GCC 14 vs. Clang 18 - AMD Ryzen Threadripper 7980X

AMD Ryzen Threadripper 7980X compiler benchmarking on Fedora 40 by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2404242-NE-GCC14AMDR04
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
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
GCC 14.0.1 20240411
April 23
  6 Hours, 36 Minutes
Clang 18.1.1
April 23
  7 Hours, 8 Minutes
Invert Behavior (Only Show Selected Data)
  6 Hours, 52 Minutes
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):

GCC 14.0.1 20240411

Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900 45GB, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E

OS: Fedora Linux 40, Kernel: 6.8.5-301.fc40.x86_64 (x86_64), Desktop: GNOME Shell 46.1, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.5 (LLVM 18.1.1 DRM 3.57), Compiler: GCC 14.0.1 20240411, File-System: btrfs, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,m2,lto --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-multilib --enable-offload-defaulted --enable-offload-targets=nvptx-none,amdgcn-amdhsa --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
Python Notes: Python 3.12.2
Security Notes: SELinux + 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: 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; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Clang 18.1.1

OS: Fedora Linux 40, Kernel: 6.8.5-301.fc40.x86_64 (x86_64), Desktop: GNOME Shell 46.1, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.5 (LLVM 18.1.1 DRM 3.57), Compiler: Clang 18.1.1 + LLVM 18.1.1, File-System: btrfs, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
Python Notes: Python 3.12.2
Security Notes: SELinux + 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: 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; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

GCC 14 vs. Clang 18 - AMD Ryzen Threadripper 7980XOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads)System76 Thelio Major (FA Z5 BIOS)AMD Device 14a44 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA21000GB CT1000T700SSD5AMD Radeon Pro W7900 45GBAMD Device 14ccDELL P2415QAquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6EFedora Linux 406.8.5-301.fc40.x86_64 (x86_64)GNOME Shell 46.1X Server + Wayland4.6 Mesa 24.0.5 (LLVM 18.1.1 DRM 3.57)GCC 14.0.1 20240411Clang 18.1.1 + LLVM 18.1.1btrfs1920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilersFile-SystemScreen ResolutionGCC 14 Vs. Clang 18 - AMD Ryzen Threadripper 7980X BenchmarksSystem Logs- Transparent Huge Pages: madvise- CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"- GCC 14.0.1 20240411: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,m2,lto --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-multilib --enable-offload-defaulted --enable-offload-targets=nvptx-none,amdgcn-amdhsa --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105- Python 3.12.2- SELinux + 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: 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; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

GCC 14.0.1 20240411 vs. Clang 18.1.1 ComparisonPhoronix Test SuiteBaseline+16.4%+16.4%+32.8%+32.8%+49.2%+49.2%60.2%28.3%23.4%20.4%20.4%20%14.3%11.4%9.1%8.1%6.7%6.3%5.9%5.2%5%4.5%4.4%4.1%4%4%3.6%3.5%3.4%3.2%3.2%3.2%2.9%2.9%2.7%2.5%2.4%2.3%2.3%2.2%2.1%2%3.7%65.5%41.3%SHA3-256ChaCha20-Poly130558.2%ChaCha2052%HMAC-SHA51239.4%Total Time - 4.1.R.P.P37.4%1 - 256 - 512HWB Color Space23.9%Q.1.H.C14 digit23.3%CORAL2 P121.2%Swirl21.2%F.x.A20.7%OpenMP - BM2OpenMP - BM264 - 256 - 512WPA PSK17.6%Noise-Gaussian16.4%N.S.P.L.F - CPU15.5%N.S.P.L.F - CPU14.8%wyhashCTS213.9%M.T.E.T.D.F - CPU12.1%M.T.E.T.D.F - CPU11.9%MD5CoreMark Size 666 - I.P.S10.5%JPEG - 90Sharpen8.5%Resizing8.4%A.C.PP.P.B.T.T8%9 - Compression Speed6.9%FarmHash1286.7%WAV To FLAC96000 - 1024MPI CPU - water_GMX50_bare6.2%Bosphorus 4K - Very FastBosphorus 4K - Very FastWAV To Opus Encode128 - 256 - 512Bosphorus 4K - Medium9 - D.S4.3%12 - Compression Speed4.1%bcryptSecureMark-TLS12 - D.SBosphorus 4K - Super Fast3 - Compression Speed3.5%Bosphorus 4K - Super Fast20k Atoms3.5%192000 - 1024BlowfishBosphorus 4K - Ultra FastExhaustiveR.S.A.F.I - CPU3.1%R.S.A.F.I - CPU3.1%Bosphorus 4K - Medium3%3 - D.S3%Spooky32SHA2562.9%Very Thoroughfasthash322.8%LionBosphorus 4K - Slow2.7%Church FacadeEnhancedBosphorus 4K19 - D.SM.x.A.NPreset 8 - Bosphorus 4K2.2%Medium19, Long Mode - D.SwyhashSHA3-256FarmHash128F.x.A12%SMHasherOpenSSLOpenSSLJohn The RipperC-RayLiquid-DSPGraphicsMagickWebP Image EncodeHelsingQuicksilverGraphicsMagickSMHasherminiBUDEminiBUDELiquid-DSPJohn The RipperGraphicsMagickOpenVINOOpenVINOSMHasherQuicksilverOpenVINOOpenVINOJohn The RipperCoremarkJPEG-XL libjxlGraphicsMagickGraphicsMagickTSCPsrsRAN ProjectLZ4 CompressionSMHasherFLAC Audio EncodingStargate Digital Audio WorkstationGROMACSKvazaaruvg266Opus Codec EncodingLiquid-DSPKvazaarLZ4 CompressionZstd CompressionJohn The RipperSecureMarkZstd Compressionuvg266LZ4 CompressionKvazaarLAMMPS Molecular Dynamics SimulatorStargate Digital Audio WorkstationJohn The Ripperuvg266ASTC EncoderOpenVINOOpenVINOuvg266LZ4 CompressionSMHasherOpenSSLASTC EncoderSMHasherGoogle Dracouvg266Google DracoGraphicsMagickx265Zstd CompressionSMHasherSVT-AV1ASTC EncoderZstd CompressionSMHasherSMHasherSMHasherSMHasherGCC 14.0.1 20240411Clang 18.1.1

GCC 14 vs. Clang 18 - AMD Ryzen Threadripper 7980Xminibude: OpenMP - BM1minibude: OpenMP - BM2openssl: SHA256openssl: SHA512openssl: ChaCha20openssl: AES-128-GCMopenssl: AES-256-GCMopenssl: ChaCha20-Poly1305quicksilver: CTS2quicksilver: CORAL2 P1quicksilver: CORAL2 P2openvino: Person Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUkvazaar: Bosphorus 4K - Mediumkvazaar: Bosphorus 4K - Very Fastkvazaar: Bosphorus 4K - Super Fastkvazaar: Bosphorus 4K - Ultra Fastsvt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Kuvg266: Bosphorus 4K - Slowuvg266: Bosphorus 4K - Mediumuvg266: Bosphorus 4K - Very Fastuvg266: Bosphorus 4K - Super Fastuvg266: Bosphorus 4K - Ultra Fastx265: Bosphorus 4Kminibude: OpenMP - BM1minibude: OpenMP - BM2graphics-magick: Swirlgraphics-magick: Rotategraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Resizinggraphics-magick: Noise-Gaussiangraphics-magick: HWB Color Spacecoremark: CoreMark Size 666 - Iterations Per Secondsecuremark: SecureMark-TLScompress-lz4: 3 - Compression Speedcompress-lz4: 3 - Decompression Speedcompress-lz4: 9 - Compression Speedcompress-lz4: 9 - Decompression Speedcompress-zstd: 12 - Compression Speedcompress-zstd: 12 - Decompression Speedcompress-zstd: 19 - Compression Speedcompress-zstd: 19 - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedcompress-zstd: 19, Long Mode - Decompression Speedsrsran: PDSCH Processor Benchmark, Throughput Totalsrsran: PUSCH Processor Benchmark, Throughput Totalquantlib: Multi-Threadedquantlib: Single-Threadedsmhasher: wyhashsmhasher: SHA3-256smhasher: Spooky32smhasher: fasthash32smhasher: FarmHash128smhasher: t1ha2_atoncesmhasher: FarmHash32 x86_64 AVXsmhasher: t1ha0_aes_avx2 x86_64smhasher: MeowHash x86_64 AES-NIjpegxl: PNG - 90jpegxl: JPEG - 90jpegxl: PNG - 100jpegxl: JPEG - 100jpegxl-decode: Allwebp: Quality 100webp: Quality 100, Losslesswebp: Quality 100, Highest Compressionwebp: Quality 100, Lossless, Highest Compressionastcenc: Mediumastcenc: Thoroughastcenc: Exhaustiveastcenc: Very Thoroughtscp: AI Chess Performancegromacs: MPI CPU - water_GMX50_barelammps: 20k Atomsjohn-the-ripper: bcryptjohn-the-ripper: WPA PSKjohn-the-ripper: Blowfishjohn-the-ripper: HMAC-SHA512john-the-ripper: MD5stargate: 96000 - 1024stargate: 192000 - 1024liquid-dsp: 1 - 256 - 512liquid-dsp: 64 - 256 - 512liquid-dsp: 128 - 256 - 512openssl: RSA4096openssl: RSA4096synthmark: VoiceMark_100smhasher: wyhashsmhasher: SHA3-256smhasher: Spooky32smhasher: fasthash32smhasher: FarmHash128smhasher: t1ha2_atoncesmhasher: FarmHash32 x86_64 AVXsmhasher: t1ha0_aes_avx2 x86_64smhasher: MeowHash x86_64 AES-NIdraco: Liondraco: Church Facadeopenvino: Person Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUc-ray: Total Time - 4K, 16 Rays Per Pixelprimesieve: 1e13encode-flac: WAV To FLACencode-opus: WAV To Opus Encodehelsing: 14 digitrnnoise: 26 Minute Long Talking Sampleencode-wavpack: WAV To WavPackGCC 14.0.1 20240411Clang 18.1.1175.902175.05011251352716337084177003437829686883822088248977707658246553310352617927218533332857333321786667200.0684.534938.0713824.921304.85355.938089.554299.753367.265969.172288.66116609.4437.0579.4993.1297.059.84895.246197.492193.77927.1630.3970.7372.6574.0739.164397.5444376.2445541552162501931852593365815.032822416097146.675658.049.025882.1399.12251.425.91917.812.11825.320064.54801.9293011.24611.626137.98237.3320053.078833.7121159.3719662.3337461.4696787.5750680.4048.57546.96941.17541.694600.86814.802.074.570.81450.109862.44845.34468.712019600845.57127.242153446541461152866298853000133186676.1616164.097617182589171025733333124220000044305.11280463.3990.57013.4421648.90525.09420.79743.84719.11024.11419.08541.83640495240159.76377.586.384.3824.4489.777.647.3318.285.3327.860.436.17926.35111.39219.32863.2857.6073.702174.766210.78210934582436037246099377288123851390816719157710701069882433196215871807191866672357000022130000199.4783.824888.5613601.851266.10317.988024.944232.672933.125885.262283.11115684.8538.6784.1696.3797.809.85393.194194.885195.30726.4529.5074.3875.2776.4540.084369.1405269.5504571531992561781592093044772.380526432909141.725493.745.865640.1383.42340.925.81962.812.31861.020338.74446.1295240.54697.629888.69380.2720643.458593.7819825.3619737.3931033.6297667.2651816.5449.45451.25440.70741.653597.36214.582.055.640.82459.583163.56065.51308.961521183895.24726.333159726460525157785214448333148403336.5507664.238755234263081231066667129786666744172.31275596.81002.51512.968996.37225.14620.56431.02419.35126.99918.83942.39339425112160.20380.506.454.4625.20100.607.707.4421.125.4027.930.438.49226.43110.68018.41678.0577.4843.701OpenBenchmarking.org

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1GCC 14.0.1 20240411Clang 18.1.14080120160200SE +/- 0.09, N = 3SE +/- 1.52, N = 15175.90174.771. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Clang 18.1.1GCC 14.0.1 2024041150100150200250SE +/- 0.27, N = 3SE +/- 0.24, N = 3210.78175.051. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: SHA256GCC 14.0.1 20240411Clang 18.1.120000M40000M60000M80000M100000MSE +/- 254544356.50, N = 3SE +/- 281782565.20, N = 3112513527163109345824360-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: SHA512Clang 18.1.1GCC 14.0.1 202404118000M16000M24000M32000M40000MSE +/- 38811972.88, N = 3SE +/- 40543653.85, N = 33724609937737084177003-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20GCC 14.0.1 20240411Clang 18.1.190000M180000M270000M360000M450000MSE +/- 56533218.78, N = 3SE +/- 161435637.78, N = 3437829686883288123851390-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: AES-128-GCMGCC 14.0.1 20240411Clang 18.1.1200000M400000M600000M800000M1000000MSE +/- 665285492.45, N = 3SE +/- 246618519.80, N = 3822088248977816719157710-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: AES-256-GCMGCC 14.0.1 20240411Clang 18.1.1150000M300000M450000M600000M750000MSE +/- 612129667.02, N = 3SE +/- 847452668.98, N = 3707658246553701069882433-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20-Poly1305GCC 14.0.1 20240411Clang 18.1.170000M140000M210000M280000M350000MSE +/- 34389860.61, N = 3SE +/- 32266915.14, N = 3310352617927196215871807-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

Quicksilver

Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CTS2GCC 14.0.1 20240411Clang 18.1.15M10M15M20M25MSE +/- 6666.67, N = 3SE +/- 75351.03, N = 321853333191866671. (CXX) g++ options: -fopenmp -O3 -march=native

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P1GCC 14.0.1 20240411Clang 18.1.16M12M18M24M30MSE +/- 26034.17, N = 3SE +/- 32145.50, N = 328573333235700001. (CXX) g++ options: -fopenmp -O3 -march=native

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P2Clang 18.1.1GCC 14.0.1 202404115M10M15M20M25MSE +/- 10000.00, N = 3SE +/- 80069.41, N = 322130000217866671. (CXX) g++ options: -fopenmp -O3 -march=native

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUGCC 14.0.1 20240411Clang 18.1.14080120160200SE +/- 0.27, N = 3SE +/- 0.66, N = 3200.06199.47-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.120406080100SE +/- 0.07, N = 3SE +/- 0.08, N = 384.5383.82-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.111002200330044005500SE +/- 6.00, N = 3SE +/- 8.31, N = 34938.074888.56-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.13K6K9K12K15KSE +/- 11.99, N = 3SE +/- 5.86, N = 313824.9213601.85-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.130060090012001500SE +/- 9.55, N = 3SE +/- 16.52, N = 31304.851266.10-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUGCC 14.0.1 20240411Clang 18.1.180160240320400SE +/- 0.54, N = 3SE +/- 2.83, N = 15355.93317.98-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.12K4K6K8K10KSE +/- 6.57, N = 3SE +/- 9.39, N = 38089.558024.94-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUGCC 14.0.1 20240411Clang 18.1.19001800270036004500SE +/- 5.60, N = 3SE +/- 5.05, N = 34299.754232.67-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUGCC 14.0.1 20240411Clang 18.1.17001400210028003500SE +/- 28.58, N = 15SE +/- 27.73, N = 153367.262933.12-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUGCC 14.0.1 20240411Clang 18.1.113002600390052006500SE +/- 3.36, N = 3SE +/- 2.64, N = 35969.175885.26-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.15001000150020002500SE +/- 1.62, N = 3SE +/- 4.45, N = 32288.662283.11-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.120K40K60K80K100KSE +/- 108.76, N = 3SE +/- 47.46, N = 3116609.44115684.85-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumClang 18.1.1GCC 14.0.1 20240411918273645SE +/- 0.06, N = 3SE +/- 0.04, N = 338.6737.05-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastClang 18.1.1GCC 14.0.1 2024041120406080100SE +/- 0.17, N = 3SE +/- 0.12, N = 384.1679.49-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastClang 18.1.1GCC 14.0.1 2024041120406080100SE +/- 0.32, N = 3SE +/- 0.91, N = 596.3793.12-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastClang 18.1.1GCC 14.0.1 2024041120406080100SE +/- 0.86, N = 3SE +/- 0.89, N = 397.8097.05-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4KClang 18.1.1GCC 14.0.1 202404113691215SE +/- 0.023, N = 3SE +/- 0.023, N = 39.8539.8481. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4KGCC 14.0.1 20240411Clang 18.1.120406080100SE +/- 0.71, N = 3SE +/- 0.39, N = 395.2593.191. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4KGCC 14.0.1 20240411Clang 18.1.14080120160200SE +/- 1.09, N = 3SE +/- 1.72, N = 8197.49194.891. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KClang 18.1.1GCC 14.0.1 202404114080120160200SE +/- 1.67, N = 15SE +/- 1.61, N = 3195.31193.781. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: SlowGCC 14.0.1 20240411Clang 18.1.1612182430SE +/- 0.02, N = 3SE +/- 0.03, N = 327.1626.451. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumGCC 14.0.1 20240411Clang 18.1.1714212835SE +/- 0.06, N = 3SE +/- 0.02, N = 330.3929.501. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastClang 18.1.1GCC 14.0.1 2024041120406080100SE +/- 0.26, N = 3SE +/- 0.15, N = 374.3870.731. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastClang 18.1.1GCC 14.0.1 2024041120406080100SE +/- 0.22, N = 3SE +/- 0.25, N = 375.2772.651. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastClang 18.1.1GCC 14.0.1 2024041120406080100SE +/- 0.08, N = 3SE +/- 0.13, N = 376.4574.071. (CXX) g++ options: -O3 -march=native

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.6Video Input: Bosphorus 4KClang 18.1.1GCC 14.0.1 20240411918273645SE +/- 0.12, N = 3SE +/- 0.17, N = 340.0839.161. (CXX) g++ options: -O3 -march=native -rdynamic -lpthread -lrt -ldl

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1GCC 14.0.1 20240411Clang 18.1.19001800270036004500SE +/- 2.34, N = 3SE +/- 37.96, N = 154397.544369.141. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Clang 18.1.1GCC 14.0.1 2024041111002200330044005500SE +/- 6.63, N = 3SE +/- 5.94, N = 35269.554376.241. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SwirlGCC 14.0.1 20240411Clang 18.1.1120240360480600SE +/- 0.88, N = 3SE +/- 0.58, N = 3554457-lgomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=native -ljpeg -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: RotateGCC 14.0.1 20240411Clang 18.1.1306090120150SE +/- 0.00, N = 3SE +/- 0.00, N = 3155153-lgomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=native -ljpeg -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SharpenGCC 14.0.1 20240411Clang 18.1.150100150200250SE +/- 0.33, N = 3SE +/- 1.00, N = 3216199-lgomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=native -ljpeg -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedClang 18.1.1GCC 14.0.1 2024041160120180240300SE +/- 0.33, N = 3SE +/- 0.33, N = 3256250-lomp-lgomp1. (CC) gcc options: -fopenmp -O3 -march=native -ljpeg -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: ResizingGCC 14.0.1 20240411Clang 18.1.14080120160200SE +/- 0.58, N = 3SE +/- 0.33, N = 3193178-lgomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=native -ljpeg -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianGCC 14.0.1 20240411Clang 18.1.14080120160200SE +/- 0.33, N = 3SE +/- 0.00, N = 3185159-lgomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=native -ljpeg -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: HWB Color SpaceGCC 14.0.1 20240411Clang 18.1.160120180240300SE +/- 0.67, N = 3SE +/- 0.33, N = 3259209-lgomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=native -ljpeg -lX11 -lz -lm -lpthread

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondGCC 14.0.1 20240411Clang 18.1.1700K1400K2100K2800K3500KSE +/- 1831.80, N = 3SE +/- 24583.22, N = 153365815.033044772.381. (CC) gcc options: -O2 -O3 -march=native -lrt" -lrt

SecureMark

SecureMark is an objective, standardized benchmarking framework for measuring the efficiency of cryptographic processing solutions developed by EEMBC. SecureMark-TLS is benchmarking Transport Layer Security performance with a focus on IoT/edge computing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSClang 18.1.1GCC 14.0.1 2024041190K180K270K360K450KSE +/- 1948.09, N = 3SE +/- 1794.60, N = 34329094160971. (CC) gcc options: -pedantic -O3

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: 3 - Compression SpeedGCC 14.0.1 20240411Clang 18.1.1306090120150SE +/- 0.46, N = 3SE +/- 1.63, N = 4146.67141.721. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 3 - Decompression SpeedGCC 14.0.1 20240411Clang 18.1.112002400360048006000SE +/- 20.86, N = 3SE +/- 60.76, N = 45658.05493.71. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 9 - Compression SpeedGCC 14.0.1 20240411Clang 18.1.11122334455SE +/- 0.30, N = 3SE +/- 0.07, N = 349.0245.861. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.4Compression Level: 9 - Decompression SpeedGCC 14.0.1 20240411Clang 18.1.113002600390052006500SE +/- 36.97, N = 3SE +/- 4.45, N = 35882.15640.11. (CC) gcc options: -O3 -march=native

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression SpeedGCC 14.0.1 20240411Clang 18.1.190180270360450SE +/- 3.11, N = 3SE +/- 0.40, N = 3399.1383.4-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression SpeedClang 18.1.1GCC 14.0.1 202404115001000150020002500SE +/- 2.17, N = 3SE +/- 21.94, N = 32340.92251.4-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedGCC 14.0.1 20240411Clang 18.1.1612182430SE +/- 0.03, N = 3SE +/- 0.07, N = 325.925.8-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression SpeedClang 18.1.1GCC 14.0.1 20240411400800120016002000SE +/- 2.11, N = 3SE +/- 2.52, N = 31962.81917.8-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedClang 18.1.1GCC 14.0.1 202404113691215SE +/- 0.03, N = 3SE +/- 0.07, N = 312.312.1-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression SpeedClang 18.1.1GCC 14.0.1 20240411400800120016002000SE +/- 3.56, N = 3SE +/- 10.14, N = 31861.01825.3-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalClang 18.1.1GCC 14.0.1 202404114K8K12K16K20KSE +/- 173.47, N = 3SE +/- 160.00, N = 1520338.720064.51. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalGCC 14.0.1 20240411Clang 18.1.110002000300040005000SE +/- 0.38, N = 3SE +/- 0.23, N = 34801.94446.1MIN: 3393.9 / MAX: 4802.5MIN: 2910.7 / MAX: 4446.51. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedClang 18.1.1GCC 14.0.1 2024041160K120K180K240K300KSE +/- 1085.73, N = 3SE +/- 975.48, N = 3295240.5293011.21. (CXX) g++ options: -O3 -march=native -fPIE -pie

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Single-ThreadedClang 18.1.1GCC 14.0.1 2024041110002000300040005000SE +/- 22.05, N = 3SE +/- 36.95, N = 34697.64611.61. (CXX) g++ options: -O3 -march=native -fPIE -pie

SMHasher

SMHasher is a hash function tester supporting various algorithms and able to make use of AVX and other modern CPU instruction set extensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: wyhashClang 18.1.1GCC 14.0.1 202404116K12K18K24K30KSE +/- 26.97, N = 3SE +/- 77.66, N = 329888.6926137.98-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: wyhashClang 18.1.1GCC 14.0.1 202404113691215SE +/- 0.00, N = 3SE +/- 0.01, N = 312.9713.44-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: SHA3-256Clang 18.1.1GCC 14.0.1 2024041180160240320400SE +/- 3.36, N = 3SE +/- 1.54, N = 3380.27237.33-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: SHA3-256Clang 18.1.1GCC 14.0.1 20240411400800120016002000SE +/- 3.42, N = 3SE +/- 5.66, N = 3996.371648.91-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: Spooky32Clang 18.1.1GCC 14.0.1 202404114K8K12K16K20KSE +/- 64.55, N = 3SE +/- 51.73, N = 320643.4520053.07-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: Spooky32GCC 14.0.1 20240411Clang 18.1.1612182430SE +/- 0.13, N = 3SE +/- 0.14, N = 325.0925.15-flto=auto -fno-fat-lto-objects-flto=thin1. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: fasthash32GCC 14.0.1 20240411Clang 18.1.12K4K6K8K10KSE +/- 25.94, N = 3SE +/- 13.72, N = 38833.718593.78-flto=auto -fno-fat-lto-objects-flto=thin1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: fasthash32Clang 18.1.1GCC 14.0.1 20240411510152025SE +/- 0.07, N = 3SE +/- 0.03, N = 320.5620.80-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: FarmHash128GCC 14.0.1 20240411Clang 18.1.15K10K15K20K25KSE +/- 114.70, N = 3SE +/- 58.42, N = 321159.3719825.36-flto=auto -fno-fat-lto-objects-flto=thin1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: FarmHash128Clang 18.1.1GCC 14.0.1 202404111020304050SE +/- 0.01, N = 3SE +/- 0.03, N = 331.0243.85-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: t1ha2_atonceClang 18.1.1GCC 14.0.1 202404114K8K12K16K20KSE +/- 62.32, N = 3SE +/- 10.73, N = 319737.3919662.33-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: t1ha2_atonceGCC 14.0.1 20240411Clang 18.1.1510152025SE +/- 0.01, N = 3SE +/- 0.00, N = 319.1119.35-flto=auto -fno-fat-lto-objects-flto=thin1. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: FarmHash32 x86_64 AVXGCC 14.0.1 20240411Clang 18.1.18K16K24K32K40KSE +/- 13.98, N = 3SE +/- 154.09, N = 337461.4631033.62-flto=auto -fno-fat-lto-objects-flto=thin1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: FarmHash32 x86_64 AVXGCC 14.0.1 20240411Clang 18.1.1612182430SE +/- 0.06, N = 3SE +/- 0.04, N = 324.1127.00-flto=auto -fno-fat-lto-objects-flto=thin1. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: t1ha0_aes_avx2 x86_64Clang 18.1.1GCC 14.0.1 2024041120K40K60K80K100KSE +/- 51.02, N = 3SE +/- 144.34, N = 397667.2696787.57-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: t1ha0_aes_avx2 x86_64Clang 18.1.1GCC 14.0.1 20240411510152025SE +/- 0.00, N = 3SE +/- 0.01, N = 318.8419.09-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: MeowHash x86_64 AES-NIClang 18.1.1GCC 14.0.1 2024041111K22K33K44K55KSE +/- 397.13, N = 3SE +/- 105.54, N = 351816.5450680.40-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: MeowHash x86_64 AES-NIGCC 14.0.1 20240411Clang 18.1.11020304050SE +/- 0.08, N = 3SE +/- 0.59, N = 341.8442.39-flto=auto -fno-fat-lto-objects-flto=thin1. (CXX) g++ options: -O3 -march=native

JPEG-XL libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 90Clang 18.1.1GCC 14.0.1 202404111122334455SE +/- 0.47, N = 15SE +/- 0.41, N = 1549.4548.581. (CXX) g++ options: -O3 -march=native -fno-rtti -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 90Clang 18.1.1GCC 14.0.1 202404111224364860SE +/- 0.62, N = 4SE +/- 0.51, N = 551.2546.971. (CXX) g++ options: -O3 -march=native -fno-rtti -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: PNG - Quality: 100GCC 14.0.1 20240411Clang 18.1.1918273645SE +/- 0.13, N = 3SE +/- 0.04, N = 341.1840.711. (CXX) g++ options: -O3 -march=native -fno-rtti -fPIE -pie -lm

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL libjxl 0.10.1Input: JPEG - Quality: 100GCC 14.0.1 20240411Clang 18.1.11020304050SE +/- 0.17, N = 3SE +/- 0.04, N = 341.6941.651. (CXX) g++ options: -O3 -march=native -fno-rtti -fPIE -pie -lm

JPEG-XL Decoding libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is suited for JPEG XL decode performance testing to PNG output file, the pts/jpexl test is for encode performance. The JPEG XL encoding/decoding is done using the libjxl codebase. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG-XL Decoding libjxl 0.10.1CPU Threads: AllGCC 14.0.1 20240411Clang 18.1.1130260390520650SE +/- 1.93, N = 3SE +/- 3.24, N = 3600.87597.36

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100GCC 14.0.1 20240411Clang 18.1.148121620SE +/- 0.03, N = 3SE +/- 0.04, N = 314.8014.58-lpng16 -ljpeg1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, LosslessGCC 14.0.1 20240411Clang 18.1.10.46580.93161.39741.86322.329SE +/- 0.01, N = 3SE +/- 0.01, N = 32.072.05-lpng16 -ljpeg1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionClang 18.1.1GCC 14.0.1 202404111.2692.5383.8075.0766.345SE +/- 0.01, N = 3SE +/- 0.00, N = 35.644.57-lpng16 -ljpeg1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Lossless, Highest CompressionClang 18.1.1GCC 14.0.1 202404110.18450.3690.55350.7380.9225SE +/- 0.00, N = 3SE +/- 0.00, N = 30.820.81-lpng16 -ljpeg1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: MediumClang 18.1.1GCC 14.0.1 20240411100200300400500SE +/- 0.34, N = 3SE +/- 0.79, N = 3459.58450.111. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ThoroughClang 18.1.1GCC 14.0.1 202404111428425670SE +/- 0.11, N = 3SE +/- 0.03, N = 363.5662.451. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ExhaustiveClang 18.1.1GCC 14.0.1 202404111.24042.48083.72124.96166.202SE +/- 0.0146, N = 3SE +/- 0.0104, N = 35.51305.34461. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: Very ThoroughClang 18.1.1GCC 14.0.1 202404113691215SE +/- 0.0212, N = 3SE +/- 0.0183, N = 38.96158.71201. (CXX) g++ options: -O3 -flto -pthread

TSCP

This is a performance test of TSCP, Tom Kerrigan's Simple Chess Program, which has a built-in performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceClang 18.1.1GCC 14.0.1 20240411500K1000K1500K2000K2500KSE +/- 2576.48, N = 5SE +/- 3119.54, N = 5211838919600841. (CC) gcc options: -O3 -march=native

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_bareGCC 14.0.1 20240411Clang 18.1.11.25352.5073.76055.0146.2675SE +/- 0.005, N = 3SE +/- 0.008, N = 35.5715.2471. (CXX) g++ options: -O3 -march=native -lm

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsGCC 14.0.1 20240411Clang 18.1.1612182430SE +/- 0.28, N = 3SE +/- 0.04, N = 327.2426.331. (CXX) g++ options: -O3 -march=native -lm -ldl

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptClang 18.1.1GCC 14.0.1 2024041130K60K90K120K150KSE +/- 1053.28, N = 3SE +/- 239.95, N = 31597261534461. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKGCC 14.0.1 20240411Clang 18.1.1120K240K360K480K600KSE +/- 668.00, N = 3SE +/- 3691.65, N = 35414614605251. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishClang 18.1.1GCC 14.0.1 2024041130K60K90K120K150KSE +/- 609.99, N = 3SE +/- 79.08, N = 31577851528661. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512GCC 14.0.1 20240411Clang 18.1.160M120M180M240M300MSE +/- 1504066.82, N = 3SE +/- 6642498.38, N = 152988530002144483331. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5Clang 18.1.1GCC 14.0.1 202404113M6M9M12M15MSE +/- 17975.29, N = 3SE +/- 15878.01, N = 314840333133186671. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 96000 - Buffer Size: 1024Clang 18.1.1GCC 14.0.1 20240411246810SE +/- 0.013288, N = 3SE +/- 0.000716, N = 36.5507666.1616161. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 1024Clang 18.1.1GCC 14.0.1 202404110.95371.90742.86113.81484.7685SE +/- 0.003706, N = 3SE +/- 0.009323, N = 34.2387554.0976171. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 512Clang 18.1.1GCC 14.0.1 202404115M10M15M20M25MSE +/- 343818.42, N = 13SE +/- 417025.62, N = 1223426308182589171. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 512Clang 18.1.1GCC 14.0.1 20240411300M600M900M1200M1500MSE +/- 5417358.93, N = 3SE +/- 3868821.24, N = 3123106666710257333331. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 512Clang 18.1.1GCC 14.0.1 20240411300M600M900M1200M1500MSE +/- 7521155.35, N = 3SE +/- 4106498.91, N = 3129786666712422000001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.3Algorithm: RSA4096GCC 14.0.1 20240411Clang 18.1.19K18K27K36K45KSE +/- 89.80, N = 3SE +/- 71.24, N = 344305.144172.3-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.3Algorithm: RSA4096GCC 14.0.1 20240411Clang 18.1.1300K600K900K1200K1500KSE +/- 1971.44, N = 3SE +/- 967.52, N = 31280463.31275596.8-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

Google SynthMark

SynthMark is a cross platform tool for benchmarking CPU performance under a variety of real-time audio workloads. It uses a polyphonic synthesizer model to provide standardized tests for latency, jitter and computational throughput. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100Clang 18.1.1GCC 14.0.1 202404112004006008001000SE +/- 2.74, N = 3SE +/- 2.19, N = 31002.52990.571. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: LionClang 18.1.1GCC 14.0.1 202404119001800270036004500SE +/- 18.35, N = 3SE +/- 16.90, N = 3394240491. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.6Model: Church FacadeClang 18.1.1GCC 14.0.1 2024041111002200330044005500SE +/- 9.17, N = 3SE +/- 9.33, N = 3511252401. (CXX) g++ options: -O3 -march=native

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUGCC 14.0.1 20240411Clang 18.1.14080120160200SE +/- 0.22, N = 3SE +/- 0.53, N = 3159.76160.20-fno-strict-overflow -fwrapv - MIN: 54.41 / MAX: 238.04MIN: 50.55 / MAX: 283.621. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.180160240320400SE +/- 0.25, N = 3SE +/- 0.31, N = 3377.58380.50-fno-strict-overflow -fwrapv - MIN: 186.1 / MAX: 401.52MIN: 321.62 / MAX: 405.781. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.1246810SE +/- 0.01, N = 3SE +/- 0.01, N = 36.386.45-fno-strict-overflow -fwrapv - MIN: 3.23 / MAX: 27.63MIN: 3.45 / MAX: 34.451. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.11.00352.0073.01054.0145.0175SE +/- 0.00, N = 3SE +/- 0.00, N = 34.384.46-fno-strict-overflow -fwrapv - MIN: 2.05 / MAX: 26.42MIN: 2.1 / MAX: 27.331. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.1612182430SE +/- 0.18, N = 3SE +/- 0.33, N = 324.4425.20-fno-strict-overflow -fwrapv - MIN: 11.45 / MAX: 51.44MIN: 10.11 / MAX: 731. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUGCC 14.0.1 20240411Clang 18.1.120406080100SE +/- 0.13, N = 3SE +/- 0.85, N = 1589.77100.60-fno-strict-overflow -fwrapv - MIN: 33.39 / MAX: 179.49MIN: 33.14 / MAX: 247.721. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.1246810SE +/- 0.01, N = 3SE +/- 0.01, N = 37.647.70-fno-strict-overflow -fwrapv - MIN: 3.6 / MAX: 33.44MIN: 3.41 / MAX: 30.421. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUGCC 14.0.1 20240411Clang 18.1.1246810SE +/- 0.01, N = 3SE +/- 0.01, N = 37.337.44-fno-strict-overflow -fwrapv - MIN: 3.9 / MAX: 28.61MIN: 4.21 / MAX: 29.461. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUGCC 14.0.1 20240411Clang 18.1.1510152025SE +/- 0.14, N = 15SE +/- 0.18, N = 1518.2821.12-fno-strict-overflow -fwrapv - MIN: 7.31 / MAX: 109.14MIN: 7.43 / MAX: 121.231. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUGCC 14.0.1 20240411Clang 18.1.11.2152.433.6454.866.075SE +/- 0.00, N = 3SE +/- 0.00, N = 35.335.40-fno-strict-overflow -fwrapv - MIN: 3.15 / MAX: 26.39MIN: 3.38 / MAX: 23.081. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.1714212835SE +/- 0.02, N = 3SE +/- 0.06, N = 327.8627.93-fno-strict-overflow -fwrapv - MIN: 16.47 / MAX: 52.7MIN: 16.08 / MAX: 54.791. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUGCC 14.0.1 20240411Clang 18.1.10.09680.19360.29040.38720.484SE +/- 0.00, N = 3SE +/- 0.00, N = 30.430.43-fno-strict-overflow -fwrapv - MIN: 0.19 / MAX: 22.84MIN: 0.2 / MAX: 25.551. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelGCC 14.0.1 20240411Clang 18.1.1246810SE +/- 0.026, N = 3SE +/- 0.018, N = 36.1798.4921. (CC) gcc options: -lm -lpthread -O3 -march=native

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13GCC 14.0.1 20240411Clang 18.1.1612182430SE +/- 0.06, N = 3SE +/- 0.02, N = 326.3526.431. (CXX) g++ options: -O3 -march=native

FLAC Audio Encoding

This test times how long it takes to encode a sample WAV file to FLAC audio format ten times using the --best preset settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.4WAV To FLACClang 18.1.1GCC 14.0.1 202404113691215SE +/- 0.03, N = 5SE +/- 0.02, N = 510.6811.391. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -logg -lm

Opus Codec Encoding

Opus is an open audio codec. Opus is a lossy audio compression format designed primarily for interactive real-time applications over the Internet. This test uses Opus-Tools and measures the time required to encode a WAV file to Opus five times. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.4WAV To Opus EncodeClang 18.1.1GCC 14.0.1 20240411510152025SE +/- 0.02, N = 5SE +/- 0.02, N = 518.4219.331. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -logg -lm

Helsing

Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digitGCC 14.0.1 20240411Clang 18.1.120406080100SE +/- 0.21, N = 3SE +/- 0.30, N = 363.2978.061. (CC) gcc options: -O2 -pthread

RNNoise

RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 0.2Input: 26 Minute Long Talking SampleClang 18.1.1GCC 14.0.1 20240411246810SE +/- 0.046, N = 3SE +/- 0.035, N = 37.4847.6071. (CC) gcc options: -O3 -march=native -pedantic -fvisibility=hidden

WavPack Audio Encoding

This test times how long it takes to encode a sample WAV file to WavPack format with very high quality settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.7WAV To WavPackClang 18.1.1GCC 14.0.1 202404110.8331.6662.4993.3324.165SE +/- 0.002, N = 5SE +/- 0.009, N = 53.7013.7021. (CXX) g++ options: -O3 -march=native

121 Results Shown

miniBUDE:
  OpenMP - BM1
  OpenMP - BM2
OpenSSL:
  SHA256
  SHA512
  ChaCha20
  AES-128-GCM
  AES-256-GCM
  ChaCha20-Poly1305
Quicksilver:
  CTS2
  CORAL2 P1
  CORAL2 P2
OpenVINO:
  Person Detection FP16 - CPU
  Face Detection FP16-INT8 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Face Detection Retail FP16-INT8 - CPU
  Road Segmentation ADAS FP16-INT8 - CPU
  Machine Translation EN To DE FP16 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
  Person Vehicle Bike Detection FP16 - CPU
  Noise Suppression Poconet-Like FP16 - CPU
  Person Re-Identification Retail FP16 - CPU
  Handwritten English Recognition FP16-INT8 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
Kvazaar:
  Bosphorus 4K - Medium
  Bosphorus 4K - Very Fast
  Bosphorus 4K - Super Fast
  Bosphorus 4K - Ultra Fast
SVT-AV1:
  Preset 4 - Bosphorus 4K
  Preset 8 - Bosphorus 4K
  Preset 12 - Bosphorus 4K
  Preset 13 - Bosphorus 4K
uvg266:
  Bosphorus 4K - Slow
  Bosphorus 4K - Medium
  Bosphorus 4K - Very Fast
  Bosphorus 4K - Super Fast
  Bosphorus 4K - Ultra Fast
x265
miniBUDE:
  OpenMP - BM1
  OpenMP - BM2
GraphicsMagick:
  Swirl
  Rotate
  Sharpen
  Enhanced
  Resizing
  Noise-Gaussian
  HWB Color Space
Coremark
SecureMark
LZ4 Compression:
  3 - Compression Speed
  3 - Decompression Speed
  9 - Compression Speed
  9 - Decompression Speed
Zstd Compression:
  12 - Compression Speed
  12 - Decompression Speed
  19 - Compression Speed
  19 - Decompression Speed
  19, Long Mode - Compression Speed
  19, Long Mode - Decompression Speed
srsRAN Project:
  PDSCH Processor Benchmark, Throughput Total
  PUSCH Processor Benchmark, Throughput Total
QuantLib:
  Multi-Threaded
  Single-Threaded
SMHasher:
  wyhash
  SHA3-256
  Spooky32
  fasthash32
  FarmHash128
  t1ha2_atonce
  FarmHash32 x86_64 AVX
  t1ha0_aes_avx2 x86_64
  MeowHash x86_64 AES-NI
JPEG-XL libjxl:
  PNG - 90
  JPEG - 90
  PNG - 100
  JPEG - 100
JPEG-XL Decoding libjxl
WebP Image Encode:
  Quality 100
  Quality 100, Lossless
  Quality 100, Highest Compression
  Quality 100, Lossless, Highest Compression
ASTC Encoder:
  Medium
  Thorough
  Exhaustive
  Very Thorough
TSCP
GROMACS
LAMMPS Molecular Dynamics Simulator
John The Ripper:
  bcrypt
  WPA PSK
  Blowfish
  HMAC-SHA512
  MD5
Stargate Digital Audio Workstation:
  96000 - 1024
  192000 - 1024
Liquid-DSP:
  1 - 256 - 512
  64 - 256 - 512
  128 - 256 - 512
OpenSSL:
  RSA4096:
    sign/s
    verify/s
Google SynthMark
Google Draco:
  Lion
  Church Facade
OpenVINO:
  Person Detection FP16 - CPU
  Face Detection FP16-INT8 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Face Detection Retail FP16-INT8 - CPU
  Road Segmentation ADAS FP16-INT8 - CPU
  Machine Translation EN To DE FP16 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
  Person Vehicle Bike Detection FP16 - CPU
  Noise Suppression Poconet-Like FP16 - CPU
  Person Re-Identification Retail FP16 - CPU
  Handwritten English Recognition FP16-INT8 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
C-Ray
Primesieve
FLAC Audio Encoding
Opus Codec Encoding
Helsing
RNNoise
WavPack Audio Encoding

GCC 14.0.1 20240411

Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900 45GB, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E

OS: Fedora Linux 40, Kernel: 6.8.5-301.fc40.x86_64 (x86_64), Desktop: GNOME Shell 46.1, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.5 (LLVM 18.1.1 DRM 3.57), Compiler: GCC 14.0.1 20240411, File-System: btrfs, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,m2,lto --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-multilib --enable-offload-defaulted --enable-offload-targets=nvptx-none,amdgcn-amdhsa --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
Python Notes: Python 3.12.2
Security Notes: SELinux + 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: 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; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 April 2024 15:56 by user phoronix.

Clang 18.1.1

Processor: AMD Ryzen Threadripper 7980X 64-Cores @ 7.79GHz (64 Cores / 128 Threads), Motherboard: System76 Thelio Major (FA Z5 BIOS), Chipset: AMD Device 14a4, Memory: 4 x 32GB DDR5-4800MT/s Micron MTC20F1045S1RC48BA2, Disk: 1000GB CT1000T700SSD5, Graphics: AMD Radeon Pro W7900 45GB, Audio: AMD Device 14cc, Monitor: DELL P2415Q, Network: Aquantia AQC113C NBase-T/IEEE + Realtek RTL8125 2.5GbE + Intel Wi-Fi 6E

OS: Fedora Linux 40, Kernel: 6.8.5-301.fc40.x86_64 (x86_64), Desktop: GNOME Shell 46.1, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.0.5 (LLVM 18.1.1 DRM 3.57), Compiler: Clang 18.1.1 + LLVM 18.1.1, File-System: btrfs, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
Python Notes: Python 3.12.2
Security Notes: SELinux + 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: 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; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 April 2024 23:44 by user phoronix.