NVIDIA TITAN RTX On Linux

AMD Ryzen 9 3950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS) and NVIDIA TITAN RTX 24GB on Ubuntu 20.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2010017-PTS-NVIDIATI83
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

HPC - High Performance Computing 2 Tests
Machine Learning 2 Tests
NVIDIA GPU Compute 6 Tests
Vulkan Compute 3 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
1
October 01 2020
  32 Minutes
2
October 01 2020
  29 Minutes
3
October 01 2020
  29 Minutes
4
October 01 2020
  29 Minutes
5
October 01 2020
  29 Minutes
Invert Hiding All Results Option
  30 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


NVIDIA TITAN RTX On LinuxProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen Resolution12345AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS)AMD Starship/Matisse16GB2000GB Corsair Force MP600 + 2000GBNVIDIA TITAN RTX 24GB (390/405MHz)NVIDIA TU102 HD AudioDELL P2415QRealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.045.4.0-48-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8NVIDIA 450.664.6.0OpenCL 2.0 AMD-APP (3182.0) + OpenCL 1.2 CUDA 11.0.2281.2.133GCC 9.3.0 + CUDA 11.0ext43840x2160NVIDIA TITAN RTX 24GB (1350/7000MHz)NVIDIA TITAN RTX 24GB (390/405MHz)NVIDIA TITAN RTX 24GB (1350/7000MHz)NVIDIA TITAN RTX 24GB (390/405MHz)OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013OpenCL Details- GPU Compute Cores: 4608Python Details- Python 3.8.2Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

12345Result OverviewPhoronix Test Suite100%100%101%101%102%RealSR-NCNNNCNNVkFFTHashcatRedShift DemoCaffe

NVIDIA TITAN RTX On Linuxrealsr-ncnn: 4x - Norealsr-ncnn: 4x - Yesvkfft: hashcat: MD5hashcat: SHA1hashcat: 7-Ziphashcat: SHA-512hashcat: TrueCrypt RIPEMD160 + XTSredshift: caffe: AlexNet - NVIDIA CUDA - 100caffe: AlexNet - NVIDIA CUDA - 200caffe: AlexNet - NVIDIA CUDA - 1000caffe: GoogleNet - NVIDIA CUDA - 100caffe: GoogleNet - NVIDIA CUDA - 200caffe: GoogleNet - NVIDIA CUDA - 1000ncnn: Vulkan GPU - squeezenetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tiny123457.83142.8844013857420166667183076000009165332541833333672533235922.1231805.538921.312855.005680.1628171.03.864.141.381.641.281.442.60.583.025.081.321.633.067.347.97643.0854004757241333333182597666679172002534366667670800235924.7031806.408920.172875.905678.6028230.83.864.131.391.641.291.452.590.572.975.091.321.573.057.177.85842.6554001957365533333183223000009170002541733333672600235923.2381810.298900.182860.435693.3428178.63.904.141.381.641.281.452.600.582.985.081.321.623.057.157.84942.8164004857329633333182854333339151672540333333671700235923.6671812.078934.212861.315657.5128240.13.904.131.381.641.281.452.600.592.975.091.311.583.067.177.82542.6064006157416166667183244666679199332541766667672200235931.0241811.358986.352878.315693.6628365.73.884.161.401.641.281.452.610.582.975.071.311.603.067.15OpenBenchmarking.org

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No12345246810SE +/- 0.063, N = 3SE +/- 0.063, N = 3SE +/- 0.068, N = 3SE +/- 0.073, N = 3SE +/- 0.087, N = 37.8317.9767.8587.8497.825
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No123453691215Min: 7.75 / Avg: 7.83 / Max: 7.96Min: 7.91 / Avg: 7.98 / Max: 8.1Min: 7.79 / Avg: 7.86 / Max: 7.99Min: 7.77 / Avg: 7.85 / Max: 7.99Min: 7.71 / Avg: 7.83 / Max: 7.99

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Yes123451020304050SE +/- 0.16, N = 3SE +/- 0.18, N = 3SE +/- 0.24, N = 3SE +/- 0.18, N = 3SE +/- 0.23, N = 342.8843.0942.6642.8242.61
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Yes12345918273645Min: 42.57 / Avg: 42.88 / Max: 43.07Min: 42.79 / Avg: 43.08 / Max: 43.4Min: 42.25 / Avg: 42.66 / Max: 43.07Min: 42.46 / Avg: 42.82 / Max: 43.06Min: 42.19 / Avg: 42.61 / Max: 42.98

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 2020-09-29123459K18K27K36K45KSE +/- 35.69, N = 3SE +/- 17.33, N = 3SE +/- 11.20, N = 3SE +/- 17.68, N = 3SE +/- 7.23, N = 34013840047400194004840061
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 2020-09-29123457K14K21K28K35KMin: 40068 / Avg: 40137.67 / Max: 40186Min: 40018 / Avg: 40047.33 / Max: 40078Min: 40006 / Avg: 40018.67 / Max: 40041Min: 40013 / Avg: 40047.67 / Max: 40071Min: 40049 / Avg: 40061 / Max: 40074

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD51234512000M24000M36000M48000M60000MSE +/- 31137883.32, N = 3SE +/- 70861139.64, N = 3SE +/- 47871262.55, N = 3SE +/- 85923577.15, N = 3SE +/- 76423651.08, N = 35742016666757241333333573655333335732963333357416166667
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD51234510000M20000M30000M40000M50000MMin: 57360200000 / Avg: 57420166666.67 / Max: 57464700000Min: 57164800000 / Avg: 57241333333.33 / Max: 57382900000Min: 57314400000 / Avg: 57365533333.33 / Max: 57461200000Min: 57216800000 / Avg: 57329633333.33 / Max: 57498300000Min: 57307800000 / Avg: 57416166666.67 / Max: 57563700000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1123454000M8000M12000M16000M20000MSE +/- 14435719.59, N = 3SE +/- 7574592.03, N = 3SE +/- 14301048.91, N = 3SE +/- 14493025.14, N = 3SE +/- 10927844.15, N = 31830760000018259766667183223000001828543333318324466667
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1123453000M6000M9000M12000M15000MMin: 18279900000 / Avg: 18307600000 / Max: 18328500000Min: 18251600000 / Avg: 18259766666.67 / Max: 18274900000Min: 18307700000 / Avg: 18322300000 / Max: 18350900000Min: 18257700000 / Avg: 18285433333.33 / Max: 18306600000Min: 18311600000 / Avg: 18324466666.67 / Max: 18346200000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-Zip12345200K400K600K800K1000KSE +/- 290.59, N = 3SE +/- 4404.92, N = 3SE +/- 2150.19, N = 3SE +/- 218.58, N = 3SE +/- 2945.24, N = 3916533917200917000915167919933
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-Zip12345160K320K480K640K800KMin: 916000 / Avg: 916533.33 / Max: 917000Min: 908800 / Avg: 917200 / Max: 923700Min: 914100 / Avg: 917000 / Max: 921200Min: 914900 / Avg: 915166.67 / Max: 915600Min: 915300 / Avg: 919933.33 / Max: 925400

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-51212345500M1000M1500M2000M2500MSE +/- 1348249.89, N = 3SE +/- 2493547.23, N = 3SE +/- 2233333.33, N = 3SE +/- 1920358.76, N = 3SE +/- 2162046.36, N = 325418333332534366667254173333325403333332541766667
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-51212345400M800M1200M1600M2000MMin: 2539300000 / Avg: 2541833333.33 / Max: 2543900000Min: 2530300000 / Avg: 2534366666.67 / Max: 2538900000Min: 2539500000 / Avg: 2541733333.33 / Max: 2546200000Min: 2537800000 / Avg: 2540333333.33 / Max: 2544100000Min: 2538400000 / Avg: 2541766666.67 / Max: 2545800000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTS12345140K280K420K560K700KSE +/- 66.67, N = 3SE +/- 300.00, N = 3SE +/- 57.74, N = 3SE +/- 400.00, N = 3SE +/- 702.38, N = 3672533670800672600671700672200
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTS12345120K240K360K480K600KMin: 672400 / Avg: 672533.33 / Max: 672600Min: 670200 / Avg: 670800 / Max: 671100Min: 672500 / Avg: 672600 / Max: 672700Min: 670900 / Avg: 671700 / Max: 672100Min: 670800 / Avg: 672200 / Max: 673000

RedShift Demo

This is a test of MAXON's RedShift demo build that currently requires NVIDIA GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.01234550100150200250SE +/- 0.33, N = 3235235235235235
OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.0123454080120160200Min: 235 / Avg: 235.33 / Max: 236

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 100123452004006008001000SE +/- 3.49, N = 3SE +/- 6.92, N = 3SE +/- 5.77, N = 3SE +/- 6.30, N = 3SE +/- 6.25, N = 3922.12924.70923.24923.67931.021. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 10012345160320480640800Min: 917.64 / Avg: 922.12 / Max: 928.99Min: 911.74 / Avg: 924.7 / Max: 935.38Min: 912.84 / Avg: 923.24 / Max: 932.76Min: 911.87 / Avg: 923.67 / Max: 933.38Min: 919.11 / Avg: 931.02 / Max: 940.241. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 20012345400800120016002000SE +/- 4.34, N = 3SE +/- 3.74, N = 3SE +/- 7.02, N = 3SE +/- 1.42, N = 3SE +/- 4.80, N = 31805.531806.401810.291812.071811.351. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 2001234530060090012001500Min: 1798.79 / Avg: 1805.53 / Max: 1813.65Min: 1799.45 / Avg: 1806.4 / Max: 1812.29Min: 1796.54 / Avg: 1810.29 / Max: 1819.63Min: 1809.34 / Avg: 1812.07 / Max: 1814.12Min: 1802.17 / Avg: 1811.35 / Max: 1818.341. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 1000123452K4K6K8K10KSE +/- 3.89, N = 3SE +/- 2.81, N = 3SE +/- 10.24, N = 3SE +/- 25.22, N = 3SE +/- 66.63, N = 38921.318920.178900.188934.218986.351. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 10001234516003200480064008000Min: 8917.11 / Avg: 8921.31 / Max: 8929.08Min: 8915.14 / Avg: 8920.17 / Max: 8924.85Min: 8885.47 / Avg: 8900.18 / Max: 8919.87Min: 8904.39 / Avg: 8934.21 / Max: 8984.35Min: 8904.55 / Avg: 8986.35 / Max: 9118.351. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 100123456001200180024003000SE +/- 2.35, N = 3SE +/- 6.81, N = 3SE +/- 13.01, N = 3SE +/- 19.64, N = 3SE +/- 16.43, N = 32855.002875.902860.432861.312878.311. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 100123455001000150020002500Min: 2852.07 / Avg: 2855 / Max: 2859.64Min: 2863.03 / Avg: 2875.9 / Max: 2886.19Min: 2835.02 / Avg: 2860.43 / Max: 2878Min: 2838.22 / Avg: 2861.31 / Max: 2900.37Min: 2856.25 / Avg: 2878.31 / Max: 2910.441. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 2001234512002400360048006000SE +/- 9.16, N = 3SE +/- 5.02, N = 3SE +/- 23.06, N = 3SE +/- 15.61, N = 3SE +/- 9.15, N = 35680.165678.605693.345657.515693.661. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 2001234510002000300040005000Min: 5663.46 / Avg: 5680.16 / Max: 5695.05Min: 5671.19 / Avg: 5678.6 / Max: 5688.16Min: 5651.86 / Avg: 5693.34 / Max: 5731.55Min: 5626.61 / Avg: 5657.51 / Max: 5676.8Min: 5678.38 / Avg: 5693.66 / Max: 5710.031. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 1000123456K12K18K24K30KSE +/- 93.92, N = 3SE +/- 11.37, N = 3SE +/- 39.43, N = 3SE +/- 49.35, N = 3SE +/- 60.61, N = 328171.028230.828178.628240.128365.71. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 1000123455K10K15K20K25KMin: 27983.2 / Avg: 28171.03 / Max: 28266.9Min: 28215.1 / Avg: 28230.8 / Max: 28252.9Min: 28114.9 / Avg: 28178.57 / Max: 28250.7Min: 28183.2 / Avg: 28240.1 / Max: 28338.4Min: 28244.6 / Avg: 28365.7 / Max: 28430.81. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenet123450.87751.7552.63253.514.3875SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 33.863.863.903.903.88MIN: 3.74 / MAX: 5.31MIN: 3.71 / MAX: 5.2MIN: 3.74 / MAX: 4.41MIN: 3.77 / MAX: 7.98MIN: 3.76 / MAX: 51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenet12345246810Min: 3.86 / Avg: 3.86 / Max: 3.87Min: 3.82 / Avg: 3.86 / Max: 3.89Min: 3.84 / Avg: 3.9 / Max: 3.94Min: 3.89 / Avg: 3.9 / Max: 3.92Min: 3.85 / Avg: 3.88 / Max: 3.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenet123450.9361.8722.8083.7444.68SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 34.144.134.144.134.16MIN: 4.06 / MAX: 7.21MIN: 4.03 / MAX: 8.16MIN: 4.08 / MAX: 5.99MIN: 4.04 / MAX: 7.11MIN: 4.09 / MAX: 15.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenet12345246810Min: 4.12 / Avg: 4.14 / Max: 4.18Min: 4.08 / Avg: 4.13 / Max: 4.17Min: 4.12 / Avg: 4.14 / Max: 4.17Min: 4.11 / Avg: 4.13 / Max: 4.15Min: 4.13 / Avg: 4.16 / Max: 4.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2123450.3150.630.9451.261.575SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 31.381.391.381.381.40MIN: 1.36 / MAX: 1.43MIN: 1.37 / MAX: 2.58MIN: 1.37 / MAX: 1.77MIN: 1.37 / MAX: 2.56MIN: 1.37 / MAX: 9.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v212345246810Min: 1.38 / Avg: 1.38 / Max: 1.38Min: 1.38 / Avg: 1.39 / Max: 1.39Min: 1.38 / Avg: 1.38 / Max: 1.38Min: 1.38 / Avg: 1.38 / Max: 1.39Min: 1.38 / Avg: 1.4 / Max: 1.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3123450.3690.7381.1071.4761.845SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.641.641.641.641.64MIN: 1.62 / MAX: 1.67MIN: 1.63 / MAX: 1.71MIN: 1.62 / MAX: 1.67MIN: 1.61 / MAX: 2.74MIN: 1.62 / MAX: 2.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v312345246810Min: 1.63 / Avg: 1.64 / Max: 1.64Min: 1.63 / Avg: 1.64 / Max: 1.65Min: 1.63 / Avg: 1.64 / Max: 1.64Min: 1.64 / Avg: 1.64 / Max: 1.64Min: 1.63 / Avg: 1.64 / Max: 1.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v2123450.29030.58060.87091.16121.4515SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.281.291.281.281.28MIN: 1.27 / MAX: 1.34MIN: 1.27 / MAX: 1.5MIN: 1.27 / MAX: 1.35MIN: 1.27 / MAX: 1.47MIN: 1.27 / MAX: 1.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v212345246810Min: 1.28 / Avg: 1.28 / Max: 1.28Min: 1.28 / Avg: 1.29 / Max: 1.29Min: 1.28 / Avg: 1.28 / Max: 1.28Min: 1.28 / Avg: 1.28 / Max: 1.28Min: 1.28 / Avg: 1.28 / Max: 1.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnet123450.32630.65260.97891.30521.6315SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 31.441.451.451.451.45MIN: 1.43 / MAX: 1.49MIN: 1.43 / MAX: 6.87MIN: 1.43 / MAX: 2.12MIN: 1.43 / MAX: 2.58MIN: 1.43 / MAX: 2.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnet12345246810Min: 1.44 / Avg: 1.44 / Max: 1.44Min: 1.44 / Avg: 1.45 / Max: 1.47Min: 1.44 / Avg: 1.45 / Max: 1.45Min: 1.45 / Avg: 1.45 / Max: 1.45Min: 1.44 / Avg: 1.45 / Max: 1.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0123450.58731.17461.76192.34922.9365SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 32.602.592.602.602.61MIN: 2.59 / MAX: 2.89MIN: 2.58 / MAX: 2.79MIN: 2.59 / MAX: 2.87MIN: 2.59 / MAX: 3.69MIN: 2.59 / MAX: 3.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b012345246810Min: 2.6 / Avg: 2.6 / Max: 2.6Min: 2.59 / Avg: 2.59 / Max: 2.6Min: 2.59 / Avg: 2.6 / Max: 2.61Min: 2.59 / Avg: 2.6 / Max: 2.61Min: 2.6 / Avg: 2.61 / Max: 2.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazeface123450.13280.26560.39840.53120.664SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 30.580.570.580.590.58MIN: 0.57 / MAX: 0.71MAX: 0.6MIN: 0.56 / MAX: 0.62MIN: 0.57 / MAX: 1.82MIN: 0.57 / MAX: 1.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazeface12345246810Min: 0.58 / Avg: 0.58 / Max: 0.58Min: 0.57 / Avg: 0.57 / Max: 0.58Min: 0.57 / Avg: 0.58 / Max: 0.58Min: 0.58 / Avg: 0.59 / Max: 0.59Min: 0.57 / Avg: 0.58 / Max: 0.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenet123450.67951.3592.03852.7183.3975SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 33.022.972.982.972.97MIN: 2.96 / MAX: 7.02MIN: 2.95 / MAX: 3.79MIN: 2.95 / MAX: 4.92MIN: 2.95 / MAX: 4.06MIN: 2.95 / MAX: 3.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenet12345246810Min: 2.97 / Avg: 3.02 / Max: 3.09Min: 2.96 / Avg: 2.97 / Max: 2.97Min: 2.97 / Avg: 2.98 / Max: 3Min: 2.97 / Avg: 2.97 / Max: 2.97Min: 2.96 / Avg: 2.97 / Max: 2.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16123451.14532.29063.43594.58125.7265SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 35.085.095.085.095.07MIN: 4.92 / MAX: 18.61MIN: 4.93 / MAX: 9.69MIN: 4.92 / MAX: 18.32MIN: 4.93 / MAX: 18.51MIN: 4.92 / MAX: 18.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg1612345246810Min: 5.06 / Avg: 5.08 / Max: 5.11Min: 5.01 / Avg: 5.09 / Max: 5.24Min: 5.03 / Avg: 5.08 / Max: 5.16Min: 5.01 / Avg: 5.09 / Max: 5.13Min: 5.04 / Avg: 5.07 / Max: 5.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18123450.2970.5940.8911.1881.485SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.321.321.321.311.31MIN: 1.3 / MAX: 3.18MIN: 1.3 / MAX: 1.45MIN: 1.31 / MAX: 1.5MIN: 1.3 / MAX: 1.97MIN: 1.3 / MAX: 2.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet1812345246810Min: 1.31 / Avg: 1.32 / Max: 1.33Min: 1.31 / Avg: 1.32 / Max: 1.32Min: 1.31 / Avg: 1.32 / Max: 1.32Min: 1.31 / Avg: 1.31 / Max: 1.32Min: 1.31 / Avg: 1.31 / Max: 1.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnet123450.36680.73361.10041.46721.834SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 2SE +/- 0.01, N = 3SE +/- 0.03, N = 31.631.571.621.581.60MIN: 1.54 / MAX: 4.84MIN: 1.54 / MAX: 1.82MIN: 1.55 / MAX: 1.86MIN: 1.54 / MAX: 6.38MIN: 1.55 / MAX: 2.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnet12345246810Min: 1.6 / Avg: 1.63 / Max: 1.66Min: 1.56 / Avg: 1.57 / Max: 1.58Min: 1.62 / Avg: 1.62 / Max: 1.62Min: 1.56 / Avg: 1.58 / Max: 1.59Min: 1.57 / Avg: 1.6 / Max: 1.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet50123450.68851.3772.06552.7543.4425SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 33.063.053.053.063.06MIN: 3.03 / MAX: 4.65MIN: 3.03 / MAX: 3.55MIN: 3.02 / MAX: 4.01MIN: 3.04 / MAX: 4.53MIN: 3.02 / MAX: 7.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet5012345246810Min: 3.05 / Avg: 3.06 / Max: 3.06Min: 3.05 / Avg: 3.05 / Max: 3.06Min: 3.04 / Avg: 3.05 / Max: 3.06Min: 3.06 / Avg: 3.06 / Max: 3.06Min: 3.04 / Avg: 3.06 / Max: 3.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tiny12345246810SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 37.347.177.157.177.15MIN: 6.93 / MAX: 18.18MIN: 6.94 / MAX: 13.24MIN: 6.93 / MAX: 13.66MIN: 6.93 / MAX: 8.75MIN: 6.92 / MAX: 9.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tiny123453691215Min: 7.15 / Avg: 7.34 / Max: 7.56Min: 7.13 / Avg: 7.17 / Max: 7.21Min: 7.11 / Avg: 7.15 / Max: 7.22Min: 7.15 / Avg: 7.17 / Max: 7.18Min: 7.13 / Avg: 7.15 / Max: 7.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread