tgl tgl

Intel Core i7-1185G7 testing with a Dell XPS 13 9310 0DXP1F (3.7.0 BIOS) and Intel Xe TGL GT2 15GB on Ubuntu 23.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2402202-NE-TGLTGL07808
Jump To Table - Results

View

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

Limit displaying results to tests within:

C/C++ Compiler Tests 2 Tests
CPU Massive 3 Tests
Creator Workloads 2 Tests
HPC - High Performance Computing 5 Tests
Large Language Models 2 Tests
Machine Learning 3 Tests
Molecular Dynamics 2 Tests
Multi-Core 4 Tests
NVIDIA GPU Compute 3 Tests
Python Tests 2 Tests
Scientific Computing 2 Tests
Server CPU Tests 2 Tests
Vulkan Compute 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
Performance Per
Dollar
Date
Run
  Test
  Duration
a
February 20
  6 Hours, 53 Minutes
b
February 20
  7 Hours, 20 Minutes
c
February 20
  7 Hours, 18 Minutes
Invert Hiding All Results Option
  7 Hours, 10 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):


tgl tglOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-1185G7 @ 4.80GHz (4 Cores / 8 Threads)Dell XPS 13 9310 0DXP1F (3.7.0 BIOS)Intel Tiger Lake-LP8 x 2GB LPDDR4-4267MT/sMicron 2300 NVMe 512GBIntel Xe TGL GT2 15GB (1350MHz)Realtek ALC289Intel Wi-Fi 6 AX201Ubuntu 23.106.7.0-060700rc5-generic (x86_64)GNOME Shell 45.1X Server + Wayland4.6 Mesa 24.0~git2312220600.68c53e~oibaf~m (git-68c53ec 2023-12-22 mantic-oibaf-ppa)OpenCL 3.0GCC 13.2.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionTgl Tgl BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xb4 - Thermald 2.5.4- Python 3.11.6- gather_data_sampling: Mitigation of Microcode + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%102%104%107%109%dav1dLibplaceboGROMACSNAMDONNX RuntimeVkFFTLZ4 CompressionLlamafileCacheBenchLlama.cppIntel Open Image Denoise

tgl tglvkfft: FFT + iFFT R2C / C2Rvkfft: FFT + iFFT C2C 1D batched in half precisionvkfft: FFT + iFFT C2C Bluestein in single precisionvkfft: FFT + iFFT C2C 1D batched in single precisionvkfft: FFT + iFFT C2C multidimensional in single precisionvkfft: FFT + iFFT C2C 1D batched in single precision, no reshufflinglibplacebo: deband_heavylibplacebo: polar_nocomputelibplacebo: hdr_peakdetectlibplacebo: hdr_lutlibplacebo: av1_grain_laplibplacebo: gaussiannamd: ATPase with 327,506 Atomsnamd: STMV with 1,066,628 Atomscachebench: Readcachebench: Writecachebench: Read / Modify / Writecompress-lz4: 1 - Compression Speedcompress-lz4: 1 - Decompression Speedcompress-lz4: 3 - Compression Speedcompress-lz4: 3 - Decompression Speedcompress-lz4: 9 - Compression Speedcompress-lz4: 9 - Decompression Speeddav1d: Chimera 1080pdav1d: Summer Nature 4Kdav1d: Summer Nature 1080pdav1d: Chimera 1080p 10-bitoidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyoidn: RTLightmap.hdr.4096x4096 - CPU-Onlygromacs: MPI CPU - water_GMX50_bareonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - Standardonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: T5 Encoder - CPU - Parallelonnx: T5 Encoder - CPU - Parallelonnx: T5 Encoder - CPU - Standardonnx: T5 Encoder - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: super-resolution-10 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardllama-cpp: llama-2-7b.Q4_0.ggufllama-cpp: llama-2-13b.Q4_0.ggufllama-cpp: llama-2-70b-chat.Q5_0.ggufllamafile: llava-v1.5-7b-q4 - CPUllamafile: mistral-7b-instruct-v0.2.Q8_0 - CPUllamafile: wizardcoder-python-34b-v1.0.Q6_K - CPUabc631013702111275005869851078.22151.38336.77371.63405.16370.730.546400.167938945.279885109630.165987103769.795772755.414114.5118.713850.641.134072.4403.4392.92325.6296.560.150.160.070.57381.610512.2437105.4869.473092.89643345.2495.06166197.5690.918510.9972146.8616.806044.25933234.7756.90025144.917239.5854.17219333.9242.993150.4710172123.060.6861471457.419.98691100.1314.91967.026499.278510.0709129.1677.7399726.96437.084445.327522.058220.917947.803337.047826.98927.373.840.037.074.260.05614613923111674955952850378.16151.42254.33371.86405.8370.690.552720.168108946.160249109813.145754104513.363289754.764123.5119.043870.741.164077405.66102.65409.89296.790.150.160.070.5777.202212.9464101.5979.835713.25429307.2834.72968211.42789.811811.1326146.7166.81344.8325206.9296.38547156.599238.1644.19665350.12.854820.4156422405.910.7539191326.48.98048111.35116.30961.313598.487710.1511129.0577.7465128.398935.210247.039621.255121.601146.290837.459526.69267.413.840.037.094.280.05619813748111174965843850678.1151.27274.71371.35403.9370.580.534650.168128946.289183109693.870056104746.114943752.434139.1117.873857.840.774080401.1194.69381.24297.270.150.160.070.56383.353811.987104.9169.523713.12461320.0364.91617203.40689.559411.1641147.4966.777373.977251.4426.83843146.226240.2214.16112328.3633.043570.4623952162.650.6808861468.6710.194898.087214.800667.562297.33310.2724128.3787.7871328.251835.393442.810623.355423.194443.111335.551428.12557.433.840.037.124.270.05OpenBenchmarking.org

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT R2C / C2Rbca140028004200560070006146619863101. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in half precisionacb3K6K9K12K15K1370213748139231. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C Bluestein in single precisioncab20040060080010001111111211161. (CXX) g++ options: -O3

Test: FFT + iFFT C2C 1D batched in double precision

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

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

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

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in single precisionbca160032004800640080007495749675001. (CXX) g++ options: -O3

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C multidimensional in single precisioncab130026003900520065005843586959521. (CXX) g++ options: -O3

Test: FFT + iFFT C2C Bluestein benchmark in double precision

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

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

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

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.3.4Test: FFT + iFFT C2C 1D batched in single precision, no reshufflingbca2K4K6K8K10K8503850685101. (CXX) g++ options: -O3

Libplacebo

Libplacebo is a multimedia rendering library based on the core rendering code of the MPV player. The libplacebo benchmark relies on the Vulkan API and tests various primitives. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: deband_heavycba2040608010078.1078.1678.221. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: polar_nocomputecab306090120150151.27151.38151.421. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: hdr_peakdetectbca70140210280350254.33274.71336.771. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: hdr_lutcab80160240320400371.35371.63371.861. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: av1_grain_lapcab90180270360450403.90405.16405.801. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

OpenBenchmarking.orgFPS, More Is BetterLibplacebo 6.338.2Test: gaussiancba80160240320400370.58370.69370.731. (CXX) g++ options: -fvisibility=hidden -std=c++20 -O2 -fno-math-errno -fPIC -pthread -MD -MQ -MF

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: ATPase with 327,506 Atomscab0.12440.24880.37320.49760.6220.534650.546400.55272

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: STMV with 1,066,628 Atomsabc0.03780.07560.11340.15120.1890.167930.168100.16812

CacheBench

This is a performance test of CacheBench, which is part of LLCbench. CacheBench is designed to test the memory and cache bandwidth performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Readabc2K4K6K8K10K8945.288946.168946.29MIN: 8942.72 / MAX: 8947.89MIN: 8944.76 / MAX: 8946.98MIN: 8939.89 / MAX: 8948.191. (CC) gcc options: -O3 -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Writeacb20K40K60K80K100K109630.17109693.87109813.15MIN: 78349.8 / MAX: 127046.33MIN: 78492.75 / MAX: 127175.97MIN: 78789.09 / MAX: 126929.161. (CC) gcc options: -O3 -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / Writeabc20K40K60K80K100K103769.80104513.36104746.11MIN: 79762.44 / MAX: 113377.99MIN: 83065.75 / MAX: 113865.39MIN: 80807.87 / MAX: 113668.221. (CC) gcc options: -O3 -lrt

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (silesia archive) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 1 - Compression Speedcba160320480640800752.43754.76755.411. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 1 - Decompression Speedabc90018002700360045004114.54123.54139.11. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 3 - Compression Speedcab306090120150117.87118.71119.041. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 3 - Decompression Speedacb80016002400320040003850.63857.83870.71. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 9 - Compression Speedcab91827364540.7741.1341.161. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 9 - Decompression Speedabc90018002700360045004072.44077.04080.01. (CC) gcc options: -O3

dav1d

Dav1d is an open-source, speedy AV1 video decoder supporting modern SIMD CPU features. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.4Video Input: Chimera 1080pcab90180270360450401.11403.43405.661. (CC) gcc options: -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.4Video Input: Summer Nature 4Kacb2040608010092.9294.69102.651. (CC) gcc options: -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.4Video Input: Summer Nature 1080pacb90180270360450325.60381.24409.891. (CC) gcc options: -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.4Video Input: Chimera 1080p 10-bitabc60120180240300296.56296.79297.271. (CC) gcc options: -pthread

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Onlyabc0.03380.06760.10140.13520.1690.150.150.15

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Onlyabc0.0360.0720.1080.1440.180.160.160.16

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RTLightmap.hdr.4096x4096 - Device: CPU-Onlyabc0.01580.03160.04740.06320.0790.070.070.07

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_barecba0.12890.25780.38670.51560.64450.5630.5700.5731. (CXX) g++ options: -O3 -lm

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Parallelbac2040608010077.2081.6183.351. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Standardbca20406080100101.60104.92105.491. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Parallelacb0.73221.46442.19662.92883.6612.896433.124613.254291. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Standardbca1.13892.27783.41674.55565.69454.729684.916175.061661. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Parallelcba2040608010089.5689.8190.921. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Standardbac306090120150146.72146.86147.501. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Parallelcab1.08732.17463.26194.34925.43653.977004.259334.832501. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Standardbca2468106.385476.838436.900251. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelbac50100150200250238.16239.59240.221. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardcab80160240320400328.36333.92350.101. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelbca0.1060.2120.3180.4240.530.4156420.4623950.4710171. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Standardcab0.16960.33920.50880.67840.8480.6808860.6861470.7539191. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelbac36912158.980489.9869110.194801. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardcab4812162014.8014.9216.311. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelcba2040608010097.3398.4999.281. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardcba306090120150128.38129.06129.171. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Parallelacb71421283526.9628.2528.401. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Standardcab112233445542.8145.3347.041. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelabc61218243020.9221.6023.191. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardcab91827364535.5537.0537.461. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Llama.cpp

Llama.cpp is a port of Facebook's LLaMA model in C/C++ developed by Georgi Gerganov. Llama.cpp allows the inference of LLaMA and other supported models in C/C++. For CPU inference Llama.cpp supports AVX2/AVX-512, ARM NEON, and other modern ISAs along with features like OpenBLAS usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-7b.Q4_0.ggufabc2468107.377.417.431. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-13b.Q4_0.ggufabc0.8641.7282.5923.4564.323.843.843.841. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-70b-chat.Q5_0.ggufabc0.00680.01360.02040.02720.0340.030.030.031. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas

Llamafile

Mozilla's Llamafile allows distributing and running large language models (LLMs) as a single file. Llamafile aims to make open-source LLMs more accessible to developers and users. Llamafile supports a variety of models, CPUs and GPUs, and other options. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: llava-v1.5-7b-q4 - Acceleration: CPUabc2468107.077.097.12

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPUacb0.9631.9262.8893.8524.8154.264.274.28

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.6Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPUabc0.01130.02260.03390.04520.05650.050.050.05

57 Results Shown

VkFFT:
  FFT + iFFT R2C / C2R
  FFT + iFFT C2C 1D batched in half precision
  FFT + iFFT C2C Bluestein in single precision
  FFT + iFFT C2C 1D batched in single precision
  FFT + iFFT C2C multidimensional in single precision
  FFT + iFFT C2C 1D batched in single precision, no reshuffling
Libplacebo:
  deband_heavy
  polar_nocompute
  hdr_peakdetect
  hdr_lut
  av1_grain_lap
  gaussian
NAMD:
  ATPase with 327,506 Atoms
  STMV with 1,066,628 Atoms
CacheBench:
  Read
  Write
  Read / Modify / Write
LZ4 Compression:
  1 - Compression Speed
  1 - Decompression Speed
  3 - Compression Speed
  3 - Decompression Speed
  9 - Compression Speed
  9 - Decompression Speed
dav1d:
  Chimera 1080p
  Summer Nature 4K
  Summer Nature 1080p
  Chimera 1080p 10-bit
Intel Open Image Denoise:
  RT.hdr_alb_nrm.3840x2160 - CPU-Only
  RT.ldr_alb_nrm.3840x2160 - CPU-Only
  RTLightmap.hdr.4096x4096 - CPU-Only
GROMACS
ONNX Runtime:
  GPT-2 - CPU - Parallel
  GPT-2 - CPU - Standard
  yolov4 - CPU - Parallel
  yolov4 - CPU - Standard
  T5 Encoder - CPU - Parallel
  T5 Encoder - CPU - Standard
  bertsquad-12 - CPU - Parallel
  bertsquad-12 - CPU - Standard
  CaffeNet 12-int8 - CPU - Parallel
  CaffeNet 12-int8 - CPU - Standard
  fcn-resnet101-11 - CPU - Parallel
  fcn-resnet101-11 - CPU - Standard
  ArcFace ResNet-100 - CPU - Parallel
  ArcFace ResNet-100 - CPU - Standard
  ResNet50 v1-12-int8 - CPU - Parallel
  ResNet50 v1-12-int8 - CPU - Standard
  super-resolution-10 - CPU - Parallel
  super-resolution-10 - CPU - Standard
  Faster R-CNN R-50-FPN-int8 - CPU - Parallel
  Faster R-CNN R-50-FPN-int8 - CPU - Standard
Llama.cpp:
  llama-2-7b.Q4_0.gguf
  llama-2-13b.Q4_0.gguf
  llama-2-70b-chat.Q5_0.gguf
Llamafile:
  llava-v1.5-7b-q4 - CPU
  mistral-7b-instruct-v0.2.Q8_0 - CPU
  wizardcoder-python-34b-v1.0.Q6_K - CPU