sunny

Intel Core Ultra 7 256V testing with a ASUS Zenbook S 14 UX5406SA_UX5406SA UX5406SA v1.0 (UX5406SA.300 BIOS) and ASUS Intel LNL 7GB 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 2411241-NE-SUNNY000284
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
November 24
  3 Hours, 25 Minutes
b
November 24
  3 Hours, 24 Minutes
Invert Behavior (Only Show Selected Data)
  3 Hours, 24 Minutes
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):


sunnyOpenBenchmarking.orgPhoronix Test SuiteIntel Core Ultra 7 256V @ 4.70GHz (8 Cores)ASUS Zenbook S 14 UX5406SA_UX5406SA UX5406SA v1.0 (UX5406SA.300 BIOS)Intel Device a87f8 x 2GB LPDDR5-8533MT/s Samsung1024GB Western Digital WD PC SN560 SDDPNQE-1T00-1102ASUS Intel LNL 7GBIntel Lunar Lake-M HD AudioIntel Device a840Ubuntu 24.106.12.0-rc3-phx-aipt (x86_64)GNOME Shell 47.0X Server + Wayland4.6 Mesa 24.3~git2410200600.4bc2d2~oibaf~o (git-4bc2d22 2024-10-20 oracular-oibaf-ppOpenCL 3.0GCC 14.2.0ext42880x1800ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionSunny BenchmarksSystem Logs- 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: intel_pstate powersave (EPP: balance_performance) - Platform Profile: balanced - CPU Microcode: 0x114 - Thermald 2.5.8 - ACPI Profile: balanced - OpenJDK Runtime Environment (build 21.0.5+11-Ubuntu-1ubuntu124.10)- Python 3.12.7- 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; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

a vs. b ComparisonPhoronix Test SuiteBaseline+11.2%+11.2%+22.4%+22.4%+33.6%+33.6%44.8%14.5%9.9%5%3.9%3.2%2.6%2.6%2.6%2.3%2.3%F.D.R.F.I - CPUCPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.1CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - T.G.1I.M.D.S8%A.U.C.T7.9%Scala Dotty6%Apache Spark BayesR.S.A.F - CPU4.2%R.S.A.F - CPU4.2%CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - T.G.1F.D.R.F.I - CPU3.9%Rand Forest3.6%P.V.B.D.F - CPU3.3%P.V.B.D.F - CPU3.3%CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.5Junkshop - CPU-Only2.6%CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - P.P.5V.D.F - CPUV.D.F - CPUCPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - P.P.2CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - P.P.2A.S.P2.2%A.G.R.R.0.F.I - CPU2%OpenVINOLlama.cppLlama.cppRenaissanceRenaissanceRenaissanceRenaissanceOpenVINOOpenVINOLlama.cppOpenVINORenaissanceOpenVINOOpenVINOLlama.cppBlenderLlama.cppOpenVINOOpenVINOLlama.cppLlama.cppRenaissanceOpenVINOab

sunnyopenvino: Face Detection Retail FP16-INT8 - CPUllama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128renaissance: In-Memory Database Shootoutrenaissance: Akka Unbalanced Cobwebbed Treerenaissance: Scala Dottyrenaissance: Apache Spark Bayesopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128openvino: Face Detection Retail FP16-INT8 - CPUrenaissance: Rand Forestopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUllama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512blender: Junkshop - CPU-Onlyllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512openvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048renaissance: Apache Spark PageRankopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUrenaissance: Savina Reactors.IOopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048blender: Classroom - CPU-Onlyrenaissance: ALS Movie Lensrenaissance: Finagle HTTP Requestsllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024renaissance: Gaussian Mixture Modelopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024openvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUblender: Pabellon Barcelona - CPU-Onlyopenvino: Person Re-Identification Retail FP16 - CPUblender: BMW27 - CPU-Onlyopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUblender: Barbershop - CPU-Onlyllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128openvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUblender: Fishy Cat - CPU-Onlyllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512vkpeak: int16-vec4openvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Person Detection FP16 - CPUprimesieve: 1e12openvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP16 - CPUprimesieve: 1e13renaissance: Genetic Algorithm Using Jenetics + Futuresvkpeak: int32-scalarvkpeak: fp64-vec4vkpeak: fp32-scalarvkpeak: int32-vec4vkpeak: int16-scalarvkpeak: fp64-scalarvkpeak: fp16-scalarvkpeak: fp32-vec4vkpeak: fp16-vec4openvino: Age Gender Recognition Retail 0013 FP16 - CPUrenaissance: Apache Spark ALSab5.8222.028.183666.04680.4504.9576.164.0362.3836.911026.9530.0219.7318.1425.04325.7982.433.06120.723.4623.322499.10.515040.011199.9466.4640.1511841.51603.674.153998.591.9365.186.11.6121.3878.3725.3338.57155.0676.47186.74836.9216.22222.76245.2231.3127.48653.942528.858.694019.35316.0212.5810.42340.4525.773616.14284.7220.99571.49.532484.8416.8517.5324.633229.6317.39227.74375.3541345.6826.97213.371989.85848.973189.67218.716201.562928.036532.131.434.0225.228.993960.05048.7535.0548.566.7559.8438.36988.82549.0212.7918.7325.84334.3684.5632.23123.824.0123.862555.20.524962.211036.0165.53632.3311978.11620.874.853964.191.1665.736.061.621.2577.9225.1938.78154.2376.88187.74841.416.3221.76244.231.43126.97656.462538.078.664033.0131512.6210.45339.525.73625.91283.9721.04570.089.552479.73416.0517.5624.599229.917.37227.5375.6831344.7827.21213.431990.33849.173190.35218.756202.632928.516532.631.43OpenBenchmarking.org

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16-INT8 - Device: CPUba1.30952.6193.92855.2386.54754.025.82MIN: 2.26 / MAX: 10.32MIN: 4.19 / MAX: 15.871. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024ba61218243025.2222.021. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128ba36912158.998.181. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: In-Memory Database Shootoutba80016002400320040003960.03666.0MIN: 3506.06 / MAX: 4250.74MIN: 3310.92 / MAX: 4011.42

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Akka Unbalanced Cobwebbed Treeba110022003300440055005048.74680.4MIN: 5048.68 / MAX: 6733.71MAX: 6368.49

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Scala Dottyba120240360480600535.0504.9MIN: 423.09 / MAX: 1208.18MIN: 414.43 / MAX: 1051.65

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Apache Spark Bayesba120240360480600548.5576.1MIN: 479.93 / MAX: 622.49MIN: 487.72 / MAX: 639.08

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16 - Device: CPUba153045607566.7564.03MIN: 37.15 / MAX: 103.09MIN: 38.34 / MAX: 92.381. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16 - Device: CPUba142842567059.8462.381. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128ba91827364538.3636.911. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16-INT8 - Device: CPUba2004006008001000988.821026.901. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Random Forestba120240360480600549.0530.0MIN: 432.9 / MAX: 695.6MIN: 433.94 / MAX: 631.56

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Vehicle Bike Detection FP16 - Device: CPUba50100150200250212.79219.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Vehicle Bike Detection FP16 - Device: CPUba51015202518.7318.14MIN: 10.83 / MAX: 30.37MIN: 10.6 / MAX: 32.581. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512ba61218243025.8425.041. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: CPU-Onlyba70140210280350334.36325.79

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512ba2040608010084.5682.401. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16 - Device: CPUba81624324032.2333.06MIN: 18.43 / MAX: 42.01MIN: 18.51 / MAX: 45.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16 - Device: CPUba306090120150123.8120.71. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048ba61218243024.0123.461. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048ba61218243023.8623.321. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Apache Spark PageRankba50010001500200025002555.22499.1MIN: 2311.16 / MAX: 2555.25MIN: 2241.43

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUba0.1170.2340.3510.4680.5850.520.51MIN: 0.32 / MAX: 5.59MIN: 0.31 / MAX: 4.691. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Savina Reactors.IOba110022003300440055004962.25040.0MAX: 6756.71MAX: 6798.06

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUba2K4K6K8K10K11036.0111199.941. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048ba153045607565.5366.401. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: CPU-Onlyba140280420560700632.33640.15

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: ALS Movie Lensba3K6K9K12K15K11978.111841.5MIN: 11444.74 / MAX: 12030.59MIN: 11513.13 / MAX: 11841.51

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Finagle HTTP Requestsba300600900120015001620.81603.6MIN: 1416.42 / MAX: 1684.8MIN: 1387.17 / MAX: 1649.09

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024ba2040608010074.8574.151. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Gaussian Mixture Modelba90018002700360045003964.13998.5MIN: 3964.09 / MAX: 4527.22MIN: 3952.45 / MAX: 4600.23

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16-INT8 - Device: CPUba2040608010091.1691.931. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16-INT8 - Device: CPUba153045607565.7365.18MIN: 45.14 / MAX: 93.91MIN: 44.34 / MAX: 92.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection FP16-INT8 - Device: CPUba2468106.066.101. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUba0.36230.72461.08691.44921.81151.601.611. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Machine Translation EN To DE FP16 - Device: CPUba51015202521.2521.381. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16 - Device: CPUba2040608010077.9278.371. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024ba61218243025.1925.331. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16 - Device: CPUba91827364538.7838.57MIN: 24.36 / MAX: 58.4MIN: 24.14 / MAX: 62.331. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16 - Device: CPUba306090120150154.23155.061. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16 - Device: CPUba2040608010076.8876.47MIN: 50.85 / MAX: 128.2MIN: 50.95 / MAX: 112.211. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Machine Translation EN To DE FP16 - Device: CPUba4080120160200187.74186.74MIN: 124.83 / MAX: 225.14MIN: 124.74 / MAX: 224.641. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: CPU-Onlyba2004006008001000841.40836.92

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Re-Identification Retail FP16 - Device: CPUba4812162016.3016.22MIN: 9.29 / MAX: 25.68MIN: 9.29 / MAX: 27.061. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: CPU-Onlyba50100150200250221.76222.76

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Re-Identification Retail FP16 - Device: CPUba50100150200250244.20245.221. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16-INT8 - Device: CPUba71421283531.4331.30MIN: 17.6 / MAX: 52.95MIN: 17.4 / MAX: 41.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16-INT8 - Device: CPUba306090120150126.97127.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16-INT8 - Device: CPUba140280420560700656.46653.94MIN: 441.08 / MAX: 743.39MIN: 449.53 / MAX: 748.391. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: CPU-Onlyba50010001500200025002538.072528.85

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128ba2468108.668.691. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUba90018002700360045004033.014019.351. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16-INT8 - Device: CPUba70140210280350315.00316.021. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16-INT8 - Device: CPUba369121512.6212.58MIN: 6.68 / MAX: 20.14MIN: 6.7 / MAX: 20.641. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16-INT8 - Device: CPUba369121510.4510.42MIN: 6.31 / MAX: 23.39MIN: 6.3 / MAX: 24.721. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: CPU-Onlyba70140210280350339.50340.45

Llama.cpp

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512ba61218243025.7025.771. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

vkpeak

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-vec4ba80016002400320040003625.913616.14

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Noise Suppression Poconet-Like FP16 - Device: CPUba60120180240300283.97284.721. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Noise Suppression Poconet-Like FP16 - Device: CPUba51015202521.0420.99MIN: 14.56 / MAX: 37.55MIN: 14.56 / MAX: 36.41. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16-INT8 - Device: CPUba120240360480600570.08571.401. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16 - Device: CPUba36912159.559.53MIN: 5.49 / MAX: 23.25MIN: 5.45 / MAX: 17.121. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUba50010001500200025002479.732484.80MIN: 1667.31 / MAX: 2739.54MIN: 1667.39 / MAX: 2664.081. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16 - Device: CPUba90180270360450416.05416.851. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUba4812162017.5617.531. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.6Length: 1e12ba61218243024.6024.631. (CXX) g++ options: -O3

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP32 - Device: CPUba50100150200250229.90229.63MIN: 150.52 / MAX: 280.47MIN: 151.86 / MAX: 275.831. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Detection FP32 - Device: CPUba4812162017.3717.391. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUba50100150200250227.50227.74MIN: 150.76 / MAX: 266.09MIN: 148.49 / MAX: 268.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.6Length: 1e13ba80160240320400375.68375.351. (CXX) g++ options: -O3

Renaissance

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Genetic Algorithm Using Jenetics + Futuresba300600900120015001344.71345.6MIN: 1309.34 / MAX: 1413.55MIN: 1290.39 / MAX: 1379.78

vkpeak

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-scalarba2004006008001000827.21826.97

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp64-vec4ba50100150200250213.43213.37

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-scalarba4008001200160020001990.331989.85

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-vec4ba2004006008001000849.17848.97

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-scalarba70014002100280035003190.353189.67

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp64-scalarba50100150200250218.75218.71

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-scalarba130026003900520065006202.636201.56

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-vec4ba60012001800240030002928.512928.03

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-vec4ba140028004200560070006532.636532.13

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUba0.32180.64360.96541.28721.6091.431.43MIN: 0.89 / MAX: 6.95MIN: 0.89 / MAX: 5.191. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Renaissance

Test: Apache Spark ALS

a: The test quit with a non-zero exit status.

b: The test quit with a non-zero exit status.

81 Results Shown

OpenVINO
Llama.cpp:
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128
Renaissance:
  In-Memory Database Shootout
  Akka Unbalanced Cobwebbed Tree
  Scala Dotty
  Apache Spark Bayes
OpenVINO:
  Road Segmentation ADAS FP16 - CPU:
    ms
    FPS
Llama.cpp
OpenVINO
Renaissance
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU:
    FPS
    ms
Llama.cpp
Blender
Llama.cpp
OpenVINO:
  Vehicle Detection FP16 - CPU:
    ms
    FPS
Llama.cpp:
  CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048
  CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048
Renaissance
OpenVINO
Renaissance
OpenVINO
Llama.cpp
Blender
Renaissance:
  ALS Movie Lens
  Finagle HTTP Requests
Llama.cpp
Renaissance
OpenVINO:
  Handwritten English Recognition FP16-INT8 - CPU:
    FPS
    ms
  Face Detection FP16-INT8 - CPU:
    FPS
  Face Detection FP16 - CPU:
    FPS
  Machine Translation EN To DE FP16 - CPU:
    FPS
  Handwritten English Recognition FP16 - CPU:
    FPS
Llama.cpp
OpenVINO:
  Weld Porosity Detection FP16 - CPU:
    ms
    FPS
  Handwritten English Recognition FP16 - CPU:
    ms
  Machine Translation EN To DE FP16 - CPU:
    ms
Blender
OpenVINO
Blender
OpenVINO:
  Person Re-Identification Retail FP16 - CPU
  Road Segmentation ADAS FP16-INT8 - CPU
  Road Segmentation ADAS FP16-INT8 - CPU
  Face Detection FP16-INT8 - CPU
Blender
Llama.cpp
OpenVINO:
  Age Gender Recognition Retail 0013 FP16 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
Blender
Llama.cpp
vkpeak
OpenVINO:
  Noise Suppression Poconet-Like FP16 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16-INT8 - CPU:
    FPS
  Face Detection Retail FP16 - CPU:
    ms
  Face Detection FP16 - CPU:
    ms
  Face Detection Retail FP16 - CPU:
    FPS
  Person Detection FP16 - CPU:
    FPS
Primesieve
OpenVINO:
  Person Detection FP32 - CPU:
    ms
    FPS
  Person Detection FP16 - CPU:
    ms
Primesieve
Renaissance
vkpeak:
  int32-scalar
  fp64-vec4
  fp32-scalar
  int32-vec4
  int16-scalar
  fp64-scalar
  fp16-scalar
  fp32-vec4
  fp16-vec4
OpenVINO