AMD EPYC Turin Linux Kernels

2 x AMD EPYC 9755 128-Core testing with a AMD VOLCANO (RVOT1001B BIOS) and ASPEED on Ubuntu 24.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2410151-NE-AMDEPYCTU77
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Linux 6.8 - Ubuntu 24.04 Default
October 15
  10 Hours, 15 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


AMD EPYC Turin Linux KernelsOpenBenchmarking.orgPhoronix Test Suite2 x AMD EPYC 9755 128-Core @ 2.70GHz (256 Cores / 512 Threads)AMD VOLCANO (RVOT1001B BIOS)AMD Device 153a1520GB512GB SAMSUNG MZVL2512HCJQ-00B00 + 3201GB Micron_7450_MTFDKCB3T2TFSASPEEDBroadcom NetXtreme BCM5720 PCIeUbuntu 24.046.8.0-45-generic (x86_64)GCC 13.2.0 + Clang 18.1.3ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionAMD EPYC Turin Linux Kernels PerformanceSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002116- OpenJDK Runtime Environment (build 21.0.4+7-Ubuntu-1ubuntu224.04)- Python 3.12.3- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable; IBPB: disabled; STIBP: disabled; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

AMD EPYC Turin Linux Kernelshpcg: 104 104 104 - 60hpcg: 144 144 144 - 60namd: STMV with 1,066,628 Atomsdacapobench: Jythondacapobench: Tradesoapdacapobench: Tradebeansdacapobench: Apache Kafkadacapobench: Apache Lucene Search Indexdacapobench: Apache Lucene Search Enginecompress-7zip: Compression Ratingcompress-7zip: Decompression Ratingstockfish: Chess Benchmarkbuild-linux-kernel: defconfigbuild-linux-kernel: allmodconfigbuild-llvm: Ninjahackbench: 16 - Threadhackbench: 32 - Threadhackbench: 16 - Processhackbench: 32 - Processrabbitmq: 120 Queues, 400 Producers, 400 Consumersrabbitmq: 120 Queues, 400 Producers, 400 Consumersrabbitmq: 200 Queues, 400 Producers, 400 Consumersrabbitmq: 200 Queues, 400 Producers, 400 Consumersclickhouse: 100M Rows Hits Dataset, First Run / Cold Cacheclickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, Third Runcockroach: KV, 50% Reads - 512cockroach: KV, 60% Reads - 512cockroach: KV, 95% Reads - 512memcached: 1:10memcached: 1:100gromacs: MPI CPU - water_GMX50_baremysqlslap: 512pgbench: 100 - 1000 - Read Onlypgbench: 100 - 1000 - Read Only - Average Latencypgbench: 100 - 1000 - Read Writepgbench: 100 - 1000 - Read Write - Average Latencystress-ng: Hashstress-ng: MMAPstress-ng: NUMAstress-ng: Pipestress-ng: Pollstress-ng: Zlibstress-ng: Futexstress-ng: MEMFDstress-ng: Mutexstress-ng: Atomicstress-ng: Mallocstress-ng: Cloningstress-ng: Forkingstress-ng: Pthreadstress-ng: AVL Treestress-ng: IO_uringstress-ng: SENDFILEstress-ng: CPU Cachestress-ng: Power Mathstress-ng: Semaphoresstress-ng: Matrix Mathstress-ng: Vector Mathstress-ng: AVX-512 VNNIstress-ng: Function Callstress-ng: x86_64 RdRandstress-ng: Floating Pointstress-ng: Matrix 3D Mathstress-ng: Memory Copyingstress-ng: Vector Shufflestress-ng: Mixed Schedulerstress-ng: Socket Activitystress-ng: Exponential Mathstress-ng: Jpeg Compressionstress-ng: Logarithmic Mathstress-ng: Wide Vector Mathstress-ng: Context Switchingstress-ng: Fractal Generatorstress-ng: Radix String Sortstress-ng: Fused Multiply-Addstress-ng: Trigonometric Mathstress-ng: Bitonic Integer Sortstress-ng: Vector Floating Pointstress-ng: Glibc C String Functionsstress-ng: Glibc Qsort Data Sortingstress-ng: System V Message Passingcassandra: Writesrocksdb: Rand Readrocksdb: Update Randrocksdb: Read While Writingrocksdb: Read Rand Write Randonednn: IP Shapes 1D - CPUonednn: IP Shapes 3D - CPUonednn: Convolution Batch Shapes Auto - CPUonednn: Deconvolution Batch shapes_1d - CPUonednn: Deconvolution Batch shapes_3d - CPUonednn: Recurrent Neural Network Training - CPUonednn: Recurrent Neural Network Inference - CPUlitert: DeepLab V3litert: SqueezeNetlitert: Inception V4litert: NASNet Mobilelitert: Mobilenet Floatlitert: Mobilenet Quantlitert: Inception ResNet V2litert: Quantized COCO SSD MobileNet v1xnnpack: FP32MobileNetV1xnnpack: FP32MobileNetV2xnnpack: FP32MobileNetV3Largexnnpack: FP32MobileNetV3Smallxnnpack: FP16MobileNetV1xnnpack: FP16MobileNetV2xnnpack: FP16MobileNetV3Largexnnpack: FP16MobileNetV3Smallxnnpack: QS8MobileNetV2Linux 6.8 - Ubuntu 24.04 Default126.057126.2379.6868047114237990161322927268691174028168524983597226420.128161.47365.2564.3988.5434.4008.664137558138452141653142587647.15655.60665.7134572.440876.754061.74369003.3412110851.5532.51010243174080.2321239880.67267268953.24204377.33135.57135056921.4438109349.1933690.742734152.872460.42172204489.05288.242288575656.137509.3255056.23112319.683544.3320439405.603786571.991718159.64631380.691333120424.541317399.051790633.0128928185.52238006.08116877700.9769059.0134546.87111219.74232011.08364029.9339761.381330363.80256339.391983227.488692532.11123173437.0464.273350.10383781024.48697215.962807.41774632.71328367459.246975.3723180083.8727985215683115245047873086873846266780.7929270.6477630.30109324.72590.418359750.424509.36461288.040421.623381855440723982.824146.631504241574.6244765454780404652192482055060802286623263570OpenBenchmarking.org

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 104 104 104 - RT: 60Linux 6.8 - Ubuntu 24.04 Default306090120150SE +/- 0.08, N = 3126.061. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 144 144 144 - RT: 60Linux 6.8 - Ubuntu 24.04 Default306090120150SE +/- 0.02, N = 3126.241. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

NAMD

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0Input: STMV with 1,066,628 AtomsLinux 6.8 - Ubuntu 24.04 Default3691215SE +/- 0.00512, N = 39.68680

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance of various popular real-world Java workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: JythonLinux 6.8 - Ubuntu 24.04 Default10002000300040005000SE +/- 41.83, N = 34711

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: TradesoapLinux 6.8 - Ubuntu 24.04 Default9001800270036004500SE +/- 68.42, N = 154237

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: TradebeansLinux 6.8 - Ubuntu 24.04 Default2K4K6K8K10KSE +/- 115.23, N = 159901

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache KafkaLinux 6.8 - Ubuntu 24.04 Default13002600390052006500SE +/- 10.79, N = 36132

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search IndexLinux 6.8 - Ubuntu 24.04 Default6001200180024003000SE +/- 18.37, N = 32927

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 23.11Java Test: Apache Lucene Search EngineLinux 6.8 - Ubuntu 24.04 Default6K12K18K24K30KSE +/- 134.09, N = 326869

Java Test: H2O In-Memory Platform For Machine Learning

Linux 6.8 - Ubuntu 24.04 Default: The test quit with a non-zero exit status.

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 24.05Test: Compression RatingLinux 6.8 - Ubuntu 24.04 Default300K600K900K1200K1500KSE +/- 5013.27, N = 311740281. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 24.05Test: Decompression RatingLinux 6.8 - Ubuntu 24.04 Default400K800K1200K1600K2000KSE +/- 1398.36, N = 316852491. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Stockfish

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 17Chess BenchmarkLinux 6.8 - Ubuntu 24.04 Default200M400M600M800M1000MSE +/- 11506315.47, N = 158359722641. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigLinux 6.8 - Ubuntu 24.04 Default510152025SE +/- 0.18, N = 720.13

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigLinux 6.8 - Ubuntu 24.04 Default4080120160200SE +/- 0.17, N = 3161.47

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaLinux 6.8 - Ubuntu 24.04 Default1530456075SE +/- 0.36, N = 365.26

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ThreadLinux 6.8 - Ubuntu 24.04 Default0.98961.97922.96883.95844.948SE +/- 0.019, N = 34.3981. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: ThreadLinux 6.8 - Ubuntu 24.04 Default246810SE +/- 0.040, N = 38.5431. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ProcessLinux 6.8 - Ubuntu 24.04 Default0.991.982.973.964.95SE +/- 0.015, N = 34.4001. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: ProcessLinux 6.8 - Ubuntu 24.04 Default246810SE +/- 0.086, N = 38.6641. (CC) gcc options: -lpthread

RabbitMQ

RabbitMQ is an open-source message broker. This test profile makes use of the RabbitMQ PerfTest with the RabbitMQ server and PerfTest client running on the same host namely as a system/CPU performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSending Messages/s, More Is BetterRabbitMQ 3.12.7Scenario: 120 Queues, 400 Producers, 400 ConsumersLinux 6.8 - Ubuntu 24.04 Default30K60K90K120K150KSE +/- 937.03, N = 12137558

OpenBenchmarking.orgReceiving Messages/s, More Is BetterRabbitMQ 3.12.7Scenario: 120 Queues, 400 Producers, 400 ConsumersLinux 6.8 - Ubuntu 24.04 Default30K60K90K120K150KSE +/- 927.69, N = 12138452

OpenBenchmarking.orgSending Messages/s, More Is BetterRabbitMQ 3.12.7Scenario: 200 Queues, 400 Producers, 400 ConsumersLinux 6.8 - Ubuntu 24.04 Default30K60K90K120K150KSE +/- 720.24, N = 3141653

OpenBenchmarking.orgReceiving Messages/s, More Is BetterRabbitMQ 3.12.7Scenario: 200 Queues, 400 Producers, 400 ConsumersLinux 6.8 - Ubuntu 24.04 Default30K60K90K120K150KSE +/- 712.60, N = 3142587

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheLinux 6.8 - Ubuntu 24.04 Default140280420560700SE +/- 3.55, N = 3647.15MIN: 120.97 / MAX: 6666.67

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunLinux 6.8 - Ubuntu 24.04 Default140280420560700SE +/- 1.44, N = 3655.60MIN: 124.22 / MAX: 6000

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunLinux 6.8 - Ubuntu 24.04 Default140280420560700SE +/- 4.78, N = 3665.71MIN: 124.22 / MAX: 6666.67

Apache Spark TPC-DS

This is a benchmark of Apache Spark using the TPC-DS data-set. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmarks the Apache Spark in a single-system configuration and leverages the https://github.com/databricks/tpcds-kit and https://github.com/IBM/spark-tpc-ds-performance-test/ projects for testing. Learn more via the OpenBenchmarking.org test page.

Scale Factor: 10

Linux 6.8 - Ubuntu 24.04 Default: The test run did not produce a result. E: sh: 1: exec: ./spark-tpcds: not found

CockroachDB

CockroachDB is a cloud-native, distributed SQL database for data intensive applications. This test profile uses a server-less CockroachDB configuration to test various Coackroach workloads on the local host with a single node. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 50% Reads - Concurrency: 512Linux 6.8 - Ubuntu 24.04 Default7K14K21K28K35KSE +/- 635.19, N = 1534572.4

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 60% Reads - Concurrency: 512Linux 6.8 - Ubuntu 24.04 Default9K18K27K36K45KSE +/- 157.12, N = 340876.7

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 512Linux 6.8 - Ubuntu 24.04 Default12K24K36K48K60KSE +/- 7.30, N = 354061.7

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10Linux 6.8 - Ubuntu 24.04 Default900K1800K2700K3600K4500KSE +/- 9484.75, N = 34369003.341. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100Linux 6.8 - Ubuntu 24.04 Default3M6M9M12M15MSE +/- 195439.38, N = 1212110851.551. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

GROMACS

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

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareLinux 6.8 - Ubuntu 24.04 Default816243240SE +/- 0.31, N = 1532.511. (CXX) g++ options: -O3 -lm

MariaDB mariadb-slap

This is a MariaDB MySQL database server benchmark making use of mysqlslap (mariadb-slap). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB mariadb-slap 11.5Clients: 512Linux 6.8 - Ubuntu 24.04 Default20406080100SE +/- 0.67, N = 31021. (CXX) g++ options: -fPIC -pie -fstack-protector -O3 -shared -lrt -lpthread -lz -ldl -lm -lstdc++

PostgreSQL

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyLinux 6.8 - Ubuntu 24.04 Default900K1800K2700K3600K4500KSE +/- 48300.83, N = 343174081. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencyLinux 6.8 - Ubuntu 24.04 Default0.05220.10440.15660.20880.261SE +/- 0.003, N = 30.2321. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read WriteLinux 6.8 - Ubuntu 24.04 Default3K6K9K12K15KSE +/- 112.84, N = 3123981. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 17Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average LatencyLinux 6.8 - Ubuntu 24.04 Default20406080100SE +/- 0.74, N = 380.671. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpq -lpgcommon -lpgport -lm

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: HashLinux 6.8 - Ubuntu 24.04 Default14M28M42M56M70MSE +/- 100899.78, N = 367268953.241. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: MMAPLinux 6.8 - Ubuntu 24.04 Default40K80K120K160K200KSE +/- 716.44, N = 3204377.331. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: NUMALinux 6.8 - Ubuntu 24.04 Default306090120150SE +/- 0.01, N = 3135.571. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: PipeLinux 6.8 - Ubuntu 24.04 Default30M60M90M120M150MSE +/- 972593.21, N = 3135056921.441. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: PollLinux 6.8 - Ubuntu 24.04 Default8M16M24M32M40MSE +/- 46019.58, N = 338109349.191. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: ZlibLinux 6.8 - Ubuntu 24.04 Default7K14K21K28K35KSE +/- 3.03, N = 333690.741. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: FutexLinux 6.8 - Ubuntu 24.04 Default600K1200K1800K2400K3000KSE +/- 32419.30, N = 42734152.871. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: MEMFDLinux 6.8 - Ubuntu 24.04 Default5001000150020002500SE +/- 14.50, N = 32460.421. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: MutexLinux 6.8 - Ubuntu 24.04 Default40M80M120M160M200MSE +/- 1619333.28, N = 3172204489.051. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: AtomicLinux 6.8 - Ubuntu 24.04 Default60120180240300SE +/- 1.60, N = 3288.241. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: MallocLinux 6.8 - Ubuntu 24.04 Default500M1000M1500M2000M2500MSE +/- 2348690.82, N = 32288575656.131. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: CloningLinux 6.8 - Ubuntu 24.04 Default16003200480064008000SE +/- 16.39, N = 37509.321. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: ForkingLinux 6.8 - Ubuntu 24.04 Default12K24K36K48K60KSE +/- 636.07, N = 455056.231. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: PthreadLinux 6.8 - Ubuntu 24.04 Default20K40K60K80K100KSE +/- 477.42, N = 3112319.681. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: AVL TreeLinux 6.8 - Ubuntu 24.04 Default8001600240032004000SE +/- 5.54, N = 33544.331. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: IO_uringLinux 6.8 - Ubuntu 24.04 Default4M8M12M16M20MSE +/- 449641.03, N = 1220439405.601. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: SENDFILELinux 6.8 - Ubuntu 24.04 Default800K1600K2400K3200K4000KSE +/- 36148.87, N = 153786571.991. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: CPU CacheLinux 6.8 - Ubuntu 24.04 Default400K800K1200K1600K2000KSE +/- 35013.43, N = 121718159.641. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Power MathLinux 6.8 - Ubuntu 24.04 Default140K280K420K560K700KSE +/- 626.58, N = 3631380.691. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: SemaphoresLinux 6.8 - Ubuntu 24.04 Default300M600M900M1200M1500MSE +/- 4219045.43, N = 31333120424.541. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Matrix MathLinux 6.8 - Ubuntu 24.04 Default300K600K900K1200K1500KSE +/- 104.32, N = 31317399.051. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Vector MathLinux 6.8 - Ubuntu 24.04 Default400K800K1200K1600K2000KSE +/- 173.70, N = 31790633.011. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: AVX-512 VNNILinux 6.8 - Ubuntu 24.04 Default6M12M18M24M30MSE +/- 6525.49, N = 328928185.521. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Function CallLinux 6.8 - Ubuntu 24.04 Default50K100K150K200K250KSE +/- 116.57, N = 3238006.081. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: x86_64 RdRandLinux 6.8 - Ubuntu 24.04 Default30M60M90M120M150MSE +/- 94055.51, N = 3116877700.971. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Floating PointLinux 6.8 - Ubuntu 24.04 Default15K30K45K60K75KSE +/- 35.19, N = 369059.011. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Matrix 3D MathLinux 6.8 - Ubuntu 24.04 Default7K14K21K28K35KSE +/- 23.82, N = 334546.871. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Memory CopyingLinux 6.8 - Ubuntu 24.04 Default20K40K60K80K100KSE +/- 539.90, N = 3111219.741. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Vector ShuffleLinux 6.8 - Ubuntu 24.04 Default50K100K150K200K250KSE +/- 120.36, N = 3232011.081. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Mixed SchedulerLinux 6.8 - Ubuntu 24.04 Default80K160K240K320K400KSE +/- 381.01, N = 3364029.931. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Socket ActivityLinux 6.8 - Ubuntu 24.04 Default9K18K27K36K45KSE +/- 31.90, N = 339761.381. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Exponential MathLinux 6.8 - Ubuntu 24.04 Default300K600K900K1200K1500KSE +/- 418.33, N = 31330363.801. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Jpeg CompressionLinux 6.8 - Ubuntu 24.04 Default50K100K150K200K250KSE +/- 1171.09, N = 3256339.391. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Logarithmic MathLinux 6.8 - Ubuntu 24.04 Default400K800K1200K1600K2000KSE +/- 771.06, N = 31983227.481. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Wide Vector MathLinux 6.8 - Ubuntu 24.04 Default2M4M6M8M10MSE +/- 1923.72, N = 38692532.111. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Context SwitchingLinux 6.8 - Ubuntu 24.04 Default30M60M90M120M150MSE +/- 1230077.20, N = 3123173437.041. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Fractal GeneratorLinux 6.8 - Ubuntu 24.04 Default1428425670SE +/- 0.29, N = 364.271. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Radix String SortLinux 6.8 - Ubuntu 24.04 Default7001400210028003500SE +/- 1.30, N = 33350.101. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Fused Multiply-AddLinux 6.8 - Ubuntu 24.04 Default80M160M240M320M400MSE +/- 312938.81, N = 3383781024.481. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Trigonometric MathLinux 6.8 - Ubuntu 24.04 Default150K300K450K600K750KSE +/- 412.34, N = 3697215.961. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Bitonic Integer SortLinux 6.8 - Ubuntu 24.04 Default6001200180024003000SE +/- 5.04, N = 32807.411. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Vector Floating PointLinux 6.8 - Ubuntu 24.04 Default170K340K510K680K850KSE +/- 945.62, N = 3774632.711. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Glibc C String FunctionsLinux 6.8 - Ubuntu 24.04 Default70M140M210M280M350MSE +/- 417484.75, N = 3328367459.241. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: Glibc Qsort Data SortingLinux 6.8 - Ubuntu 24.04 Default15003000450060007500SE +/- 21.93, N = 36975.371. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.17.08Test: System V Message PassingLinux 6.8 - Ubuntu 24.04 Default5M10M15M20M25MSE +/- 12761.95, N = 323180083.871. (CXX) g++ options: -lm -laio -lapparmor -latomic -lcrypt -ldl -ljpeg -lEGL -lgmp -lmpfr -lsctp -lz -lrt -lpthread -lc -std=gnu99 -O2 -U_FORTIFY_SOURCE

Apache Cassandra

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 5.0Test: WritesLinux 6.8 - Ubuntu 24.04 Default60K120K180K240K300KSE +/- 2009.33, N = 3279852

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random ReadLinux 6.8 - Ubuntu 24.04 Default300M600M900M1200M1500MSE +/- 924495.62, N = 315683115241. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Update RandomLinux 6.8 - Ubuntu 24.04 Default110K220K330K440K550KSE +/- 1365.90, N = 35047871. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While WritingLinux 6.8 - Ubuntu 24.04 Default7M14M21M28M35MSE +/- 370727.45, N = 15308687381. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read Random Write RandomLinux 6.8 - Ubuntu 24.04 Default1000K2000K3000K4000K5000KSE +/- 14460.69, N = 346266781. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 1D - Engine: CPULinux 6.8 - Ubuntu 24.04 Default0.17840.35680.53520.71360.892SE +/- 0.002860, N = 30.792927MIN: 0.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: IP Shapes 3D - Engine: CPULinux 6.8 - Ubuntu 24.04 Default0.14570.29140.43710.58280.7285SE +/- 0.001079, N = 30.647763MIN: 0.611. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Convolution Batch Shapes Auto - Engine: CPULinux 6.8 - Ubuntu 24.04 Default0.06770.13540.20310.27080.3385SE +/- 0.000786, N = 30.301093MIN: 0.291. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_1d - Engine: CPULinux 6.8 - Ubuntu 24.04 Default612182430SE +/- 0.21, N = 324.73MIN: 22.491. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Deconvolution Batch shapes_3d - Engine: CPULinux 6.8 - Ubuntu 24.04 Default0.09410.18820.28230.37640.4705SE +/- 0.000841, N = 30.418359MIN: 0.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Training - Engine: CPULinux 6.8 - Ubuntu 24.04 Default160320480640800SE +/- 2.36, N = 3750.42MIN: 744.091. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.6Harness: Recurrent Neural Network Inference - Engine: CPULinux 6.8 - Ubuntu 24.04 Default110220330440550SE +/- 1.16, N = 3509.36MIN: 504.161. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl -lpthread

LiteRT

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: DeepLab V3Linux 6.8 - Ubuntu 24.04 Default13K26K39K52K65KSE +/- 618.93, N = 361288.0

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: SqueezeNetLinux 6.8 - Ubuntu 24.04 Default9K18K27K36K45KSE +/- 106.78, N = 340421.6

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception V4Linux 6.8 - Ubuntu 24.04 Default50K100K150K200K250KSE +/- 763.64, N = 3233818

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: NASNet MobileLinux 6.8 - Ubuntu 24.04 Default120K240K360K480K600KSE +/- 2349.68, N = 3554407

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet FloatLinux 6.8 - Ubuntu 24.04 Default5K10K15K20K25KSE +/- 343.99, N = 323982.8

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Mobilenet QuantLinux 6.8 - Ubuntu 24.04 Default5K10K15K20K25KSE +/- 195.57, N = 324146.6

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Inception ResNet V2Linux 6.8 - Ubuntu 24.04 Default70K140K210K280K350KSE +/- 1811.35, N = 3315042

OpenBenchmarking.orgMicroseconds, Fewer Is BetterLiteRT 2024-10-15Model: Quantized COCO SSD MobileNet v1Linux 6.8 - Ubuntu 24.04 Default9K18K27K36K45KSE +/- 362.10, N = 341574.6

XNNPACK

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV1Linux 6.8 - Ubuntu 24.04 Default5K10K15K20K25KSE +/- 67.26, N = 3244761. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV2Linux 6.8 - Ubuntu 24.04 Default12K24K36K48K60KSE +/- 572.53, N = 3545471. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3LargeLinux 6.8 - Ubuntu 24.04 Default20K40K60K80K100KSE +/- 344.59, N = 3804041. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP32MobileNetV3SmallLinux 6.8 - Ubuntu 24.04 Default14K28K42K56K70KSE +/- 336.77, N = 3652191. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV1Linux 6.8 - Ubuntu 24.04 Default5K10K15K20K25KSE +/- 79.01, N = 3248201. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV2Linux 6.8 - Ubuntu 24.04 Default12K24K36K48K60KSE +/- 375.66, N = 3550601. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3LargeLinux 6.8 - Ubuntu 24.04 Default20K40K60K80K100KSE +/- 488.47, N = 3802281. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: FP16MobileNetV3SmallLinux 6.8 - Ubuntu 24.04 Default14K28K42K56K70KSE +/- 446.89, N = 3662321. (CXX) g++ options: -O3 -lrt -lm

OpenBenchmarking.orgus, Fewer Is BetterXNNPACK b7b048Model: QS8MobileNetV2Linux 6.8 - Ubuntu 24.04 Default14K28K42K56K70KSE +/- 623.72, N = 3635701. (CXX) g++ options: -O3 -lrt -lm

111 Results Shown

High Performance Conjugate Gradient:
  104 104 104 - 60
  144 144 144 - 60
NAMD
DaCapo Benchmark:
  Jython
  Tradesoap
  Tradebeans
  Apache Kafka
  Apache Lucene Search Index
  Apache Lucene Search Engine
7-Zip Compression:
  Compression Rating
  Decompression Rating
Stockfish
Timed Linux Kernel Compilation:
  defconfig
  allmodconfig
Timed LLVM Compilation
Hackbench:
  16 - Thread
  32 - Thread
  16 - Process
  32 - Process
RabbitMQ:
  120 Queues, 400 Producers, 400 Consumers:
    Sending Messages/s
    Receiving Messages/s
  200 Queues, 400 Producers, 400 Consumers:
    Sending Messages/s
    Receiving Messages/s
ClickHouse:
  100M Rows Hits Dataset, First Run / Cold Cache
  100M Rows Hits Dataset, Second Run
  100M Rows Hits Dataset, Third Run
CockroachDB:
  KV, 50% Reads - 512
  KV, 60% Reads - 512
  KV, 95% Reads - 512
Memcached:
  1:10
  1:100
GROMACS
MariaDB mariadb-slap
PostgreSQL:
  100 - 1000 - Read Only
  100 - 1000 - Read Only - Average Latency
  100 - 1000 - Read Write
  100 - 1000 - Read Write - Average Latency
Stress-NG:
  Hash
  MMAP
  NUMA
  Pipe
  Poll
  Zlib
  Futex
  MEMFD
  Mutex
  Atomic
  Malloc
  Cloning
  Forking
  Pthread
  AVL Tree
  IO_uring
  SENDFILE
  CPU Cache
  Power Math
  Semaphores
  Matrix Math
  Vector Math
  AVX-512 VNNI
  Function Call
  x86_64 RdRand
  Floating Point
  Matrix 3D Math
  Memory Copying
  Vector Shuffle
  Mixed Scheduler
  Socket Activity
  Exponential Math
  Jpeg Compression
  Logarithmic Math
  Wide Vector Math
  Context Switching
  Fractal Generator
  Radix String Sort
  Fused Multiply-Add
  Trigonometric Math
  Bitonic Integer Sort
  Vector Floating Point
  Glibc C String Functions
  Glibc Qsort Data Sorting
  System V Message Passing
Apache Cassandra
RocksDB:
  Rand Read
  Update Rand
  Read While Writing
  Read Rand Write Rand
oneDNN:
  IP Shapes 1D - CPU
  IP Shapes 3D - CPU
  Convolution Batch Shapes Auto - CPU
  Deconvolution Batch shapes_1d - CPU
  Deconvolution Batch shapes_3d - CPU
  Recurrent Neural Network Training - CPU
  Recurrent Neural Network Inference - CPU
LiteRT:
  DeepLab V3
  SqueezeNet
  Inception V4
  NASNet Mobile
  Mobilenet Float
  Mobilenet Quant
  Inception ResNet V2
  Quantized COCO SSD MobileNet v1
XNNPACK:
  FP32MobileNetV1
  FP32MobileNetV2
  FP32MobileNetV3Large
  FP32MobileNetV3Small
  FP16MobileNetV1
  FP16MobileNetV2
  FP16MobileNetV3Large
  FP16MobileNetV3Small
  QS8MobileNetV2