AMD EPYC 7763 1P spec_rstack_overflow

Benchmarks by Michael Larabel for a future article looking at AMD Inception impact.

HTML result view exported from: https://openbenchmarking.org/result/2308109-NE-EPYC7763169&grs&sor.

AMD EPYC 7763 1P spec_rstack_overflowProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen Resolutionoffsafe RET no microcodesafe RETAMD EPYC 7763 64-Core @ 2.45GHz (64 Cores / 128 Threads)AMD DAYTONA_X (RYM1009B BIOS)AMD Starship/Matisse256GB800GB INTEL SSDPF21Q800GBASPEEDVE2282 x Mellanox MT27710Ubuntu 22.046.5.0-rc5-phx-tues (x86_64)GNOME Shell 42.5X Server 1.21.1.31.3.224GCC 11.3.0 + LLVM 14.0.0ext41920x1080OpenBenchmarking.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-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/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- off: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- safe RET no microcode: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173 - safe RET: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa0011d1 Java Details- OpenJDK Runtime Environment (build 11.0.20+8-post-Ubuntu-1ubuntu122.04)Python Details- Python 3.10.6Security Details- off: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - safe RET no microcode: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - safe RET: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

AMD EPYC 7763 1P spec_rstack_overflowmysqlslap: 4096sqlite: 16sqlite: 8build-linux-kernel: defconfigbuild-linux-kernel: allmodconfignginx: 500nginx: 1000spark: 1000000 - 100 - Inner Join Test Timemysqlslap: 8192pgbench: 100 - 800 - Read Only - Average Latencypgbench: 100 - 800 - Read Onlyapache-iotdb: 500 - 1 - 500compress-7zip: Compression Ratingtensorflow: CPU - 64 - ResNet-50apache-iotdb: 500 - 1 - 500pgbench: 100 - 800 - Read Writepgbench: 100 - 800 - Read Write - Average Latencyclickhouse: 100M Rows Hits Dataset, Third Runopenradioss: Cell Phone Drop Testclickhouse: 100M Rows Hits Dataset, First Run / Cold Cacheopenradioss: Rubber O-Ring Seal Installationnumpy: spark: 1000000 - 100 - Broadcast Inner Join Test Timerocksdb: Update Randapache-iotdb: 500 - 100 - 200apache-iotdb: 200 - 100 - 200apache-iotdb: 200 - 1 - 500clickhouse: 100M Rows Hits Dataset, Second Runopenradioss: Bumper Beamapache-iotdb: 500 - 100 - 200apache-iotdb: 200 - 100 - 200apache-iotdb: 200 - 1 - 200apache-iotdb: 200 - 1 - 500openradioss: Bird Strike on Windshieldbuild-nodejs: Time To Compilespark: 1000000 - 100 - Group By Test Timeapache-iotdb: 500 - 1 - 200apache-iotdb: 200 - 100 - 500apache-iotdb: 200 - 100 - 500apache-iotdb: 200 - 1 - 200apache-iotdb: 500 - 100 - 500mt-dgemm: Sustained Floating-Point Ratecockroach: KV, 50% Reads - 128rocksdb: Read Rand Write Randdacapobench: Tradebeansmemtier-benchmark: Redis - 50 - 1:5remhos: Sample Remap Examplebuild-llvm: Ninjaopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timebuild-godot: Time To Compileapache-iotdb: 500 - 1 - 200specfem3d: Water-layered Halfspacecockroach: KV, 95% Reads - 128apache-iotdb: 500 - 100 - 500memtier-benchmark: Redis - 100 - 1:5cassandra: Writesspark: 1000000 - 100 - SHA-512 Benchmark Timememtier-benchmark: Redis - 100 - 1:10specfem3d: Tomographic Modelspark: 1000000 - 100 - Calculate Pi Benchmarkspecfem3d: Mount St. Helensospray: particle_volume/pathtracer/real_timeopenfoam: drivaerFastback, Medium Mesh Size - Execution Timemrbayes: Primate Phylogeny Analysisspecfem3d: Homogeneous Halfspaceopenvino: Person Detection FP16 - CPUamg: dacapobench: Jythonopenradioss: INIVOL and Fluid Structure Interaction Drop Containerospray: gravity_spheres_volume/dim_512/pathtracer/real_timegromacs: MPI CPU - water_GMX50_bareblender: BMW27 - CPU-Onlyopenvino: Person Detection FP16 - CPUcompress-7zip: Decompression Ratingdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamspecfem3d: Layered Halfspacedeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamembree: Pathtracer ISPC - Asian Dragondeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamospray: gravity_spheres_volume/dim_512/ao/real_timeospray: particle_volume/ao/real_timedeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamblender: Pabellon Barcelona - CPU-Onlyembree: Pathtracer ISPC - Crownopenvkl: vklBenchmark ISPCmemtier-benchmark: Redis - 50 - 1:10deepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamopenvino: Face Detection FP16-INT8 - CPUdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamospray: gravity_spheres_volume/dim_512/scivis/real_timedeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamospray: particle_volume/scivis/real_timeopenvino: Face Detection FP16-INT8 - CPUnamd: ATPase Simulation - 327,506 Atomsopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamspark: 1000000 - 100 - Repartition Test Timeoffsafe RET no microcodesafe RET5906.2733.75531.192289.063169583.15166499.891.883550.256312871931.4938437417.781415756.336160412.988362.6433.10349.4377.46457.231.3046228736.5837.7032.36361.8187.7249501499.1343665846.2813.831271946.57144.83164.2684.9114.05117.9739463981.42960525.6678.9224.200551103635.0295168439932204628.9217.375176.374140.61562121.9481176385.3529.772535386135187.258682618.182197287.302387413.392195705.5114.13426560631.8411.801238732157.829633.51902136.68617.4171209337.6810117990004193162.1313.13555.68027.344092.913855858.30783840.630731.84563042465.5911487.2450678.933064.596446.70208.9605118.022637.603784.5057.42294532177211.8068.148327.83468.83068.33174839.720117.75111141.430.3813028.401126.0355.392253.5968576.9722596.59152.094128.8344.85037.623344.242144020.03140555.982.223010.296270728031.9333481215.561408658.835517514.499329.1936.37323.4285.04418.951.3942811238.5435.1030.29337.0193.6847445770.1846538766.0114.051342031.11152.91172.7495.1713.61123.6137720117.40947741.3479.1924.695818100851.4287276540962218601.7917.788182.169145.06069125.6631202637.3630.427531709131487.058073516.792167181.092330693.422154339.2614.40441923832.0211.982163460155.165644.36223137.51817.6436803977.589996454004191163.0213.26215.73027.584124.743830398.36123816.767631.82926187065.8910485.0069679.576664.391646.72398.9694118.028837.698784.6957.29564522173694.7768.259527.79468.36468.32749840.772117.73051142.290.3811528.381126.6455.374753.5972577.0589596.55792.384188.8005.00637.243338.157142619.84143271.262.143010.289276844527.7333559515.651583717.625483714.589337.4536.40318.1284.48422.581.4142694735.8237.5330.14337.1293.9050578426.5444027904.8914.731345598.59152.27173.0645.1513.36120.0638833415.97918691.4582.2423.70288999601.6283908541432145436.2617.958181.528144.02174125.0601211172.1329.590868260132046.057099408.152145052.142362413.472157815.6914.18805896231.4312.010380781156.419643.71316138.85117.6902986507.609991021004241163.9713.25385.70627.464114.583835158.32193834.243931.65994088565.5662487.3677682.207164.674246.56778.9404917.981737.631984.4957.31384532172804.7168.232527.82468.21708.33813840.423617.73051142.530.3809828.391126.1455.402853.5729576.8166596.78222.26OpenBenchmarking.org

MariaDB

Clients: 4096

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.0.1Clients: 4096offsafe RETsafe RET no microcode130260390520650SE +/- 5.48, N = 3SE +/- 3.51, N = 3SE +/- 2.96, N = 35904184121. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -lpthread -ldl

SQLite

Threads / Copies: 16

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.41.2Threads / Copies: 16offsafe RETsafe RET no microcode246810SE +/- 0.020, N = 3SE +/- 0.052, N = 3SE +/- 0.024, N = 36.2738.8008.8341. (CC) gcc options: -O2 -lz -lm

SQLite

Threads / Copies: 8

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.41.2Threads / Copies: 8offsafe RET no microcodesafe RET1.12642.25283.37924.50565.632SE +/- 0.013, N = 3SE +/- 0.016, N = 3SE +/- 0.036, N = 33.7554.8505.0061. (CC) gcc options: -O2 -lz -lm

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigoffsafe RETsafe RET no microcode918273645SE +/- 0.34, N = 5SE +/- 0.37, N = 6SE +/- 0.35, N = 631.1937.2437.62

Timed Linux Kernel Compilation

Build: allmodconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigoffsafe RETsafe RET no microcode70140210280350SE +/- 0.49, N = 3SE +/- 0.79, N = 3SE +/- 0.90, N = 3289.06338.16344.24

nginx

Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500offsafe RET no microcodesafe RET40K80K120K160K200KSE +/- 284.72, N = 3SE +/- 284.55, N = 3SE +/- 251.96, N = 3169583.15144020.03142619.841. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

nginx

Connections: 1000

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 1000offsafe RETsafe RET no microcode40K80K120K160K200KSE +/- 362.13, N = 3SE +/- 314.03, N = 3SE +/- 352.89, N = 3166499.89143271.26140555.981. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Apache Spark

Row Count: 1000000 - Partitions: 100 - Inner Join Test Time

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Inner Join Test Timeoffsafe RETsafe RET no microcode0.49950.9991.49851.9982.4975SE +/- 0.02, N = 15SE +/- 0.06, N = 3SE +/- 0.05, N = 31.882.142.22

MariaDB

Clients: 8192

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 11.0.1Clients: 8192offsafe RETsafe RET no microcode80160240320400SE +/- 3.35, N = 3SE +/- 1.18, N = 3SE +/- 0.73, N = 33553013011. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -lpthread -ldl

PostgreSQL

Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latencyoffsafe RETsafe RET no microcode0.06660.13320.19980.26640.333SE +/- 0.000, N = 3SE +/- 0.004, N = 3SE +/- 0.003, N = 30.2560.2890.2961. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL

Scaling Factor: 100 - Clients: 800 - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Onlyoffsafe RETsafe RET no microcode700K1400K2100K2800K3500KSE +/- 1705.16, N = 3SE +/- 34286.68, N = 3SE +/- 29158.10, N = 33128719276844527072801. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 500

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.1.2Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 500safe REToffsafe RET no microcode714212835SE +/- 0.22, N = 3SE +/- 0.29, N = 3SE +/- 0.49, N = 327.7331.4931.93MAX: 938.92MAX: 939.96MAX: 930.97

7-Zip Compression

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression Ratingoffsafe RETsafe RET no microcode80K160K240K320K400KSE +/- 1018.75, N = 3SE +/- 435.27, N = 3SE +/- 25.38, N = 33843743355953348121. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

TensorFlow

Device: CPU - Batch Size: 64 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50offsafe RETsafe RET no microcode48121620SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 317.7815.6515.56

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 500

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.1.2Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 500safe REToffsafe RET no microcode300K600K900K1200K1500KSE +/- 5073.96, N = 3SE +/- 4294.81, N = 3SE +/- 13029.07, N = 31583717.621415756.331408658.83

PostgreSQL

Scaling Factor: 100 - Clients: 800 - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Writeoffsafe RET no microcodesafe RET13K26K39K52K65KSE +/- 418.78, N = 3SE +/- 66.28, N = 3SE +/- 207.71, N = 36160455175548371. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PostgreSQL

Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latencyoffsafe RET no microcodesafe RET48121620SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 312.9914.5014.591. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

ClickHouse

100M Rows Hits Dataset, Third Run

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third Runoffsafe RETsafe RET no microcode80160240320400SE +/- 2.21, N = 3SE +/- 1.85, N = 3SE +/- 3.27, N = 5362.64337.45329.19MIN: 31.5 / MAX: 4285.71MIN: 31.46 / MAX: 4000MIN: 31.32 / MAX: 2857.14

OpenRadioss

Model: Cell Phone Drop Test

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Cell Phone Drop Testoffsafe RET no microcodesafe RET816243240SE +/- 0.11, N = 3SE +/- 0.26, N = 3SE +/- 0.03, N = 333.1036.3736.40

ClickHouse

100M Rows Hits Dataset, First Run / Cold Cache

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold Cacheoffsafe RET no microcodesafe RET80160240320400SE +/- 0.68, N = 3SE +/- 3.38, N = 5SE +/- 2.94, N = 3349.43323.42318.12MIN: 31.06 / MAX: 4285.71MIN: 30.82 / MAX: 5000MIN: 30.57 / MAX: 3333.33

OpenRadioss

Model: Rubber O-Ring Seal Installation

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Rubber O-Ring Seal Installationoffsafe RETsafe RET no microcode20406080100SE +/- 0.23, N = 3SE +/- 0.24, N = 3SE +/- 0.17, N = 377.4684.4885.04

Numpy Benchmark

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarkoffsafe RETsafe RET no microcode100200300400500SE +/- 1.76, N = 3SE +/- 0.84, N = 3SE +/- 2.01, N = 3457.23422.58418.95

Apache Spark

Row Count: 1000000 - Partitions: 100 - Broadcast Inner Join Test Time

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Broadcast Inner Join Test Timeoffsafe RET no microcodesafe RET0.31730.63460.95191.26921.5865SE +/- 0.01, N = 15SE +/- 0.02, N = 3SE +/- 0.01, N = 31.301.391.41

RocksDB

Test: Update Random

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Update Randomoffsafe RET no microcodesafe RET100K200K300K400K500KSE +/- 893.82, N = 3SE +/- 426.73, N = 3SE +/- 185.49, N = 34622874281124269471. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 200

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 200safe REToffsafe RET no microcode918273645SE +/- 0.49, N = 3SE +/- 0.61, N = 3SE +/- 0.11, N = 335.8236.5838.54MAX: 3267.55MAX: 2252.73MAX: 3276.77

Apache IoTDB

Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 200

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.1.2Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 200safe RET no microcodesafe REToff918273645SE +/- 0.62, N = 3SE +/- 0.52, N = 15SE +/- 0.55, N = 1535.1037.5337.70MAX: 728.37MAX: 755.16MAX: 802.64

Apache IoTDB

Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 500

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.1.2Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 500safe RETsafe RET no microcodeoff816243240SE +/- 0.22, N = 3SE +/- 0.02, N = 3SE +/- 0.24, N = 330.1430.2932.36MAX: 641.04MAX: 715.01MAX: 646.51

ClickHouse

100M Rows Hits Dataset, Second Run

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second Runoffsafe RETsafe RET no microcode80160240320400SE +/- 1.42, N = 3SE +/- 4.86, N = 3SE +/- 2.16, N = 5361.81337.12337.01MIN: 31.46 / MAX: 4000MIN: 30.79 / MAX: 4000MIN: 30.49 / MAX: 3529.41

OpenRadioss

Model: Bumper Beam

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Bumper Beamoffsafe RET no microcodesafe RET20406080100SE +/- 0.33, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 387.7293.6893.90

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 200

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 200safe REToffsafe RET no microcode11M22M33M44M55MSE +/- 634314.77, N = 3SE +/- 681823.31, N = 3SE +/- 147114.88, N = 350578426.5449501499.1347445770.18

Apache IoTDB

Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 200

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.1.2Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 200safe RET no microcodesafe REToff10M20M30M40M50MSE +/- 614274.26, N = 3SE +/- 543529.82, N = 15SE +/- 574678.74, N = 1546538766.0144027904.8943665846.28

Apache IoTDB

Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 200

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.1.2Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 200offsafe RET no microcodesafe RET48121620SE +/- 0.19, N = 3SE +/- 0.16, N = 12SE +/- 0.21, N = 813.8314.0514.73MAX: 596.78MAX: 609.96MAX: 645.11

Apache IoTDB

Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 500

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.1.2Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 500safe RETsafe RET no microcodeoff300K600K900K1200K1500KSE +/- 9180.92, N = 3SE +/- 1525.49, N = 3SE +/- 7578.67, N = 31345598.591342031.111271946.57

OpenRadioss

Model: Bird Strike on Windshield

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Bird Strike on Windshieldoffsafe RETsafe RET no microcode306090120150SE +/- 0.07, N = 3SE +/- 0.73, N = 3SE +/- 0.67, N = 3144.83152.27152.91

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To Compileoffsafe RET no microcodesafe RET4080120160200SE +/- 0.14, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 3164.27172.75173.06

Apache Spark

Row Count: 1000000 - Partitions: 100 - Group By Test Time

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Group By Test Timeoffsafe RETsafe RET no microcode1.16332.32663.48994.65325.8165SE +/- 0.04, N = 15SE +/- 0.07, N = 3SE +/- 0.08, N = 34.915.155.17

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 200

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.1.2Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 200safe RETsafe RET no microcodeoff48121620SE +/- 0.19, N = 3SE +/- 0.14, N = 3SE +/- 0.07, N = 313.3613.6114.05MAX: 881.3MAX: 854.4MAX: 858.17

Apache IoTDB

Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 500

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.1.2Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 500offsafe RETsafe RET no microcode306090120150SE +/- 0.95, N = 10SE +/- 0.86, N = 15SE +/- 1.63, N = 5117.97120.06123.61MAX: 4652.25MAX: 4495.21MAX: 4533.33

Apache IoTDB

Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 500

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.1.2Device Count: 200 - Batch Size Per Write: 100 - Sensor Count: 500offsafe RETsafe RET no microcode8M16M24M32M40MSE +/- 302926.36, N = 10SE +/- 288707.73, N = 15SE +/- 394126.89, N = 539463981.4238833415.9737720117.40

Apache IoTDB

Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 200

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.1.2Device Count: 200 - Batch Size Per Write: 1 - Sensor Count: 200offsafe RET no microcodesafe RET200K400K600K800K1000KSE +/- 8467.91, N = 3SE +/- 6730.71, N = 12SE +/- 7998.38, N = 8960525.66947741.34918691.45

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500offsafe RET no microcodesafe RET20406080100SE +/- 2.14, N = 3SE +/- 0.81, N = 4SE +/- 1.29, N = 378.9279.1982.24MAX: 1729.94MAX: 5165.86MAX: 3625.32

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Ratesafe RET no microcodeoffsafe RET612182430SE +/- 0.34, N = 3SE +/- 0.21, N = 8SE +/- 0.26, N = 524.7024.2023.701. (CC) gcc options: -O3 -march=native -fopenmp

CockroachDB

Workload: KV, 50% Reads - Concurrency: 128

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 50% Reads - Concurrency: 128offsafe RET no microcodesafe RET20K40K60K80K100KSE +/- 275.86, N = 3SE +/- 719.41, N = 15SE +/- 948.29, N = 15103635.0100851.499601.6

RocksDB

Test: Read Random Write Random

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Read Random Write Randomoffsafe RET no microcodesafe RET600K1200K1800K2400K3000KSE +/- 35283.44, N = 4SE +/- 18652.89, N = 3SE +/- 21895.20, N = 32951684287276528390851. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

DaCapo Benchmark

Java Test: Tradebeans

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradebeansoffsafe RET no microcodesafe RET9001800270036004500SE +/- 42.66, N = 4SE +/- 44.47, N = 4SE +/- 28.11, N = 4399340964143

Redis 7.0.12 + memtier_benchmark

Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:5

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:5safe RET no microcodeoffsafe RET500K1000K1500K2000K2500KSE +/- 31351.12, N = 3SE +/- 11955.97, N = 3SE +/- 1778.76, N = 32218601.792204628.922145436.261. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Remhos

Test: Sample Remap Example

OpenBenchmarking.orgSeconds, Fewer Is BetterRemhos 1.0Test: Sample Remap Exampleoffsafe RET no microcodesafe RET48121620SE +/- 0.23, N = 3SE +/- 0.17, N = 3SE +/- 0.19, N = 317.3817.7917.961. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

Timed LLVM Compilation

Build System: Ninja

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Ninjaoffsafe RETsafe RET no microcode4080120160200SE +/- 0.11, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 3176.37181.53182.17

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Mesh Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh Timeoffsafe RETsafe RET no microcode306090120150140.62144.02145.061. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

Timed Godot Game Engine Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To Compileoffsafe RETsafe RET no microcode306090120150SE +/- 0.19, N = 3SE +/- 0.24, N = 3SE +/- 0.33, N = 3121.95125.06125.66

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 200

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.1.2Device Count: 500 - Batch Size Per Write: 1 - Sensor Count: 200safe RETsafe RET no microcodeoff300K600K900K1200K1500KSE +/- 4253.29, N = 3SE +/- 6553.14, N = 3SE +/- 1566.77, N = 31211172.131202637.361176385.35

SPECFEM3D

Model: Water-layered Halfspace

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Water-layered Halfspacesafe REToffsafe RET no microcode714212835SE +/- 0.35, N = 3SE +/- 0.15, N = 3SE +/- 0.25, N = 329.5929.7730.431. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

CockroachDB

Workload: KV, 95% Reads - Concurrency: 128

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 128offsafe RETsafe RET no microcode30K60K90K120K150KSE +/- 931.05, N = 3SE +/- 1387.70, N = 15SE +/- 1043.12, N = 13135187.2132046.0131487.0

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500offsafe RET no microcodesafe RET13M26M39M52M65MSE +/- 817020.04, N = 3SE +/- 648692.91, N = 4SE +/- 721225.08, N = 358682618.1858073516.7957099408.15

Redis 7.0.12 + memtier_benchmark

Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5offsafe RET no microcodesafe RET500K1000K1500K2000K2500KSE +/- 14704.83, N = 3SE +/- 17712.54, N = 3SE +/- 4916.89, N = 32197287.302167181.092145052.141. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.1.3Test: Writesoffsafe RETsafe RET no microcode50K100K150K200K250KSE +/- 413.74, N = 3SE +/- 479.91, N = 3SE +/- 950.59, N = 3238741236241233069

Apache Spark

Row Count: 1000000 - Partitions: 100 - SHA-512 Benchmark Time

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - SHA-512 Benchmark Timeoffsafe RET no microcodesafe RET0.78081.56162.34243.12323.904SE +/- 0.03, N = 15SE +/- 0.04, N = 3SE +/- 0.04, N = 33.393.423.47

Redis 7.0.12 + memtier_benchmark

Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10offsafe RETsafe RET no microcode500K1000K1500K2000K2500KSE +/- 30210.22, N = 3SE +/- 792.70, N = 3SE +/- 16754.20, N = 102195705.512157815.692154339.261. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

SPECFEM3D

Model: Tomographic Model

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Tomographic Modeloffsafe RETsafe RET no microcode48121620SE +/- 0.09, N = 3SE +/- 0.20, N = 3SE +/- 0.15, N = 314.1314.1914.401. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Apache Spark

Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmarksafe REToffsafe RET no microcode714212835SE +/- 0.33, N = 3SE +/- 0.12, N = 15SE +/- 0.01, N = 331.4331.8432.02

SPECFEM3D

Model: Mount St. Helens

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Mount St. Helensoffsafe RET no microcodesafe RET3691215SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 311.8011.9812.011. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OSPRay

Benchmark: particle_volume/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/pathtracer/real_timeoffsafe RETsafe RET no microcode306090120150SE +/- 0.21, N = 3SE +/- 0.07, N = 3SE +/- 1.83, N = 3157.83156.42155.17

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Execution Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution Timeoffsafe RETsafe RET no microcode140280420560700633.52643.71644.361. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

Timed MrBayes Analysis

Primate Phylogeny Analysis

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny Analysisoffsafe RET no microcodesafe RET306090120150SE +/- 0.85, N = 3SE +/- 0.66, N = 3SE +/- 1.05, N = 3136.69137.52138.851. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm

SPECFEM3D

Model: Homogeneous Halfspace

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Homogeneous Halfspaceoffsafe RET no microcodesafe RET48121620SE +/- 0.07, N = 3SE +/- 0.20, N = 4SE +/- 0.21, N = 317.4217.6417.691. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUoffsafe RETsafe RET no microcode246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 37.687.607.581. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Algebraic Multi-Grid Benchmark

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2offsafe RET no microcodesafe RET200M400M600M800M1000MSE +/- 839009.73, N = 3SE +/- 575791.94, N = 3SE +/- 367255.40, N = 310117990009996454009991021001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

DaCapo Benchmark

Java Test: Jython

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jythonsafe RET no microcodeoffsafe RET9001800270036004500SE +/- 47.28, N = 4SE +/- 18.07, N = 4SE +/- 49.88, N = 4419141934241

OpenRadioss

Model: INIVOL and Fluid Structure Interaction Drop Container

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: INIVOL and Fluid Structure Interaction Drop Containeroffsafe RET no microcodesafe RET4080120160200SE +/- 0.16, N = 3SE +/- 0.39, N = 3SE +/- 0.50, N = 3162.13163.02163.97

OSPRay

Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timesafe RET no microcodesafe REToff3691215SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.13, N = 313.2613.2513.14

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_baresafe RET no microcodesafe REToff1.28932.57863.86795.15726.4465SE +/- 0.006, N = 3SE +/- 0.010, N = 3SE +/- 0.012, N = 35.7305.7065.6801. (CXX) g++ options: -O3

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-Onlyoffsafe RETsafe RET no microcode612182430SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 327.3427.4627.58

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUoffsafe RETsafe RET no microcode9001800270036004500SE +/- 14.65, N = 3SE +/- 10.77, N = 3SE +/- 6.87, N = 34092.914114.584124.74MIN: 3409.52 / MAX: 4641.43MIN: 2087 / MAX: 5053.62MIN: 2129.26 / MAX: 5016.361. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression Ratingoffsafe RETsafe RET no microcode80K160K240K320K400KSE +/- 845.58, N = 3SE +/- 605.48, N = 3SE +/- 380.69, N = 33855853835153830391. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamoffsafe RETsafe RET no microcode246810SE +/- 0.0095, N = 3SE +/- 0.0271, N = 3SE +/- 0.0167, N = 38.30788.32198.3612

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamoffsafe RETsafe RET no microcode8001600240032004000SE +/- 4.76, N = 3SE +/- 12.28, N = 3SE +/- 7.72, N = 33840.633834.243816.77

SPECFEM3D

Model: Layered Halfspace

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Layered Halfspacesafe RETsafe RET no microcodeoff714212835SE +/- 0.18, N = 3SE +/- 0.23, N = 3SE +/- 0.35, N = 331.6631.8331.851. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamsafe REToffsafe RET no microcode1530456075SE +/- 0.16, N = 3SE +/- 0.15, N = 3SE +/- 0.14, N = 365.5765.5965.89

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamsafe REToffsafe RET no microcode110220330440550SE +/- 1.01, N = 3SE +/- 1.15, N = 3SE +/- 0.96, N = 3487.37487.25485.01

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamoffsafe RET no microcodesafe RET150300450600750SE +/- 1.21, N = 3SE +/- 1.47, N = 3SE +/- 0.96, N = 3678.93679.58682.21

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: Asian Dragonsafe REToffsafe RET no microcode1428425670SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 364.6764.6064.39MIN: 64.11 / MAX: 66.01MIN: 64.05 / MAX: 66.13MIN: 63.77 / MAX: 66.16

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamsafe RET no microcodeoffsafe RET1122334455SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 346.7246.7046.57

OSPRay

Benchmark: gravity_spheres_volume/dim_512/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/ao/real_timesafe RET no microcodeoffsafe RET3691215SE +/- 0.02941, N = 3SE +/- 0.02460, N = 3SE +/- 0.01456, N = 38.969418.960518.94049

OSPRay

Benchmark: particle_volume/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/ao/real_timesafe RET no microcodeoffsafe RET48121620SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 318.0318.0217.98

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamsafe RET no microcodesafe REToff918273645SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 337.7037.6337.60

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Pabellon Barcelona - Compute: CPU-Onlysafe REToffsafe RET no microcode20406080100SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.02, N = 384.4984.5084.69

Embree

Binary: Pathtracer ISPC - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: Crownoffsafe RETsafe RET no microcode1326395265SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.14, N = 357.4257.3157.30MIN: 56.59 / MAX: 58.54MIN: 56.2 / MAX: 58.59MIN: 56.26 / MAX: 58.69

OpenVKL

Benchmark: vklBenchmark ISPC

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark ISPCsafe REToffsafe RET no microcode100200300400500SE +/- 0.00, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 3453453452MIN: 84 / MAX: 2520MIN: 84 / MAX: 2528MIN: 85 / MAX: 2535

Redis 7.0.12 + memtier_benchmark

Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10offsafe RET no microcodesafe RET500K1000K1500K2000K2500KSE +/- 14630.02, N = 3SE +/- 17754.58, N = 3SE +/- 2448.62, N = 32177211.802173694.772172804.711. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamoffsafe RETsafe RET no microcode1530456075SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 368.1568.2368.26

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUoffsafe RETsafe RET no microcode714212835SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 327.8327.8227.791. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamoffsafe RET no microcodesafe RET100200300400500SE +/- 0.24, N = 3SE +/- 0.42, N = 3SE +/- 0.31, N = 3468.83468.36468.22

OSPRay

Benchmark: gravity_spheres_volume/dim_512/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/scivis/real_timesafe REToffsafe RET no microcode246810SE +/- 0.01059, N = 3SE +/- 0.00864, N = 3SE +/- 0.01659, N = 38.338138.331748.32749

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamoffsafe RETsafe RET no microcode2004006008001000SE +/- 0.50, N = 3SE +/- 0.34, N = 3SE +/- 0.36, N = 3839.72840.42840.77

OSPRay

Benchmark: particle_volume/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/scivis/real_timeoffsafe RETsafe RET no microcode48121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 317.7517.7317.73

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUoffsafe RET no microcodesafe RET2004006008001000SE +/- 0.32, N = 3SE +/- 0.27, N = 3SE +/- 1.09, N = 31141.431142.291142.53MIN: 998.76 / MAX: 1165.45MIN: 985.75 / MAX: 1168.76MIN: 999.01 / MAX: 1177.021. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atomssafe RETsafe RET no microcodeoff0.08580.17160.25740.34320.429SE +/- 0.00028, N = 3SE +/- 0.00029, N = 3SE +/- 0.00017, N = 30.380980.381150.38130

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUsafe RET no microcodesafe REToff714212835SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 328.3828.3928.40MIN: 14.89 / MAX: 51.63MIN: 14.64 / MAX: 50.33MIN: 14.74 / MAX: 48.661. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUsafe RET no microcodesafe REToff2004006008001000SE +/- 0.72, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 31126.641126.141126.031. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamsafe RET no microcodeoffsafe RET1224364860SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 355.3755.3955.40

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamsafe RET no microcodeoffsafe RET1224364860SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 353.6053.6053.57

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamsafe RET no microcodeoffsafe RET120240360480600SE +/- 0.39, N = 3SE +/- 0.44, N = 3SE +/- 0.39, N = 3577.06576.97576.82

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamsafe RET no microcodeoffsafe RET130260390520650SE +/- 0.26, N = 3SE +/- 0.18, N = 3SE +/- 0.11, N = 3596.56596.59596.78

Apache Spark

Row Count: 1000000 - Partitions: 100 - Repartition Test Time

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Repartition Test Timeoffsafe RETsafe RET no microcode0.53551.0711.60652.1422.6775SE +/- 0.04, N = 15SE +/- 0.04, N = 3SE +/- 0.04, N = 32.092.262.38


Phoronix Test Suite v10.8.5