nov

Intel Core i7-1280P testing with a MSI Prestige 14Evo A12M MS-14C6 (E14C6IMS.115 BIOS) and MSI Intel ADL GT2 8GB on Ubuntu 24.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2411271-NE-NOV20712723&grr.

novProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionabbbcIntel Core i7-1280P @ 4.70GHz (14 Cores / 20 Threads)MSI Prestige 14Evo A12M MS-14C6 (E14C6IMS.115 BIOS)Intel Alder Lake PCH8 x 2GB LPDDR4-4267MT/s SK Hynix H9HCNNNCPMMLXR-1024GB Micron_3400_MTFDKBA1T0TFHMSI Intel ADL GT2 8GBRealtek ALC274Intel Alder Lake-P PCH CNVi WiFiUbuntu 24.106.11.0-rc6-phx (x86_64)GNOME Shell 47.0X Server + Wayland4.6 Mesa 24.2.3-1ubuntu1GCC 14.2.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --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 Processor Details- Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x434 - Thermald 2.5.8 Java Details- OpenJDK Runtime Environment (build 21.0.5-ea+8-Ubuntu-1)Python Details- Python 3.12.7Security Details- 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: Mitigation of Clear Register File + 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: SW sequence; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected

novllama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048blender: Pabellon Barcelona - CPU-Onlyblender: Classroom - CPU-Onlyrustls: handshake-resume - TLS13_CHACHA20_POLY1305_SHA256llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024rustls: handshake-ticket - TLS13_CHACHA20_POLY1305_SHA256rustls: handshake-ticket - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024rustls: handshake-resume - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384blender: Fishy Cat - CPU-Onlyblender: Junkshop - CPU-Onlyopenvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Gemma-7b-int4-ov - CPU - Time To First Tokenmt-dgemm: Sustained Floating-Point Raterustls: handshake - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512blender: BMW27 - CPU-Onlyllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512palabos: 100openvino-genai: Gemma-7b-int4-ov - CPUrustls: handshake - TLS13_CHACHA20_POLY1305_SHA256rustls: handshake - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256build-eigen: Time To Compilepalabos: 400llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128vkpeak: int16-vec4vkpeak: int16-scalarvkpeak: int32-vec4vkpeak: int32-scalarvkpeak: fp16-vec4vkpeak: fp16-scalarvkpeak: fp32-vec4vkpeak: fp32-scalaropenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: Falcon-7b-instruct-int4-ov - CPUllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024rustls: handshake-ticket - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256renaissance: ALS Movie Lensrustls: handshake-resume - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time To First Tokenopenvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPUrenaissance: In-Memory Database Shootoutrenaissance: Apache Spark PageRankrenaissance: Akka Unbalanced Cobwebbed Treeopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUrenaissance: Savina Reactors.IOrenaissance: Gaussian Mixture Modelrenaissance: Finagle HTTP Requestsrenaissance: Apache Spark Bayesopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUrenaissance: Rand Forestrenaissance: Genetic Algorithm Using Jenetics + Futuresrenaissance: Scala Dottyopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time Per Output Tokenopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time To First Tokenopenvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPUsupertuxkart: 1920 x 1080 - High - Vulkan - Mostly Stable FPSsupertuxkart: 1920 x 1080 - High - Vulkan - Steady FPSsupertuxkart: 1920 x 1080 - Ultimate - Vulkan - Mostly Stable FPSsupertuxkart: 1920 x 1080 - Ultimate - Vulkan - Steady FPSllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512supertuxkart: 1920 x 1080 - Low - Vulkan - Mostly Stable FPSsupertuxkart: 1920 x 1080 - Low - Vulkan - Steady FPSsupertuxkart: 1920 x 1080 - Medium - Vulkan - Mostly Stable FPSsupertuxkart: 1920 x 1080 - Medium - Vulkan - Steady FPSsupertuxkart: 1920 x 1080 - High - OpenGL - Mostly Stable FPSsupertuxkart: 1920 x 1080 - High - OpenGL - Steady FPSsupertuxkart: 1920 x 1080 - Low - OpenGL - Mostly Stable FPSsupertuxkart: 1920 x 1080 - Low - OpenGL - Steady FPSsupertuxkart: 1920 x 1080 - Ultimate - OpenGL - Mostly Stable FPSsupertuxkart: 1920 x 1080 - Ultimate - OpenGL - Steady FPSsupertuxkart: 1920 x 1080 - Medium - OpenGL - Mostly Stable FPSsupertuxkart: 1920 x 1080 - Medium - OpenGL - Steady FPSllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128renaissance: Apache Spark ALSabbbc13.3412.48916.89755.48105546.1812.77106054.04356237.6813.7415559.3403.53368.84179.4640292044.913.09271.3752.1814.0743.31049355.199526.43147.80374.92556.181919.651013.63550.78473.563551.692503.321652.721868.4494.57191.3310.5757.88809762.8114459.41082805.96.698.98345.810.15302.83063.29185.65004.251.175338.74643.44385.9638.21402.54.27570.11244.5550.0439.6113.38392.4815.25259.9661.0565.6891.1238.6666.62117.550.7629.11205.0234.21174.7832.52183.9462.0196.288.78678.8417.793351.668888.154.013750.5744.1280.6422.6629724529424561.5132125031424765591351136055867628.1313.4801.74687.92111914.7613.76112736.73379460.5113.79445443.44349.6322.47181.14305797635.314.11235.5514.8240.838710102.4210169.47148.02571.13476.421919.431013.52550.7473.513551.192502.951652.471868.13864815.5515204.01154350.716086.22809.09157.14489.061.315229.64581.13884.6745.21285.294.61600.61222.8561.4411.3314.53350.7417.05246.5664.7159.62100.47217.8673.28114.3252.3626.71223.6230.68195.0229.42203.3959.37100.768.15731.8716.04372.291.539570.873.634146.332962482862363181513022476157135465651867313.3913.38801.96753.66105168.6713.76104991.4355887.3213.77416122.79399.23366.21222.88943.04181.33411291665.5314.13270.0952.3114.126.5294.499387.989571.62147.95550.72956.421609.56939.02542.62473.4935512502.821652.351868.0194.78191.7410.5557.7808705.1614475.61079421.746.6100.11335.049.995054.42922.28669.34504.411.315360.84616.04297.2716.91281.774.62624.21230.5596.6410.9114.57352.8116.96240.7166.3359.42100.83210.7575.74114.6552.2426.59224.6630.48196.3729.28204.459.8799.988.09737.3115.99373.561.539615.643.624149.8644.2873.0322.5828022926821161.423032482862366255131595650817028.189.369.381054.24864.22105132.057.17105650.04379788.69.59448873.55450.68355.04278.261158.18180.51615192487.827.21237.1444.059.7241.18773.599367.739594148.03971.40354.151919.41013.51550.72473.53551.162502.981652.461868.28104.88238.249.5348.15811877.8614302.41083026.435.09121.95473.058.24797.62815.18570.65415.461.085250.64534.23929.9789.71568.683.73601.91251.9573.8454.2513.01432.5513.75273.6658.0671.1383.92241.5665.86119.5350.0733.81175.6737.93157.3838157.1463.1594.6510.48565.2119.39306.992.087143.564.793171.5448.8188.2420.4929824428623651.63202513072526357135475852877523.68OpenBenchmarking.org

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048abbc369121513.3413.399.361. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048abbbc369121512.4813.4013.389.381. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: CPU-Onlyabbbc2004006008001000916.89801.74801.961054.24

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: CPU-Onlyabbbc2004006008001000755.48687.92753.66864.22

Rustls

Benchmark: handshake-resume - Suite: TLS13_CHACHA20_POLY1305_SHA256

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-resume - Suite: TLS13_CHACHA20_POLY1305_SHA256abbbc20K40K60K80K100K105546.18111914.76105168.67105132.051. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024abbbc4812162012.7713.7613.767.171. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Rustls

Benchmark: handshake-ticket - Suite: TLS13_CHACHA20_POLY1305_SHA256

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-ticket - Suite: TLS13_CHACHA20_POLY1305_SHA256abbbc20K40K60K80K100K106054.04112736.73104991.40105650.041. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

Rustls

Benchmark: handshake-ticket - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-ticket - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384abbbc80K160K240K320K400K356237.68379460.51355887.32379788.601. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024abbbc4812162013.7013.7913.779.591. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Rustls

Benchmark: handshake-resume - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-resume - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384abbbc100K200K300K400K500K415559.30445443.44416122.79448873.551. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: CPU-Onlyabbbc100200300400500403.53349.60399.23450.68

Blender

Blend File: Junkshop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: CPU-Onlyabbbc80160240320400368.84322.47366.21355.04

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Tokenbbc60120180240300222.88278.26

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPU - Time To First Tokenbbc2004006008001000943.041158.18

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Rateabbbc4080120160200179.46181.14181.33180.521. (CC) gcc options: -ffast-math -mavx2 -O3 -fopenmp -lopenblas

Rustls

Benchmark: handshake - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384abbbc20K40K60K80K100K92044.9097635.3091665.5392487.821. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512abbbc4812162013.0914.1114.137.211. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: CPU-Onlyabbbc60120180240300271.37235.55270.09237.14

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048abbc122436486052.1852.3144.051. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512abbbc4812162014.0714.8214.109.721. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Palabos

Grid Size: 100

OpenBenchmarking.orgMega Site Updates Per Second, More Is BetterPalabos 2.3Grid Size: 100abbbc102030405043.3140.8426.5341.191. (CXX) g++ options: -std=c++17 -pedantic -O3 -rdynamic -lcrypto -lcurl -lsz -lz -ldl -lm

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPUbbc1.01032.02063.03094.04125.05154.493.59

Rustls

Benchmark: handshake - Suite: TLS13_CHACHA20_POLY1305_SHA256

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake - Suite: TLS13_CHACHA20_POLY1305_SHA256abbbc2K4K6K8K10K9355.1910102.429387.989367.731. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

Rustls

Benchmark: handshake - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256abbbc2K4K6K8K10K9526.4310169.479571.629594.001. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

Timed Eigen Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.4.0Time To Compileabbbc306090120150147.80148.03147.96148.04

Palabos

Grid Size: 400

OpenBenchmarking.orgMega Site Updates Per Second, More Is BetterPalabos 2.3Grid Size: 400abbbc2040608010074.9371.1350.7371.401. (CXX) g++ options: -std=c++17 -pedantic -O3 -rdynamic -lcrypto -lcurl -lsz -lz -ldl -lm

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128abbbc2468106.186.426.424.151. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

vkpeak

int16-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-vec4abbbc4008001200160020001919.651919.431609.561919.40

vkpeak

int16-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-scalarabbbc20040060080010001013.631013.52939.021013.51

vkpeak

int32-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-vec4abbbc120240360480600550.78550.70542.62550.72

vkpeak

int32-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-scalarabbbc100200300400500473.56473.51473.49473.50

vkpeak

fp16-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-vec4abbbc80016002400320040003551.693551.193551.003551.16

vkpeak

fp16-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-scalarabbbc50010001500200025002503.322502.952502.822502.98

vkpeak

fp32-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-vec4abbbc4008001200160020001652.721652.471652.351652.46

vkpeak

fp32-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-scalarabbbc4008001200160020001868.441868.131868.011868.28

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Tokenabbc2040608010094.5794.78104.88

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Tokenabbc50100150200250191.33191.74238.24

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Falcon-7b-instruct-int4-ov - Device: CPUabbc369121510.5710.559.53

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024abbc132639526557.8857.7048.151. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Rustls

Benchmark: handshake-ticket - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-ticket - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256abbbc200K400K600K800K1000K809762.81864815.55808705.16811877.861. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

Renaissance

Test: ALS Movie Lens

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: ALS Movie Lensabbbc3K6K9K12K15K14459.415204.014475.614302.4MIN: 13527.85 / MAX: 14809.99MIN: 14604.93 / MAX: 15315.73MIN: 13363.8 / MAX: 14850.22MIN: 13229.02 / MAX: 14790.02

Rustls

Benchmark: handshake-resume - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256

OpenBenchmarking.orghandshakes/s, More Is BetterRustls 0.23.17Benchmark: handshake-resume - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256abbbc200K400K600K800K1000K1082805.901154350.711079421.741083026.431. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128abbc2468106.606.605.091. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Tokenabbc30609012015098.98100.11121.95

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Tokenabbc100200300400500345.80335.04473.05

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPUabbc369121510.109.998.20

Renaissance

Test: In-Memory Database Shootout

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: In-Memory Database Shootoutabbbc130026003900520065005302.86086.25054.44797.6MIN: 4531.82 / MAX: 5427.64MIN: 5581.49 / MAX: 6632.91MIN: 4319.98 / MAX: 5749.04MIN: 4238.93 / MAX: 5345.86

Renaissance

Test: Apache Spark PageRank

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Apache Spark PageRankabbbc70014002100280035003063.22809.02922.22815.1MIN: 2879.98 / MAX: 3230.31MIN: 2658.75MIN: 2752.32 / MAX: 3030.18MIN: 2628.83 / MAX: 2815.13

Renaissance

Test: Akka Unbalanced Cobwebbed Tree

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Akka Unbalanced Cobwebbed Treeabbbc2K4K6K8K10K9185.69157.18669.38570.6MIN: 9185.56 / MAX: 9829.42MAX: 9628.95MIN: 8535.62 / MAX: 9221.73MIN: 8210.22 / MAX: 9186.21

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUabbbc120024003600480060005004.254489.064504.415415.46MIN: 2565.77 / MAX: 11954.25MIN: 2543.37 / MAX: 7801.22MIN: 2560.7 / MAX: 7228.61MIN: 2567.66 / MAX: 21634.631. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUabbbc0.29480.58960.88441.17921.4741.171.311.311.081. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Renaissance

Test: Savina Reactors.IO

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Savina Reactors.IOabbbc110022003300440055005338.75229.65360.85250.6MAX: 7566.83MAX: 7901.15MIN: 5360.76 / MAX: 7595.61MIN: 5250.57 / MAX: 7316.25

Renaissance

Test: Gaussian Mixture Model

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Gaussian Mixture Modelabbbc100020003000400050004643.44581.14616.04534.2MIN: 4643.38 / MAX: 5248.85MIN: 4423.98 / MAX: 5050.76MAX: 5157.94MIN: 4412.76 / MAX: 4943.27

Renaissance

Test: Finagle HTTP Requests

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Finagle HTTP Requestsabbbc90018002700360045004385.93884.64297.23929.9MAX: 5421.32MIN: 3335.79 / MAX: 4399.52MAX: 4817.4MIN: 3248.37 / MAX: 4520.84

Renaissance

Test: Apache Spark Bayes

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Apache Spark Bayesabbbc2004006008001000638.2745.2716.9789.7MIN: 580.8 / MAX: 828.74MIN: 609.15 / MAX: 891.9MIN: 591.68 / MAX: 844.76MIN: 640.59 / MAX: 897.21

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16-INT8 - Device: CPUabbbc300600900120015001402.501285.291281.771568.68MIN: 660.35 / MAX: 5619.27MIN: 661.66 / MAX: 2931.41MIN: 663.22 / MAX: 2901.61MIN: 666.6 / MAX: 9839.791. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection FP16-INT8 - Device: CPUabbbc1.03952.0793.11854.1585.19754.274.614.623.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Renaissance

Test: Random Forest

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Random Forestabbbc130260390520650570.1600.6624.2601.9MIN: 534.15 / MAX: 651.47MIN: 560.53 / MAX: 656.17MIN: 564.93 / MAX: 776.27MIN: 554.87 / MAX: 660.27

Renaissance

Test: Genetic Algorithm Using Jenetics + Futures

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Genetic Algorithm Using Jenetics + Futuresabbbc300600900120015001244.51222.81230.51251.9MIN: 1130.89 / MAX: 1359.65MIN: 1123.42 / MAX: 1307.54MIN: 1114.96 / MAX: 1356.94MIN: 1146.96 / MAX: 1404.63

Renaissance

Test: Scala Dotty

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.16Test: Scala Dottyabbbc130260390520650550.0561.4596.6573.8MIN: 463.24 / MAX: 928.24MIN: 478.02 / MAX: 968.67MIN: 486.85 / MAX: 1078.3MIN: 477.81 / MAX: 939.92

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUabbbc100200300400500439.61411.33410.91454.25MIN: 232.29 / MAX: 1903.58MIN: 224.97 / MAX: 963.04MIN: 222.81 / MAX: 845.42MIN: 192.15 / MAX: 1904.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUabbbc4812162013.3814.5314.5713.011. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Machine Translation EN To DE FP16 - Device: CPUabbbc90180270360450392.48350.74352.81432.55MIN: 168.33 / MAX: 1771.01MIN: 169.89 / MAX: 756.81MIN: 183.5 / MAX: 837.79MIN: 164.06 / MAX: 1770.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Machine Translation EN To DE FP16 - Device: CPUabbbc4812162015.2517.0516.9613.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16 - Device: CPUabbbc60120180240300259.96246.56240.71273.66MIN: 130.23 / MAX: 1000.64MIN: 128.61 / MAX: 661.55MIN: 129.63 / MAX: 979.78MIN: 131.85 / MAX: 999.971. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16 - Device: CPUabbbc153045607561.0564.7166.3358.061. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabbbc163248648065.6859.6259.4271.13MIN: 30.63 / MAX: 319.44MIN: 31.69 / MAX: 109.78MIN: 29.99 / MAX: 117.72MIN: 30.21 / MAX: 364.451. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabbbc2040608010091.10100.47100.8383.921. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16-INT8 - Device: CPUabbbc50100150200250238.66217.86210.75241.56MIN: 101.28 / MAX: 947.08MIN: 103.9 / MAX: 635.93MIN: 103.37 / MAX: 548.96MIN: 104.83 / MAX: 911.971. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Handwritten English Recognition FP16-INT8 - Device: CPUabbbc2040608010066.6273.2875.7465.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16 - Device: CPUabbbc306090120150117.50114.32114.65119.53MIN: 45.67 / MAX: 445.31MIN: 48.61 / MAX: 405.31MIN: 76.78 / MAX: 342.17MIN: 72.87 / MAX: 434.21. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Road Segmentation ADAS FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Road Segmentation ADAS FP16 - Device: CPUabbbc122436486050.7652.3652.2450.071. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Noise Suppression Poconet-Like FP16 - Device: CPUabbbc81624324029.1126.7126.5933.81MIN: 13.53 / MAX: 79.9MIN: 13.32 / MAX: 44.78MIN: 13.16 / MAX: 47.31MIN: 13.51 / MAX: 143.781. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Noise Suppression Poconet-Like FP16 - Device: CPUabbbc50100150200250205.02223.62224.66175.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Vehicle Bike Detection FP16 - Device: CPUabbbc91827364534.2130.6830.4837.93MIN: 14.72 / MAX: 152.84MIN: 16.13 / MAX: 55.32MIN: 13.66 / MAX: 56.89MIN: 15.71 / MAX: 152.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Vehicle Bike Detection FP16 - Device: CPUabbbc4080120160200174.78195.02196.37157.381. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Re-Identification Retail FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Re-Identification Retail FP16 - Device: CPUabbbc91827364532.5229.4229.2838.00MIN: 13.27 / MAX: 98.34MIN: 13.3 / MAX: 50.36MIN: 13.23 / MAX: 56.48MIN: 13.58 / MAX: 150.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Re-Identification Retail FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Re-Identification Retail FP16 - Device: CPUabbbc4080120160200183.94203.39204.40157.141. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16 - Device: CPUabbbc142842567062.0159.3759.8763.15MIN: 27.87 / MAX: 273.2MIN: 31.87 / MAX: 215.48MIN: 26.15 / MAX: 156.54MIN: 32.01 / MAX: 273.441. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16 - Device: CPUabbbc2040608010096.28100.7699.9894.651. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16-INT8 - Device: CPUabbbc36912158.788.158.0910.48MIN: 3.74 / MAX: 28.34MIN: 3.56 / MAX: 16.97MIN: 3.69 / MAX: 17.48MIN: 3.94 / MAX: 72.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16-INT8 - Device: CPUabbbc160320480640800678.84731.87737.31565.211. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16 - Device: CPUabbbc51015202517.7916.0415.9919.39MIN: 6.93 / MAX: 78.65MIN: 7.67 / MAX: 35.36MIN: 7.49 / MAX: 39.2MIN: 8.01 / MAX: 78.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Face Detection Retail FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Face Detection Retail FP16 - Device: CPUabbbc80160240320400335.00372.29373.56306.991. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabbbc0.4680.9361.4041.8722.341.661.531.532.08MIN: 0.45 / MAX: 6.8MIN: 0.48 / MAX: 5.15MIN: 0.48 / MAX: 4.89MIN: 0.46 / MAX: 11.031. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabbbc2K4K6K8K10K8888.159570.879615.647143.561. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabbbc1.07782.15563.23344.31125.3894.013.633.624.79MIN: 1.23 / MAX: 11.41MIN: 1.26 / MAX: 10.8MIN: 1.25 / MAX: 11.17MIN: 1.1 / MAX: 20.471. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabbbc90018002700360045003750.574146.334149.863171.541. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Tokenabbc112233445544.1244.2848.81

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Tokenabbc2040608010080.6473.0388.24

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPUabbc51015202522.6622.5820.49

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: Vulkan - Mostly Stable FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: Vulkan - Mostly Stable FPSabbbc60120180240300297296280298

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: Vulkan - Steady FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: Vulkan - Steady FPSabbbc50100150200250245248229244

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: Vulkan - Mostly Stable FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: Vulkan - Mostly Stable FPSabbbc60120180240300294286268286

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: Vulkan - Steady FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: Vulkan - Steady FPSabbbc50100150200250245236211236

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512abbc142842567061.5161.4251.601. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: Vulkan - Mostly Stable FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: Vulkan - Mostly Stable FPSabbbc70140210280350321318303320

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: Vulkan - Steady FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: Vulkan - Steady FPSabbbc50100150200250250151248251

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: Vulkan - Mostly Stable FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: Vulkan - Mostly Stable FPSabbbc70140210280350314302286307

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: Vulkan - Steady FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: Vulkan - Steady FPSabbbc60120180240300247247236252

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: OpenGL - Mostly Stable FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: OpenGL - Mostly Stable FPSabbbc153045607565616263

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: OpenGL - Steady FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: OpenGL - Steady FPSabbbc132639526559575557

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: OpenGL - Mostly Stable FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: OpenGL - Mostly Stable FPSabbbc306090120150135135131135

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: OpenGL - Steady FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: OpenGL - Steady FPSabbbc306090120150113465947

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: OpenGL - Mostly Stable FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: OpenGL - Mostly Stable FPSabbbc132639526560565658

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: OpenGL - Steady FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: OpenGL - Steady FPSabbbc122436486055515052

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: OpenGL - Mostly Stable FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: OpenGL - Mostly Stable FPSabbbc2040608010086868187

SuperTuxKart

Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: OpenGL - Steady FPS

OpenBenchmarking.orgFrames Per Second, More Is BetterSuperTuxKart 1.5 Beta 1Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: OpenGL - Steady FPSabbbc2040608010076737075

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128abbc71421283528.1328.1823.681. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas


Phoronix Test Suite v10.8.5