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 .
nov Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution a b bb c Intel Core i7-1280P @ 4.70GHz (14 Cores / 20 Threads) MSI Prestige 14Evo A12M MS-14C6 (E14C6IMS.115 BIOS) Intel Alder Lake PCH 8 x 2GB LPDDR4-4267MT/s SK Hynix H9HCNNNCPMMLXR- 1024GB Micron_3400_MTFDKBA1T0TFH MSI Intel ADL GT2 8GB Realtek ALC274 Intel Alder Lake-P PCH CNVi WiFi Ubuntu 24.10 6.11.0-rc6-phx (x86_64) GNOME Shell 47.0 X Server + Wayland 4.6 Mesa 24.2.3-1ubuntu1 GCC 14.2.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler 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 3.12.7 Security 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
nov llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 2048 llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 2048 blender: Pabellon Barcelona - CPU-Only blender: Classroom - CPU-Only rustls: handshake-resume - TLS13_CHACHA20_POLY1305_SHA256 llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024 rustls: handshake-ticket - TLS13_CHACHA20_POLY1305_SHA256 rustls: handshake-ticket - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024 rustls: handshake-resume - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 blender: Fishy Cat - CPU-Only blender: Junkshop - CPU-Only openvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Token openvino-genai: Gemma-7b-int4-ov - CPU - Time To First Token mt-dgemm: Sustained Floating-Point Rate rustls: handshake - TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512 blender: BMW27 - CPU-Only llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048 llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512 palabos: 100 openvino-genai: Gemma-7b-int4-ov - CPU rustls: handshake - TLS13_CHACHA20_POLY1305_SHA256 rustls: handshake - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 build-eigen: Time To Compile palabos: 400 llama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128 vkpeak: int16-vec4 vkpeak: int16-scalar vkpeak: int32-vec4 vkpeak: int32-scalar vkpeak: fp16-vec4 vkpeak: fp16-scalar vkpeak: fp32-vec4 vkpeak: fp32-scalar openvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time Per Output Token openvino-genai: Falcon-7b-instruct-int4-ov - CPU - Time To First Token openvino-genai: Falcon-7b-instruct-int4-ov - CPU llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024 rustls: handshake-ticket - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 renaissance: ALS Movie Lens rustls: handshake-resume - TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128 openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time Per Output Token openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU - Time To First Token openvino-genai: Phi-3-mini-128k-instruct-int4-ov - CPU renaissance: In-Memory Database Shootout renaissance: Apache Spark PageRank renaissance: Akka Unbalanced Cobwebbed Tree openvino: Face Detection FP16 - CPU openvino: Face Detection FP16 - CPU renaissance: Savina Reactors.IO renaissance: Gaussian Mixture Model renaissance: Finagle HTTP Requests renaissance: Apache Spark Bayes openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU renaissance: Rand Forest renaissance: Genetic Algorithm Using Jenetics + Futures renaissance: Scala Dotty openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time Per Output Token openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU - Time To First Token openvino-genai: TinyLlama-1.1B-Chat-v1.0 - CPU supertuxkart: 1920 x 1080 - High - Vulkan - Mostly Stable FPS supertuxkart: 1920 x 1080 - High - Vulkan - Steady FPS supertuxkart: 1920 x 1080 - Ultimate - Vulkan - Mostly Stable FPS supertuxkart: 1920 x 1080 - Ultimate - Vulkan - Steady FPS llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512 supertuxkart: 1920 x 1080 - Low - Vulkan - Mostly Stable FPS supertuxkart: 1920 x 1080 - Low - Vulkan - Steady FPS supertuxkart: 1920 x 1080 - Medium - Vulkan - Mostly Stable FPS supertuxkart: 1920 x 1080 - Medium - Vulkan - Steady FPS supertuxkart: 1920 x 1080 - High - OpenGL - Mostly Stable FPS supertuxkart: 1920 x 1080 - High - OpenGL - Steady FPS supertuxkart: 1920 x 1080 - Low - OpenGL - Mostly Stable FPS supertuxkart: 1920 x 1080 - Low - OpenGL - Steady FPS supertuxkart: 1920 x 1080 - Ultimate - OpenGL - Mostly Stable FPS supertuxkart: 1920 x 1080 - Ultimate - OpenGL - Steady FPS supertuxkart: 1920 x 1080 - Medium - OpenGL - Mostly Stable FPS supertuxkart: 1920 x 1080 - Medium - OpenGL - Steady FPS llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128 renaissance: Apache Spark ALS a b bb c 13.34 12.48 916.89 755.48 105546.18 12.77 106054.04 356237.68 13.7 415559.3 403.53 368.84 179.46402 92044.9 13.09 271.37 52.18 14.07 43.3104 9355.19 9526.43 147.803 74.9255 6.18 1919.65 1013.63 550.78 473.56 3551.69 2503.32 1652.72 1868.44 94.57 191.33 10.57 57.88 809762.81 14459.4 1082805.9 6.6 98.98 345.8 10.1 5302.8 3063.2 9185.6 5004.25 1.17 5338.7 4643.4 4385.9 638.2 1402.5 4.27 570.1 1244.5 550.0 439.61 13.38 392.48 15.25 259.96 61.05 65.68 91.1 238.66 66.62 117.5 50.76 29.11 205.02 34.21 174.78 32.52 183.94 62.01 96.28 8.78 678.84 17.79 335 1.66 8888.15 4.01 3750.57 44.12 80.64 22.66 297 245 294 245 61.51 321 250 314 247 65 59 135 113 60 55 86 76 28.13 13.4 801.74 687.92 111914.76 13.76 112736.73 379460.51 13.79 445443.44 349.6 322.47 181.143057 97635.3 14.11 235.55 14.82 40.8387 10102.42 10169.47 148.025 71.1347 6.42 1919.43 1013.52 550.7 473.51 3551.19 2502.95 1652.47 1868.13 864815.55 15204.0 1154350.71 6086.2 2809.0 9157.1 4489.06 1.31 5229.6 4581.1 3884.6 745.2 1285.29 4.61 600.6 1222.8 561.4 411.33 14.53 350.74 17.05 246.56 64.71 59.62 100.47 217.86 73.28 114.32 52.36 26.71 223.62 30.68 195.02 29.42 203.39 59.37 100.76 8.15 731.87 16.04 372.29 1.53 9570.87 3.63 4146.33 296 248 286 236 318 151 302 247 61 57 135 46 56 51 86 73 13.39 13.38 801.96 753.66 105168.67 13.76 104991.4 355887.32 13.77 416122.79 399.23 366.21 222.88 943.04 181.334112 91665.53 14.13 270.09 52.31 14.1 26.529 4.49 9387.98 9571.62 147.955 50.7295 6.42 1609.56 939.02 542.62 473.49 3551 2502.82 1652.35 1868.01 94.78 191.74 10.55 57.7 808705.16 14475.6 1079421.74 6.6 100.11 335.04 9.99 5054.4 2922.2 8669.3 4504.41 1.31 5360.8 4616.0 4297.2 716.9 1281.77 4.62 624.2 1230.5 596.6 410.91 14.57 352.81 16.96 240.71 66.33 59.42 100.83 210.75 75.74 114.65 52.24 26.59 224.66 30.48 196.37 29.28 204.4 59.87 99.98 8.09 737.31 15.99 373.56 1.53 9615.64 3.62 4149.86 44.28 73.03 22.58 280 229 268 211 61.42 303 248 286 236 62 55 131 59 56 50 81 70 28.18 9.36 9.38 1054.24 864.22 105132.05 7.17 105650.04 379788.6 9.59 448873.55 450.68 355.04 278.26 1158.18 180.516151 92487.82 7.21 237.14 44.05 9.72 41.1877 3.59 9367.73 9594 148.039 71.4035 4.15 1919.4 1013.51 550.72 473.5 3551.16 2502.98 1652.46 1868.28 104.88 238.24 9.53 48.15 811877.86 14302.4 1083026.43 5.09 121.95 473.05 8.2 4797.6 2815.1 8570.6 5415.46 1.08 5250.6 4534.2 3929.9 789.7 1568.68 3.73 601.9 1251.9 573.8 454.25 13.01 432.55 13.75 273.66 58.06 71.13 83.92 241.56 65.86 119.53 50.07 33.81 175.67 37.93 157.38 38 157.14 63.15 94.65 10.48 565.21 19.39 306.99 2.08 7143.56 4.79 3171.54 48.81 88.24 20.49 298 244 286 236 51.6 320 251 307 252 63 57 135 47 58 52 87 75 23.68 OpenBenchmarking.org
Llama.cpp Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048 a bb c 3 6 9 12 15 13.34 13.39 9.36 1. (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.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048 a b bb c 3 6 9 12 15 12.48 13.40 13.38 9.38 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Pabellon Barcelona - Compute: CPU-Only a b bb c 200 400 600 800 1000 916.89 801.74 801.96 1054.24
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Classroom - Compute: CPU-Only a b bb c 200 400 600 800 1000 755.48 687.92 753.66 864.22
Rustls Benchmark: handshake-resume - Suite: TLS13_CHACHA20_POLY1305_SHA256 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-resume - Suite: TLS13_CHACHA20_POLY1305_SHA256 a b bb c 20K 40K 60K 80K 100K 105546.18 111914.76 105168.67 105132.05 1. (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.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024 a b bb c 4 8 12 16 20 12.77 13.76 13.76 7.17 1. (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.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-ticket - Suite: TLS13_CHACHA20_POLY1305_SHA256 a b bb c 20K 40K 60K 80K 100K 106054.04 112736.73 104991.40 105650.04 1. (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.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-ticket - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 a b bb c 80K 160K 240K 320K 400K 356237.68 379460.51 355887.32 379788.60 1. (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.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024 a b bb c 4 8 12 16 20 13.70 13.79 13.77 9.59 1. (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.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-resume - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 a b bb c 100K 200K 300K 400K 500K 415559.30 445443.44 416122.79 448873.55 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Fishy Cat - Compute: CPU-Only a b bb c 100 200 300 400 500 403.53 349.60 399.23 450.68
Blender Blend File: Junkshop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: Junkshop - Compute: CPU-Only a b bb c 80 160 240 320 400 368.84 322.47 366.21 355.04
OpenVINO GenAI Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time Per Output Token bb c 60 120 180 240 300 222.88 278.26
OpenVINO GenAI Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU - Time To First Token bb c 200 400 600 800 1000 943.04 1158.18
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate a b bb c 40 80 120 160 200 179.46 181.14 181.33 180.52 1. (CC) gcc options: -ffast-math -mavx2 -O3 -fopenmp -lopenblas
Rustls Benchmark: handshake - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 a b bb c 20K 40K 60K 80K 100K 92044.90 97635.30 91665.53 92487.82 1. (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.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512 a b bb c 4 8 12 16 20 13.09 14.11 14.13 7.21 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.3 Blend File: BMW27 - Compute: CPU-Only a b bb c 60 120 180 240 300 271.37 235.55 270.09 237.14
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048 a bb c 12 24 36 48 60 52.18 52.31 44.05 1. (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.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512 a b bb c 4 8 12 16 20 14.07 14.82 14.10 9.72 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Palabos Grid Size: 100 OpenBenchmarking.org Mega Site Updates Per Second, More Is Better Palabos 2.3 Grid Size: 100 a b bb c 10 20 30 40 50 43.31 40.84 26.53 41.19 1. (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.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Gemma-7b-int4-ov - Device: CPU bb c 1.0103 2.0206 3.0309 4.0412 5.0515 4.49 3.59
Rustls Benchmark: handshake - Suite: TLS13_CHACHA20_POLY1305_SHA256 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake - Suite: TLS13_CHACHA20_POLY1305_SHA256 a b bb c 2K 4K 6K 8K 10K 9355.19 10102.42 9387.98 9367.73 1. (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.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 a b bb c 2K 4K 6K 8K 10K 9526.43 10169.47 9571.62 9594.00 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
Timed Eigen Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Eigen Compilation 3.4.0 Time To Compile a b bb c 30 60 90 120 150 147.80 148.03 147.96 148.04
Palabos Grid Size: 400 OpenBenchmarking.org Mega Site Updates Per Second, More Is Better Palabos 2.3 Grid Size: 400 a b bb c 20 40 60 80 100 74.93 71.13 50.73 71.40 1. (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.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128 a b bb c 2 4 6 8 10 6.18 6.42 6.42 4.15 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
vkpeak int16-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20240505 int16-vec4 a b bb c 400 800 1200 1600 2000 1919.65 1919.43 1609.56 1919.40
vkpeak int16-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20240505 int16-scalar a b bb c 200 400 600 800 1000 1013.63 1013.52 939.02 1013.51
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20240505 int32-vec4 a b bb c 120 240 360 480 600 550.78 550.70 542.62 550.72
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20240505 int32-scalar a b bb c 100 200 300 400 500 473.56 473.51 473.49 473.50
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp16-vec4 a b bb c 800 1600 2400 3200 4000 3551.69 3551.19 3551.00 3551.16
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp16-scalar a b bb c 500 1000 1500 2000 2500 2503.32 2502.95 2502.82 2502.98
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp32-vec4 a b bb c 400 800 1200 1600 2000 1652.72 1652.47 1652.35 1652.46
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp32-scalar a b bb c 400 800 1200 1600 2000 1868.44 1868.13 1868.01 1868.28
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time Per Output Token a bb c 20 40 60 80 100 94.57 94.78 104.88
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU - Time To First Token a bb c 50 100 150 200 250 191.33 191.74 238.24
OpenVINO GenAI Model: Falcon-7b-instruct-int4-ov - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Falcon-7b-instruct-int4-ov - Device: CPU a bb c 3 6 9 12 15 10.57 10.55 9.53
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024 a bb c 13 26 39 52 65 57.88 57.70 48.15 1. (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.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-ticket - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 a b bb c 200K 400K 600K 800K 1000K 809762.81 864815.55 808705.16 811877.86 1. (CC) gcc options: -m64 -lgcc_s -lutil -lrt -lpthread -lm -ldl -lc -pie -nodefaultlibs
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: ALS Movie Lens a b bb c 3K 6K 9K 12K 15K 14459.4 15204.0 14475.6 14302.4 MIN: 13527.85 / MAX: 14809.99 MIN: 14604.93 / MAX: 15315.73 MIN: 13363.8 / MAX: 14850.22 MIN: 13229.02 / MAX: 14790.02
Rustls Benchmark: handshake-resume - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 OpenBenchmarking.org handshakes/s, More Is Better Rustls 0.23.17 Benchmark: handshake-resume - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 a b bb c 200K 400K 600K 800K 1000K 1082805.90 1154350.71 1079421.74 1083026.43 1. (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.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128 a bb c 2 4 6 8 10 6.60 6.60 5.09 1. (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.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time Per Output Token a bb c 30 60 90 120 150 98.98 100.11 121.95
OpenVINO GenAI Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU - Time To First Token a bb c 100 200 300 400 500 345.80 335.04 473.05
OpenVINO GenAI Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU a bb c 3 6 9 12 15 10.10 9.99 8.20
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: In-Memory Database Shootout a b bb c 1300 2600 3900 5200 6500 5302.8 6086.2 5054.4 4797.6 MIN: 4531.82 / MAX: 5427.64 MIN: 5581.49 / MAX: 6632.91 MIN: 4319.98 / MAX: 5749.04 MIN: 4238.93 / MAX: 5345.86
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Apache Spark PageRank a b bb c 700 1400 2100 2800 3500 3063.2 2809.0 2922.2 2815.1 MIN: 2879.98 / MAX: 3230.31 MIN: 2658.75 MIN: 2752.32 / MAX: 3030.18 MIN: 2628.83 / MAX: 2815.13
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Akka Unbalanced Cobwebbed Tree a b bb c 2K 4K 6K 8K 10K 9185.6 9157.1 8669.3 8570.6 MIN: 9185.56 / MAX: 9829.42 MAX: 9628.95 MIN: 8535.62 / MAX: 9221.73 MIN: 8210.22 / MAX: 9186.21
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU a b bb c 1200 2400 3600 4800 6000 5004.25 4489.06 4504.41 5415.46 MIN: 2565.77 / MAX: 11954.25 MIN: 2543.37 / MAX: 7801.22 MIN: 2560.7 / MAX: 7228.61 MIN: 2567.66 / MAX: 21634.63 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU a b bb c 0.2948 0.5896 0.8844 1.1792 1.474 1.17 1.31 1.31 1.08 1. (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.org ms, Fewer Is Better Renaissance 0.16 Test: Savina Reactors.IO a b bb c 1100 2200 3300 4400 5500 5338.7 5229.6 5360.8 5250.6 MAX: 7566.83 MAX: 7901.15 MIN: 5360.76 / MAX: 7595.61 MIN: 5250.57 / MAX: 7316.25
Renaissance Test: Gaussian Mixture Model OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Gaussian Mixture Model a b bb c 1000 2000 3000 4000 5000 4643.4 4581.1 4616.0 4534.2 MIN: 4643.38 / MAX: 5248.85 MIN: 4423.98 / MAX: 5050.76 MAX: 5157.94 MIN: 4412.76 / MAX: 4943.27
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Finagle HTTP Requests a b bb c 900 1800 2700 3600 4500 4385.9 3884.6 4297.2 3929.9 MAX: 5421.32 MIN: 3335.79 / MAX: 4399.52 MAX: 4817.4 MIN: 3248.37 / MAX: 4520.84
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Apache Spark Bayes a b bb c 200 400 600 800 1000 638.2 745.2 716.9 789.7 MIN: 580.8 / MAX: 828.74 MIN: 609.15 / MAX: 891.9 MIN: 591.68 / MAX: 844.76 MIN: 640.59 / MAX: 897.21
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU a b bb c 300 600 900 1200 1500 1402.50 1285.29 1281.77 1568.68 MIN: 660.35 / MAX: 5619.27 MIN: 661.66 / MAX: 2931.41 MIN: 663.22 / MAX: 2901.61 MIN: 666.6 / MAX: 9839.79 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU a b bb c 1.0395 2.079 3.1185 4.158 5.1975 4.27 4.61 4.62 3.73 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Random Forest a b bb c 130 260 390 520 650 570.1 600.6 624.2 601.9 MIN: 534.15 / MAX: 651.47 MIN: 560.53 / MAX: 656.17 MIN: 564.93 / MAX: 776.27 MIN: 554.87 / MAX: 660.27
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Genetic Algorithm Using Jenetics + Futures a b bb c 300 600 900 1200 1500 1244.5 1222.8 1230.5 1251.9 MIN: 1130.89 / MAX: 1359.65 MIN: 1123.42 / MAX: 1307.54 MIN: 1114.96 / MAX: 1356.94 MIN: 1146.96 / MAX: 1404.63
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.16 Test: Scala Dotty a b bb c 130 260 390 520 650 550.0 561.4 596.6 573.8 MIN: 463.24 / MAX: 928.24 MIN: 478.02 / MAX: 968.67 MIN: 486.85 / MAX: 1078.3 MIN: 477.81 / MAX: 939.92
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU a b bb c 100 200 300 400 500 439.61 411.33 410.91 454.25 MIN: 232.29 / MAX: 1903.58 MIN: 224.97 / MAX: 963.04 MIN: 222.81 / MAX: 845.42 MIN: 192.15 / MAX: 1904.48 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU a b bb c 4 8 12 16 20 13.38 14.53 14.57 13.01 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU a b bb c 90 180 270 360 450 392.48 350.74 352.81 432.55 MIN: 168.33 / MAX: 1771.01 MIN: 169.89 / MAX: 756.81 MIN: 183.5 / MAX: 837.79 MIN: 164.06 / MAX: 1770.86 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU a b bb c 4 8 12 16 20 15.25 17.05 16.96 13.75 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU a b bb c 60 120 180 240 300 259.96 246.56 240.71 273.66 MIN: 130.23 / MAX: 1000.64 MIN: 128.61 / MAX: 661.55 MIN: 129.63 / MAX: 979.78 MIN: 131.85 / MAX: 999.97 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU a b bb c 15 30 45 60 75 61.05 64.71 66.33 58.06 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b bb c 16 32 48 64 80 65.68 59.62 59.42 71.13 MIN: 30.63 / MAX: 319.44 MIN: 31.69 / MAX: 109.78 MIN: 29.99 / MAX: 117.72 MIN: 30.21 / MAX: 364.45 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b bb c 20 40 60 80 100 91.10 100.47 100.83 83.92 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b bb c 50 100 150 200 250 238.66 217.86 210.75 241.56 MIN: 101.28 / MAX: 947.08 MIN: 103.9 / MAX: 635.93 MIN: 103.37 / MAX: 548.96 MIN: 104.83 / MAX: 911.97 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b bb c 20 40 60 80 100 66.62 73.28 75.74 65.86 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU a b bb c 30 60 90 120 150 117.50 114.32 114.65 119.53 MIN: 45.67 / MAX: 445.31 MIN: 48.61 / MAX: 405.31 MIN: 76.78 / MAX: 342.17 MIN: 72.87 / MAX: 434.2 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU a b bb c 12 24 36 48 60 50.76 52.36 52.24 50.07 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU a b bb c 8 16 24 32 40 29.11 26.71 26.59 33.81 MIN: 13.53 / MAX: 79.9 MIN: 13.32 / MAX: 44.78 MIN: 13.16 / MAX: 47.31 MIN: 13.51 / MAX: 143.78 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU a b bb c 50 100 150 200 250 205.02 223.62 224.66 175.67 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b bb c 9 18 27 36 45 34.21 30.68 30.48 37.93 MIN: 14.72 / MAX: 152.84 MIN: 16.13 / MAX: 55.32 MIN: 13.66 / MAX: 56.89 MIN: 15.71 / MAX: 152.86 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b bb c 40 80 120 160 200 174.78 195.02 196.37 157.38 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU a b bb c 9 18 27 36 45 32.52 29.42 29.28 38.00 MIN: 13.27 / MAX: 98.34 MIN: 13.3 / MAX: 50.36 MIN: 13.23 / MAX: 56.48 MIN: 13.58 / MAX: 150.48 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU a b bb c 40 80 120 160 200 183.94 203.39 204.40 157.14 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU a b bb c 14 28 42 56 70 62.01 59.37 59.87 63.15 MIN: 27.87 / MAX: 273.2 MIN: 31.87 / MAX: 215.48 MIN: 26.15 / MAX: 156.54 MIN: 32.01 / MAX: 273.44 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU a b bb c 20 40 60 80 100 96.28 100.76 99.98 94.65 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU a b bb c 3 6 9 12 15 8.78 8.15 8.09 10.48 MIN: 3.74 / MAX: 28.34 MIN: 3.56 / MAX: 16.97 MIN: 3.69 / MAX: 17.48 MIN: 3.94 / MAX: 72.26 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU a b bb c 160 320 480 640 800 678.84 731.87 737.31 565.21 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU a b bb c 5 10 15 20 25 17.79 16.04 15.99 19.39 MIN: 6.93 / MAX: 78.65 MIN: 7.67 / MAX: 35.36 MIN: 7.49 / MAX: 39.2 MIN: 8.01 / MAX: 78.86 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU a b bb c 80 160 240 320 400 335.00 372.29 373.56 306.99 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b bb c 0.468 0.936 1.404 1.872 2.34 1.66 1.53 1.53 2.08 MIN: 0.45 / MAX: 6.8 MIN: 0.48 / MAX: 5.15 MIN: 0.48 / MAX: 4.89 MIN: 0.46 / MAX: 11.03 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b bb c 2K 4K 6K 8K 10K 8888.15 9570.87 9615.64 7143.56 1. (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.org ms, Fewer Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b bb c 1.0778 2.1556 3.2334 4.3112 5.389 4.01 3.63 3.62 4.79 MIN: 1.23 / MAX: 11.41 MIN: 1.26 / MAX: 10.8 MIN: 1.25 / MAX: 11.17 MIN: 1.1 / MAX: 20.47 1. (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.org FPS, More Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b bb c 900 1800 2700 3600 4500 3750.57 4146.33 4149.86 3171.54 1. (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.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time Per Output Token a bb c 11 22 33 44 55 44.12 44.28 48.81
OpenVINO GenAI Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token OpenBenchmarking.org ms, Fewer Is Better OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU - Time To First Token a bb c 20 40 60 80 100 80.64 73.03 88.24
OpenVINO GenAI Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU OpenBenchmarking.org tokens/s, More Is Better OpenVINO GenAI 2024.5 Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU a bb c 5 10 15 20 25 22.66 22.58 20.49
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: Vulkan - Mostly Stable FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: Vulkan - Mostly Stable FPS a b bb c 60 120 180 240 300 297 296 280 298
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: Vulkan - Steady FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: Vulkan - Steady FPS a b bb c 50 100 150 200 250 245 248 229 244
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: Vulkan - Mostly Stable FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: Vulkan - Mostly Stable FPS a b bb c 60 120 180 240 300 294 286 268 286
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: Vulkan - Steady FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: Vulkan - Steady FPS a b bb c 50 100 150 200 250 245 236 211 236
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512 a bb c 14 28 42 56 70 61.51 61.42 51.60 1. (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.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: Vulkan - Mostly Stable FPS a b bb c 70 140 210 280 350 321 318 303 320
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: Vulkan - Steady FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: Vulkan - Steady FPS a b bb c 50 100 150 200 250 250 151 248 251
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: Vulkan - Mostly Stable FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: Vulkan - Mostly Stable FPS a b bb c 70 140 210 280 350 314 302 286 307
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: Vulkan - Steady FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: Vulkan - Steady FPS a b bb c 60 120 180 240 300 247 247 236 252
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: OpenGL - Mostly Stable FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: OpenGL - Mostly Stable FPS a b bb c 15 30 45 60 75 65 61 62 63
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: OpenGL - Steady FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: High - Renderer: OpenGL - Steady FPS a b bb c 13 26 39 52 65 59 57 55 57
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: OpenGL - Mostly Stable FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: OpenGL - Mostly Stable FPS a b bb c 30 60 90 120 150 135 135 131 135
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: OpenGL - Steady FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Low - Renderer: OpenGL - Steady FPS a b bb c 30 60 90 120 150 113 46 59 47
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: OpenGL - Mostly Stable FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: OpenGL - Mostly Stable FPS a b bb c 13 26 39 52 65 60 56 56 58
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: OpenGL - Steady FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Ultimate - Renderer: OpenGL - Steady FPS a b bb c 12 24 36 48 60 55 51 50 52
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: OpenGL - Mostly Stable FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: OpenGL - Mostly Stable FPS a b bb c 20 40 60 80 100 86 86 81 87
SuperTuxKart Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: OpenGL - Steady FPS OpenBenchmarking.org Frames Per Second, More Is Better SuperTuxKart 1.5 Beta 1 Resolution: 1920 x 1080 - Graphics Effects: Medium - Renderer: OpenGL - Steady FPS a b bb c 20 40 60 80 100 76 73 70 75
Llama.cpp Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 OpenBenchmarking.org Tokens Per Second, More Is Better Llama.cpp b4154 Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128 a bb c 7 14 21 28 35 28.13 28.18 23.68 1. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas
Phoronix Test Suite v10.8.5