new

AMD Ryzen 7 7840HS testing with a NB05 TUXEDO Pulse 14 Gen3 R14FA1 (8.06 BIOS) and AMD Phoenix1 4GB on Tuxedo 22.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2403266-NE-NEW59105411
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

CPU Massive 5 Tests
Creator Workloads 7 Tests
HPC - High Performance Computing 2 Tests
Imaging 2 Tests
Machine Learning 2 Tests
Multi-Core 5 Tests
Python Tests 2 Tests
Server CPU Tests 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
a
March 25
  2 Hours, 8 Minutes
b
March 26
  2 Hours, 8 Minutes
c
March 26
  2 Hours, 9 Minutes
Invert Hiding All Results Option
  2 Hours, 8 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

a

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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 Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa704104
Python Notes: Python 3.10.12
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + 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 + srbds: Not affected + tsx_async_abort: Not affected

b

c

Processor: AMD Ryzen 7 7840HS @ 5.29GHz (8 Cores / 16 Threads), Motherboard: NB05 TUXEDO Pulse 14 Gen3 R14FA1 (8.06 BIOS), Chipset: AMD Device 14e8, Memory: 4 x 8GB DRAM-6400MT/s Micron MT62F2G32D4DS-026 WT, Disk: 2000GB Samsung SSD 980 PRO 2TB + 31GB SanDisk 3.2Gen1, Graphics: AMD Phoenix1 4GB (2700/800MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK MT7921K

OS: Tuxedo 22.04, Kernel: 6.5.0-10022-tuxedo (x86_64), Desktop: KDE Plasma 5.27.10, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 24.0.3-0tux2 (LLVM 15.0.7 DRM 3.54), Vulkan: 1.3.274, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 2880x1800

newOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 7 7840HS @ 5.29GHz (8 Cores / 16 Threads)NB05 TUXEDO Pulse 14 Gen3 R14FA1 (8.06 BIOS)AMD Device 14e84 x 8GB DRAM-6400MT/s Micron MT62F2G32D4DS-026 WT2000GB Samsung SSD 980 PRO 2TB + 31GB SanDisk 3.2Gen1AMD Phoenix1 4GB (2700/800MHz)AMD Rembrandt Radeon HD AudioMEDIATEK MT7921KTuxedo 22.046.5.0-10022-tuxedo (x86_64)KDE Plasma 5.27.10X Server 1.21.1.44.6 Mesa 24.0.3-0tux2 (LLVM 15.0.7 DRM 3.54)1.3.274GCC 11.4.0ext42880x1800ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionNew BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa704104 - Python 3.10.12- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + 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 + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%102%105%107%BRL-CADJPEG-XL Decoding libjxlSVT-AV1JPEG-XL libjxlTimed Linux Kernel CompilationRocksDBOpenVINOPrimesieveNeural Magic DeepSparseGoogle Draco

newjpegxl-decode: 1brl-cad: VGR Performance Metricsvt-av1: Preset 13 - Bosphorus 4Kjpegxl-decode: Allsvt-av1: Preset 12 - Bosphorus 4Krocksdb: Seq Filljpegxl: PNG - 90jpegxl: PNG - 80svt-av1: Preset 4 - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 1080psvt-av1: Preset 12 - Bosphorus 1080popenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUdeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamdeepsparse: Llama2 Chat 7b Quantized - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamsvt-av1: Preset 4 - Bosphorus 4Kjpegxl: JPEG - 80openvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUsvt-av1: Preset 8 - Bosphorus 1080popenvino: Noise Suppression Poconet-Like FP16 - CPUrocksdb: Read While Writingrocksdb: Rand Fill Syncrocksdb: Overwritedeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamjpegxl: JPEG - 90draco: Church Facadedeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamopenvino: Road Segmentation ADAS FP16 - CPUbuild-linux-kernel: defconfigdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamopenvino: Handwritten English Recognition FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16 - CPUdraco: Lionopenvino: Road Segmentation ADAS FP16-INT8 - CPUv-ray: CPUdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamopenvino: Road Segmentation ADAS FP16-INT8 - CPUdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamjpegxl: JPEG - 100jpegxl: PNG - 100openvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Face Detection Retail FP16 - CPUrocksdb: Update Randopenvino: Handwritten English Recognition FP16-INT8 - CPUdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamopenvino: Face Detection Retail FP16 - CPUopenvino: Face Detection FP16 - CPUrocksdb: Rand Fillsvt-av1: Preset 8 - Bosphorus 4Kopenvino: Vehicle Detection FP16 - CPUdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamopenvino: Vehicle Detection FP16 - CPUdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamprimesieve: 1e13deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamprimesieve: 1e12deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamrocksdb: Read Rand Write Randopenvino: Person Re-Identification Retail FP16 - CPUbuild-linux-kernel: allmodconfigopenvino: Face Detection FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamopenvino: Person Detection FP32 - CPUdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamopenvino: Person Detection FP32 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamopenvino: Weld Porosity Detection FP16 - CPUdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamopenvino: Weld Porosity Detection FP16 - CPUdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamopenvino: Person Detection FP16 - CPUdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamopenvino: Person Detection FP16 - CPUdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamrocksdb: Rand Readopenvino: Weld Porosity Detection FP16-INT8 - CPUdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamdeepsparse: Llama2 Chat 7b Quantized - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUabc72.68819762992.045347.06996.412167141028.59930.97715.391487.088410.0157.04566.41961.36733.08463.858967.0259.64772.99134.42132.753747.573.912038.66110.51410.5720973391629193111246314.1829211.44330.295685459.2873136.82104.40550.566526.2329.2125643.6304.85501319.361787246.1964206.4521.630113.36313.443328.641368.2266725124.33328.71319.10312.915.94109967436.205297.9615.010466.6042215.405513.4176.894212.9936186.0034.6315340.711.7367.2714.855974.095915.10840.456419275755.191412.031672.53769.478.45242.263928.4705105.2651438.797643.37353.674292.217845.5420.1641148.5349116.66538.5704589.549.743913.5513.011791.7276.7921102.481143.68.46546.86646.058.5716116.6477104.621328.6434603965501163.76183.59975.4459353.60360.310.446.1878.40219759891.144368.5791.273159210430.2432.62515.944509.4425.3037.1562.38995.84352.98413.803766.7959.87783.87624.5331.879758.674.011988.45112.66910.4321458761600211109999414.2388210.52330.409675258.7366136.66103.69451.040725.929.2425543.04308.63495819.361769146.6672206.421.413413.49613.548326.111362.7166444224.51326.33189.1662.925.92109880136.146296.9514.959966.8284214.443813.4676.828213.0055185.9994.6521339.3511.7667.130514.887274.225715.14540.382519290855.181410.639673.78770.48.45932.264228.5546104.9554438.905943.48353.549491.9817817.7620.2089148.2161116.75668.5637590.359.74813.5313.012791.8876.7873102.445943.538.47896.86645.118.5678116.6994104.768828.6077604166621163.2183.7345.442353.57650.310.446.1879.51118103197.04369.33196.682168564129.20231.84616.107508.569426.946.82584.85980.42683.02473.925864.9561.54759.944.55632.495738.754.011990.07113.28210.6921165531634751109298914.4256207.889830.771674858.5286135.08103.0851.210926.1229.5825328.05306495419.1646.5432208.521.473713.46313.555327.21373.2566215124.43327.40589.13562.95.96109300036.33296.5815.027766.5273214.544713.4777.171912.9476186.8294.6507340.8411.7167.000314.915673.935615.08640.540419216265.21406.626671.26767.988.43412.270628.5543104.9568437.684543.36354.510792.2317864.7320.2172148.1466116.4668.585590.919.726413.5212.984291.9276.954102.667343.518.4736.87645.868.5595116.8124104.739828.6128604470221162.84183.73135.442353.78980.310.446.18OpenBenchmarking.org

JPEG-XL Decoding libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL Decoding libjxl 0.10.1CPU Threads: 1abc2040608010072.6978.4079.51

BRL-CAD

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.38.2VGR Performance Metricabc40K80K120K160K200K1976291975981810311. (CXX) g++ options: -std=c++17 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lnetpbm -lregex_brl -lz_brl -lassimp -ldl -lm

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4Kabc2040608010092.0591.1497.041. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

JPEG-XL Decoding libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL Decoding libjxl 0.10.1CPU Threads: Allabc80160240320400347.07368.57369.33

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4Kabc2040608010096.4191.2796.681. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

RocksDB

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Sequential Fillabc400K800K1200K1600K2000K1671410159210416856411. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

JPEG-XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 90abc71421283528.6030.2429.201. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 80abc81624324030.9832.6331.851. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 1080pabc4812162015.3915.9416.111. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 1080pabc110220330440550487.09509.40508.571. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 1080pabc90180270360450410.02425.30426.941. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUabc2468107.047.106.82MIN: 4.32 / MAX: 18.16MIN: 4.17 / MAX: 17.57MIN: 4.39 / MAX: 18.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUabc130260390520650566.41562.38584.851. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streamabc2004006008001000961.37995.84980.43

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Streamabc0.6941.3882.0822.7763.473.08462.98413.0247

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc0.88331.76662.64993.53324.41653.85893.80373.9258

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUabc153045607567.0266.7964.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUabc142842567059.6459.8761.54MIN: 32.61 / MAX: 76.01MIN: 48.93 / MAX: 74.1MIN: 38.59 / MAX: 73.921. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc2004006008001000772.99783.88759.94

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4Kabc1.02512.05023.07534.10045.12554.4214.5304.5561. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

JPEG-XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 80abc81624324032.7531.8832.501. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUabc160320480640800747.57758.67738.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUabc0.90231.80462.70693.60924.51153.914.014.01MIN: 2.3 / MAX: 16.13MIN: 2.29 / MAX: 17.66MIN: 2.47 / MAX: 17.91. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUabc4008001200160020002038.661988.451990.071. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 1080pabc306090120150110.51112.67113.281. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUabc369121510.5710.4310.69MIN: 8.23 / MAX: 23.64MIN: 8.41 / MAX: 23.92MIN: 7.76 / MAX: 22.981. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

RocksDB

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While Writingabc500K1000K1500K2000K2500K2097339214587621165531. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Fill Syncabc400K800K1200K1600K2000K1629193160021116347511. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Overwriteabc200K400K600K800K1000K1112463109999410929891. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabc4812162014.1814.2414.43

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamabc50100150200250211.44210.52207.89

JPEG-XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 90abc71421283530.3030.4130.771. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

Google Draco

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Church Facadeabc150030004500600075006854675267481. (CXX) g++ options: -O3

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc132639526559.2958.7458.53

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUabc306090120150136.82136.66135.081. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Timed Linux Kernel Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigabc20406080100104.41103.69103.08

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc122436486050.5751.0451.21

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUabc61218243026.2325.9026.12MIN: 18.13 / MAX: 39.59MIN: 17.28 / MAX: 41.77MIN: 19.78 / MAX: 39.251. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16 - Device: CPUabc71421283529.2129.2429.58MIN: 12.86 / MAX: 42.86MIN: 15.65 / MAX: 44.46MIN: 15 / MAX: 44.191. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabc5K10K15K20K25K25643.6025543.0425328.051. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16 - Device: CPUabc70140210280350304.85308.63306.001. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Google Draco

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Lionabc110022003300440055005013495849541. (CXX) g++ options: -O3

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabc51015202519.3619.3619.16MIN: 15.31 / MAX: 27.96MIN: 9.14 / MAX: 26.21MIN: 8.77 / MAX: 28.851. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Chaos Group V-RAY

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 6.0Mode: CPUab4K8K12K16K20K1787217691

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabc112233445546.2046.6746.54

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUabc50100150200250206.45206.40208.501. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamabc51015202521.6321.4121.47

JPEG-XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 100abc369121513.3613.5013.461. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 100abc369121513.4413.5513.561. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUabc70140210280350328.64326.11327.201. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUabc300600900120015001368.221362.711373.251. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

RocksDB

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Update Randomabc140K280K420K560K700K6672516644426621511. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUabc61218243024.3324.5124.43MIN: 14.75 / MAX: 43.24MIN: 15.35 / MAX: 38.97MIN: 15.08 / MAX: 39.021. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc70140210280350328.71326.33327.41

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc36912159.10319.16609.1356

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16 - Device: CPUabc0.6571.3141.9712.6283.2852.912.922.90MIN: 1.67 / MAX: 11.21MIN: 1.71 / MAX: 13.74MIN: 1.69 / MAX: 14.781. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUabc1.3412.6824.0235.3646.7055.945.925.961. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

RocksDB

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Fillabc200K400K600K800K1000K1099674109880110930001. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4Kabc81624324036.2136.1536.331. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUabc60120180240300297.96296.95296.581. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabc4812162015.0114.9615.03

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamabc153045607566.6066.8366.53

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabc50100150200250215.41214.44214.54

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16 - Device: CPUabc369121513.4113.4613.47MIN: 7.17 / MAX: 22.72MIN: 4.74 / MAX: 23.86MIN: 6.61 / MAX: 25.181. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabc2040608010076.8976.8377.17

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Synchronous Single-Streamabc369121512.9913.0112.95

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13abc4080120160200186.00186.00186.831. (CXX) g++ options: -O3

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Streamabc1.04672.09343.14014.18685.23354.63154.65214.6507

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUabc70140210280350340.70339.35340.84MIN: 330.5 / MAX: 351.75MIN: 275.39 / MAX: 352.98MIN: 281.09 / MAX: 351.581. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUabc369121511.7311.7611.711. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabc153045607567.2767.1367.00

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamabc4812162014.8614.8914.92

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabc163248648074.1074.2373.94

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e12abc4812162015.1115.1515.091. (CXX) g++ options: -O3

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamabc91827364540.4640.3840.54

RocksDB

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write Randomabc400K800K1200K1600K2000K1927575192908519216261. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUabc1.172.343.514.685.855.195.185.20MIN: 3.19 / MAX: 16.47MIN: 3.22 / MAX: 16.29MIN: 3.23 / MAX: 16.151. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Timed Linux Kernel Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigabc300600900120015001412.031410.641406.63

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16 - Device: CPUabc150300450600750672.53673.78671.26MIN: 596.32 / MAX: 693.61MIN: 602.96 / MAX: 693.77MIN: 652.35 / MAX: 691.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUabc170340510680850769.47770.40767.981. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabc2468108.45248.45938.4341

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabc0.51091.02181.53272.04362.55452.26392.26422.2706

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabc71421283528.4728.5528.55

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamabc20406080100105.27104.96104.96

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Streamabc100200300400500438.80438.91437.68

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUabc102030405043.3743.4843.361. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamabc80160240320400353.67353.55354.51

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP32 - Device: CPUabc2040608010092.2091.9892.23MIN: 76.05 / MAX: 105.63MIN: 79.12 / MAX: 106.99MIN: 80.44 / MAX: 111.421. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabc4K8K12K16K20K17845.5417817.7617864.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc51015202520.1620.2120.22

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamabc306090120150148.53148.22148.15

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabc306090120150116.67116.76116.47

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamabc2468108.57048.56378.5850

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUabc130260390520650589.54590.35590.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabc36912159.74399.74809.7264

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16 - Device: CPUabc369121513.5513.5313.52MIN: 6.81 / MAX: 26.53MIN: 7.5 / MAX: 27.32MIN: 7.51 / MAX: 26.081. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabc369121513.0113.0112.98

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUabc2040608010091.7291.8891.92MIN: 77.18 / MAX: 106.3MIN: 77.74 / MAX: 103.93MIN: 77.73 / MAX: 110.521. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Streamabc2040608010076.7976.7976.95

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Streamabc20406080100102.48102.45102.67

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUabc102030405043.6043.5343.511. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabc2468108.46548.47898.4730

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUabc2468106.866.866.87MIN: 3.52 / MAX: 18.21MIN: 3.63 / MAX: 20.47MIN: 3.63 / MAX: 20.211. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUabc140280420560700646.05645.11645.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabc2468108.57168.56788.5595

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamabc306090120150116.65116.70116.81

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc20406080100104.62104.77104.74

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamabc71421283528.6428.6128.61

RocksDB

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random Readabc13M26M39M52M65M6039655060416662604470221. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUabc300600900120015001163.761163.201162.841. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamabc4080120160200183.60183.73183.73

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.7Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Streamabc1.22532.45063.67594.90126.12655.44595.44205.4420

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.7Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamabc80160240320400353.60353.58353.79

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUabc0.06980.13960.20940.27920.3490.310.310.31MIN: 0.19 / MAX: 11.22MIN: 0.21 / MAX: 11.45MIN: 0.2 / MAX: 11.251. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUabc0.0990.1980.2970.3960.4950.440.440.44MIN: 0.25 / MAX: 11.02MIN: 0.27 / MAX: 11.21MIN: 0.27 / MAX: 11.771. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUabc2468106.186.186.18MIN: 3.74 / MAX: 19.08MIN: 3.45 / MAX: 16.94MIN: 3.34 / MAX: 17.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

116 Results Shown

JPEG-XL Decoding libjxl
BRL-CAD
SVT-AV1
JPEG-XL Decoding libjxl
SVT-AV1
RocksDB
JPEG-XL libjxl:
  PNG - 90
  PNG - 80
SVT-AV1:
  Preset 4 - Bosphorus 1080p
  Preset 13 - Bosphorus 1080p
  Preset 12 - Bosphorus 1080p
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU:
    ms
    FPS
Neural Magic DeepSparse:
  Llama2 Chat 7b Quantized - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
OpenVINO:
  Machine Translation EN To DE FP16 - CPU:
    FPS
    ms
Neural Magic DeepSparse
SVT-AV1
JPEG-XL libjxl
OpenVINO:
  Noise Suppression Poconet-Like FP16 - CPU
  Face Detection Retail FP16-INT8 - CPU
  Face Detection Retail FP16-INT8 - CPU
SVT-AV1
OpenVINO
RocksDB:
  Read While Writing
  Rand Fill Sync
  Overwrite
Neural Magic DeepSparse:
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    items/sec
    ms/batch
JPEG-XL libjxl
Google Draco
Neural Magic DeepSparse
OpenVINO
Timed Linux Kernel Compilation
Neural Magic DeepSparse
OpenVINO:
  Handwritten English Recognition FP16 - CPU
  Road Segmentation ADAS FP16 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
  Handwritten English Recognition FP16 - CPU
Google Draco
OpenVINO
Chaos Group V-RAY
Neural Magic DeepSparse
OpenVINO
Neural Magic DeepSparse
JPEG-XL libjxl:
  JPEG - 100
  PNG - 100
OpenVINO:
  Handwritten English Recognition FP16-INT8 - CPU
  Face Detection Retail FP16 - CPU
RocksDB
OpenVINO
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
OpenVINO:
  Face Detection Retail FP16 - CPU
  Face Detection FP16 - CPU
RocksDB
SVT-AV1
OpenVINO
Neural Magic DeepSparse:
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream:
    items/sec
OpenVINO
Neural Magic DeepSparse:
  ResNet-50, Baseline - Synchronous Single-Stream:
    items/sec
    ms/batch
Primesieve
Neural Magic DeepSparse
OpenVINO:
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
Neural Magic DeepSparse:
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    items/sec
Primesieve
Neural Magic DeepSparse
RocksDB
OpenVINO
Timed Linux Kernel Compilation
OpenVINO:
  Face Detection FP16 - CPU
  Person Re-Identification Retail FP16 - CPU
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream
  ResNet-50, Sparse INT8 - Synchronous Single-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
  ResNet-50, Sparse INT8 - Synchronous Single-Stream
OpenVINO
Neural Magic DeepSparse
OpenVINO:
  Person Detection FP32 - CPU
  Age Gender Recognition Retail 0013 FP16 - CPU
Neural Magic DeepSparse:
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    ms/batch
    items/sec
OpenVINO
Neural Magic DeepSparse
OpenVINO
Neural Magic DeepSparse
OpenVINO
Neural Magic DeepSparse:
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream
  BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream
OpenVINO
Neural Magic DeepSparse
OpenVINO:
  Weld Porosity Detection FP16-INT8 - CPU
  Vehicle Detection FP16-INT8 - CPU
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    items/sec
    ms/batch
RocksDB
OpenVINO
Neural Magic DeepSparse:
  Llama2 Chat 7b Quantized - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    ms/batch
OpenVINO:
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
  Age Gender Recognition Retail 0013 FP16 - CPU
  Vehicle Detection FP16-INT8 - CPU

a

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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 Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa704104
Python Notes: Python 3.10.12
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + 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 + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 25 March 2024 21:19 by user phoronix.

b

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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 Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa704104
Python Notes: Python 3.10.12
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + 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 + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 26 March 2024 00:47 by user phoronix.

c

Processor: AMD Ryzen 7 7840HS @ 5.29GHz (8 Cores / 16 Threads), Motherboard: NB05 TUXEDO Pulse 14 Gen3 R14FA1 (8.06 BIOS), Chipset: AMD Device 14e8, Memory: 4 x 8GB DRAM-6400MT/s Micron MT62F2G32D4DS-026 WT, Disk: 2000GB Samsung SSD 980 PRO 2TB + 31GB SanDisk 3.2Gen1, Graphics: AMD Phoenix1 4GB (2700/800MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK MT7921K

OS: Tuxedo 22.04, Kernel: 6.5.0-10022-tuxedo (x86_64), Desktop: KDE Plasma 5.27.10, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 24.0.3-0tux2 (LLVM 15.0.7 DRM 3.54), Vulkan: 1.3.274, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 2880x1800

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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 Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa704104
Python Notes: Python 3.10.12
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + 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 + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 26 March 2024 02:42 by user phoronix.