ddda

AMD Ryzen AI 9 365 testing with a ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS) and AMD Radeon 512MB on Ubuntu 24.10 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 2412307-NE-DDDA8846655
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
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
December 30 2024
  1 Hour, 10 Minutes
b
December 30 2024
  1 Hour, 8 Minutes
c
December 30 2024
  1 Hour, 7 Minutes
d
December 30 2024
  1 Hour, 8 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 8 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):


dddaOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen AI 9 365 @ 4.31GHz (10 Cores / 20 Threads)ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS)AMD Device 15074 x 6GB LPDDR5-7500MT/s Micron MT62F1536M32D4DS-0261024GB MTFDKBA1T0QFM-1BD1AABGBAMD Radeon 512MBAMD Rembrandt Radeon HD AudioMEDIATEK Device 7925Ubuntu 24.106.12.0-rc7-phx-eraps (x86_64)GNOME Shell 47.0X Server + Wayland4.6 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 DRM 3.59)GCC 14.2.0ext42880x1800ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionDdda BenchmarksSystem Logs- amdgpu.dcdebugmask=0x600 - Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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 - Scaling Governor: amd-pstate-epp powersave (Boost: Enabled EPP: balance_performance) - Platform Profile: balanced - CPU Microcode: 0xb204011 - ACPI Profile: balanced - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; PBRSB-eIBRS: Not affected; BHI: Not affected; ERAPS hardware RSB flush + srbds: Not affected + tsx_async_abort: Not affected

abcdResult OverviewPhoronix Test Suite100%111%122%134%145%NCNNLlama.cppNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNLlama.cppNCNNLlama.cppNCNNNCNNNCNNLlama.cppNCNNNCNNNCNNLlama.cppNCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNLlama.cppNCNNLlama.cppNCNNNCNNLlama.cppNCNNNCNNNCNNNCNNNCNNNCNNNCNNLlama.cppNCNNNCNNLlama.cppLlama.cppLlama.cppVulkan GPU - FastestDetCPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - P.P.5CPU - resnet18CPU - alexnetVulkan GPU - blazefaceCPU - googlenetCPU - squeezenet_ssdCPU - blazefaceCPU - mobilenetCPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - P.P.1Vulkan GPU - yolov4-tinyCPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - P.P.2CPU-v3-v3 - mobilenet-v3Vulkan GPU - resnet18CPU - yolov4-tinyCPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.1Vulkan GPU - googlenetVulkan GPU - squeezenet_ssdVulkan GPU-v3-v3 - mobilenet-v3CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.2Vulkan GPU - mnasnetCPU - mnasnetVulkan GPU - shufflenet-v2Vulkan GPU - vision_transformerCPU-v2-v2 - mobilenet-v2Vulkan GPU - alexnetCPU - resnet50Vulkan GPU - efficientnet-b0CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.5Vulkan GPU - regnety_400mCPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - T.G.1CPU - shufflenet-v2CPU - regnety_400mCPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - P.P.5CPU - efficientnet-b0Vulkan GPU - vgg16CPU - vgg16CPU - FastestDetVulkan GPU - resnet50Vulkan GPU - mobilenetV.G.y.y - mobilenetv2-yolov3CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - P.P.1Vulkan GPU-v2-v2 - mobilenet-v2CPU - vision_transformerCPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - T.G.1CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - P.P.2CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - T.G.1

dddancnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetncnn: 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 GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDetllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048abcd11.884.683.763.233.735.141.1710.2233.837.055.8313.9211.8815.888.449.1770.924.1211.394.343.652.993.494.841.249.0133.385.974.9614.111.3915.188.059.1271.322.7710.338.7137.2831.6210.7536.1134.331.5859.22151.41151.53139.2810.734.423.43.123.9951.3310.5733.425.965.2914.3610.7314.698.049.1971.624.2411.524.293.562.823.414.921.129.3532.296.015.041411.5217.068.738.8971.773.4910.3337.4237.4235.410.8637.4637.7333.1260.7158.37158.82139.5711.874.473.53.113.864.971.279.4932.756.124.9714.6511.8716.199.139.271.614.1711.514.333.6933.465.051.199.5332.386.65.1714.111.5116.178.539.1468.182.7510.3238.436.9435.1610.837.9736.5733.8160.75151.53150.48140.3610.514.543.513.223.934.991.289.1933.195.935.0814.4410.5114.858.038.8771.744.2511.694.323.412.913.264.81.078.7433.236.145.2314.3811.6916.528.318.7472.363.9810.337.3437.3832.9810.8136.3235.2532.6358.28131.74141.29139.91OpenBenchmarking.org

NCNN

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: mobilenetabcd369121511.8810.7311.8710.51MIN: 11.76 / MAX: 17.05MIN: 10.62 / MAX: 12.77MIN: 11.6 / MAX: 35.77MIN: 10.4 / MAX: 12.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU-v2-v2 - Model: mobilenet-v2abcd1.0532.1063.1594.2125.2654.684.424.474.54MIN: 4.11 / MAX: 35.42MIN: 3.66 / MAX: 33.56MIN: 3.78 / MAX: 33.88MIN: 3.8 / MAX: 29.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU-v3-v3 - Model: mobilenet-v3abcd0.8461.6922.5383.3844.233.763.403.503.51MIN: 3.53 / MAX: 28.89MIN: 3.25 / MAX: 26.22MIN: 3.3 / MAX: 45.42MIN: 3.35 / MAX: 27.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: shufflenet-v2abcd0.72681.45362.18042.90723.6343.233.123.113.22MIN: 2.93 / MAX: 35.88MIN: 2.99 / MAX: 25.69MIN: 2.86 / MAX: 32.43MIN: 3.07 / MAX: 34.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: mnasnetabcd0.89781.79562.69343.59124.4893.733.993.863.93MIN: 3.52 / MAX: 25.76MIN: 3.66 / MAX: 30.25MIN: 3.51 / MAX: 53.01MIN: 3.64 / MAX: 32.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: efficientnet-b0abcd1.15652.3133.46954.6265.78255.145.004.974.99MIN: 5.1 / MAX: 5.68MIN: 4.92 / MAX: 9.16MIN: 4.92 / MAX: 6.74MIN: 4.93 / MAX: 5.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: blazefaceabcd0.29930.59860.89791.19721.49651.171.331.271.28MIN: 1.15 / MAX: 1.32MIN: 1.3 / MAX: 2MIN: 1.26 / MAX: 1.43MIN: 1.26 / MAX: 1.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: googlenetabcd369121510.2210.579.499.19MIN: 10.02 / MAX: 14.16MIN: 9.04 / MAX: 50.3MIN: 8.97 / MAX: 57.01MIN: 8.9 / MAX: 49.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: vgg16abcd81624324033.8333.4232.7533.19MIN: 31.89 / MAX: 74.06MIN: 32.44 / MAX: 75.15MIN: 31.39 / MAX: 55.09MIN: 31.59 / MAX: 64.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: resnet18abcd2468107.055.966.125.93MIN: 7 / MAX: 7.99MIN: 5.89 / MAX: 7.95MIN: 5.81 / MAX: 30.87MIN: 5.83 / MAX: 7.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: alexnetabcd1.31182.62363.93545.24726.5595.835.294.975.08MIN: 5.76 / MAX: 7.28MIN: 5.01 / MAX: 17.98MIN: 4.66 / MAX: 10.74MIN: 4.97 / MAX: 6.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: resnet50abcd4812162013.9214.3614.6514.44MIN: 13.33 / MAX: 58.77MIN: 12.97 / MAX: 61.42MIN: 14.54 / MAX: 15.47MIN: 13.49 / MAX: 34.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3abcd369121511.8810.7311.8710.51MIN: 11.76 / MAX: 17.05MIN: 10.62 / MAX: 12.77MIN: 11.6 / MAX: 35.77MIN: 10.4 / MAX: 12.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: yolov4-tinyabcd4812162015.8814.6916.1914.85MIN: 15.09 / MAX: 54.54MIN: 14.27 / MAX: 69.64MIN: 14.04 / MAX: 25.8MIN: 14.14 / MAX: 85.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: squeezenet_ssdabcd36912158.448.049.138.03MIN: 8.25 / MAX: 27.11MIN: 7.86 / MAX: 25.17MIN: 8.78 / MAX: 67.75MIN: 7.87 / MAX: 12.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: regnety_400mabcd36912159.179.199.208.87MIN: 9.11 / MAX: 11.17MIN: 9.1 / MAX: 12.28MIN: 8.93 / MAX: 57.09MIN: 8.63 / MAX: 46.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: vision_transformerabcd163248648070.9271.6271.6171.74MIN: 68.66 / MAX: 103.73MIN: 69.18 / MAX: 102.55MIN: 67.29 / MAX: 115.35MIN: 69.59 / MAX: 91.141. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: CPU - Model: FastestDetabcd0.95631.91262.86893.82524.78154.124.244.174.25MIN: 4.08 / MAX: 5.73MIN: 4.12 / MAX: 25.65MIN: 3.99 / MAX: 32.13MIN: 4.21 / MAX: 8.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: mobilenetabcd369121511.3911.5211.5111.69MIN: 11.22 / MAX: 16.67MIN: 11.29 / MAX: 40.04MIN: 11.28 / MAX: 31.2MIN: 11.56 / MAX: 17.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2abcd0.97651.9532.92953.9064.88254.344.294.334.32MIN: 3.65 / MAX: 34.66MIN: 3.64 / MAX: 29.66MIN: 3.66 / MAX: 31.75MIN: 3.64 / MAX: 27.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3abcd0.83031.66062.49093.32124.15153.653.563.693.41MIN: 3.38 / MAX: 31.52MIN: 3.32 / MAX: 26.9MIN: 3.34 / MAX: 53.01MIN: 3.11 / MAX: 34.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: shufflenet-v2abcd0.6751.352.0252.73.3752.992.823.002.91MIN: 2.87 / MAX: 25.33MIN: 2.69 / MAX: 25.04MIN: 2.79 / MAX: 47.27MIN: 2.66 / MAX: 51.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: mnasnetabcd0.78531.57062.35593.14123.92653.493.413.463.26MIN: 3.36 / MAX: 29.39MIN: 3.26 / MAX: 31.3MIN: 3.33 / MAX: 25.82MIN: 3.09 / MAX: 31.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: efficientnet-b0abcd1.13632.27263.40894.54525.68154.844.925.054.80MIN: 4.8 / MAX: 6.4MIN: 4.88 / MAX: 6.43MIN: 4.86 / MAX: 28.25MIN: 4.72 / MAX: 9.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: blazefaceabcd0.2790.5580.8371.1161.3951.241.121.191.07MIN: 1.18 / MAX: 5.63MIN: 1.11 / MAX: 1.34MIN: 1.18 / MAX: 1.23MIN: 1.06 / MAX: 1.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: googlenetabcd36912159.019.359.538.74MIN: 8.55 / MAX: 49.29MIN: 9.02 / MAX: 29.75MIN: 8.98 / MAX: 50.27MIN: 8.35 / MAX: 66.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: vgg16abcd81624324033.3832.2932.3833.23MIN: 31.56 / MAX: 65.09MIN: 30.48 / MAX: 69.49MIN: 31.27 / MAX: 63.71MIN: 30.69 / MAX: 148.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: resnet18abcd2468105.976.016.606.14MIN: 5.88 / MAX: 7.65MIN: 5.92 / MAX: 7.29MIN: 5.87 / MAX: 53.8MIN: 5.83 / MAX: 26.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: alexnetabcd1.17682.35363.53044.70725.8844.965.045.175.23MIN: 4.89 / MAX: 6.2MIN: 4.89 / MAX: 6.96MIN: 4.98 / MAX: 20.08MIN: 5.08 / MAX: 5.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: resnet50abcd4812162014.1014.0014.1014.38MIN: 13.4 / MAX: 38.99MIN: 13.83 / MAX: 15.63MIN: 13.45 / MAX: 36.9MIN: 13.78 / MAX: 58.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3abcd369121511.3911.5211.5111.69MIN: 11.22 / MAX: 16.67MIN: 11.29 / MAX: 40.04MIN: 11.28 / MAX: 31.2MIN: 11.56 / MAX: 17.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: yolov4-tinyabcd4812162015.1817.0616.1716.52MIN: 14.42 / MAX: 56.53MIN: 16.45 / MAX: 52.49MIN: 15.1 / MAX: 60.38MIN: 15.5 / MAX: 86.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: squeezenet_ssdabcd2468108.058.738.538.31MIN: 7.93 / MAX: 13.96MIN: 8.63 / MAX: 9.35MIN: 8.45 / MAX: 10.18MIN: 8.2 / MAX: 13.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: regnety_400mabcd36912159.128.899.148.74MIN: 8.89 / MAX: 34.9MIN: 8.74 / MAX: 10.45MIN: 9.05 / MAX: 13.54MIN: 8.64 / MAX: 9.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: vision_transformerabcd163248648071.3271.7768.1872.36MIN: 66.94 / MAX: 100.96MIN: 66.86 / MAX: 121.7MIN: 61.64 / MAX: 135.53MIN: 70.52 / MAX: 91.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20241226Target: Vulkan GPU - Model: FastestDetabcd0.89551.7912.68653.5824.47752.773.492.753.98MIN: 2.72 / MAX: 4.61MIN: 3.46 / MAX: 3.88MIN: 2.71 / MAX: 4.51MIN: 3.94 / MAX: 5.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128abcd369121510.3010.3310.3210.301. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512abcd91827364538.7137.4238.4037.341. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024abcd91827364537.2837.4236.9437.381. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048abcd81624324031.6235.4035.1632.981. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128abcd369121510.7510.8610.8010.811. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512abcd91827364536.1137.4637.9736.321. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024abcd91827364534.3037.7336.5735.251. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048abcd81624324031.5833.1233.8132.631. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128abcd142842567059.2260.7060.7558.281. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512abcd4080120160200151.41158.37151.53131.741. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024abcd4080120160200151.53158.82150.48141.291. (CXX) g++ options: -O3

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4397Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048abcd306090120150139.28139.57140.36139.911. (CXX) g++ options: -O3

48 Results Shown

NCNN:
  CPU - mobilenet
  CPU-v2-v2 - mobilenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU - shufflenet-v2
  CPU - mnasnet
  CPU - efficientnet-b0
  CPU - blazeface
  CPU - googlenet
  CPU - vgg16
  CPU - resnet18
  CPU - alexnet
  CPU - resnet50
  CPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3
  CPU - yolov4-tiny
  CPU - squeezenet_ssd
  CPU - regnety_400m
  CPU - vision_transformer
  CPU - FastestDet
  Vulkan GPU - mobilenet
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU - shufflenet-v2
  Vulkan GPU - mnasnet
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - blazeface
  Vulkan GPU - googlenet
  Vulkan GPU - vgg16
  Vulkan GPU - resnet18
  Vulkan GPU - alexnet
  Vulkan GPU - resnet50
  Vulkan GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - regnety_400m
  Vulkan GPU - vision_transformer
  Vulkan GPU - FastestDet
Llama.cpp:
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024
  CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048