EPYC 75F3 2P Linux 5.16

2 x AMD EPYC 75F3 32-Core testing with a ASRockRack ROME2D16-2T (P3.10 BIOS) and ASPEED on Ubuntu 21.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2111266-TJ-EPYC75F3245&sor&grs.

EPYC 75F3 2P Linux 5.16ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionLinux 5.14Linux 5.15Linux 5.16 Git2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads)ASRockRack ROME2D16-2T (P3.10 BIOS)AMD Starship/Matisse126GB1000GB Western Digital WD_BLACK SN850 1TBASPEEDAMD Starship/MatisseVE2282 x Intel 10G X550TUbuntu 21.105.14.0-051400-generic (x86_64)GNOME Shell 40.5X Server1.1.182GCC 11.2.0ext41920x10805.15.0-051500-generic (x86_64)5.16.0-051600rc2daily20211124-generic (x86_64)OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/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 Disk Details- NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Details- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114Python Details- Python 3.9.7Security Details- Linux 5.14: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected - Linux 5.15: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected - Linux 5.16 Git: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

EPYC 75F3 2P Linux 5.16redis: GETredis: LPUSH and LPOP: lpushstress-ng: IO_uringnginx: 1redis: SETfio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directorystress-ng: NUMAapache: 200apache: 1000fio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directorygimp: resizeapache: 100fs-mark: 1000 Files, 1MB Size, No Sync/FSyncplaidml: No - Inference - VGG19 - CPUgimp: auto-levelscompilebench: Read Compiled Treenginx: 1000kvazaar: Bosphorus 1080p - Very Fastgimp: rotatesvt-vp9: Visual Quality Optimized - Bosphorus 1080ppyhpc: CPU - Numba - 4194304 - Isoneutral Mixingkvazaar: Bosphorus 1080p - Mediumapache: 500nginx: 500compilebench: Compileosbench: Create Threadsstress-ng: MEMFDpyhpc: CPU - JAX - 4194304 - Isoneutral Mixingnginx: Short Connection - 500stress-ng: MMAPjpegxl-decode: 1stress-ng: Context Switchingnginx: 200rawtherapee: Total Benchmark Timecompilebench: Initial Createnginx: 100osbench: Launch Programssqlite-speedtest: Timed Time - Size 1,000svt-hevc: 10 - Bosphorus 1080ppgbench: 100 - 250 - Read Onlykvazaar: Bosphorus 1080p - Ultra Fastnginx: Short Connection - 1000pyhpc: CPU - TensorFlow - 1048576 - Equation of Statepyhpc: CPU - JAX - 1048576 - Isoneutral Mixingosbench: Create Processesaom-av1: Speed 8 Realtime - Bosphorus 4Kpgbench: 100 - 250 - Read Only - Average Latencycpuminer-opt: Garlicoinfio: Rand Write - IO_uring - No - Yes - 2MB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 2MB - Default Test Directoryosbench: Create Filespyhpc: CPU - Numpy - 1048576 - Isoneutral Mixingplaidml: No - Inference - VGG16 - CPUcpuminer-opt: Skeincoinsvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080pnpb: SP.Bsvt-av1: Preset 8 - Bosphorus 4Krodinia: OpenMP CFD Solvercompress-zstd: 19 - Compression Speedpyhpc: CPU - JAX - 4194304 - Equation of Statepyhpc: CPU - Numpy - 4194304 - Isoneutral Mixingaom-av1: Speed 6 Two-Pass - Bosphorus 4Knpb: EP.Cbuild-godot: Time To Compilenginx: Long Connection - 500npb: FT.Cparboil: OpenMP Stencilkvazaar: Bosphorus 4K - Very Fastbuild-linux-kernel: Time To Compilekvazaar: Bosphorus 1080p - Slowpyhpc: CPU - TensorFlow - 4194304 - Equation of Statefio: Seq Read - IO_uring - No - Yes - 2MB - Default Test Directoryfio: Seq Read - IO_uring - No - Yes - 2MB - Default Test Directoryrodinia: OpenMP Leukocytenpb: IS.Dsvt-hevc: 7 - Bosphorus 1080pcompress-zstd: 19 - Decompression Speedkvazaar: Bosphorus 4K - Slownginx: Long Connection - 1000stress-ng: Glibc C String Functionspybench: Total For Average Test Timescpuminer-opt: LBC, LBRY Creditspyhpc: CPU - Numpy - 4194304 - Equation of Stateaom-av1: Speed 10 Realtime - Bosphorus 4Kfio: Seq Write - IO_uring - No - Yes - 2MB - Default Test Directoryfio: Seq Write - IO_uring - No - Yes - 2MB - Default Test Directoryaom-av1: Speed 9 Realtime - Bosphorus 4Kjpegxl: JPEG - 8osbench: Memory Allocationspgbench: 100 - 500 - Read Only - Average Latencyrav1e: 5fio: Rand Read - IO_uring - No - Yes - 2MB - Default Test Directoryfio: Rand Read - IO_uring - No - Yes - 2MB - Default Test Directorypyhpc: CPU - Numba - 1048576 - Isoneutral Mixingpyhpc: CPU - PyTorch - 1048576 - Isoneutral Mixingpgbench: 100 - 500 - Read Onlycompress-zstd: 8 - Decompression Speedparboil: OpenMP CUTCPsvt-av1: Preset 4 - Bosphorus 4Kplaidml: No - Inference - ResNet 50 - CPUstress-ng: Memory Copyingrodinia: OpenMP LavaMDjpegxl: JPEG - 7stress-ng: Atomicparboil: OpenMP MRI Griddingsvt-hevc: 1 - Bosphorus 1080pbuild-nodejs: Time To Compilepyhpc: CPU - Numpy - 1048576 - Equation of Statejpegxl: PNG - 8build-wasmer: Time To Compilecompress-zstd: 19, Long Mode - Compression Speedaom-av1: Speed 6 Realtime - Bosphorus 4Kkvazaar: Bosphorus 4K - Ultra Fastsynthmark: VoiceMark_100jpegxl: PNG - 7stress-ng: CPU Stressnpb: LU.Cnpb: MG.Cstress-ng: Matrix Mathpyhpc: CPU - PyTorch - 4194304 - Isoneutral Mixinghugin: Panorama Photo Assistant + Stitching Timestress-ng: Socket Activitypyhpc: CPU - Aesara - 4194304 - Isoneutral Mixingpyhpc: CPU - Aesara - 1048576 - Isoneutral Mixingnpb: EP.Dblender: BMW27 - CPU-Onlyrav1e: 1sockperf: Throughputcompress-zstd: 8, Long Mode - Decompression Speedrav1e: 10stress-ng: SENDFILEnpb: SP.Ccpuminer-opt: Triple SHA-256, Onecoinkvazaar: Bosphorus 4K - Mediumpyhpc: CPU - Numba - 4194304 - Equation of Stateastcenc: Thoroughcoremark: CoreMark Size 666 - Iterations Per Secondcpuminer-opt: Quad SHA-256, Pyritepyhpc: CPU - Aesara - 4194304 - Equation of Staterav1e: 6openssl: compress-zstd: 19, Long Mode - Decompression Speednpb: BT.Cnamd: ATPase Simulation - 327,506 Atomsstress-ng: Semaphoresblender: Barbershop - CPU-Onlyopenssl: stress-ng: Cryptostress-ng: Forkingstress-ng: Glibc Qsort Data Sortingastcenc: Exhaustivestress-ng: Vector Mathstress-ng: Mallocpyhpc: CPU - Aesara - 1048576 - Equation of Statepyhpc: CPU - Numba - 1048576 - Equation of Statepyhpc: CPU - JAX - 1048576 - Equation of Statestargate: 192000 - 512stargate: 96000 - 512stargate: 44100 - 512opencv: DNN - Deep Neural Networkopencv: Object Detectionopencv: Features 2Dpyhpc: CPU - PyTorch - 4194304 - Equation of Statepyhpc: CPU - PyTorch - 1048576 - Equation of Statecompress-rar: Linux Source Tree Archiving To RARapache: 20apache: 1onnx: super-resolution-10 - CPUonnx: shufflenet-v2-10 - CPUonnx: fcn-resnet101-11 - CPUonnx: yolov4 - CPUnginx: 20redis: MIXredis: LPUSH and LPOP: lpopstress-ng: System V Message Passingstress-ng: CPU Cachegimp: unsharp-maskpgbench: 100 - 500 - Read Write - Average Latencypgbench: 100 - 500 - Read Writepgbench: 100 - 250 - Read Write - Average Latencypgbench: 100 - 250 - Read Writegromacs: MPI CPU - water_GMX50_barekeydb: cpuminer-opt: Myriad-Groestlcpuminer-opt: Blake-2 Scpuminer-opt: Ringcoincpuminer-opt: Deepcoincpuminer-opt: x25xcpuminer-opt: Magisvt-vp9: VMAF Optimized - Bosphorus 1080pjpegxl-decode: Allcompress-zstd: 8, Long Mode - Compression Speedcompress-zstd: 8 - Compression Speedrodinia: OpenMP Streamclusterrodinia: OpenMP HotSpot3Dparboil: OpenMP LBMnpb: CG.Csockperf: Latency Under Loadsockperf: Latency Ping Pongfs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizefs-mark: 5000 Files, 1MB Size, 4 Threadsfs-mark: 1000 Files, 1MB Sizefio: Seq Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Seq Read - IO_uring - No - Yes - 4KB - Default Test DirectoryLinux 5.14Linux 5.15Linux 5.16 Git840518.831282731.25218218.4759479.82336736.3433700013171331340600235.28111041.99110183.3336600014298.73579423.252312.630.2715.5743255.1596274.00125.1411.321308.761.19258.3698783.9495336.802227.8622.1403442327.130.82542506.612164.7954.8429114551.2092745.1949.061586.4791191.8354.90620953.498527.641679150235.9737757.730.0280.16944.18055226.780.1491165.342406481914.1219320.50130.28259079387.12159135.9558.7306.98878.10.0832.1338.236019.6845.244170923.0383950.225.13742925.7020.30455.600.1403356671944.4053521.88343.713538.914.70178966.489282586.488781128771.05740.322470494835.7528.1566.4254030.2712.262326465350.2990.29818449143891.50.8701785.5528.2910462.4936.81470.37164050.23283.58587748.3680.8450.1860.9534.66739.05.8949.21815.4449.40178339.70257715.4180504.43265236.911.41346.63644646.781.4170.3256268.3826.430.5006933274115.76.3431300565.6783630.8025483314.910.2235.02552724407.3037051273330.3212.9161103127.83599.8187950.730.304929832609.9796.6417097.317388.1457083.55867.329.3344383303.642020739687.780.0810.0560.0352.5983034.0369745.6586791157210009012265600.0900.022136.96938522.895787.2760266499181272113767.17497118.291224669.927223733.6744.8622.26611.487435505.758435787.38199646.77112178954850985.7620219.741885.002499.95375.18244.58186.03241.87.99177.78531.64882340391.3712.4824.714551.31216.6660.53746671465390741.861322987.16840227.9558697.94349993.99236333924941241000243.97117737.98106024.3832633312768.69791230.652556.527.1914.6323571.6095536.75135.8911.562330.811.27454.9599259.7096204.682361.1721.3527682462.200.87144838.252259.9957.5627807770.5294210.5648.943610.6994232.0857.03926151.715543.371662624244.5339124.560.0280.17544.24731026.050.1501149.482334467514.5450230.50129.46255050379.00155640.0960.2406.87776.70.0822.1858.386034.6344.199174938.9985857.535.23683126.2719.86754.670.1413285657744.7673587.80350.493607.014.97180288.029123960.668821115031.07539.662430486836.3127.9266.1687850.2682.285331166290.2970.30218635643912.50.8682565.5858.3110338.8636.42269.57165643.13286.75730448.9079.9530.1860.9635.03039.45.8649.56808.4109.49180041.41260133.0381255.47262897.381.40446.28844932.671.4260.3276267.7626.320.5036966214117.16.3771307379.2584059.0225444314.900.2245.04492729637.7689471275830.3222.9221101646.33608.5187436.390.304299850759.0296.7117109.817371.3357126.71867.979.3408383450.162020703794.620.0810.0560.0351122310876912512260.0930.022130.16131819.875746.6852178026162280115953.22370509.971234436.939104773.8144.8020.24911.288445615.794441527.34288643.421088931012175505.1024318.961928.942673.13389.96238.36196.23262.97.57878.87531.34987737683.2012.3504.402725.61423.7571.62710671059185507.15313178.1428680.17183534.1426333310301005257400199.2397507.3692727.0830933312097.54584447.792632.427.2714.0003544.96104669.51131.7710.650320.811.25755.0293482.06101150.792331.3722.6259232414.380.86944473.372144.1256.1996950.0346.945584.9790281.2757.25224851.422523.121726379239.2438639.240.0290.17445.71994225.880.1451188.382337468114.4952180.51630.32252150389.40159697.0859.0677.04978.60.0842.1828.435892.7345.059173681.9185869.545.12224325.8120.07554.410.1383307662243.8603517.61349.623580.214.79177123.958671134311.07440.162431486935.8928.3567.1740370.2722.295327065480.2950.30218390663861.40.8796495.6208.2136.39370.00163786.83285.68185448.8480.3520.1880.9634.81939.15.9249.69816.2229.44258932.2081198.741.41646.4041.4210.3266230.3926.270.5036972394094.56.36783935.5025566714.970.2245.03322734106.4115501271670.3222.9131104766.13609.9187464.070.3045196.5917090.717371.429.33750.0810.0560.0351253210108912789450.0910.021167.73729625.794020.6660028062175257118614.09172975.64300780.8720.76017.997308045.975418567.17267689.41120101.059615371147.29161432025.732471.90389.01251.23193.13176.67.61273.89331.30224138505.0912.3814.301635.51136.9505.62680001047OpenBenchmarking.org

Redis Memtier / Redis Benchmark

Test: GET

OpenBenchmarking.orgOperations Per Second, More Is BetterRedis Memtier / Redis BenchmarkTest: GETLinux 5.14Linux 5.15Linux 5.16 Git200K400K600K800K1000KSE +/- 7100.00, N = 3SE +/- 1840.53, N = 3SE +/- 1110.87, N = 3840518.83390741.86185507.151. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre2. Redis server v=6.0.15 sha=00000000:0 malloc=jemalloc-5.2.1 bits=64 build=4610f4c3acf7fb25

Redis Memtier / Redis Benchmark

Test: LPUSH and LPOP: lpush

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis Memtier / Redis BenchmarkTest: LPUSH and LPOP: lpushLinux 5.15Linux 5.14Linux 5.16 Git300K600K900K1200K1500KSE +/- 17584.08, N = 3SE +/- 2764.09, N = 3SE +/- 2788.07, N = 31322987.161282731.25313178.141. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre2. Redis server v=6.0.15 sha=00000000:0 malloc=jemalloc-5.2.1 bits=64 build=4610f4c3acf7fb25

Stress-NG

Test: IO_uring

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: IO_uringLinux 5.15Linux 5.14200K400K600K800K1000KSE +/- 10688.68, N = 12SE +/- 1086.76, N = 3840227.95218218.471. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

nginx

Concurrent Requests: 1

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1Linux 5.14Linux 5.15Linux 5.16 Git13K26K39K52K65KSE +/- 517.34, N = 3SE +/- 510.99, N = 8SE +/- 182.67, N = 359479.8258697.9428680.171. (CC) gcc options: -lcrypt -lz -O3 -march=native

Redis Memtier / Redis Benchmark

Test: SET

OpenBenchmarking.orgOperations Per Second, More Is BetterRedis Memtier / Redis BenchmarkTest: SETLinux 5.15Linux 5.14Linux 5.16 Git70K140K210K280K350KSE +/- 3844.52, N = 12SE +/- 3082.86, N = 12SE +/- 2324.74, N = 3349993.99336736.34183534.141. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre2. Redis server v=6.0.15 sha=00000000:0 malloc=jemalloc-5.2.1 bits=64 build=4610f4c3acf7fb25

Flexible IO Tester

Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.16 GitLinux 5.1570K140K210K280K350KSE +/- 2788.87, N = 9SE +/- 1201.85, N = 3SE +/- 1666.67, N = 33370002633332363331. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Flexible IO Tester

Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.16 GitLinux 5.1530060090012001500SE +/- 10.97, N = 9SE +/- 5.04, N = 3SE +/- 5.84, N = 3131710309241. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Flexible IO Tester

Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.16 GitLinux 5.1530060090012001500SE +/- 10.41, N = 15SE +/- 14.76, N = 15SE +/- 6.68, N = 12133110059411. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Flexible IO Tester

Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.16 GitLinux 5.1570K140K210K280K350KSE +/- 2620.07, N = 15SE +/- 3781.91, N = 15SE +/- 1683.25, N = 123406002574002410001. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Stress-NG

Test: NUMA

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: NUMALinux 5.15Linux 5.14Linux 5.16 Git50100150200250SE +/- 0.55, N = 3SE +/- 0.34, N = 3SE +/- 0.39, N = 3243.97235.28199.231. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

Apache HTTP Server

Concurrent Requests: 200

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 200Linux 5.15Linux 5.14Linux 5.16 Git30K60K90K120K150KSE +/- 1218.70, N = 3SE +/- 371.75, N = 3SE +/- 628.63, N = 3117737.98111041.9997507.361. (CC) gcc options: -shared -fPIC -O2

Apache HTTP Server

Concurrent Requests: 1000

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1000Linux 5.14Linux 5.15Linux 5.16 Git20K40K60K80K100KSE +/- 1649.90, N = 15SE +/- 1436.71, N = 15SE +/- 727.25, N = 3110183.33106024.3892727.081. (CC) gcc options: -shared -fPIC -O2

Flexible IO Tester

Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.15Linux 5.16 Git80K160K240K320K400KSE +/- 4415.88, N = 4SE +/- 2403.70, N = 3SE +/- 3527.67, N = 33660003263333093331. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Flexible IO Tester

Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.15Linux 5.16 Git30060090012001500SE +/- 16.93, N = 4SE +/- 9.53, N = 3SE +/- 13.61, N = 31429127612091. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

GIMP

Test: resize

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.24Test: resizeLinux 5.16 GitLinux 5.15Linux 5.14246810SE +/- 0.008, N = 3SE +/- 0.074, N = 15SE +/- 0.052, N = 37.5458.6978.735

Apache HTTP Server

Concurrent Requests: 100

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 100Linux 5.15Linux 5.16 GitLinux 5.1420K40K60K80K100KSE +/- 218.37, N = 3SE +/- 456.04, N = 3SE +/- 117.37, N = 391230.6584447.7979423.251. (CC) gcc options: -shared -fPIC -O2

FS-Mark

Test: 1000 Files, 1MB Size, No Sync/FSync

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Size, No Sync/FSyncLinux 5.16 GitLinux 5.15Linux 5.146001200180024003000SE +/- 17.76, N = 3SE +/- 18.24, N = 12SE +/- 5.77, N = 32632.42556.52312.6

PlaidML

FP16: No - Mode: Inference - Network: VGG19 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPULinux 5.14Linux 5.16 GitLinux 5.15714212835SE +/- 0.26, N = 3SE +/- 0.36, N = 3SE +/- 0.23, N = 330.2727.2727.19

GIMP

Test: auto-levels

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.24Test: auto-levelsLinux 5.16 GitLinux 5.15Linux 5.1448121620SE +/- 0.20, N = 15SE +/- 0.11, N = 3SE +/- 0.17, N = 314.0014.6315.57

Compile Bench

Test: Read Compiled Tree

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled TreeLinux 5.15Linux 5.16 GitLinux 5.148001600240032004000SE +/- 44.29, N = 3SE +/- 74.42, N = 3SE +/- 45.77, N = 33571.603544.963255.15

nginx

Concurrent Requests: 1000

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1000Linux 5.16 GitLinux 5.14Linux 5.1520K40K60K80K100KSE +/- 759.19, N = 3SE +/- 371.03, N = 3SE +/- 57.77, N = 3104669.5196274.0095536.751. (CC) gcc options: -lcrypt -lz -O3 -march=native

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 1080p - Video Preset: Very FastLinux 5.15Linux 5.16 GitLinux 5.14306090120150SE +/- 0.84, N = 3SE +/- 1.28, N = 15SE +/- 1.35, N = 15135.89131.77125.141. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

GIMP

Test: rotate

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.24Test: rotateLinux 5.16 GitLinux 5.14Linux 5.153691215SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 310.6511.3211.56

SVT-VP9

Tuning: Visual Quality Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pLinux 5.15Linux 5.16 GitLinux 5.1470140210280350SE +/- 2.59, N = 3SE +/- 2.45, N = 3SE +/- 2.75, N = 3330.81320.81308.761. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

PyHPC Benchmarks

Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Isoneutral Mixing

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Isoneutral MixingLinux 5.14Linux 5.16 GitLinux 5.150.28670.57340.86011.14681.4335SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 31.1921.2571.274

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 1080p - Video Preset: MediumLinux 5.14Linux 5.16 GitLinux 5.151326395265SE +/- 0.40, N = 15SE +/- 0.18, N = 3SE +/- 0.68, N = 358.3655.0254.951. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Apache HTTP Server

Concurrent Requests: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 500Linux 5.15Linux 5.14Linux 5.16 Git20K40K60K80K100KSE +/- 1002.07, N = 3SE +/- 305.75, N = 3SE +/- 43.22, N = 399259.7098783.9493482.061. (CC) gcc options: -shared -fPIC -O2

nginx

Concurrent Requests: 500

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 500Linux 5.16 GitLinux 5.15Linux 5.1420K40K60K80K100KSE +/- 542.49, N = 3SE +/- 797.11, N = 9SE +/- 373.54, N = 3101150.7996204.6895336.801. (CC) gcc options: -lcrypt -lz -O3 -march=native

Compile Bench

Test: Compile

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: CompileLinux 5.15Linux 5.16 GitLinux 5.145001000150020002500SE +/- 2.61, N = 3SE +/- 4.52, N = 3SE +/- 11.18, N = 32361.172331.372227.86

OSBench

Test: Create Threads

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create ThreadsLinux 5.15Linux 5.14Linux 5.16 Git510152025SE +/- 0.16, N = 3SE +/- 0.12, N = 3SE +/- 0.18, N = 321.3522.1422.631. (CC) gcc options: -lm

Stress-NG

Test: MEMFD

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: MEMFDLinux 5.15Linux 5.16 GitLinux 5.145001000150020002500SE +/- 0.35, N = 3SE +/- 2.76, N = 3SE +/- 13.45, N = 32462.202414.382327.131. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

PyHPC Benchmarks

Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Isoneutral Mixing

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Isoneutral MixingLinux 5.14Linux 5.16 GitLinux 5.150.1960.3920.5880.7840.98SE +/- 0.008, N = 13SE +/- 0.012, N = 3SE +/- 0.008, N = 30.8250.8690.871

Nginx

Test: Short Connection - Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterNginxTest: Short Connection - Connections: 500Linux 5.15Linux 5.16 GitLinux 5.1410K20K30K40K50KSE +/- 86.68, N = 3SE +/- 266.17, N = 3SE +/- 269.64, N = 1544838.2544473.3742506.611. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O22. nginx version: nginx/1.18.0 (Ubuntu)

Stress-NG

Test: MMAP

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: MMAPLinux 5.15Linux 5.14Linux 5.16 Git5001000150020002500SE +/- 4.10, N = 3SE +/- 20.42, N = 7SE +/- 21.05, N = 32259.992164.792144.121. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

JPEG XL Decoding libjxl

CPU Threads: 1

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding libjxl 0.6.1CPU Threads: 1Linux 5.15Linux 5.16 GitLinux 5.141326395265SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 357.5656.1954.84

Stress-NG

Test: Context Switching

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Context SwitchingLinux 5.14Linux 5.156M12M18M24M30MSE +/- 199715.41, N = 3SE +/- 305842.42, N = 529114551.2027807770.521. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

nginx

Concurrent Requests: 200

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 200Linux 5.16 GitLinux 5.15Linux 5.1420K40K60K80K100KSE +/- 234.41, N = 3SE +/- 121.73, N = 3SE +/- 473.44, N = 396950.0394210.5692745.191. (CC) gcc options: -lcrypt -lz -O3 -march=native

RawTherapee

Total Benchmark Time

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeLinux 5.16 GitLinux 5.15Linux 5.141122334455SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 346.9548.9449.061. RawTherapee, version 5.8, command line.

Compile Bench

Test: Initial Create

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial CreateLinux 5.15Linux 5.14Linux 5.16 Git130260390520650SE +/- 5.62, N = 3SE +/- 2.25, N = 3SE +/- 1.39, N = 3610.69586.47584.97

nginx

Concurrent Requests: 100

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 100Linux 5.15Linux 5.14Linux 5.16 Git20K40K60K80K100KSE +/- 684.60, N = 3SE +/- 386.34, N = 3SE +/- 1010.02, N = 394232.0891191.8390281.271. (CC) gcc options: -lcrypt -lz -O3 -march=native

OSBench

Test: Launch Programs

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch ProgramsLinux 5.14Linux 5.15Linux 5.16 Git1326395265SE +/- 0.07, N = 3SE +/- 0.63, N = 3SE +/- 0.57, N = 354.9157.0457.251. (CC) gcc options: -lm

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Linux 5.16 GitLinux 5.15Linux 5.141224364860SE +/- 0.07, N = 3SE +/- 0.19, N = 3SE +/- 0.21, N = 351.4251.7253.501. (CC) gcc options: -O2 -lz

SVT-HEVC

Tuning: 10 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pLinux 5.15Linux 5.14Linux 5.16 Git120240360480600SE +/- 7.77, N = 3SE +/- 4.95, N = 3SE +/- 2.30, N = 3543.37527.64523.121. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyLinux 5.16 GitLinux 5.14Linux 5.15400K800K1200K1600K2000KSE +/- 11831.17, N = 3SE +/- 8367.18, N = 3SE +/- 4184.99, N = 31726379167915016626241. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 1080p - Video Preset: Ultra FastLinux 5.15Linux 5.16 GitLinux 5.1450100150200250SE +/- 2.11, N = 15SE +/- 1.57, N = 3SE +/- 0.93, N = 3244.53239.24235.971. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Nginx

Test: Short Connection - Connections: 1000

OpenBenchmarking.orgRequests Per Second, More Is BetterNginxTest: Short Connection - Connections: 1000Linux 5.15Linux 5.16 GitLinux 5.148K16K24K32K40KSE +/- 303.55, N = 3SE +/- 401.75, N = 4SE +/- 282.66, N = 1139124.5638639.2437757.731. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O22. nginx version: nginx/1.18.0 (Ubuntu)

PyHPC Benchmarks

Device: CPU - Backend: TensorFlow - Project Size: 1048576 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: TensorFlow - Project Size: 1048576 - Benchmark: Equation of StateLinux 5.14Linux 5.15Linux 5.16 Git0.00650.0130.01950.0260.0325SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0280.0280.029

PyHPC Benchmarks

Device: CPU - Backend: JAX - Project Size: 1048576 - Benchmark: Isoneutral Mixing

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 1048576 - Benchmark: Isoneutral MixingLinux 5.14Linux 5.16 GitLinux 5.150.03940.07880.11820.15760.197SE +/- 0.003, N = 15SE +/- 0.002, N = 3SE +/- 0.002, N = 150.1690.1740.175

OSBench

Test: Create Processes

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create ProcessesLinux 5.14Linux 5.15Linux 5.16 Git1020304050SE +/- 0.20, N = 3SE +/- 0.15, N = 3SE +/- 0.58, N = 344.1844.2545.721. (CC) gcc options: -lm

AOM AV1

Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.2Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KLinux 5.14Linux 5.15Linux 5.16 Git612182430SE +/- 0.32, N = 4SE +/- 0.06, N = 3SE +/- 0.26, N = 326.7826.0525.881. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyLinux 5.16 GitLinux 5.14Linux 5.150.03380.06760.10140.13520.169SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 30.1450.1490.1501. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Cpuminer-Opt

Algorithm: Garlicoin

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: GarlicoinLinux 5.16 GitLinux 5.14Linux 5.1530060090012001500SE +/- 16.53, N = 15SE +/- 12.92, N = 4SE +/- 12.33, N = 151188.381165.341149.481. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Flexible IO Tester

Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.16 GitLinux 5.155001000150020002500SE +/- 2.65, N = 3SE +/- 24.04, N = 3SE +/- 1.86, N = 32406233723341. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Flexible IO Tester

Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.16 GitLinux 5.1510002000300040005000SE +/- 5.29, N = 3SE +/- 48.29, N = 3SE +/- 3.38, N = 34819468146751. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OSBench

Test: Create Files

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create FilesLinux 5.14Linux 5.16 GitLinux 5.1548121620SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 314.1214.5014.551. (CC) gcc options: -lm

PyHPC Benchmarks

Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Isoneutral Mixing

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Isoneutral MixingLinux 5.14Linux 5.15Linux 5.16 Git0.11610.23220.34830.46440.5805SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.5010.5010.516

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPULinux 5.16 GitLinux 5.14Linux 5.15714212835SE +/- 0.22, N = 12SE +/- 0.32, N = 3SE +/- 0.20, N = 330.3230.2829.46

Cpuminer-Opt

Algorithm: Skeincoin

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: SkeincoinLinux 5.14Linux 5.15Linux 5.16 Git60K120K180K240K300KSE +/- 1778.18, N = 15SE +/- 1049.63, N = 3SE +/- 1597.16, N = 32590792550502521501. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

SVT-VP9

Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pLinux 5.16 GitLinux 5.14Linux 5.1580160240320400SE +/- 4.25, N = 15SE +/- 4.71, N = 15SE +/- 4.71, N = 15389.40387.12379.001. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

NAS Parallel Benchmarks

Test / Class: SP.B

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BLinux 5.16 GitLinux 5.14Linux 5.1530K60K90K120K150KSE +/- 369.75, N = 3SE +/- 596.50, N = 3SE +/- 1294.01, N = 9159697.08159135.95155640.091. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.0

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4KLinux 5.15Linux 5.16 GitLinux 5.141326395265SE +/- 0.41, N = 3SE +/- 0.67, N = 3SE +/- 0.66, N = 460.2459.0758.731. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Rodinia

Test: OpenMP CFD Solver

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverLinux 5.15Linux 5.14Linux 5.16 Git246810SE +/- 0.050, N = 15SE +/- 0.009, N = 3SE +/- 0.057, N = 36.8776.9887.0491. (CXX) g++ options: -O2 -lOpenCL

Zstd Compression

Compression Level: 19 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19 - Compression SpeedLinux 5.16 GitLinux 5.14Linux 5.1520406080100SE +/- 0.91, N = 3SE +/- 0.69, N = 15SE +/- 0.74, N = 678.678.176.71. *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***

PyHPC Benchmarks

Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Equation of StateLinux 5.15Linux 5.14Linux 5.16 Git0.01890.03780.05670.07560.0945SE +/- 0.001, N = 3SE +/- 0.001, N = 4SE +/- 0.001, N = 30.0820.0830.084

PyHPC Benchmarks

Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral Mixing

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral MixingLinux 5.14Linux 5.16 GitLinux 5.150.49160.98321.47481.96642.458SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 32.1332.1822.185

AOM AV1

Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.2Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KLinux 5.16 GitLinux 5.15Linux 5.14246810SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 38.438.388.231. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

NAS Parallel Benchmarks

Test / Class: EP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CLinux 5.15Linux 5.14Linux 5.16 Git13002600390052006500SE +/- 50.98, N = 3SE +/- 45.99, N = 10SE +/- 41.13, N = 36034.636019.685892.731. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.0

Timed Godot Game Engine Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileLinux 5.15Linux 5.16 GitLinux 5.141020304050SE +/- 0.25, N = 3SE +/- 0.53, N = 4SE +/- 0.22, N = 344.2045.0645.24

Nginx

Test: Long Connection - Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterNginxTest: Long Connection - Connections: 500Linux 5.15Linux 5.16 GitLinux 5.1440K80K120K160K200KSE +/- 1530.94, N = 3SE +/- 868.35, N = 3SE +/- 648.17, N = 3174938.99173681.91170923.031. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O22. nginx version: nginx/1.18.0 (Ubuntu)

NAS Parallel Benchmarks

Test / Class: FT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CLinux 5.16 GitLinux 5.15Linux 5.1420K40K60K80K100KSE +/- 200.12, N = 3SE +/- 295.62, N = 3SE +/- 962.01, N = 485869.5485857.5383950.221. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.0

Parboil

Test: OpenMP Stencil

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP StencilLinux 5.16 GitLinux 5.14Linux 5.151.17832.35663.53494.71325.8915SE +/- 0.047938, N = 14SE +/- 0.009600, N = 3SE +/- 0.063237, N = 35.1222435.1374295.2368311. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Very FastLinux 5.15Linux 5.16 GitLinux 5.14612182430SE +/- 0.18, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 326.2725.8125.701. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.14Time To CompileLinux 5.15Linux 5.16 GitLinux 5.14510152025SE +/- 0.17, N = 8SE +/- 0.17, N = 8SE +/- 0.17, N = 919.8720.0820.30

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 1080p - Video Preset: SlowLinux 5.14Linux 5.15Linux 5.16 Git1224364860SE +/- 0.77, N = 3SE +/- 0.75, N = 3SE +/- 0.13, N = 355.6054.6754.411. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

PyHPC Benchmarks

Device: CPU - Backend: TensorFlow - Project Size: 4194304 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: TensorFlow - Project Size: 4194304 - Benchmark: Equation of StateLinux 5.16 GitLinux 5.14Linux 5.150.03170.06340.09510.12680.1585SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 30.1380.1400.141

Flexible IO Tester

Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.16 GitLinux 5.157001400210028003500SE +/- 2.65, N = 3SE +/- 35.69, N = 3SE +/- 36.27, N = 53356330732851. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Flexible IO Tester

Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.16 GitLinux 5.1514002800420056007000SE +/- 5.51, N = 3SE +/- 71.37, N = 3SE +/- 72.43, N = 56719662265771. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Rodinia

Test: OpenMP Leukocyte

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteLinux 5.16 GitLinux 5.14Linux 5.151020304050SE +/- 0.54, N = 4SE +/- 0.31, N = 12SE +/- 0.33, N = 343.8644.4144.771. (CXX) g++ options: -O2 -lOpenCL

NAS Parallel Benchmarks

Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DLinux 5.15Linux 5.14Linux 5.16 Git8001600240032004000SE +/- 24.72, N = 3SE +/- 13.29, N = 3SE +/- 28.48, N = 33587.803521.883517.611. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.0

SVT-HEVC

Tuning: 7 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pLinux 5.15Linux 5.16 GitLinux 5.1480160240320400SE +/- 3.88, N = 3SE +/- 2.50, N = 3SE +/- 0.56, N = 3350.49349.62343.711. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Zstd Compression

Compression Level: 19 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19 - Decompression SpeedLinux 5.15Linux 5.16 GitLinux 5.148001600240032004000SE +/- 15.35, N = 6SE +/- 15.19, N = 3SE +/- 13.40, N = 153607.03580.23538.91. *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Slow

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: SlowLinux 5.15Linux 5.16 GitLinux 5.1448121620SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 314.9714.7914.701. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Nginx

Test: Long Connection - Connections: 1000

OpenBenchmarking.orgRequests Per Second, More Is BetterNginxTest: Long Connection - Connections: 1000Linux 5.15Linux 5.14Linux 5.16 Git40K80K120K160K200KSE +/- 289.67, N = 3SE +/- 129.45, N = 3SE +/- 460.60, N = 3180288.02178966.48177123.951. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O22. nginx version: nginx/1.18.0 (Ubuntu)

Stress-NG

Test: Glibc C String Functions

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Glibc C String FunctionsLinux 5.14Linux 5.152M4M6M8M10MSE +/- 10223.99, N = 3SE +/- 52140.90, N = 39282586.489123960.661. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesLinux 5.16 GitLinux 5.14Linux 5.152004006008001000SE +/- 7.42, N = 3SE +/- 2.33, N = 3SE +/- 2.19, N = 3867878882

Cpuminer-Opt

Algorithm: LBC, LBRY Credits

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: LBC, LBRY CreditsLinux 5.16 GitLinux 5.14Linux 5.1520K40K60K80K100KSE +/- 1030.04, N = 7SE +/- 56.96, N = 3SE +/- 1318.65, N = 31134311128771115031. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

PyHPC Benchmarks

Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of StateLinux 5.14Linux 5.16 GitLinux 5.150.24190.48380.72570.96761.2095SE +/- 0.001, N = 3SE +/- 0.003, N = 3SE +/- 0.000, N = 31.0571.0741.075

AOM AV1

Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.2Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KLinux 5.14Linux 5.16 GitLinux 5.15918273645SE +/- 0.02, N = 3SE +/- 0.30, N = 3SE +/- 0.33, N = 340.3240.1639.661. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Flexible IO Tester

Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.16 GitLinux 5.155001000150020002500SE +/- 21.37, N = 3SE +/- 1.53, N = 3SE +/- 5.24, N = 32470243124301. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Flexible IO Tester

Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.16 GitLinux 5.1511002200330044005500SE +/- 42.46, N = 3SE +/- 3.18, N = 3SE +/- 10.60, N = 34948486948681. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

AOM AV1

Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.2Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KLinux 5.15Linux 5.16 GitLinux 5.14816243240SE +/- 0.14, N = 3SE +/- 0.26, N = 15SE +/- 0.41, N = 1536.3135.8935.751. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

JPEG XL libjxl

Input: JPEG - Encode Speed: 8

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: JPEG - Encode Speed: 8Linux 5.16 GitLinux 5.14Linux 5.15714212835SE +/- 0.19, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 328.3528.1527.921. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

OSBench

Test: Memory Allocations

OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory AllocationsLinux 5.15Linux 5.14Linux 5.16 Git1530456075SE +/- 0.01, N = 3SE +/- 0.39, N = 3SE +/- 0.44, N = 366.1766.4367.171. (CC) gcc options: -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyLinux 5.15Linux 5.14Linux 5.16 Git0.06120.12240.18360.24480.306SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 30.2680.2710.2721. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

rav1e

Speed: 5

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.5Speed: 5Linux 5.16 GitLinux 5.15Linux 5.140.51641.03281.54922.06562.582SE +/- 0.011, N = 3SE +/- 0.024, N = 4SE +/- 0.009, N = 32.2952.2852.262

Flexible IO Tester

Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryLinux 5.15Linux 5.16 GitLinux 5.147001400210028003500SE +/- 17.06, N = 3SE +/- 13.35, N = 3SE +/- 46.23, N = 33311327032641. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Flexible IO Tester

Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test DirectoryLinux 5.15Linux 5.16 GitLinux 5.1414002800420056007000SE +/- 34.12, N = 3SE +/- 26.85, N = 3SE +/- 92.52, N = 36629654865351. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

PyHPC Benchmarks

Device: CPU - Backend: Numba - Project Size: 1048576 - Benchmark: Isoneutral Mixing

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 1048576 - Benchmark: Isoneutral MixingLinux 5.16 GitLinux 5.15Linux 5.140.06730.13460.20190.26920.3365SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 30.2950.2970.299

PyHPC Benchmarks

Device: CPU - Backend: PyTorch - Project Size: 1048576 - Benchmark: Isoneutral Mixing

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 1048576 - Benchmark: Isoneutral MixingLinux 5.14Linux 5.15Linux 5.16 Git0.0680.1360.2040.2720.34SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 30.2980.3020.302

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 500 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyLinux 5.15Linux 5.14Linux 5.16 Git400K800K1200K1600K2000KSE +/- 23255.77, N = 3SE +/- 16032.30, N = 3SE +/- 5469.42, N = 31863564184491418390661. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Zstd Compression

Compression Level: 8 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8 - Decompression SpeedLinux 5.15Linux 5.14Linux 5.16 Git8001600240032004000SE +/- 20.28, N = 3SE +/- 29.97, N = 3SE +/- 29.53, N = 43912.53891.53861.41. *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***

Parboil

Test: OpenMP CUTCP

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPLinux 5.15Linux 5.14Linux 5.16 Git0.19790.39580.59370.79160.9895SE +/- 0.005555, N = 3SE +/- 0.007978, N = 3SE +/- 0.005811, N = 30.8682560.8701780.8796491. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4KLinux 5.16 GitLinux 5.15Linux 5.141.26452.5293.79355.0586.3225SE +/- 0.010, N = 3SE +/- 0.024, N = 3SE +/- 0.038, N = 35.6205.5855.5521. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPULinux 5.15Linux 5.14Linux 5.16 Git246810SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 38.318.298.21

Stress-NG

Test: Memory Copying

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Memory CopyingLinux 5.14Linux 5.152K4K6K8K10KSE +/- 22.01, N = 3SE +/- 55.95, N = 310462.4910338.861. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

Rodinia

Test: OpenMP LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDLinux 5.16 GitLinux 5.15Linux 5.14816243240SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 336.3936.4236.811. (CXX) g++ options: -O2 -lOpenCL

JPEG XL libjxl

Input: JPEG - Encode Speed: 7

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: JPEG - Encode Speed: 7Linux 5.14Linux 5.16 GitLinux 5.151632486480SE +/- 0.43, N = 3SE +/- 0.14, N = 3SE +/- 0.52, N = 370.3770.0069.571. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

Stress-NG

Test: Atomic

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: AtomicLinux 5.15Linux 5.14Linux 5.16 Git40K80K120K160K200KSE +/- 354.03, N = 3SE +/- 595.91, N = 3SE +/- 125.74, N = 3165643.13164050.23163786.831. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

Parboil

Test: OpenMP MRI Gridding

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI GriddingLinux 5.14Linux 5.16 GitLinux 5.1560120180240300SE +/- 2.83, N = 3SE +/- 1.04, N = 3SE +/- 2.18, N = 3283.59285.68286.761. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

SVT-HEVC

Tuning: 1 - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pLinux 5.15Linux 5.16 GitLinux 5.141122334455SE +/- 0.27, N = 3SE +/- 0.25, N = 3SE +/- 0.31, N = 348.9048.8448.361. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileLinux 5.15Linux 5.16 GitLinux 5.1420406080100SE +/- 0.22, N = 3SE +/- 0.45, N = 3SE +/- 0.13, N = 379.9580.3580.85

PyHPC Benchmarks

Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Equation of StateLinux 5.14Linux 5.15Linux 5.16 Git0.04230.08460.12690.16920.2115SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 30.1860.1860.188

JPEG XL libjxl

Input: PNG - Encode Speed: 8

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: PNG - Encode Speed: 8Linux 5.16 GitLinux 5.15Linux 5.140.2160.4320.6480.8641.08SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 30.960.960.951. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

Timed Wasmer Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 1.0.2Time To CompileLinux 5.14Linux 5.16 GitLinux 5.15816243240SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 334.6734.8235.031. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19, Long Mode - Compression SpeedLinux 5.15Linux 5.16 GitLinux 5.14918273645SE +/- 0.26, N = 3SE +/- 0.67, N = 12SE +/- 0.39, N = 1539.439.139.01. *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***

AOM AV1

Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.2Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KLinux 5.16 GitLinux 5.14Linux 5.151.3322.6643.9965.3286.66SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 35.925.895.861. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Ultra FastLinux 5.16 GitLinux 5.15Linux 5.141122334455SE +/- 0.35, N = 3SE +/- 0.21, N = 3SE +/- 0.38, N = 349.6949.5649.211. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Google SynthMark

Test: VoiceMark_100

OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100Linux 5.16 GitLinux 5.14Linux 5.152004006008001000SE +/- 0.48, N = 3SE +/- 1.23, N = 3SE +/- 4.61, N = 3816.22815.44808.411. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast

JPEG XL libjxl

Input: PNG - Encode Speed: 7

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: PNG - Encode Speed: 7Linux 5.15Linux 5.16 GitLinux 5.143691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 39.499.449.401. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: CPU StressLinux 5.15Linux 5.1440K80K120K160K200KSE +/- 631.34, N = 3SE +/- 176.32, N = 3180041.41178339.701. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

NAS Parallel Benchmarks

Test / Class: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CLinux 5.15Linux 5.16 GitLinux 5.1460K120K180K240K300KSE +/- 1536.62, N = 3SE +/- 2354.59, N = 3SE +/- 1476.90, N = 3260133.03258932.20257715.411. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.0

NAS Parallel Benchmarks

Test / Class: MG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CLinux 5.15Linux 5.16 GitLinux 5.1420K40K60K80K100KSE +/- 369.92, N = 3SE +/- 568.12, N = 3SE +/- 319.61, N = 381255.4781198.7480504.431. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.0

Stress-NG

Test: Matrix Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Matrix MathLinux 5.14Linux 5.1560K120K180K240K300KSE +/- 525.88, N = 3SE +/- 425.68, N = 3265236.91262897.381. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

PyHPC Benchmarks

Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Isoneutral Mixing

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Isoneutral MixingLinux 5.15Linux 5.14Linux 5.16 Git0.31860.63720.95581.27441.593SE +/- 0.010, N = 3SE +/- 0.013, N = 3SE +/- 0.004, N = 31.4041.4131.416

Hugin

Panorama Photo Assistant + Stitching Time

OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching TimeLinux 5.15Linux 5.16 GitLinux 5.141122334455SE +/- 0.52, N = 3SE +/- 0.18, N = 3SE +/- 0.26, N = 346.2946.4046.64

Stress-NG

Test: Socket Activity

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Socket ActivityLinux 5.15Linux 5.1410K20K30K40K50KSE +/- 475.38, N = 3SE +/- 188.94, N = 344932.6744646.781. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

PyHPC Benchmarks

Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Isoneutral Mixing

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Isoneutral MixingLinux 5.14Linux 5.16 GitLinux 5.150.32090.64180.96271.28361.6045SE +/- 0.000, N = 3SE +/- 0.002, N = 3SE +/- 0.005, N = 31.4171.4211.426

PyHPC Benchmarks

Device: CPU - Backend: Aesara - Project Size: 1048576 - Benchmark: Isoneutral Mixing

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 1048576 - Benchmark: Isoneutral MixingLinux 5.14Linux 5.16 GitLinux 5.150.07360.14720.22080.29440.368SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.3250.3260.327

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DLinux 5.14Linux 5.15Linux 5.16 Git13002600390052006500SE +/- 64.62, N = 15SE +/- 76.36, N = 12SE +/- 81.54, N = 36268.386267.766230.391. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.0

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-OnlyLinux 5.16 GitLinux 5.15Linux 5.14612182430SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 326.2726.3226.43

rav1e

Speed: 1

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.5Speed: 1Linux 5.16 GitLinux 5.15Linux 5.140.11320.22640.33960.45280.566SE +/- 0.002, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 30.5030.5030.500

Sockperf

Test: Throughput

OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.7Test: ThroughputLinux 5.16 GitLinux 5.15Linux 5.14150K300K450K600K750KSE +/- 3286.41, N = 25SE +/- 5508.05, N = 5SE +/- 4176.53, N = 56972396966216933271. (CXX) g++ options: --param -O3 -rdynamic

Zstd Compression

Compression Level: 8, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8, Long Mode - Decompression SpeedLinux 5.15Linux 5.14Linux 5.16 Git9001800270036004500SE +/- 16.94, N = 15SE +/- 14.05, N = 15SE +/- 125.76, N = 34117.14115.74094.51. *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***

rav1e

Speed: 10

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.5Speed: 10Linux 5.15Linux 5.16 GitLinux 5.14246810SE +/- 0.031, N = 3SE +/- 0.063, N = 3SE +/- 0.050, N = 156.3776.3676.343

Stress-NG

Test: SENDFILE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: SENDFILELinux 5.15Linux 5.14300K600K900K1200K1500KSE +/- 2228.52, N = 3SE +/- 2091.66, N = 31307379.251300565.671. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

NAS Parallel Benchmarks

Test / Class: SP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CLinux 5.15Linux 5.16 GitLinux 5.1420K40K60K80K100KSE +/- 98.59, N = 3SE +/- 201.10, N = 3SE +/- 95.57, N = 384059.0283935.5083630.801. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.0

Cpuminer-Opt

Algorithm: Triple SHA-256, Onecoin

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Triple SHA-256, OnecoinLinux 5.16 GitLinux 5.14Linux 5.1550K100K150K200K250KSE +/- 333.33, N = 3SE +/- 600.93, N = 3SE +/- 294.18, N = 32556672548332544431. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: MediumLinux 5.16 GitLinux 5.14Linux 5.1548121620SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 314.9714.9114.901. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

PyHPC Benchmarks

Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Equation of StateLinux 5.14Linux 5.15Linux 5.16 Git0.05040.10080.15120.20160.252SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.2230.2240.224

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ThoroughLinux 5.14Linux 5.16 GitLinux 5.151.13512.27023.40534.54045.6755SE +/- 0.0085, N = 3SE +/- 0.0061, N = 3SE +/- 0.0085, N = 35.02555.03325.04491. (CXX) g++ options: -O3 -flto -pthread

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondLinux 5.16 GitLinux 5.15Linux 5.14600K1200K1800K2400K3000KSE +/- 2589.76, N = 3SE +/- 2941.53, N = 3SE +/- 2543.34, N = 32734106.412729637.772724407.301. (CC) gcc options: -O2 -lrt" -lrt

Cpuminer-Opt

Algorithm: Quad SHA-256, Pyrite

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Quad SHA-256, PyriteLinux 5.15Linux 5.14Linux 5.16 Git30K60K90K120K150KSE +/- 220.48, N = 3SE +/- 166.67, N = 3SE +/- 416.67, N = 31275831273331271671. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

PyHPC Benchmarks

Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Equation of StateLinux 5.14Linux 5.15Linux 5.16 Git0.07250.1450.21750.290.3625SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 30.3210.3220.322

rav1e

Speed: 6

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.5Speed: 6Linux 5.15Linux 5.14Linux 5.16 Git0.65751.3151.97252.633.2875SE +/- 0.031, N = 3SE +/- 0.022, N = 11SE +/- 0.020, N = 32.9222.9162.913

OpenSSL

OpenBenchmarking.orgverify/s, More Is BetterOpenSSLLinux 5.16 GitLinux 5.14Linux 5.15200K400K600K800K1000KSE +/- 266.29, N = 3SE +/- 295.42, N = 3SE +/- 198.67, N = 31104766.11103127.81101646.31. OpenSSL 1.1.1l 24 Aug 2021

Zstd Compression

Compression Level: 19, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19, Long Mode - Decompression SpeedLinux 5.16 GitLinux 5.15Linux 5.148001600240032004000SE +/- 11.44, N = 12SE +/- 44.80, N = 3SE +/- 6.50, N = 153609.93608.53599.81. *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***

NAS Parallel Benchmarks

Test / Class: BT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CLinux 5.14Linux 5.16 GitLinux 5.1540K80K120K160K200KSE +/- 84.87, N = 3SE +/- 732.12, N = 3SE +/- 1310.81, N = 3187950.73187464.07187436.391. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.0

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsLinux 5.15Linux 5.16 GitLinux 5.140.06860.13720.20580.27440.343SE +/- 0.00017, N = 3SE +/- 0.00003, N = 3SE +/- 0.00078, N = 30.304290.304510.30492

Stress-NG

Test: Semaphores

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: SemaphoresLinux 5.15Linux 5.142M4M6M8M10MSE +/- 12321.83, N = 3SE +/- 21401.85, N = 39850759.029832609.971. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-OnlyLinux 5.16 GitLinux 5.14Linux 5.1520406080100SE +/- 0.13, N = 3SE +/- 0.18, N = 3SE +/- 0.13, N = 396.5996.6496.71

OpenSSL

OpenBenchmarking.orgsign/s, More Is BetterOpenSSLLinux 5.15Linux 5.14Linux 5.16 Git4K8K12K16K20KSE +/- 2.34, N = 3SE +/- 12.69, N = 3SE +/- 9.75, N = 317109.817097.317090.71. OpenSSL 1.1.1l 24 Aug 2021

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: CryptoLinux 5.14Linux 5.16 GitLinux 5.154K8K12K16K20KSE +/- 5.87, N = 3SE +/- 1.62, N = 3SE +/- 5.18, N = 317388.1417371.4217371.331. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

Stress-NG

Test: Forking

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: ForkingLinux 5.15Linux 5.1412K24K36K48K60KSE +/- 368.30, N = 3SE +/- 210.97, N = 357126.7157083.551. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

Stress-NG

Test: Glibc Qsort Data Sorting

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Glibc Qsort Data SortingLinux 5.15Linux 5.142004006008001000SE +/- 0.39, N = 3SE +/- 1.02, N = 3867.97867.321. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ExhaustiveLinux 5.14Linux 5.16 GitLinux 5.153691215SE +/- 0.0005, N = 3SE +/- 0.0036, N = 3SE +/- 0.0018, N = 39.33449.33759.34081. (CXX) g++ options: -O3 -flto -pthread

Stress-NG

Test: Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Vector MathLinux 5.15Linux 5.1480K160K240K320K400KSE +/- 60.23, N = 3SE +/- 46.03, N = 3383450.16383303.641. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

Stress-NG

Test: Malloc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: MallocLinux 5.14Linux 5.15400M800M1200M1600M2000MSE +/- 2299751.81, N = 3SE +/- 4580973.54, N = 32020739687.782020703794.621. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

PyHPC Benchmarks

Device: CPU - Backend: Aesara - Project Size: 1048576 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 1048576 - Benchmark: Equation of StateLinux 5.14Linux 5.15Linux 5.16 Git0.01820.03640.05460.07280.091SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0810.0810.081

PyHPC Benchmarks

Device: CPU - Backend: Numba - Project Size: 1048576 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 1048576 - Benchmark: Equation of StateLinux 5.14Linux 5.15Linux 5.16 Git0.01260.02520.03780.05040.063SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0560.0560.056

PyHPC Benchmarks

Device: CPU - Backend: JAX - Project Size: 1048576 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 1048576 - Benchmark: Equation of StateLinux 5.14Linux 5.15Linux 5.16 Git0.00790.01580.02370.03160.0395SE +/- 0.000, N = 9SE +/- 0.000, N = 4SE +/- 0.000, N = 150.0350.0350.035

Stargate Digital Audio Workstation

Sample Rate: 192000 - Buffer Size: 512

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 192000 - Buffer Size: 512Linux 5.140.58461.16921.75382.33842.923SE +/- 0.039181, N = 22.5983031. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

Stargate Digital Audio Workstation

Sample Rate: 96000 - Buffer Size: 512

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 96000 - Buffer Size: 512Linux 5.140.90831.81662.72493.63324.5415SE +/- 0.023685, N = 34.0369741. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

Stargate Digital Audio Workstation

Sample Rate: 44100 - Buffer Size: 512

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 44100 - Buffer Size: 512Linux 5.141.27322.54643.81965.09286.366SE +/- 0.028941, N = 35.6586791. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

OpenCV

Test: DNN - Deep Neural Network

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.5.4Test: DNN - Deep Neural NetworkLinux 5.15Linux 5.14Linux 5.16 Git3K6K9K12K15KSE +/- 194.61, N = 15SE +/- 388.98, N = 12SE +/- 296.37, N = 151122311572125321. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

OpenCV

Test: Object Detection

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.5.4Test: Object DetectionLinux 5.14Linux 5.16 GitLinux 5.1520K40K60K80K100KSE +/- 1222.05, N = 3SE +/- 3448.20, N = 15SE +/- 3198.15, N = 151000901010891087691. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

OpenCV

Test: Features 2D

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.5.4Test: Features 2DLinux 5.14Linux 5.15Linux 5.16 Git300K600K900K1200K1500KSE +/- 32498.69, N = 9SE +/- 65802.90, N = 8SE +/- 71578.33, N = 91226560125122612789451. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared

PyHPC Benchmarks

Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Equation of StateLinux 5.14Linux 5.16 GitLinux 5.150.02090.04180.06270.08360.1045SE +/- 0.001, N = 15SE +/- 0.001, N = 15SE +/- 0.002, N = 120.0900.0910.093

PyHPC Benchmarks

Device: CPU - Backend: PyTorch - Project Size: 1048576 - Benchmark: Equation of State

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 1048576 - Benchmark: Equation of StateLinux 5.16 GitLinux 5.14Linux 5.150.0050.010.0150.020.025SE +/- 0.000, N = 13SE +/- 0.000, N = 15SE +/- 0.000, N = 150.0210.0220.022

RAR Compression

Linux Source Tree Archiving To RAR

OpenBenchmarking.orgSeconds, Fewer Is BetterRAR Compression 6.0.2Linux Source Tree Archiving To RARLinux 5.15Linux 5.14Linux 5.16 Git4080120160200SE +/- 1.81, N = 9SE +/- 3.34, N = 10SE +/- 0.34, N = 3130.16136.97167.74

Apache HTTP Server

Concurrent Requests: 20

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 20Linux 5.14Linux 5.15Linux 5.16 Git8K16K24K32K40KSE +/- 873.54, N = 15SE +/- 280.27, N = 3SE +/- 478.84, N = 1538522.8931819.8729625.791. (CC) gcc options: -shared -fPIC -O2

Apache HTTP Server

Concurrent Requests: 1

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1Linux 5.14Linux 5.15Linux 5.16 Git12002400360048006000SE +/- 51.91, N = 7SE +/- 60.11, N = 15SE +/- 74.71, N = 155787.275746.684020.661. (CC) gcc options: -shared -fPIC -O2

ONNX Runtime

Model: super-resolution-10 - Device: CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.9.1Model: super-resolution-10 - Device: CPULinux 5.14Linux 5.16 GitLinux 5.1513002600390052006500SE +/- 431.80, N = 12SE +/- 477.70, N = 9SE +/- 39.04, N = 36026600252171. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: shufflenet-v2-10 - Device: CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.9.1Model: shufflenet-v2-10 - Device: CPULinux 5.16 GitLinux 5.15Linux 5.142K4K6K8K10KSE +/- 621.88, N = 12SE +/- 437.90, N = 12SE +/- 454.98, N = 128062802664991. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.9.1Model: fcn-resnet101-11 - Device: CPULinux 5.14Linux 5.16 GitLinux 5.154080120160200SE +/- 9.26, N = 12SE +/- 6.85, N = 12SE +/- 2.02, N = 31811751621. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: yolov4 - Device: CPU

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.9.1Model: yolov4 - Device: CPULinux 5.15Linux 5.14Linux 5.16 Git60120180240300SE +/- 9.15, N = 9SE +/- 6.14, N = 12SE +/- 6.75, N = 122802722571. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

nginx

Concurrent Requests: 20

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 20Linux 5.16 GitLinux 5.15Linux 5.1430K60K90K120K150KSE +/- 3815.48, N = 15SE +/- 3154.08, N = 15SE +/- 2973.72, N = 15118614.09115953.22113767.171. (CC) gcc options: -lcrypt -lz -O3 -march=native

Redis Memtier / Redis Benchmark

Test: MIX

OpenBenchmarking.orgOperations Per Second, More Is BetterRedis Memtier / Redis BenchmarkTest: MIXLinux 5.14Linux 5.15Linux 5.16 Git110K220K330K440K550KSE +/- 9610.14, N = 12SE +/- 5724.08, N = 12SE +/- 2174.13, N = 3497118.29370509.97172975.641. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre2. Redis server v=6.0.15 sha=00000000:0 malloc=jemalloc-5.2.1 bits=64 build=4610f4c3acf7fb25

Redis Memtier / Redis Benchmark

Test: LPUSH and LPOP: lpop

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis Memtier / Redis BenchmarkTest: LPUSH and LPOP: lpopLinux 5.15Linux 5.14Linux 5.16 Git300K600K900K1200K1500KSE +/- 26498.23, N = 12SE +/- 6547.57, N = 3SE +/- 2481.27, N = 151234436.931224669.92300780.871. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre2. Redis server v=6.0.15 sha=00000000:0 malloc=jemalloc-5.2.1 bits=64 build=4610f4c3acf7fb25

Stress-NG

Test: System V Message Passing

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: System V Message PassingLinux 5.15Linux 5.142M4M6M8M10MSE +/- 184885.66, N = 15SE +/- 9347.98, N = 39104773.817223733.671. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

Stress-NG

Test: CPU Cache

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: CPU CacheLinux 5.14Linux 5.151020304050SE +/- 2.66, N = 15SE +/- 2.82, N = 1244.8644.801. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -pthread -lc -latomic

GIMP

Test: unsharp-mask

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.24Test: unsharp-maskLinux 5.15Linux 5.16 GitLinux 5.14510152025SE +/- 0.23, N = 3SE +/- 0.37, N = 15SE +/- 0.40, N = 1520.2520.7622.27

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyLinux 5.15Linux 5.14Linux 5.16 Git48121620SE +/- 0.26, N = 12SE +/- 0.09, N = 9SE +/- 2.66, N = 911.2911.4918.001. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 500 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read WriteLinux 5.15Linux 5.14Linux 5.16 Git10K20K30K40K50KSE +/- 1067.94, N = 12SE +/- 360.43, N = 9SE +/- 2646.26, N = 94456143550308041. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyLinux 5.14Linux 5.15Linux 5.16 Git1.34442.68884.03325.37766.722SE +/- 0.105, N = 12SE +/- 0.318, N = 12SE +/- 0.081, N = 35.7585.7945.9751. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteLinux 5.15Linux 5.14Linux 5.16 Git9K18K27K36K45KSE +/- 1689.89, N = 12SE +/- 808.82, N = 12SE +/- 561.10, N = 34415243578418561. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bareLinux 5.14Linux 5.15Linux 5.16 Git246810SE +/- 0.011, N = 3SE +/- 0.076, N = 3SE +/- 0.139, N = 157.3817.3427.1721. (CXX) g++ options: -O3

KeyDB

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.2.0Linux 5.14Linux 5.15Linux 5.16 Git20K40K60K80K100KSE +/- 3029.01, N = 13SE +/- 2817.21, N = 15SE +/- 477.02, N = 1599646.7788643.4267689.411. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Cpuminer-Opt

Algorithm: Myriad-Groestl

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Myriad-GroestlLinux 5.16 GitLinux 5.14Linux 5.1530K60K90K120K150KSE +/- 10162.55, N = 12SE +/- 12143.76, N = 12SE +/- 11547.72, N = 15120101.05112178.00108893.001. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: Blake-2 S

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Blake-2 SLinux 5.15Linux 5.16 GitLinux 5.14200K400K600K800K1000KSE +/- 52176.46, N = 12SE +/- 8147.41, N = 3SE +/- 11078.02, N = 310121759615379548501. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: Ringcoin

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: RingcoinLinux 5.16 GitLinux 5.14Linux 5.152004006008001000SE +/- 239.77, N = 15SE +/- 239.72, N = 15SE +/- 213.31, N = 121147.29985.76505.101. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: Deepcoin

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: DeepcoinLinux 5.15Linux 5.14Linux 5.16 Git5K10K15K20K25KSE +/- 5013.61, N = 15SE +/- 3672.19, N = 15SE +/- 1084.56, N = 1224318.9620219.7416143.001. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: x25x

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: x25xLinux 5.16 GitLinux 5.15Linux 5.14400800120016002000SE +/- 33.22, N = 15SE +/- 21.63, N = 15SE +/- 27.19, N = 32025.731928.941885.001. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: Magi

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: MagiLinux 5.15Linux 5.14Linux 5.16 Git6001200180024003000SE +/- 119.46, N = 15SE +/- 144.19, N = 15SE +/- 157.98, N = 152673.132499.952471.901. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pLinux 5.15Linux 5.16 GitLinux 5.1480160240320400SE +/- 6.38, N = 15SE +/- 16.77, N = 12SE +/- 14.65, N = 12389.96389.01375.181. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

JPEG XL Decoding libjxl

CPU Threads: All

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding libjxl 0.6.1CPU Threads: AllLinux 5.16 GitLinux 5.14Linux 5.1550100150200250SE +/- 2.05, N = 3SE +/- 0.99, N = 3SE +/- 6.82, N = 12251.23244.58238.36

Zstd Compression

Compression Level: 8, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8, Long Mode - Compression SpeedLinux 5.15Linux 5.16 GitLinux 5.144080120160200SE +/- 5.22, N = 15SE +/- 2.50, N = 3SE +/- 2.47, N = 15196.2193.1186.01. *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***

Zstd Compression

Compression Level: 8 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8 - Compression SpeedLinux 5.15Linux 5.14Linux 5.16 Git7001400210028003500SE +/- 33.74, N = 15SE +/- 45.90, N = 15SE +/- 53.95, N = 153262.93241.83176.61. *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***

Rodinia

Test: OpenMP Streamcluster

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterLinux 5.15Linux 5.16 GitLinux 5.14246810SE +/- 0.134, N = 15SE +/- 0.098, N = 15SE +/- 0.357, N = 127.5787.6127.9911. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenMP HotSpot3D

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DLinux 5.16 GitLinux 5.14Linux 5.1520406080100SE +/- 0.12, N = 3SE +/- 1.47, N = 12SE +/- 1.13, N = 1573.8977.7978.881. (CXX) g++ options: -O2 -lOpenCL

Parboil

Test: OpenMP LBM

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBMLinux 5.16 GitLinux 5.15Linux 5.14714212835SE +/- 0.49, N = 15SE +/- 1.17, N = 12SE +/- 0.87, N = 1231.3031.3531.651. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

NAS Parallel Benchmarks

Test / Class: CG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CLinux 5.14Linux 5.16 GitLinux 5.159K18K27K36K45KSE +/- 424.43, N = 15SE +/- 587.97, N = 12SE +/- 630.56, N = 1540391.3738505.0937683.201. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.0

Sockperf

Test: Latency Under Load

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.7Test: Latency Under LoadLinux 5.15Linux 5.16 GitLinux 5.143691215SE +/- 0.11, N = 25SE +/- 0.11, N = 7SE +/- 0.17, N = 2412.3512.3812.481. (CXX) g++ options: --param -O3 -rdynamic

Sockperf

Test: Latency Ping Pong

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.7Test: Latency Ping PongLinux 5.16 GitLinux 5.15Linux 5.141.06072.12143.18214.24285.3035SE +/- 0.207, N = 25SE +/- 0.179, N = 25SE +/- 0.036, N = 54.3014.4024.7141. (CXX) g++ options: --param -O3 -rdynamic

FS-Mark

Test: 4000 Files, 32 Sub Dirs, 1MB Size

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB SizeLinux 5.15Linux 5.16 GitLinux 5.14160320480640800SE +/- 22.00, N = 15SE +/- 27.49, N = 12SE +/- 23.95, N = 12725.6635.5551.3

FS-Mark

Test: 5000 Files, 1MB Size, 4 Threads

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 5000 Files, 1MB Size, 4 ThreadsLinux 5.15Linux 5.14Linux 5.16 Git30060090012001500SE +/- 37.42, N = 15SE +/- 72.17, N = 12SE +/- 31.19, N = 151423.71216.61136.9

FS-Mark

Test: 1000 Files, 1MB Size

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB SizeLinux 5.14Linux 5.15Linux 5.16 Git140280420560700SE +/- 6.14, N = 7SE +/- 55.93, N = 12SE +/- 45.98, N = 15660.5571.6505.6

Flexible IO Tester

Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.15Linux 5.16 Git80K160K240K320K400KSE +/- 666.67, N = 3SE +/- 4247.65, N = 15SE +/- 4041.45, N = 33746672710672680001. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Flexible IO Tester

Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test DirectoryLinux 5.14Linux 5.15Linux 5.16 Git30060090012001500SE +/- 2.73, N = 3SE +/- 16.53, N = 15SE +/- 15.06, N = 31465105910471. (CC) gcc options: -rdynamic -ll -lnuma -lz -lm -lpthread -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Phoronix Test Suite v10.8.5