
doubleHost82.56 ms±0.92 ms105.91 ms±0.03 ms
Cuda9.46 ms±0.08 ms——
ceiling1000x1000singleHost8.01 ms±0.30 ms——
Cuda0.80 ms±0.04 ms——
doubleHost6.94 ms±0.16 ms——
Cuda0.88 ms±0.02 ms——
2000x2000singleHost17.86 ms±0.51 ms——
Cuda1.59 ms±0.08 ms——
doubleHost19.72 ms±0.55 ms——
Cuda2.51 ms±0.08 ms——
4000x4000singleHost67.21 ms±1.18 ms——
Cuda4.86 ms±0.12 ms——
doubleHost74.65 ms±1.16 ms——
Cuda11.03 ms±0.30 ms——
floor1000x1000singleHost5.91 ms±0.24 ms——
Cuda0.91 ms±0.03 ms——
doubleHost6.69 ms±0.11 ms——
Cuda0.84 ms±0.03 ms——
2000x2000singleHost17.84 ms±0.46 ms——
Cuda1.59 ms±0.08 ms——
doubleHost20.52 ms±0.20 ms——
Cuda2.48 ms±0.13 ms——
4000x4000singleHost68.82 ms±0.60 ms——
Cuda4.96 ms±0.04 ms——
doubleHost75.01 ms±0.76 ms——
Cuda10.90 ms±0.31 ms——
round1000x1000singleHost6.18 ms±0.30 ms——
Cuda0.90 ms±0.03 ms——
doubleHost6.55 ms±0.14 ms——
Cuda0.94 ms±0.03 ms——
2000x2000singleHost17.47 ms±0.41 ms——
Cuda1.60 ms±0.06 ms——
doubleHost19.92 ms±0.15 ms——
Cuda2.55 ms±0.11 ms——
4000x4000singleHost68.77 ms±0.60 ms——
Cuda4.44 ms±0.11 ms——
doubleHost74.54 ms±0.52 ms——
Cuda12.39 ms±3.97 ms——
truncate1000x1000singleHost6.86 ms±0.44 ms——
Cuda0.88 ms±0.03 ms——
doubleHost7.24 ms±0.21 ms——
Cuda0.80 ms±0.02 ms——
2000x2000singleHost20.98 ms±0.43 ms——
Cuda1.55 ms±0.05 ms——
doubleHost22.74 ms±0.18 ms——
Cuda2.49 ms±0.15 ms——
4000x4000singleHost81.93 ms±1.56 ms——
Cuda4.25 ms±0.09 ms——
doubleHost89.32 ms±1.77 ms——
Cuda11.16 ms±0.31 ms——
maxElemwise1000x1000boolHost5.75 ms±0.14 ms——
Cuda1.00 ms±0.05 ms——
int32Host2.83 ms±0.10 ms——
Cuda0.99 ms±0.01 ms——
int64Host6.82 ms±0.43 ms——
Cuda1.17 ms±0.07 ms——
singleHost2.81 ms±0.12 ms——
Cuda1.02 ms±0.04 ms——
doubleHost6.11 ms±0.27 ms——
Cuda1.13 ms±0.02 ms——
2000x2000boolHost15.93 ms±0.78 ms——
Cuda1.76 ms±0.08 ms——
int32Host11.14 ms±0.30 ms——
Cuda1.72 ms±0.03 ms——
int64Host19.10 ms±0.28 ms——
Cuda2.60 ms±0.12 ms——
singleHost11.41 ms±0.23 ms——
Cuda1.80 ms±0.04 ms——
doubleHost19.61 ms±0.29 ms——
Cuda2.56 ms±0.10 ms——
4000x4000boolHost55.53 ms±1.01 ms——
Cuda4.95 ms±0.07 ms——
int32Host39.05 ms±0.46 ms——
Cuda4.98 ms±0.10 ms——
int64Host79.92 ms±2.27 ms——
Cuda11.67 ms±2.89 ms——
singleHost40.56 ms±1.10 ms——
Cuda4.98 ms±0.08 ms——
doubleHost79.27 ms±3.37 ms——
Cuda12.12 ms±1.67 ms——
minElemwise1000x1000boolHost5.69 ms±0.09 ms——
Cuda1.01 ms±0.03 ms——
int32Host2.70 ms±0.06 ms——
Cuda0.99 ms±0.02 ms——
int64Host6.32 ms±0.52 ms——
Cuda1.14 ms±0.04 ms——
singleHost2.84 ms±0.16 ms——
Cuda1.04 ms±0.05 ms——
doubleHost5.88 ms±0.21 ms——
Cuda1.17 ms±0.03 ms——
2000x2000boolHost15.18 ms±0.20 ms——
Cuda1.78 ms±0.05 ms——
int32Host11.60 ms±0.16 ms——
Cuda1.87 ms±0.10 ms——
int64Host19.90 ms±0.79 ms——
Cuda2.58 ms±0.10 ms——
singleHost11.06 ms±0.10 ms——
Cuda1.78 ms±0.03 ms——
doubleHost19.81 ms±0.27 ms——
Cuda2.56 ms±0.06 ms——
4000x4000boolHost55.36 ms±1.97 ms——
Cuda5.01 ms±0.06 ms——
int32Host41.39 ms±1.70 ms——
Cuda5.06 ms±0.04 ms——
int64Host81.67 ms±0.97 ms——
Cuda11.74 ms±1.70 ms——
singleHost40.64 ms±1.21 ms——
Cuda5.02 ms±0.13 ms——
doubleHost80.58 ms±5.30 ms——
Cuda8.66 ms±0.30 ms——
sumAxis1000x1000int32Host3.06 ms±0.10 ms1.40 ms±0.01 ms
Cuda1.35 ms±0.08 ms——
int64Host3.03 ms±0.13 ms0.94 ms±0.01 ms
Cuda1.60 ms±0.05 ms——
singleHost3.28 ms±0.22 ms0.62 ms±0.00 ms
Cuda1.42 ms±0.01 ms——
doubleHost3.05 ms±0.15 ms0.63 ms±0.01 ms
Cuda1.65 ms±0.07 ms——
2000x2000int32Host12.62 ms±0.72 ms5.67 ms±0.01 ms
Cuda2.50 ms±0.06 ms——
int64Host12.69 ms±0.30 ms3.75 ms±0.01 ms
Cuda2.98 ms±0.08 ms——
singleHost11.83 ms±0.33 ms2.43 ms±0.01 ms
Cuda2.49 ms±0.03 ms——
doubleHost13.11 ms±0.59 ms2.69 ms±0.01 ms
Cuda3.01 ms±0.05 ms——
4000x4000int32Host44.26 ms±1.19 ms22.98 ms±0.01 ms
Cuda6.80 ms±0.05 ms——
int64Host45.82 ms±6.60 ms14.94 ms±0.08 ms
Cuda12.57 ms±0.06 ms——
singleHost49.03 ms±5.63 ms9.58 ms±0.01 ms
Cuda6.76 ms±0.13 ms——
doubleHost45.63 ms±1.17 ms10.71 ms±0.02 ms
Cuda12.51 ms±0.05 ms——
productAxis1000x1000int32Host3.03 ms±0.15 ms——
Cuda1.47 ms±0.04 ms——
int64Host3.14 ms±0.07 ms——
Cuda1.61 ms±0.03 ms——
singleHost3.01 ms±0.11 ms——
Cuda1.45 ms±0.03 ms——
doubleHost3.30 ms±0.40 ms——
Cuda1.60 ms±0.03 ms——
2000x2000int32Host12.93 ms±0.77 ms——
Cuda2.54 ms±0.09 ms——
int64Host12.50 ms±0.49 ms——
Cuda3.08 ms±0.09 ms——
singleHost12.51 ms±0.57 ms——
Cuda2.50 ms±0.03 ms——
doubleHost12.70 ms±0.86 ms——
Cuda3.02 ms±0.06 ms——
4000x4000int32Host44.99 ms±1.78 ms——
Cuda6.69 ms±0.08 ms——
int64Host46.90 ms±6.64 ms——
Cuda12.48 ms±0.01 ms——
singleHost44.97 ms±4.74 ms——
Cuda6.76 ms±0.06 ms——
doubleHost43.42 ms±2.01 ms——
Cuda12.52 ms±0.04 ms——
maxAxis1000x1000int32Host3.30 ms±0.10 ms——
Cuda1.46 ms±0.02 ms——
int64Host3.46 ms±0.06 ms——
Cuda1.59 ms±0.03 ms——
singleHost3.47 ms±0.29 ms——
Cuda1.46 ms±0.02 ms——
doubleHost3.35 ms±0.06 ms——
Cuda1.65 ms±0.05 ms——
2000x2000int32Host12.86 ms±0.68 ms——
Cuda2.47 ms±0.03 ms——
int64Host13.05 ms±0.73 ms——
Cuda3.08 ms±0.11 ms——
singleHost12.88 ms±0.35 ms——
Cuda2.46 ms±0.04 ms——
doubleHost12.74 ms±0.68 ms——
Cuda3.01 ms±0.10 ms——
4000x4000int32Host46.89 ms±1.13 ms——
Cuda6.69 ms±0.04 ms——
int64Host48.34 ms±1.49 ms——
Cuda12.54 ms±0.06 ms——
singleHost48.35 ms±1.66 ms——
Cuda6.72 ms±0.06 ms——
doubleHost48.30 ms±1.67 ms——
Cuda12.54 ms±0.05 ms——
minAxis1000x1000int32Host3.23 ms±0.16 ms——
Cuda1.40 ms±0.01 ms——
int64Host3.18 ms±0.15 ms——
Cuda1.58 ms±0.04 ms——
singleHost3.27 ms±0.09 ms——
Cuda1.45 ms±0.04 ms——
doubleHost3.29 ms±0.10 ms——
Cuda1.63 ms±0.05 ms——
2000x2000int32Host13.47 ms±0.81 ms——
Cuda2.53 ms±0.03 ms——
int64Host13.15 ms±0.75 ms——
Cuda3.00 ms±0.06 ms——
singleHost13.56 ms±1.48 ms——
Cuda2.49 ms±0.05 ms——
doubleHost13.80 ms±1.07 ms——
Cuda2.99 ms±0.03 ms——
4000x4000int32Host47.39 ms±2.33 ms——
Cuda6.80 ms±0.04 ms——
int64Host53.98 ms±0.61 ms——
Cuda12.56 ms±0.04 ms——
singleHost51.34 ms±1.03 ms——
Cuda6.75 ms±0.06 ms——
doubleHost48.59 ms±1.59 ms——
Cuda12.66 ms±0.10 ms——
argMaxAxis1000x1000int32Host4.32 ms±0.15 ms——
Cuda1.42 ms±0.03 ms——
int64Host4.62 ms±0.25 ms——
Cuda1.54 ms±0.01 ms——
singleHost4.75 ms±0.07 ms——
Cuda1.50 ms±0.05 ms——
doubleHost4.71 ms±0.31 ms——
Cuda1.61 ms±0.04 ms——
2000x2000int32Host16.13 ms±0.61 ms——
Cuda2.64 ms±0.04 ms——
int64Host16.19 ms±0.60 ms——
Cuda2.90 ms±0.04 ms——
singleHost16.68 ms±0.53 ms——
Cuda2.52 ms±0.05 ms——
doubleHost16.82 ms±0.43 ms——
Cuda2.99 ms±0.10 ms——
4000x4000int32Host61.87 ms±1.80 ms——
Cuda6.80 ms±0.08 ms——
int64Host62.13 ms±1.04 ms——
Cuda12.56 ms±0.03 ms——
singleHost74.78 ms±1.93 ms——
Cuda6.79 ms±0.06 ms——
doubleHost64.73 ms±2.11 ms——
Cuda12.56 ms±0.06 ms——
argMinAxis1000x1000int32Host4.51 ms±0.30 ms——
Cuda1.36 ms±0.04 ms——
int64Host4.22 ms±0.14 ms——
Cuda1.60 ms±0.05 ms——
singleHost4.21 ms±0.16 ms——
Cuda1.49 ms±0.05 ms——
doubleHost4.40 ms±0.14 ms——
Cuda1.57 ms±0.04 ms——
2000x2000int32Host16.16 ms±0.47 ms——
Cuda2.52 ms±0.03 ms——
int64Host16.15 ms±0.71 ms——
Cuda2.90 ms±0.04 ms——
singleHost16.30 ms±0.54 ms——
Cuda2.47 ms±0.02 ms——
doubleHost16.47 ms±0.19 ms——
Cuda2.95 ms±0.05 ms——
4000x4000int32Host63.24 ms±2.04 ms——
Cuda6.76 ms±0.10 ms——
int64Host64.42 ms±4.46 ms——
Cuda12.53 ms±0.05 ms——
singleHost61.57 ms±1.63 ms——
Cuda6.77 ms±0.10 ms——
doubleHost63.76 ms±1.90 ms——
Cuda12.60 ms±0.05 ms——
findAxis1000x1000int32Host1.10 ms±0.01 ms——
Cuda0.57 ms±0.00 ms——
int64Host1.12 ms±0.03 ms——
Cuda0.74 ms±0.02 ms——
singleHost1.39 ms±0.02 ms——
Cuda1.48 ms±0.04 ms——
doubleHost1.42 ms±0.02 ms——
Cuda1.50 ms±0.04 ms——
2000x2000int32Host3.64 ms±0.04 ms——
Cuda0.85 ms±0.03 ms——
int64Host3.66 ms±0.04 ms——
Cuda0.88 ms±0.02 ms——
singleHost4.85 ms±0.02 ms——
Cuda2.44 ms±0.07 ms——
doubleHost4.92 ms±0.08 ms——
Cuda2.69 ms±0.09 ms——
4000x4000int32Host13.17 ms±0.24 ms——
Cuda1.34 ms±0.04 ms——
int64Host13.28 ms±0.15 ms——
Cuda1.42 ms±0.06 ms——
singleHost18.01 ms±0.16 ms——
Cuda6.82 ms±0.10 ms——
doubleHost18.12 ms±0.29 ms——
Cuda12.53 ms±0.03 ms——
maskedGet1000x1000boolHost61.89 ms±4.15 ms——
int32Host61.87 ms±2.69 ms——
int64Host69.05 ms±4.59 ms——
singleHost61.39 ms±2.30 ms——
doubleHost63.59 ms±6.51 ms——
2000x2000boolHost275.66 ms±62.64 ms——
int32Host294.05 ms±59.29 ms——
int64Host275.87 ms±37.48 ms——
singleHost269.70 ms±49.99 ms——
doubleHost269.58 ms±18.39 ms——
4000x4000int32Host988.48 ms±53.13 ms——
singleHost960.94 ms±18.94 ms——
doubleHost996.74 ms±12.15 ms——
maskedSet1000x1000boolHost62.88 ms±2.11 ms——
int32Host66.68 ms±6.03 ms——
int64Host65.94 ms±5.41 ms——
singleHost65.01 ms±2.46 ms——
doubleHost67.73 ms±3.74 ms——
2000x2000boolHost254.70 ms±21.87 ms——
int32Host249.84 ms±8.72 ms——
int64Host267.47 ms±16.21 ms——
singleHost246.02 ms±20.99 ms——
doubleHost257.04 ms±25.52 ms——
4000x4000boolHost979.76 ms±22.66 ms——
int64Host979.39 ms±10.59 ms——
doubleHost972.80 ms±20.03 ms——
invert1000x1000singleHost22.04 ms±2.59 ms——
Cuda605.05 ms±2.30 ms——
doubleHost44.59 ms±6.42 ms——
2000x2000singleHost139.06 ms±14.92 ms——
doubleHost229.70 ms±32.49 ms——
4000x4000singleHost728.64 ms±63.85 ms——
pseudoInvert1000x1000singleHost304.75 ms±24.19 ms——
doubleHost430.58 ms±24.67 ms——
sVD1000x1000singleHost272.86 ms±4.36 ms——
doubleHost408.41 ms±38.34 ms——
symEigDec1000x1000singleHost75.49 ms±6.50 ms——
doubleHost127.58 ms±18.01 ms——
2000x2000singleHost346.69 ms±11.95 ms——
doubleHost593.21 ms±21.09 ms——
equal1000x1000boolHost5.80 ms±0.17 ms——
Cuda1.00 ms±0.01 ms——
int32Host4.27 ms±0.28 ms0.44 ms±0.01 ms
Cuda0.99 ms±0.03 ms——
int64Host3.79 ms±0.09 ms1.16 ms±0.01 ms
Cuda1.01 ms±0.02 ms——
singleHost4.43 ms±0.12 ms0.45 ms±0.01 ms
Cuda1.02 ms±0.02 ms——
doubleHost4.08 ms±0.22 ms1.15 ms±0.02 ms
Cuda1.03 ms±0.05 ms——
2000x2000boolHost15.78 ms±1.22 ms——
Cuda1.76 ms±0.08 ms——
int32Host14.85 ms±0.81 ms2.62 ms±0.01 ms
Cuda1.71 ms±0.07 ms——
int64Host14.65 ms±0.63 ms4.89 ms±0.00 ms
Cuda1.86 ms±0.05 ms——
singleHost14.48 ms±0.43 ms2.62 ms±0.02 ms
Cuda1.76 ms±0.06 ms——
doubleHost14.59 ms±0.70 ms4.88 ms±0.01 ms
Cuda1.91 ms±0.09 ms——
4000x4000boolHost51.58 ms±2.01 ms——
Cuda5.05 ms±0.05 ms——
int32Host54.05 ms±3.07 ms10.69 ms±0.01 ms
Cuda5.02 ms±0.11 ms——
int64Host53.66 ms±2.79 ms19.84 ms±0.02 ms
Cuda5.77 ms±0.12 ms——
singleHost52.47 ms±1.64 ms10.65 ms±0.03 ms
Cuda4.97 ms±0.13 ms——
doubleHost60.88 ms±11.53 ms19.95 ms±0.06 ms
Cuda5.76 ms±0.13 ms——
notEqual1000x1000boolHost5.64 ms±0.21 ms——
Cuda1.09 ms±0.02 ms——
int32Host4.33 ms±0.19 ms0.44 ms±0.01 ms
Cuda0.93 ms±0.03 ms——
int64Host3.82 ms±0.16 ms1.16 ms±0.01 ms
Cuda0.98 ms±0.04 ms——
singleHost4.02 ms±0.25 ms0.45 ms±0.01 ms
Cuda1.08 ms±0.04 ms——
doubleHost3.83 ms±0.08 ms1.15 ms±0.02 ms
Cuda0.98 ms±0.04 ms——
2000x2000boolHost14.22 ms±0.80 ms——
Cuda1.76 ms±0.02 ms——
int32Host15.77 ms±1.49 ms2.62 ms±0.01 ms
Cuda1.88 ms±0.09 ms——
int64Host15.32 ms±0.74 ms4.82 ms±0.01 ms
Cuda1.88 ms±0.04 ms——
singleHost14.82 ms±0.47 ms2.62 ms±0.02 ms
Cuda1.82 ms±0.04 ms——
doubleHost15.29 ms±0.38 ms4.81 ms±0.02 ms
Cuda1.99 ms±0.11 ms——
4000x4000boolHost51.50 ms±2.27 ms——
Cuda4.94 ms±0.05 ms——
int32Host53.56 ms±0.97 ms10.68 ms±0.02 ms
Cuda5.02 ms±0.06 ms——
int64Host63.66 ms±15.63 ms19.84 ms±0.02 ms
Cuda5.79 ms±0.08 ms——
singleHost53.23 ms±1.42 ms10.76 ms±0.03 ms
Cuda5.05 ms±0.09 ms——
doubleHost55.27 ms±1.34 ms19.99 ms±0.02 ms
Cuda5.76 ms±0.18 ms——
less1000x1000boolHost5.92 ms±0.20 ms——
Cuda1.08 ms±0.02 ms——
int32Host4.18 ms±0.32 ms0.44 ms±0.01 ms
Cuda0.97 ms±0.04 ms——
int64Host3.94 ms±0.12 ms1.15 ms±0.01 ms
Cuda0.95 ms±0.03 ms——
singleHost4.79 ms±0.99 ms0.45 ms±0.01 ms
Cuda1.08 ms±0.06 ms——
doubleHost3.96 ms±0.27 ms1.15 ms±0.02 ms
Cuda0.98 ms±0.05 ms——
2000x2000boolHost14.27 ms±0.73 ms——
Cuda1.77 ms±0.06 ms——
int32Host14.92 ms±1.04 ms2.60 ms±0.01 ms
Cuda1.88 ms±0.05 ms——
int64Host15.32 ms±0.62 ms4.81 ms±0.01 ms
Cuda1.90 ms±0.03 ms——
singleHost15.71 ms±0.60 ms2.62 ms±0.02 ms
Cuda1.76 ms±0.02 ms——
doubleHost15.82 ms±2.04 ms4.83 ms±0.02 ms
Cuda2.03 ms±0.08 ms——
4000x4000boolHost60.34 ms±15.67 ms——
Cuda5.03 ms±0.17 ms——
int32Host55.27 ms±1.66 ms10.63 ms±0.01 ms
Cuda5.07 ms±0.07 ms——
int64Host55.28 ms±2.07 ms19.93 ms±0.01 ms
Cuda5.81 ms±0.20 ms——
singleHost51.89 ms±1.47 ms10.76 ms±0.03 ms
Cuda5.07 ms±0.09 ms——
doubleHost54.03 ms±2.59 ms19.99 ms±0.07 ms
Cuda5.69 ms±0.17 ms——
lessOrEqual1000x1000boolHost5.69 ms±0.37 ms——
Cuda1.10 ms±0.04 ms——
int32Host4.19 ms±0.34 ms0.44 ms±0.01 ms
Cuda0.97 ms±0.02 ms——
int64Host4.04 ms±0.09 ms1.16 ms±0.01 ms
Cuda1.01 ms±0.02 ms——
singleHost4.40 ms±0.47 ms0.45 ms±0.01 ms
Cuda1.10 ms±0.03 ms——
doubleHost3.84 ms±0.23 ms1.15 ms±0.02 ms
Cuda1.02 ms±0.02 ms——
2000x2000boolHost14.76 ms±0.76 ms——
Cuda1.76 ms±0.03 ms——
int32Host14.51 ms±0.57 ms2.61 ms±0.01 ms
Cuda1.85 ms±0.04 ms——
int64Host14.33 ms±0.39 ms4.82 ms±0.01 ms
Cuda1.91 ms±0.09 ms——
singleHost14.26 ms±0.54 ms2.62 ms±0.02 ms
Cuda1.76 ms±0.04 ms——
doubleHost15.46 ms±1.43 ms4.83 ms±0.02 ms
Cuda1.99 ms±0.06 ms——
4000x4000boolHost53.10 ms±3.88 ms——
Cuda4.98 ms±0.06 ms——
int32Host53.08 ms±0.79 ms10.68 ms±0.01 ms
Cuda5.05 ms±0.15 ms——
int64Host54.34 ms±1.42 ms19.95 ms±0.01 ms
Cuda5.86 ms±0.12 ms——
singleHost54.65 ms±1.26 ms10.81 ms±0.17 ms
Cuda4.97 ms±0.08 ms——
doubleHost54.10 ms±2.05 ms19.99 ms±0.07 ms
Cuda5.88 ms±0.18 ms——
greater1000x1000boolHost5.86 ms±0.38 ms——
Cuda0.83 ms±0.06 ms——
int32Host4.21 ms±0.23 ms0.44 ms±0.01 ms
Cuda0.99 ms±0.03 ms——
int64Host3.73 ms±0.17 ms1.16 ms±0.01 ms
Cuda0.94 ms±0.01 ms——
singleHost3.91 ms±0.11 ms0.45 ms±0.01 ms
Cuda0.96 ms±0.02 ms——
doubleHost4.09 ms±0.42 ms1.15 ms±0.02 ms
Cuda1.11 ms±0.03 ms——
2000x2000boolHost14.71 ms±1.57 ms——
Cuda1.82 ms±0.04 ms——
int32Host15.23 ms±0.59 ms2.61 ms±0.01 ms
Cuda1.77 ms±0.04 ms——
int64Host14.67 ms±0.73 ms4.84 ms±0.01 ms
Cuda1.93 ms±0.04 ms——
singleHost14.67 ms±0.20 ms2.61 ms±0.02 ms
Cuda1.79 ms±0.03 ms——
doubleHost15.08 ms±0.72 ms4.83 ms±0.02 ms
Cuda1.90 ms±0.05 ms——
4000x4000boolHost62.81 ms±15.01 ms——
Cuda5.09 ms±0.12 ms——
int32Host54.15 ms±2.34 ms10.70 ms±0.13 ms
Cuda5.02 ms±0.12 ms——
int64Host53.61 ms±1.97 ms19.95 ms±0.03 ms
Cuda5.78 ms±0.13 ms——
singleHost54.14 ms±3.81 ms10.75 ms±0.03 ms
Cuda4.98 ms±0.06 ms——
doubleHost54.40 ms±1.30 ms19.95 ms±0.05 ms
Cuda5.71 ms±0.13 ms——
greaterOrEqual1000x1000boolHost5.86 ms±0.28 ms——
Cuda1.01 ms±0.03 ms——
int32Host3.99 ms±0.30 ms0.44 ms±0.01 ms
Cuda0.95 ms±0.04 ms——
int64Host3.90 ms±0.19 ms1.16 ms±0.01 ms
Cuda0.98 ms±0.02 ms——
singleHost3.98 ms±0.11 ms0.45 ms±0.01 ms
Cuda1.02 ms±0.07 ms——
doubleHost4.21 ms±0.24 ms1.15 ms±0.02 ms
Cuda0.96 ms±0.02 ms——
2000x2000boolHost14.82 ms±0.81 ms——
Cuda1.77 ms±0.07 ms——
int32Host14.86 ms±0.80 ms2.59 ms±0.01 ms
Cuda1.73 ms±0.05 ms——
int64Host14.69 ms±0.51 ms4.82 ms±0.01 ms
Cuda1.89 ms±0.04 ms——
singleHost15.06 ms±1.13 ms2.60 ms±0.02 ms
Cuda1.75 ms±0.05 ms——
doubleHost15.63 ms±0.54 ms4.83 ms±0.02 ms
Cuda1.94 ms±0.05 ms——
4000x4000boolHost54.91 ms±0.60 ms——
Cuda4.94 ms±0.03 ms——
int32Host54.11 ms±1.68 ms10.75 ms±0.02 ms
Cuda5.03 ms±0.16 ms——
int64Host54.11 ms±1.69 ms19.91 ms±0.01 ms
Cuda5.77 ms±0.20 ms——
singleHost54.39 ms±2.23 ms10.72 ms±0.03 ms
Cuda4.98 ms±0.13 ms——
doubleHost53.81 ms±2.73 ms19.97 ms±0.01 ms
Cuda5.83 ms±0.24 ms——
not1000x1000boolHost5.52 ms±0.15 ms0.11 ms±0.00 ms
Cuda0.90 ms±0.05 ms——
2000x2000Host14.59 ms±1.19 ms0.45 ms±0.01 ms
Cuda1.54 ms±0.06 ms——
4000x4000Host45.90 ms±2.41 ms2.82 ms±0.02 ms
Cuda4.78 ms±0.16 ms——
and1000x1000boolHost5.80 ms±0.17 ms0.14 ms±0.00 ms
Cuda1.00 ms±0.05 ms——
2000x2000Host17.41 ms±0.78 ms0.79 ms±0.01 ms
Cuda1.64 ms±0.05 ms——
4000x4000Host57.37 ms±8.14 ms3.90 ms±0.02 ms
Cuda5.00 ms±0.05 ms——
or1000x1000boolHost6.05 ms±1.03 ms0.14 ms±0.00 ms
Cuda1.05 ms±0.02 ms——
2000x2000Host16.03 ms±1.36 ms0.78 ms±0.01 ms
Cuda1.75 ms±0.05 ms——
4000x4000Host54.88 ms±4.52 ms3.87 ms±0.01 ms
Cuda4.88 ms±0.08 ms——
xor1000x1000boolHost5.79 ms±0.09 ms1.53 ms±0.00 ms
Cuda1.01 ms±0.02 ms——
2000x2000Host15.03 ms±0.24 ms6.15 ms±0.01 ms
Cuda1.78 ms±0.06 ms——
4000x4000Host52.76 ms±1.94 ms24.66 ms±0.01 ms
Cuda4.96 ms±0.10 ms——
countTrueAxis1000x1000boolHost3.42 ms±0.11 ms1.59 ms±0.00 ms
2000x2000Host12.76 ms±0.70 ms6.25 ms±0.01 ms
4000x4000Host44.79 ms±1.56 ms24.97 ms±0.05 ms
allAxis1000x1000boolHost3.04 ms±0.43 ms——
Cuda1.14 ms±0.02 ms——
2000x2000Host10.79 ms±0.52 ms——
Cuda2.12 ms±0.03 ms——
4000x4000Host43.31 ms±2.21 ms——
Cuda4.11 ms±0.01 ms——
anyAxis1000x1000boolHost3.10 ms±0.28 ms——
Cuda1.15 ms±0.04 ms——
2000x2000Host12.73 ms±0.49 ms——
Cuda2.16 ms±0.05 ms——
4000x4000Host42.06 ms±2.30 ms——
Cuda4.12 ms±0.02 ms——
trueIndices1000x1000boolHost33.62 ms±2.85 ms——
2000x2000Host114.49 ms±4.33 ms——
4000x4000Host459.89 ms±2.51 ms——
ifThenElse1000x1000boolHost6.35 ms±0.19 ms——
Cuda1.12 ms±0.03 ms——
int32Host5.80 ms±0.25 ms7.00 ms±0.01 ms
Cuda0.98 ms±0.05 ms——
int64Host6.49 ms±0.20 ms7.22 ms±0.01 ms
Cuda1.17 ms±0.05 ms——
singleHost6.39 ms±0.58 ms7.00 ms±0.01 ms
Cuda1.09 ms±0.03 ms——
doubleHost6.72 ms±0.37 ms7.22 ms±0.01 ms
Cuda1.13 ms±0.04 ms——
2000x2000boolHost17.06 ms±0.77 ms——
Cuda2.05 ms±0.06 ms——
int32Host17.83 ms±0.23 ms28.11 ms±0.01 ms
Cuda2.19 ms±0.06 ms——
int64Host20.08 ms±0.81 ms28.98 ms±0.01 ms
Cuda2.63 ms±0.10 ms——
singleHost17.64 ms±0.34 ms28.12 ms±0.01 ms
Cuda2.13 ms±0.09 ms——
doubleHost20.90 ms±0.59 ms29.01 ms±0.02 ms
Cuda2.55 ms±0.06 ms——
4000x4000boolHost59.95 ms±1.70 ms——
Cuda6.08 ms±0.05 ms——
int32Host68.17 ms±2.13 ms140.58 ms±0.02 ms
Cuda6.33 ms±0.11 ms——
int64Host74.97 ms±2.84 ms173.15 ms±0.03 ms
Cuda9.94 ms±0.42 ms——
singleHost66.09 ms±1.34 ms140.63 ms±0.03 ms
Cuda6.29 ms±0.19 ms——
doubleHost74.37 ms±0.80 ms173.27 ms±0.10 ms
Cuda10.17 ms±1.07 ms——
identity1000x1000int32Host——0.31 ms±0.00 ms
int64Host——0.61 ms±0.01 ms
singleHost——0.31 ms±0.00 ms
doubleHost——0.61 ms±0.01 ms
2000x2000int32Host——1.65 ms±0.02 ms
int64Host——3.64 ms±0.01 ms
singleHost——1.65 ms±0.02 ms
doubleHost——3.64 ms±0.01 ms
4000x4000int32Host——6.83 ms±0.02 ms
int64Host——6.87 ms±0.02 ms
singleHost——6.84 ms±0.02 ms
doubleHost——6.87 ms±0.02 ms

Report generated on Tue, 08 May 2018 12:49:58 GMT.