9575F smoke

AMD EPYC 9575F 64-Core testing with a Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS) and ASPEED on Ubuntu 24.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2411289-NE-9575FSMOK66&grr&sor.

9575F smokeProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionabAMD EPYC 9575F 64-Core @ 3.30GHz (64 Cores / 128 Threads)Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS)AMD 1Ah12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF3201GB Micron_7450_MTFDKCB3T2TFSASPEED2 x Broadcom NetXtreme BCM5720 PCIeUbuntu 24.106.12.0-rc7-linux-pm-next-phx (x86_64)GNOME Shell 47.0X ServerGCC 14.2.0ext41024x768OpenBenchmarking.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: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116 Java Details- OpenJDK Runtime Environment (build 21.0.5+11-Ubuntu-1ubuntu124.10)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: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

9575F smokebyte: Whetstone Doublebyte: Dhrystone 2byte: System Callbyte: Pipexnnpack: QS8MobileNetV2xnnpack: FP16MobileNetV3Smallxnnpack: FP16MobileNetV3Largexnnpack: FP16MobileNetV2xnnpack: FP16MobileNetV1xnnpack: FP32MobileNetV3Smallxnnpack: FP32MobileNetV3Largexnnpack: FP32MobileNetV2xnnpack: FP32MobileNetV1blender: Barbershop - CPU-Onlysvt-av1: Preset 3 - Bosphorus 4Kcassandra: Writessvt-av1: Preset 3 - Bosphorus 1080popenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - 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: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUlaghos: Sedov Blast Wave, ube_922_hex.meshpalabos: 400palabos: 500litert: NASNet Mobilelitert: Inception V4litert: Inception ResNet V2litert: DeepLab V3litert: Mobilenet Quantlitert: Quantized COCO SSD MobileNet v1litert: Mobilenet Floatlitert: SqueezeNetpalabos: 100blender: Pabellon Barcelona - CPU-Onlyblender: Classroom - CPU-Onlysvt-av1: Preset 5 - Bosphorus 4Kllama-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 2048laghos: Triple Point Problembuild-eigen: Time To Compileastcenc: Very Thoroughopenvino-genai: Gemma-7b-int4-ov - CPU - Time Per Output Tokenopenvino-genai: Gemma-7b-int4-ov - CPU - Time To First Tokenopenvino-genai: Gemma-7b-int4-ov - CPUastcenc: Exhaustiveprimesieve: 1e13svt-av1: Preset 5 - Bosphorus 1080popenvino-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 - CPUblender: Fishy Cat - CPU-Onlyblender: Junkshop - CPU-Onlyllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 1024namd: STMV with 1,066,628 Atomsblender: BMW27 - CPU-Onlyopenvino-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 - CPUllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Text Generation 128llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 2048llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Text Generation 128svt-av1: Preset 8 - Bosphorus 4Kopenvino-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 - CPUllama-cpp: CPU BLAS - Llama-3.1-Tulu-3-8B-Q8_0 - Prompt Processing 512llama-cpp: CPU BLAS - Mistral-7B-Instruct-v0.3-Q8_0 - Prompt Processing 512mt-dgemm: Sustained Floating-Point Rateastcenc: Thoroughsvt-av1: Preset 8 - Bosphorus 1080pastcenc: Fastllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 1024llama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Text Generation 128svt-av1: Preset 13 - Bosphorus 4Knamd: ATPase with 327,506 Atomsastcenc: Mediumllama-cpp: CPU BLAS - granite-3.0-3b-a800m-instruct-Q8_0 - Prompt Processing 512svt-av1: Preset 13 - Bosphorus 1080pprimesieve: 1e12ab1440313.36028934961.9360905676.5379708473.5504154467099469224705413724247252417148.5917.03346418144.809455.2370.11227.21140.599.566485.9740.94781.0948.68656.2948.88653.65.096219.363.419322.350.26166477.7513.762316.7517.61812.320.34137029.682.8322034.494.217561.852.0315364.866.864634.7520.553111.8220.933054.874.6413617.589.316826.87579.090715221734.242776.3121819724673.339371.716007.5194158744.912429.063814.42812.28547.4341.7160.729319.54321.82308.9228.46510.122820.3430.3649.166.216124.78147.92617.331.2857.8221.2620.13334.84335.623.7536015.1512.9415.8277.2751.84965.4454.23202.15415.3123.3465.33313.79317.195201.05592472.4097529.471077.7771055.54120.87481.96812.58888514.66751013.031299.7311.9731440301.86060068455.1360867935.4378638216.8505754177082480924715406722047432432148.617.04449166144.722455.5670.02227.4140.429.556492.4340.93781.3249.01651.8648.92653.075.096221.543.429309.660.26164424.1213.712326.5817.181856.610.34137431.922.8321941.814.227540.162.0215466.246.94609.720.593106.4520.9530534.6313596.149.316821.09567.84732.406772.49722118424727.438276.517473.418266.49116.472424.823857.68804.11947.5841.4660.767328.07327.81295.6528.3710.125520.1630.1649.616.223324.83148.16317.9329.2755.7821.2720.25325.9331.383.7973715.0112.9515.977.2551.65962.0754.01202.42915.1721.9165.91296.41317.465203.82668472.3404534.2121135.11681056.46121.27478.8412.64614514.2389998.21316.9461.975OpenBenchmarking.org

BYTE Unix Benchmark

Computational Test: Whetstone Double

OpenBenchmarking.orgMWIPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: Whetstone Doubleab300K600K900K1200K1500K1440313.31440301.81. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

BYTE Unix Benchmark

Computational Test: Dhrystone 2

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: Dhrystone 2ba1300M2600M3900M5200M6500M6060068455.16028934961.91. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

BYTE Unix Benchmark

Computational Test: System Call

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: System Callab80M160M240M320M400M360905676.5360867935.41. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

BYTE Unix Benchmark

Computational Test: Pipe

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 5.1.3-gitComputational Test: Pipeab80M160M240M320M400M379708473.5378638216.81. (CC) gcc options: -pedantic -O3 -ffast-math -march=native -mtune=native -lm

XNNPACK

Model: QS8MobileNetV2

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: QS8MobileNetV2ab11002200330044005500504150571. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP16MobileNetV3Small

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Smallba12002400360048006000541754461. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP16MobileNetV3Large

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3Largeba15003000450060007500708270991. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP16MobileNetV2

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV2ab10002000300040005000469248091. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP16MobileNetV1

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV1ab5001000150020002500247024711. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP32MobileNetV3Small

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Smallba12002400360048006000540654131. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP32MobileNetV3Large

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3Largeba16003200480064008000722072421. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP32MobileNetV2

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV2ab10002000300040005000472547431. (CXX) g++ options: -O3 -lrt -lm

XNNPACK

Model: FP32MobileNetV1

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV1ab5001000150020002500241724321. (CXX) g++ options: -O3 -lrt -lm

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: CPU-Onlyab306090120150148.59148.60

SVT-AV1

Encoder Mode: Preset 3 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 3 - Input: Bosphorus 4Kba4812162017.0417.031. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 5.0Test: Writesba110K220K330K440K550K491661464181

SVT-AV1

Encoder Mode: Preset 3 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 3 - Input: Bosphorus 1080pab102030405044.8144.721. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16 - Device: CPUab100200300400500455.23455.56MIN: 379.27 / MAX: 470.62MIN: 358.53 / MAX: 467.531. (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: CPUab163248648070.1170.021. (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.orgms, Fewer Is BetterOpenVINO 2024.5Model: Face Detection FP16-INT8 - Device: CPUab50100150200250227.21227.40MIN: 213.43 / MAX: 250.31MIN: 190.49 / MAX: 248.731. (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: CPUab306090120150140.59140.421. (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: CPUba36912159.559.56MIN: 6.24 / MAX: 20.75MIN: 6.01 / MAX: 21.581. (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: CPUba140028004200560070006492.436485.971. (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: CPUba91827364540.9340.94MIN: 22.52 / MAX: 59.28MIN: 22.77 / MAX: 58.681. (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: CPUba2004006008001000781.32781.091. (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.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP16 - Device: CPUab112233445548.6849.01MIN: 35.62 / MAX: 80.7MIN: 37.75 / MAX: 78.791. (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: CPUab140280420560700656.29651.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Person Detection FP32 - Device: CPUab112233445548.8848.92MIN: 21.94 / MAX: 80.52MIN: 36.36 / MAX: 80.161. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Person Detection FP32 - Device: CPUab140280420560700653.60653.071. (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: CPUab1.14532.29063.43594.58125.72655.095.09MIN: 3.2 / MAX: 15.27MIN: 3.24 / MAX: 12.861. (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: CPUba130026003900520065006221.546219.361. (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: CPUab0.76951.5392.30853.0783.84753.413.42MIN: 2.12 / MAX: 10.97MIN: 1.64 / MAX: 10.951. (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: CPUab2K4K6K8K10K9322.359309.661. (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: CPUab0.05850.1170.17550.2340.29250.260.26MIN: 0.11 / MAX: 18.01MIN: 0.11 / MAX: 19.061. (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: CPUab40K80K120K160K200K166477.75164424.121. (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: CPUba4812162013.7113.76MIN: 8.65 / MAX: 29.04MIN: 7.69 / MAX: 27.141. (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: CPUba50010001500200025002326.582316.751. (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: CPUba4812162017.1817.60MIN: 11.6 / MAX: 32.37MIN: 8.57 / MAX: 30.921. (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: CPUba4008001200160020001856.611812.321. (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: CPUab0.07650.1530.22950.3060.38250.340.34MIN: 0.16 / MAX: 10.05MIN: 0.15 / MAX: 10.781. (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: CPUba30K60K90K120K150K137431.92137029.681. (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: CPUab0.63681.27361.91042.54723.1842.832.83MIN: 1.66 / MAX: 11.71MIN: 1.62 / MAX: 9.11. (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: CPUab5K10K15K20K25K22034.4921941.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16-INT8 - Device: CPUab0.94951.8992.84853.7984.74754.214.22MIN: 2.44 / MAX: 16.23MIN: 2.1 / MAX: 17.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Vehicle Detection FP16-INT8 - Device: CPUab160032004800640080007561.857540.161. (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: CPUba0.45680.91361.37041.82722.2842.022.03MIN: 1.16 / MAX: 5.27MIN: 1.15 / MAX: 5.231. (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: CPUba3K6K9K12K15K15466.2415364.861. (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: CPUab2468106.866.90MIN: 3.31 / MAX: 17.14MIN: 2.86 / MAX: 15.251. (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: CPUab100020003000400050004634.754609.701. (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: CPUab51015202520.5520.59MIN: 13.3 / MAX: 28.62MIN: 13.03 / MAX: 36.121. (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: CPUab70014002100280035003111.823106.451. (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: CPUab51015202520.9320.95MIN: 15.01 / MAX: 31.5MIN: 13.73 / MAX: 32.591. (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: CPUab70014002100280035003054.873053.001. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16-INT8 - Device: CPUba1.0442.0883.1324.1765.224.634.64MIN: 2.41 / MAX: 14.26MIN: 2.41 / MAX: 12.381. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16-INT8 - Device: CPUab3K6K9K12K15K13617.5813596.141. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16 - Device: CPUab36912159.319.31MIN: 4.57 / MAX: 24.34MIN: 4.31 / MAX: 25.141. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.5Model: Weld Porosity Detection FP16 - Device: CPUab150030004500600075006826.876821.091. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs

Laghos

Test: Sedov Blast Wave, ube_922_hex.mesh

OpenBenchmarking.orgMajor Kernels Total Rate, More Is BetterLaghos 3.1Test: Sedov Blast Wave, ube_922_hex.meshab130260390520650579.09567.841. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

Palabos

Grid Size: 400

OpenBenchmarking.orgMega Site Updates Per Second, More Is BetterPalabos 2.3Grid Size: 400ab160320480640800734.24732.411. (CXX) g++ options: -std=c++17 -pedantic -O3 -rdynamic -lcrypto -lcurl -lsz -lz -ldl -lm

Palabos

Grid Size: 500

OpenBenchmarking.orgMega Site Updates Per Second, More Is BetterPalabos 2.3Grid Size: 500ab2004006008001000776.31772.501. (CXX) g++ options: -std=c++17 -pedantic -O3 -rdynamic -lcrypto -lcurl -lsz -lz -ldl -lm

LiteRT

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: NASNet Mobileab50K100K150K200K250K218197221184

LiteRT

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception V4ab5K10K15K20K25K24673.324727.4

LiteRT

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception ResNet V2ba8K16K24K32K40K38276.539371.7

LiteRT

Model: DeepLab V3

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: DeepLab V3ab4K8K12K16K20K16007.517473.4

LiteRT

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Quantba4K8K12K16K20K18266.419415.0

LiteRT

Model: Quantized COCO SSD MobileNet v1

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Quantized COCO SSD MobileNet v1ab2K4K6K8K10K8744.919116.47

LiteRT

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet Floatba50010001500200025002424.822429.06

LiteRT

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: SqueezeNetab80016002400320040003814.423857.68

Palabos

Grid Size: 100

OpenBenchmarking.orgMega Site Updates Per Second, More Is BetterPalabos 2.3Grid Size: 100ab2004006008001000812.29804.121. (CXX) g++ options: -std=c++17 -pedantic -O3 -rdynamic -lcrypto -lcurl -lsz -lz -ldl -lm

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: CPU-Onlyab112233445547.4347.58

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: CPU-Onlyba102030405041.4641.71

SVT-AV1

Encoder Mode: Preset 5 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 5 - Input: Bosphorus 4Kba142842567060.7760.731. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 2048ba70140210280350328.07319.541. (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 2048

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048ba70140210280350327.81321.821. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

Laghos

Test: Triple Point Problem

OpenBenchmarking.orgMajor Kernels Total Rate, More Is BetterLaghos 3.1Test: Triple Point Problemab70140210280350308.92295.651. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

Timed Eigen Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Eigen Compilation 3.4.0Time To Compileba71421283528.3728.47

ASTC Encoder

Preset: Very Thorough

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Very Thoroughba369121510.1310.121. (CXX) g++ options: -O3 -flto -pthread

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 Tokenba51015202520.1620.34

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 Tokenba71421283530.1630.36

OpenVINO GenAI

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

OpenBenchmarking.orgtokens/s, More Is BetterOpenVINO GenAI 2024.5Model: Gemma-7b-int4-ov - Device: CPUba112233445549.6149.16

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Exhaustiveba2468106.22336.21611. (CXX) g++ options: -O3 -flto -pthread

Primesieve

Length: 1e13

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.6Length: 1e13ab61218243024.7824.831. (CXX) g++ options: -O3

SVT-AV1

Encoder Mode: Preset 5 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 5 - Input: Bosphorus 1080pba306090120150148.16147.931. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 Tokenab4812162017.3017.93

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 Tokenba71421283529.2731.28

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: CPUab132639526557.8255.78

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: CPU-Onlyab51015202521.2621.27

Blender

Blend File: Junkshop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: CPU-Onlyab51015202520.1320.25

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 1024ab70140210280350334.84325.901. (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 1024

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b4154Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024ab70140210280350335.62331.381. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

NAMD

Input: STMV with 1,066,628 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: STMV with 1,066,628 Atomsba0.85441.70882.56323.41764.2723.797373.75360

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: CPU-Onlyba4812162015.0115.15

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 Tokenab369121512.9412.95

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 Tokenab4812162015.8215.90

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: CPUab2040608010077.2777.25

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 128ab122436486051.8451.651. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

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 2048ab2004006008001000965.44962.071. (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: 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 128ab122436486054.2354.011. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 8 - Input: Bosphorus 4Kba4080120160200202.43202.151. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 Tokenba4812162015.1715.31

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 Tokenba61218243021.9123.34

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: CPUba153045607565.9165.33

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 512ab70140210280350313.79296.411. (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 512ba70140210280350317.46317.191. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Rateba110022003300440055005203.835201.061. (CC) gcc options: -ffast-math -mavx2 -O3 -fopenmp -lopenblas

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Thoroughab163248648072.4172.341. (CXX) g++ options: -O3 -flto -pthread

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 8 - Input: Bosphorus 1080pba120240360480600534.21529.471. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

ASTC Encoder

Preset: Fast

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Fastba20040060080010001135.121077.781. (CXX) g++ options: -O3 -flto -pthread

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 1024ba20040060080010001056.461055.541. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

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 128ba306090120150121.27120.871. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 13 - Input: Bosphorus 4Kab100200300400500481.97478.841. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

NAMD

Input: ATPase with 327,506 Atoms

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: ATPase with 327,506 Atomsba369121512.6512.59

ASTC Encoder

Preset: Medium

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 5.0Preset: Mediumab110220330440550514.67514.241. (CXX) g++ options: -O3 -flto -pthread

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 512ab20040060080010001013.03998.201. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -fopenmp -march=native -mtune=native -lopenblas

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.3Encoder Mode: Preset 13 - Input: Bosphorus 1080pba300600900120015001316.951299.731. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Primesieve

Length: 1e12

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.6Length: 1e12ab0.44440.88881.33321.77762.2221.9731.9751. (CXX) g++ options: -O3

Phoronix Test Suite v10.8.5