AWS vs GCP

KVM testing on Debian 10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2102112-HA-MERGE252924
Jump To Table - Results

View

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

Limit displaying results to tests within:

Timed Code Compilation 2 Tests
C/C++ Compiler Tests 5 Tests
CPU Massive 12 Tests
Database Test Suite 3 Tests
Disk Test Suite 4 Tests
Common Kernel Benchmarks 5 Tests
Multi-Core 5 Tests
Programmer / Developer System Benchmarks 3 Tests
Server 4 Tests
Server CPU Tests 7 Tests
Single-Threaded 3 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
aws-m5.4xlarge
February 10 2021
  17 Hours, 21 Minutes
aws-c5.4xlarge
February 10 2021
  16 Hours, 15 Minutes
gcp-c2-standard-16
February 10 2021
  16 Hours, 30 Minutes
n2-standard-16
February 10 2021
  18 Hours, 44 Minutes
n2d-standard-16
February 10 2021
  22 Hours, 17 Minutes
Invert Hiding All Results Option
  18 Hours, 13 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


AWS vs GCPProcessorMotherboardChipsetMemoryDiskNetworkOSKernelCompilerFile-SystemSystem Layeraws-m5.4xlargeaws-c5.4xlargegcp-c2-standard-16n2-standard-16n2d-standard-16Intel Xeon Platinum 8175M (8 Cores / 16 Threads)Amazon EC2 m5.4xlarge (1.0 BIOS)Intel 440FX 82441FX PMC62GB32GB Amazon Elastic Block StoreAmazon ElasticDebian 104.19.0-14-cloud-amd64 (x86_64)GCC 8.3.0ext4KVMIntel Xeon Platinum 8275CL (8 Cores / 16 Threads)Amazon EC2 c5.4xlarge (1.0 BIOS)32GBIntel Xeon (8 Cores / 16 Threads)Google Compute Engine c2-standard-1664GB32GB PersistentDisk4.19.0-13-cloud-amd64 (x86_64)Google Compute Engine n2-standard-16AMD EPYC 7B12 (8 Cores / 16 Threads)Google Compute Engine n2d-standard-16OpenBenchmarking.orgKernel Details- aws-m5.4xlarge: Transparent Huge Pages: always- aws-c5.4xlarge: Transparent Huge Pages: always- gcp-c2-standard-16: scsi_mod.use_blk_mq=Y - Transparent Huge Pages: always- n2-standard-16: scsi_mod.use_blk_mq=Y - Transparent Huge Pages: always- n2d-standard-16: scsi_mod.use_blk_mq=Y - Transparent Huge Pages: alwaysCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v Disk Details- NONE / discard,errors=remount-ro,relatime,rw / Block Size: 4096Processor Details- aws-m5.4xlarge: CPU Microcode: 0x2006906- aws-c5.4xlarge: CPU Microcode: 0x5003005- gcp-c2-standard-16: CPU Microcode: 0x1- n2-standard-16: CPU Microcode: 0x1- n2d-standard-16: CPU Microcode: 0x1000065Java Details- OpenJDK Runtime Environment (build 11.0.9.1+1-post-Debian-1deb10u2)Python Details- Python 2.7.16 + Python 3.7.3Security Details- aws-m5.4xlarge: itlb_multihit: KVM: Vulnerable + l1tf: Mitigation of PTE Inversion + mds: Vulnerable: Clear buffers attempted no microcode; SMT Host state unknown + meltdown: Mitigation of PTI + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Vulnerable: Clear buffers attempted no microcode; SMT Host state unknown - aws-c5.4xlarge: itlb_multihit: KVM: Vulnerable + l1tf: Mitigation of PTE Inversion + mds: Vulnerable: Clear buffers attempted no microcode; SMT Host state unknown + meltdown: Mitigation of PTI + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected - gcp-c2-standard-16: itlb_multihit: Not affected + l1tf: Not affected + mds: Mitigation of Clear buffers; SMT Host state unknown + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of Clear buffers; SMT Host state unknown - n2-standard-16: itlb_multihit: Not affected + l1tf: Not affected + mds: Mitigation of Clear buffers; SMT Host state unknown + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of Clear buffers; SMT Host state unknown - n2d-standard-16: 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: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

aws-m5.4xlargeaws-c5.4xlargegcp-c2-standard-16n2-standard-16n2d-standard-16Logarithmic Result OverviewPhoronix Test SuiteFlexible IO TesterSQLiteIORRAMspeed SMPSockperfRedispmbenchHierarchical INTegrationOpenSSLCompile BenchCoremarkMultichase Pointer ChaserStress-NGSQLite SpeedtestTimed Apache CompilationOSBenchx2647-Zip CompressionTimed Linux Kernel Compilation

AWS vs GCPfio: Rand Read - Linux AIO - No - Yes - 4KB - Default Test Directoryfio: Rand Read - Linux AIO - No - Yes - 4KB - Default Test Directorydbench: 12 Clientsstress-ng: NUMAstress-ng: Atomicramspeed: Scale - Floating Pointramspeed: Add - Floating Pointramspeed: Triad - Floating Pointior: 16MB - Default Test Directoryior: 32MB - Default Test Directoryior: 64MB - Default Test Directoryior: 8MB - Default Test Directoryramspeed: Average - Floating Pointramspeed: Scale - Integerredis: LPOPramspeed: Triad - Integerramspeed: Average - Integerramspeed: Copy - Integerramspeed: Add - Integerramspeed: Copy - Floating Pointfio: Seq Write - Linux AIO - No - Yes - 4KB - Default Test Directoryfio: Seq Write - Linux AIO - No - Yes - 4KB - Default Test Directorystress-ng: SENDFILEredis: LPUSHpmbench: 8 - 80% Reads 20% Writespmbench: 4 - 80% Reads 20% Writesredis: SETstress-ng: Semaphorescompilebench: Compileredis: GETredis: SADDpmbench: 8 - 100% Writespmbench: 4 - 50%stress-ng: Memory Copyingsockperf: Throughputpmbench: 2 - 50%pmbench: 16 - 50%stress-ng: MMAPhint: FLOATmultichase: 256MB Array, 256 Byte Stridepmbench: 16 - 100% Writesstress-ng: Glibc Qsort Data Sortingpmbench: 1 - 80% Reads 20% Writespmbench: 1 - 50%osbench: Memory Allocationsmultichase: 1GB Array, 256 Byte Stridemultichase: 1GB Array, 256 Byte Stride, 2 Threadsosbench: Create Filesmultichase: 1GB Array, 256 Byte Stride, 4 Threadsopenssl: RSA 4096-bit Performanceosbench: Launch Programsstress-ng: Socket Activitystress-ng: MEMFDstress-ng: Cryptostress-ng: Context Switchingmultichase: 4MB Array, 64 Byte Stridestress-ng: Vector Mathcoremark: CoreMark Size 666 - Iterations Per Secondsqlite-speedtest: Timed Time - Size 1,000pmbench: 2 - 100% Readsstress-ng: Glibc C String Functionspmbench: 4 - 100% Readspmbench: 8 - 100% Readspmbench: 16 - 100% Readsstress-ng: CPU Stressbuild-apache: Time To Compilex264: H.264 Video Encodingcompress-7zip: Compress Speed Teststress-ng: Matrix Mathbuild-linux-kernel: Time To Compilestress-ng: System V Message Passingfio: Seq Read - Linux AIO - No - Yes - 4KB - Default Test Directoryfio: Seq Read - Linux AIO - No - Yes - 4KB - Default Test Directorystress-ng: Mallocior: 256MB - Default Test Directoryior: 512MB - Default Test Directoryior: 1024MB - Default Test Directorystress-ng: RdRandstress-ng: CPU Cachestress-ng: Forkingosbench: Create Processesosbench: Create Threadssockperf: Latency Under Loadsockperf: Latency Ping Pongpmbench: 16 - 80% Reads 20% Writespmbench: 2 - 80% Reads 20% Writespmbench: 4 - 100% Writespmbench: 2 - 100% Writespmbench: 1 - 100% Writespmbench: 1 - 100% Readspmbench: 8 - 50%compilebench: Read Compiled Treecompilebench: Initial Createior: 4MB - Default Test Directoryior: 2MB - Default Test Directoryfio: Seq Write - Linux AIO - No - Yes - 2MB - Default Test Directoryfio: Seq Write - Linux AIO - No - Yes - 2MB - Default Test Directoryfio: Seq Read - Linux AIO - No - Yes - 2MB - Default Test Directoryfio: Seq Read - Linux AIO - No - Yes - 2MB - Default Test Directoryfio: Rand Write - Linux AIO - No - Yes - 4KB - Default Test Directoryfio: Rand Write - Linux AIO - No - Yes - 4KB - Default Test Directoryfio: Rand Write - Linux AIO - No - Yes - 2MB - Default Test Directoryfio: Rand Write - Linux AIO - No - Yes - 2MB - Default Test Directoryfio: Rand Read - Linux AIO - No - Yes - 2MB - Default Test Directoryfio: Rand Read - Linux AIO - No - Yes - 2MB - Default Test Directorysqlite: 1aws-m5.4xlargeaws-c5.4xlargegcp-c2-standard-16n2-standard-16n2d-standard-16291911.4649.85162761.9519218.9521873.4522066.21124.41124.07123.52126.3722310.0621693.041318735.5825947.0725139.4626218.3826243.5926552.0825109.8295437.981270224.750.10190.10391409994.281314670.851492.971787305.031591476.120.04840.08487679.434603490.08490.0963166.86303251432.0639973.7910.065596.550.10580.0861114.70731178.35179.43920.29307080.9021888.552.3201626266.79650.251368.623276201.5810.07547430.91251713.08234687.8500.0525709919.610.05310.05280.06712563.9026.72059.764234136291.4196.8096029137.4411.4291772884017.29124.13125.55124.40252110.639.8217333.9335.97339019.4822959.9348.0820.11110.10380.04850.04870.04870.05320.08362122.77372.59125.20123.96601286012824589.846601286112992.540299711.71144.42648.92181896.8017758.1420489.5221127.17130.34128.09127.39134.2620947.2419434.692141238.2524412.2623118.4924451.1224987.2024780.61299711.796234.711393288.760.10780.11041625171.671401200.991076.412074873.251766598.420.04350.08677673.024313890.08720.0972178.11353889341.3180682.0090.0641111.660.11020.0867120.52226181.97281.45419.48877186.6892181.051.8232987297.90669.121582.173479432.259.37155197.84292384.76722388.5350.0474816655.950.04640.04590.05852681.3724.15065.534600439854.3789.3196314828.3711.7299771090930.30126.91126.15124.80251811.2614.9417009.1436.60043119.78445111.4517.9050.11470.11060.04370.04380.04380.04680.08552191.66392.00141.89154.176213162131299211.7621316213133.4281490.610338.840663.81189328.7019461.9322163.3322517.4012.0111.8611.8212.9222637.7421006.702390598.6725924.7624969.1626311.3926572.3926346.90399515.6151312.521529208.040.09290.09451707406.211351126.791614.332236857.501915206.710.04120.07586409.336190820.07640.0864178.98370034700.4336169.2410.0582118.880.09650.0769103.45610072.13172.42915.58547274.2662305.247.8643186265.12729.021633.944031351.429.25757956.16307476.22110773.0590.0450857228.360.04510.04500.05602563.1622.99669.164864841663.1985.3206726926.6811306073244465.51252164.0819.5916034.8934.59374115.63072211.3288.1300.10030.09570.04150.04160.04170.04510.07482613.75439.3015.0418.92514.71434.63021.2244699.54086.221.8291490.610324.813673.28174634.0219011.0421849.3122094.6012.0111.8211.8112.9322300.7220732.492171899.3325171.4524310.0825819.7125931.8225684.51305411.3135259.901362664.770.10020.10251555308.661275323.051370.402018533.081754153.420.04540.08208058.165448440.08250.0943161.26332378585.6433273.2360.0626106.590.10400.0829111.68464073.62174.23518.40330775.1702059.152.5967287462.86640.171464.503588183.489.77551788.94274845.90418782.4170.0496771032.400.04920.04920.06192302.6325.72361.334434337604.7493.6926286939.7911.1305771810852.29251886.1810.5617287.7140.72268818.44644621.2968.4730.10800.10390.04580.04600.04620.05000.08182234.45378.3114.7818.70515.11434.93041.2314699.74086.425.623720.302325.7912086.06381866.9939649.7243638.7542899.7611.9811.8411.8212.9241409.7936105.671636222.2943509.1640777.7341988.1841452.5741079.97305611.2124211.30985310.290.14410.14371124629.87925452.741600.421504492.631292686.000.06040.11069269.325855730.10800.1218222.59269367383.1347994.0820.078788.920.12890.102291.47063994.49194.74817.19253796.4031804.460.5006225963.48584.571695.333275655.888.19256129.04282525.76744883.9640.0545780364.640.05440.05420.05702256.9024.61364.194427436305.8684.9365909219.1411.5305273559568.1334.7815912.6937.85173124.36924033.20013.6600.15410.15600.06690.07120.07070.05940.12192615.09394.8414.6317.46514.9311.91710.699514.5516.033.654OpenBenchmarking.org

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16gcp-c2-standard-16n2d-standard-166001200180024003000SE +/- 0.67, N = 329972919149149721. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16gcp-c2-standard-16n2d-standard-163691215SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 311.70011.4000.6100.6100.3021. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Dbench

Dbench is a benchmark designed by the Samba project as a free alternative to netbench, but dbench contains only file-system calls for testing the disk performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterDbench 4.012 Clientsaws-c5.4xlargegcp-c2-standard-16n2d-standard-16n2-standard-162004006008001000SE +/- 15.81, N = 3SE +/- 3.45, N = 3SE +/- 3.23, N = 3SE +/- 3.05, N = 31144.42338.84325.79324.811. (CC) gcc options: -lpopt -O2

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: NUMAn2d-standard-16n2-standard-16gcp-c2-standard-16aws-m5.4xlargeaws-c5.4xlarge400800120016002000SE +/- 19.64, N = 3SE +/- 3.28, N = 3SE +/- 1.07, N = 3SE +/- 2.47, N = 3SE +/- 5.93, N = 72086.06673.28663.81649.85648.921. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Atomicn2d-standard-16gcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlarge80K160K240K320K400KSE +/- 1202.90, N = 3SE +/- 1215.69, N = 3SE +/- 1582.27, N = 7SE +/- 1470.40, N = 3SE +/- 1271.94, N = 3381866.99189328.70181896.80174634.02162761.951. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating Pointn2d-standard-16gcp-c2-standard-16aws-m5.4xlargen2-standard-16aws-c5.4xlarge8K16K24K32K40KSE +/- 426.91, N = 5SE +/- 2.96, N = 3SE +/- 41.59, N = 3SE +/- 38.05, N = 3SE +/- 136.11, N = 1039649.7219461.9319218.9519011.0417758.141. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Floating Pointn2d-standard-16gcp-c2-standard-16aws-m5.4xlargen2-standard-16aws-c5.4xlarge9K18K27K36K45KSE +/- 440.57, N = 15SE +/- 18.09, N = 3SE +/- 18.91, N = 3SE +/- 33.02, N = 3SE +/- 186.36, N = 743638.7522163.3321873.4521849.3120489.521. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating Pointn2d-standard-16gcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlarge9K18K27K36K45KSE +/- 561.19, N = 15SE +/- 28.69, N = 3SE +/- 22.77, N = 3SE +/- 16.50, N = 3SE +/- 265.83, N = 342899.7622517.4022094.6022066.2121127.171. (CC) gcc options: -O3 -march=native

IOR

IOR is a parallel I/O storage benchmark making use of MPI with a particular focus on HPC (High Performance Computing) systems. IOR is developed at the Lawrence Livermore National Laboratory (LLNL). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.3.0Block Size: 16MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16gcp-c2-standard-16n2d-standard-16306090120150SE +/- 0.13, N = 3SE +/- 0.55, N = 3SE +/- 0.13, N = 9SE +/- 0.13, N = 9SE +/- 0.12, N = 9130.34124.4112.0112.0111.98MIN: 119.26 / MAX: 446.73MIN: 95.05 / MAX: 390.351. (CC) gcc options: -O2 -lm -pthread -lmpi

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.3.0Block Size: 32MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargegcp-c2-standard-16n2d-standard-16n2-standard-16306090120150SE +/- 0.07, N = 3SE +/- 0.31, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3128.09124.0711.8611.8411.82MIN: 122.96 / MAX: 234.67MIN: 105.22 / MAX: 234.921. (CC) gcc options: -O2 -lm -pthread -lmpi

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.3.0Block Size: 64MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2d-standard-16gcp-c2-standard-16n2-standard-16306090120150SE +/- 0.02, N = 3SE +/- 0.34, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3127.39123.5211.8211.8211.81MIN: 124.86 / MAX: 160.72MIN: 109.18 / MAX: 160.831. (CC) gcc options: -O2 -lm -pthread -lmpi

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.3.0Block Size: 8MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16n2d-standard-16gcp-c2-standard-16306090120150SE +/- 0.07, N = 3SE +/- 0.87, N = 3SE +/- 0.18, N = 9SE +/- 0.17, N = 9SE +/- 0.19, N = 9134.26126.3712.9312.9212.92MIN: 112.57 / MAX: 448.25MIN: 81.39 / MAX: 364.91. (CC) gcc options: -O2 -lm -pthread -lmpi

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating Pointn2d-standard-16gcp-c2-standard-16aws-m5.4xlargen2-standard-16aws-c5.4xlarge9K18K27K36K45KSE +/- 294.04, N = 3SE +/- 14.86, N = 3SE +/- 19.34, N = 3SE +/- 50.54, N = 3SE +/- 168.32, N = 941409.7922637.7422310.0622300.7220947.241. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Integern2d-standard-16aws-m5.4xlargegcp-c2-standard-16n2-standard-16aws-c5.4xlarge8K16K24K32K40KSE +/- 212.09, N = 3SE +/- 25.24, N = 3SE +/- 24.08, N = 3SE +/- 36.64, N = 3SE +/- 101.17, N = 336105.6721693.0421006.7020732.4919434.691. (CC) gcc options: -O3 -march=native

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPOPgcp-c2-standard-16n2-standard-16aws-c5.4xlargen2d-standard-16aws-m5.4xlarge500K1000K1500K2000K2500KSE +/- 10861.56, N = 3SE +/- 4172.63, N = 3SE +/- 23310.06, N = 3SE +/- 17003.82, N = 3SE +/- 17151.29, N = 32390598.672171899.332141238.251636222.291318735.581. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Integern2d-standard-16aws-m5.4xlargegcp-c2-standard-16n2-standard-16aws-c5.4xlarge9K18K27K36K45KSE +/- 459.82, N = 3SE +/- 28.18, N = 3SE +/- 33.24, N = 3SE +/- 30.84, N = 3SE +/- 129.67, N = 343509.1625947.0725924.7625171.4524412.261. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Integern2d-standard-16aws-m5.4xlargegcp-c2-standard-16n2-standard-16aws-c5.4xlarge9K18K27K36K45KSE +/- 543.16, N = 3SE +/- 115.24, N = 3SE +/- 20.29, N = 3SE +/- 91.23, N = 3SE +/- 185.84, N = 1540777.7325139.4624969.1624310.0823118.491. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Integern2d-standard-16gcp-c2-standard-16aws-m5.4xlargen2-standard-16aws-c5.4xlarge9K18K27K36K45KSE +/- 167.45, N = 3SE +/- 58.10, N = 3SE +/- 27.20, N = 3SE +/- 39.43, N = 3SE +/- 118.78, N = 341988.1826311.3926218.3825819.7124451.121. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Integern2d-standard-16gcp-c2-standard-16aws-m5.4xlargen2-standard-16aws-c5.4xlarge9K18K27K36K45KSE +/- 407.17, N = 3SE +/- 28.59, N = 3SE +/- 16.77, N = 3SE +/- 80.69, N = 3SE +/- 256.31, N = 341452.5726572.3926243.5925931.8224987.201. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating Pointn2d-standard-16aws-m5.4xlargegcp-c2-standard-16n2-standard-16aws-c5.4xlarge9K18K27K36K45KSE +/- 451.48, N = 3SE +/- 26.52, N = 3SE +/- 19.25, N = 3SE +/- 9.77, N = 3SE +/- 164.17, N = 341079.9726552.0826346.9025684.5124780.611. (CC) gcc options: -O3 -march=native

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directorygcp-c2-standard-16n2d-standard-16n2-standard-16aws-c5.4xlargeaws-m5.4xlarge9001800270036004500SE +/- 2.76, N = 15SE +/- 2.34, N = 15399530563054299725101. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directorygcp-c2-standard-16aws-c5.4xlargen2-standard-16n2d-standard-16aws-m5.4xlarge48121620SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.11, N = 15SE +/- 0.11, N = 15SE +/- 0.01, N = 315.6011.7011.3011.209.821. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILEgcp-c2-standard-16n2-standard-16n2d-standard-16aws-c5.4xlargeaws-m5.4xlarge30K60K90K120K150KSE +/- 44.97, N = 3SE +/- 90.15, N = 3SE +/- 213.15, N = 3SE +/- 147.27, N = 3SE +/- 39.93, N = 3151312.52135259.90124211.3096234.7195437.981. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPUSHgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-16300K600K900K1200K1500KSE +/- 6396.51, N = 3SE +/- 16860.24, N = 12SE +/- 12729.64, N = 6SE +/- 9414.10, N = 3SE +/- 6487.50, N = 151529208.041393288.761362664.771270224.75985310.291. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

pmbench

Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 8 - Read-Write Ratio: 80% Reads 20% Writesgcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-160.03240.06480.09720.12960.162SE +/- 0.0000, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0011, N = 5SE +/- 0.0002, N = 30.09290.10020.10190.10780.14411. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 4 - Read-Write Ratio: 80% Reads 20% Writesgcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-160.03230.06460.09690.12920.1615SE +/- 0.0001, N = 3SE +/- 0.0003, N = 3SE +/- 0.0001, N = 3SE +/- 0.0012, N = 4SE +/- 0.0004, N = 30.09450.10250.10390.11040.14371. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-16400K800K1200K1600K2000KSE +/- 20378.39, N = 3SE +/- 4264.39, N = 3SE +/- 16687.57, N = 13SE +/- 19944.05, N = 15SE +/- 6923.76, N = 31707406.211625171.671555308.661409994.281124629.871. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Semaphoresaws-c5.4xlargegcp-c2-standard-16aws-m5.4xlargen2-standard-16n2d-standard-16300K600K900K1200K1500KSE +/- 3034.32, N = 3SE +/- 688.95, N = 3SE +/- 750.37, N = 3SE +/- 437.82, N = 3SE +/- 1313.80, N = 31401200.991351126.791314670.851275323.05925452.741. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Compilegcp-c2-standard-16n2d-standard-16aws-m5.4xlargen2-standard-16aws-c5.4xlarge30060090012001500SE +/- 4.12, N = 3SE +/- 29.77, N = 9SE +/- 1.82, N = 3SE +/- 23.79, N = 9SE +/- 6.40, N = 31614.331600.421492.971370.401076.41

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GETgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-16500K1000K1500K2000K2500KSE +/- 24505.89, N = 3SE +/- 13542.52, N = 3SE +/- 5999.45, N = 3SE +/- 12108.31, N = 13SE +/- 9075.94, N = 32236857.502074873.252018533.081787305.031504492.631. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SADDgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-16400K800K1200K1600K2000KSE +/- 13120.08, N = 3SE +/- 9722.20, N = 3SE +/- 7035.87, N = 3SE +/- 21952.80, N = 15SE +/- 6400.27, N = 31915206.711766598.421754153.421591476.121292686.001. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

pmbench

Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 8 - Read-Write Ratio: 100% Writesgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-160.01360.02720.04080.05440.068SE +/- 0.0000, N = 3SE +/- 0.0004, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0008, N = 140.04120.04350.04540.04840.06041. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 4 - Read-Write Ratio: 50%gcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-160.02490.04980.07470.09960.1245SE +/- 0.0000, N = 3SE +/- 0.0002, N = 3SE +/- 0.0000, N = 3SE +/- 0.0005, N = 3SE +/- 0.0001, N = 30.07580.08200.08480.08670.11061. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Memory Copyingn2d-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargegcp-c2-standard-162K4K6K8K10KSE +/- 14.51, N = 3SE +/- 93.12, N = 3SE +/- 18.19, N = 3SE +/- 94.95, N = 4SE +/- 77.68, N = 39269.328058.167679.437673.026409.331. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

Sockperf

This is a network socket API performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: Throughputgcp-c2-standard-16n2d-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlarge130K260K390K520K650KSE +/- 6140.00, N = 6SE +/- 6341.53, N = 25SE +/- 5065.02, N = 7SE +/- 4435.54, N = 5SE +/- 2402.87, N = 56190825855735448444603494313891. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

pmbench

Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 2 - Read-Write Ratio: 50%gcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-160.02430.04860.07290.09720.1215SE +/- 0.0000, N = 3SE +/- 0.0003, N = 3SE +/- 0.0001, N = 3SE +/- 0.0011, N = 3SE +/- 0.0006, N = 30.07640.08250.08490.08720.10801. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 16 - Read-Write Ratio: 50%gcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-160.02740.05480.08220.10960.137SE +/- 0.0001, N = 3SE +/- 0.0002, N = 3SE +/- 0.0000, N = 3SE +/- 0.0007, N = 15SE +/- 0.0010, N = 90.08640.09430.09630.09720.12181. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MMAPn2d-standard-16gcp-c2-standard-16aws-c5.4xlargeaws-m5.4xlargen2-standard-1650100150200250SE +/- 0.18, N = 3SE +/- 0.01, N = 3SE +/- 0.99, N = 3SE +/- 0.08, N = 3SE +/- 0.16, N = 3222.59178.98178.11166.86161.261. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

Hierarchical INTegration

This test runs the U.S. Department of Energy's Ames Laboratory Hierarchical INTegration (HINT) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOATgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-1680M160M240M320M400MSE +/- 611194.33, N = 3SE +/- 974897.69, N = 3SE +/- 290225.20, N = 3SE +/- 457909.69, N = 3SE +/- 136092.51, N = 3370034700.43353889341.32332378585.64303251432.06269367383.131. (CC) gcc options: -O3 -march=native -lm

Multichase Pointer Chaser

This is a benchmark of Google's multichase pointer chaser program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 256MB Array, 256 Byte Stridegcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-1620406080100SE +/- 0.55, N = 3SE +/- 0.52, N = 3SE +/- 0.38, N = 3SE +/- 0.38, N = 3SE +/- 0.52, N = 369.2473.2473.7982.0194.081. (CC) gcc options: -O2 -static -pthread -lrt

pmbench

Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 16 - Read-Write Ratio: 100% Writesgcp-c2-standard-16n2-standard-16aws-c5.4xlargeaws-m5.4xlargen2d-standard-160.01770.03540.05310.07080.0885SE +/- 0.0000, N = 3SE +/- 0.0001, N = 3SE +/- 0.0007, N = 15SE +/- 0.0001, N = 3SE +/- 0.0001, N = 30.05820.06260.06410.06550.07871. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc Qsort Data Sortinggcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-16306090120150SE +/- 0.28, N = 3SE +/- 0.12, N = 3SE +/- 0.17, N = 3SE +/- 0.17, N = 3SE +/- 1.35, N = 15118.88111.66106.5996.5588.921. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

pmbench

Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 1 - Read-Write Ratio: 80% Reads 20% Writesgcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-160.0290.0580.0870.1160.145SE +/- 0.0001, N = 3SE +/- 0.0007, N = 3SE +/- 0.0001, N = 3SE +/- 0.0014, N = 3SE +/- 0.0001, N = 30.09650.10400.10580.11020.12891. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 1 - Read-Write Ratio: 50%gcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-160.0230.0460.0690.0920.115SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0008, N = 3SE +/- 0.0001, N = 30.07690.08290.08610.08670.10221. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocationsn2d-standard-16gcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlarge306090120150SE +/- 0.15, N = 3SE +/- 0.31, N = 3SE +/- 0.17, N = 3SE +/- 0.07, N = 3SE +/- 1.00, N = 391.47103.46111.68114.71120.52-lm-lm-lm1. (CC) gcc options:

Multichase Pointer Chaser

This is a benchmark of Google's multichase pointer chaser program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 1GB Array, 256 Byte Stridegcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-1620406080100SE +/- 0.28, N = 3SE +/- 0.16, N = 3SE +/- 0.17, N = 3SE +/- 0.49, N = 3SE +/- 0.19, N = 372.1373.6278.3581.9794.491. (CC) gcc options: -O2 -static -pthread -lrt

OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 1GB Array, 256 Byte Stride, 2 Threadsgcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-1620406080100SE +/- 0.07, N = 3SE +/- 0.54, N = 3SE +/- 0.19, N = 3SE +/- 0.69, N = 3SE +/- 0.42, N = 372.4374.2479.4481.4594.751. (CC) gcc options: -O2 -static -pthread -lrt

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Filesgcp-c2-standard-16n2d-standard-16n2-standard-16aws-c5.4xlargeaws-m5.4xlarge510152025SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.24, N = 3SE +/- 0.22, N = 515.5917.1918.4019.4920.29-lm-lm-lm1. (CC) gcc options:

Multichase Pointer Chaser

This is a benchmark of Google's multichase pointer chaser program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 1GB Array, 256 Byte Stride, 4 Threadsgcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-1620406080100SE +/- 0.15, N = 3SE +/- 0.31, N = 3SE +/- 0.21, N = 3SE +/- 1.09, N = 15SE +/- 0.49, N = 374.2775.1780.9086.6996.401. (CC) gcc options: -O2 -static -pthread -lrt

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performancegcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-165001000150020002500SE +/- 1.69, N = 3SE +/- 4.99, N = 3SE +/- 3.19, N = 3SE +/- 0.59, N = 3SE +/- 1.62, N = 32305.22181.02059.11888.51804.41. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch Programsgcp-c2-standard-16aws-c5.4xlargeaws-m5.4xlargen2-standard-16n2d-standard-161428425670SE +/- 0.55, N = 4SE +/- 0.46, N = 15SE +/- 0.16, N = 3SE +/- 0.64, N = 3SE +/- 0.80, N = 1547.8651.8252.3252.6060.50-lm-lm-lm1. (CC) gcc options:

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Socket Activityn2-standard-16aws-c5.4xlargeaws-m5.4xlargegcp-c2-standard-16n2d-standard-1616003200480064008000SE +/- 51.91, N = 3SE +/- 53.49, N = 15SE +/- 68.40, N = 3SE +/- 49.21, N = 10SE +/- 60.33, N = 37462.867297.906266.796265.125963.481. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MEMFDgcp-c2-standard-16aws-c5.4xlargeaws-m5.4xlargen2-standard-16n2d-standard-16160320480640800SE +/- 0.52, N = 3SE +/- 5.69, N = 3SE +/- 2.33, N = 3SE +/- 1.84, N = 3SE +/- 3.51, N = 3729.02669.12650.25640.17584.571. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Crypton2d-standard-16gcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlarge400800120016002000SE +/- 0.35, N = 3SE +/- 6.23, N = 3SE +/- 0.57, N = 3SE +/- 0.16, N = 3SE +/- 0.51, N = 31695.331633.941582.171464.501368.621. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context Switchinggcp-c2-standard-16n2-standard-16aws-c5.4xlargeaws-m5.4xlargen2d-standard-16900K1800K2700K3600K4500KSE +/- 11496.05, N = 3SE +/- 1263.47, N = 3SE +/- 9678.58, N = 3SE +/- 2824.53, N = 3SE +/- 15624.04, N = 34031351.423588183.483479432.253276201.583275655.881. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

Multichase Pointer Chaser

This is a benchmark of Google's multichase pointer chaser program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 4MB Array, 64 Byte Striden2d-standard-16gcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlarge3691215SE +/- 0.071, N = 15SE +/- 0.093, N = 3SE +/- 0.117, N = 3SE +/- 0.096, N = 3SE +/- 0.008, N = 38.1929.2579.3719.77510.0751. (CC) gcc options: -O2 -static -pthread -lrt

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector Mathgcp-c2-standard-16n2d-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlarge12K24K36K48K60KSE +/- 5.25, N = 3SE +/- 2.59, N = 3SE +/- 8.00, N = 3SE +/- 3.33, N = 3SE +/- 4.61, N = 357956.1656129.0455197.8451788.9447430.911. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

Coremark

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

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Secondgcp-c2-standard-16aws-c5.4xlargen2d-standard-16n2-standard-16aws-m5.4xlarge70K140K210K280K350KSE +/- 333.29, N = 3SE +/- 260.73, N = 3SE +/- 393.13, N = 3SE +/- 61.84, N = 3SE +/- 66.57, N = 3307476.22292384.77282525.77274845.90251713.081. (CC) gcc options: -O2 -lrt" -lrt

SQLite Speedtest

This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000gcp-c2-standard-16n2-standard-16n2d-standard-16aws-m5.4xlargeaws-c5.4xlarge20406080100SE +/- 0.40, N = 3SE +/- 0.53, N = 3SE +/- 0.17, N = 3SE +/- 0.27, N = 3SE +/- 0.84, N = 373.0682.4283.9687.8588.541. (CC) gcc options: -O2 -ldl -lpthread

pmbench

Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 2 - Read-Write Ratio: 100% Readsgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-160.01230.02460.03690.04920.0615SE +/- 0.0000, N = 3SE +/- 0.0006, N = 3SE +/- 0.0001, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 30.04500.04740.04960.05250.05451. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String Functionsgcp-c2-standard-16aws-c5.4xlargen2d-standard-16n2-standard-16aws-m5.4xlarge200K400K600K800K1000KSE +/- 4606.24, N = 3SE +/- 4921.24, N = 3SE +/- 3322.92, N = 3SE +/- 5585.77, N = 3SE +/- 1060.26, N = 3857228.36816655.95780364.64771032.40709919.611. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

pmbench

Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 4 - Read-Write Ratio: 100% Readsgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-160.01220.02440.03660.04880.061SE +/- 0.0000, N = 3SE +/- 0.0001, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 30.04510.04640.04920.05310.05441. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 8 - Read-Write Ratio: 100% Readsgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-160.01220.02440.03660.04880.061SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0001, N = 30.04500.04590.04920.05280.05421. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 16 - Read-Write Ratio: 100% Readsgcp-c2-standard-16n2d-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlarge0.01510.03020.04530.06040.0755SE +/- 0.0000, N = 3SE +/- 0.0003, N = 3SE +/- 0.0003, N = 3SE +/- 0.0000, N = 3SE +/- 0.0002, N = 30.05600.05700.05850.06190.06711. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU Stressaws-c5.4xlargeaws-m5.4xlargegcp-c2-standard-16n2-standard-16n2d-standard-166001200180024003000SE +/- 2.88, N = 3SE +/- 0.42, N = 3SE +/- 1.42, N = 3SE +/- 5.97, N = 3SE +/- 1.91, N = 32681.372563.902563.162302.632256.901. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

Timed Apache Compilation

This test times how long it takes to build the Apache HTTPD web server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To Compilegcp-c2-standard-16aws-c5.4xlargen2d-standard-16n2-standard-16aws-m5.4xlarge612182430SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.14, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 323.0024.1524.6125.7226.72

x264

This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video Encodinggcp-c2-standard-16aws-c5.4xlargen2d-standard-16n2-standard-16aws-m5.4xlarge1530456075SE +/- 0.11, N = 3SE +/- 0.29, N = 3SE +/- 0.69, N = 5SE +/- 0.11, N = 3SE +/- 0.08, N = 369.1665.5364.1961.3359.761. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

7-Zip Compression

This is a test of 7-Zip using p7zip with its integrated benchmark feature or upstream 7-Zip for the Windows x64 build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Testgcp-c2-standard-16aws-c5.4xlargen2-standard-16n2d-standard-16aws-m5.4xlarge10K20K30K40K50KSE +/- 139.89, N = 3SE +/- 465.49, N = 3SE +/- 582.03, N = 3SE +/- 473.71, N = 3SE +/- 424.74, N = 548648460044434344274423411. (CXX) g++ options: -pipe -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Matrix Mathgcp-c2-standard-16aws-c5.4xlargen2-standard-16n2d-standard-16aws-m5.4xlarge9K18K27K36K45KSE +/- 6.77, N = 3SE +/- 53.69, N = 3SE +/- 28.32, N = 3SE +/- 22.40, N = 3SE +/- 43.59, N = 341663.1939854.3737604.7436305.8636291.411. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To Compilen2d-standard-16gcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlarge20406080100SE +/- 0.75, N = 3SE +/- 0.74, N = 3SE +/- 0.49, N = 3SE +/- 1.05, N = 3SE +/- 1.24, N = 384.9485.3289.3293.6996.81

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: System V Message Passinggcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-161.4M2.8M4.2M5.6M7MSE +/- 22246.09, N = 3SE +/- 34735.51, N = 3SE +/- 8613.26, N = 3SE +/- 7036.24, N = 3SE +/- 77069.46, N = 156726926.686314828.376286939.796029137.445909219.141. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directoryaws-c5.4xlargen2d-standard-16aws-m5.4xlargen2-standard-16gcp-c2-standard-163691215SE +/- 0.00, N = 3SE +/- 0.12, N = 15SE +/- 0.00, N = 3SE +/- 0.09, N = 911.711.511.411.111.01. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directorygcp-c2-standard-16n2-standard-16n2d-standard-16aws-c5.4xlargeaws-m5.4xlarge7001400210028003500SE +/- 1.20, N = 3SE +/- 3.58, N = 9SE +/- 2.08, N = 15SE +/- 0.67, N = 3306030573052299729171. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Mallocn2d-standard-16gcp-c2-standard-16aws-m5.4xlargen2-standard-16aws-c5.4xlarge16M32M48M64M80MSE +/- 269100.50, N = 3SE +/- 25408.10, N = 3SE +/- 31467.63, N = 3SE +/- 195733.48, N = 3SE +/- 874783.93, N = 1573559568.1373244465.5172884017.2971810852.2971090930.301. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

IOR

IOR is a parallel I/O storage benchmark making use of MPI with a particular focus on HPC (High Performance Computing) systems. IOR is developed at the Lawrence Livermore National Laboratory (LLNL). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.3.0Block Size: 256MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlarge306090120150SE +/- 0.02, N = 3SE +/- 1.53, N = 9126.91124.13MIN: 125.98 / MAX: 132MIN: 75.95 / MAX: 131.861. (CC) gcc options: -O2 -lm -pthread -lmpi

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.3.0Block Size: 512MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlarge306090120150SE +/- 0.02, N = 3SE +/- 0.03, N = 3126.15125.55MIN: 124.33 / MAX: 127.56MIN: 117.44 / MAX: 127.821. (CC) gcc options: -O2 -lm -pthread -lmpi

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.3.0Block Size: 1024MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlarge306090120150SE +/- 0.20, N = 3SE +/- 0.07, N = 3124.80124.40MIN: 104.29 / MAX: 126.17MIN: 121.37 / MAX: 126.141. (CC) gcc options: -O2 -lm -pthread -lmpi

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: RdRandgcp-c2-standard-16aws-m5.4xlargen2-standard-16aws-c5.4xlarge50K100K150K200K250KSE +/- 15.34, N = 3SE +/- 0.85, N = 3SE +/- 22.36, N = 3SE +/- 36.77, N = 3252164.08252110.63251886.18251811.261. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU Cachen2d-standard-16gcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlarge816243240SE +/- 0.63, N = 15SE +/- 0.42, N = 12SE +/- 0.27, N = 12SE +/- 0.25, N = 15SE +/- 0.15, N = 1534.7819.5914.9410.569.821. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Forkingaws-m5.4xlargen2-standard-16aws-c5.4xlargegcp-c2-standard-16n2d-standard-164K8K12K16K20KSE +/- 148.50, N = 3SE +/- 70.47, N = 3SE +/- 302.76, N = 15SE +/- 4.51, N = 3SE +/- 73.46, N = 317333.9317287.7117009.1416034.8915912.691. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -ldl -lpthread -lc

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Processesgcp-c2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-16n2-standard-16918273645SE +/- 0.15, N = 3SE +/- 0.40, N = 3SE +/- 0.47, N = 3SE +/- 1.59, N = 12SE +/- 0.23, N = 334.5935.9736.6037.8540.72-lm-lm-lm1. (CC) gcc options:

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Threadsgcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-16612182430SE +/- 0.12, N = 3SE +/- 0.21, N = 3SE +/- 0.48, N = 15SE +/- 0.61, N = 15SE +/- 0.44, N = 1515.6318.4519.4819.7824.37-lm-lm-lm1. (CC) gcc options:

Sockperf

This is a network socket API performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Under Loadaws-m5.4xlargegcp-c2-standard-16aws-c5.4xlargen2-standard-16n2d-standard-16816243240SE +/- 0.099, N = 5SE +/- 0.107, N = 25SE +/- 0.092, N = 5SE +/- 0.431, N = 25SE +/- 1.121, N = 259.93411.32811.45121.29633.2001. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping Pongaws-c5.4xlargeaws-m5.4xlargegcp-c2-standard-16n2-standard-16n2d-standard-1648121620SE +/- 0.053, N = 5SE +/- 0.071, N = 8SE +/- 0.010, N = 5SE +/- 0.025, N = 5SE +/- 0.197, N = 257.9058.0828.1308.47313.6601. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

pmbench

Pmbench is a Linux paging and virtual memory benchmark. This test profile will report the average page latency of the system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 16 - Read-Write Ratio: 80% Reads 20% Writesgcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-160.03470.06940.10410.13880.1735SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0009, N = 15SE +/- 0.0032, N = 150.10030.10800.11110.11470.15411. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 2 - Read-Write Ratio: 80% Reads 20% Writesgcp-c2-standard-16aws-m5.4xlargen2-standard-16aws-c5.4xlargen2d-standard-160.03510.07020.10530.14040.1755SE +/- 0.0001, N = 3SE +/- 0.0000, N = 3SE +/- 0.0001, N = 3SE +/- 0.0011, N = 3SE +/- 0.0046, N = 150.09570.10380.10390.11060.15601. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 4 - Read-Write Ratio: 100% Writesgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-160.01510.03020.04530.06040.0755SE +/- 0.0000, N = 3SE +/- 0.0002, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0035, N = 150.04150.04370.04580.04850.06691. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 2 - Read-Write Ratio: 100% Writesgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-160.0160.0320.0480.0640.08SE +/- 0.0000, N = 3SE +/- 0.0001, N = 3SE +/- 0.0001, N = 3SE +/- 0.0000, N = 3SE +/- 0.0041, N = 150.04160.04380.04600.04870.07121. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 1 - Read-Write Ratio: 100% Writesgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-160.01590.03180.04770.06360.0795SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0041, N = 150.04170.04380.04620.04870.07071. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 1 - Read-Write Ratio: 100% Readsgcp-c2-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlargen2d-standard-160.01340.02680.04020.05360.067SE +/- 0.0000, N = 3SE +/- 0.0004, N = 3SE +/- 0.0001, N = 3SE +/- 0.0000, N = 3SE +/- 0.0032, N = 150.04510.04680.05000.05320.05941. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

OpenBenchmarking.orgus - Average Page Latency, Fewer Is BetterpmbenchConcurrent Worker Threads: 8 - Read-Write Ratio: 50%gcp-c2-standard-16n2-standard-16aws-m5.4xlargeaws-c5.4xlargen2d-standard-160.02740.05480.08220.10960.137SE +/- 0.0000, N = 3SE +/- 0.0002, N = 3SE +/- 0.0000, N = 3SE +/- 0.0010, N = 4SE +/- 0.0045, N = 150.07480.08180.08360.08550.12191. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled Treen2d-standard-16gcp-c2-standard-16n2-standard-16aws-c5.4xlargeaws-m5.4xlarge6001200180024003000SE +/- 178.31, N = 3SE +/- 8.43, N = 3SE +/- 16.18, N = 3SE +/- 29.15, N = 3SE +/- 14.76, N = 32615.092613.752234.452191.662122.77

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial Creategcp-c2-standard-16n2d-standard-16aws-c5.4xlargen2-standard-16aws-m5.4xlarge100200300400500SE +/- 23.63, N = 3SE +/- 30.20, N = 3SE +/- 1.88, N = 3SE +/- 13.97, N = 3SE +/- 2.06, N = 3439.30394.84392.00378.31372.59

IOR

IOR is a parallel I/O storage benchmark making use of MPI with a particular focus on HPC (High Performance Computing) systems. IOR is developed at the Lawrence Livermore National Laboratory (LLNL). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.3.0Block Size: 4MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargegcp-c2-standard-16n2-standard-16n2d-standard-16306090120150SE +/- 0.51, N = 3SE +/- 0.04, N = 3SE +/- 0.34, N = 9SE +/- 0.33, N = 9SE +/- 0.28, N = 9141.89125.2015.0414.7814.63MIN: 110.29 / MAX: 421.74MIN: 80.73 / MAX: 362.63MIN: 11.21 / MAX: 261.75MIN: 11.22 / MAX: 246.511. (CC) gcc options: -O2 -lm -pthread -lmpi

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.3.0Block Size: 2MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargegcp-c2-standard-16n2-standard-16n2d-standard-16306090120150SE +/- 0.63, N = 3SE +/- 1.21, N = 3SE +/- 0.50, N = 12SE +/- 0.48, N = 12SE +/- 0.58, N = 12154.17123.9618.9218.7017.46MIN: 121.75 / MAX: 385.23MIN: 95.52 / MAX: 306.52MIN: 10.13 / MAX: 339.46MIN: 10.23 / MAX: 338.95MIN: 10.26 / MAX: 356.521. (CC) gcc options: -O2 -lm -pthread -lmpi

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2d-standard-16n2-standard-16gcp-c2-standard-161428425670SE +/- 0.16, N = 15SE +/- 0.15, N = 1562605551. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16n2d-standard-16gcp-c2-standard-16306090120150SE +/- 0.33, N = 3SE +/- 0.31, N = 15SE +/- 0.36, N = 15SE +/- 0.33, N = 15131.0128.015.114.914.71. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16gcp-c2-standard-16n2d-standard-161428425670SE +/- 0.67, N = 3SE +/- 6.14, N = 12SE +/- 6.10, N = 126260141431. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16gcp-c2-standard-16n2d-standard-16306090120150SE +/- 1.20, N = 3SE +/- 12.49, N = 12SE +/- 12.42, N = 12SE +/- 0.00, N = 3131.0128.034.934.611.91. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16gcp-c2-standard-16n2d-standard-166001200180024003000SE +/- 3.18, N = 3SE +/- 2.08, N = 3SE +/- 1.00, N = 3SE +/- 3.62, N = 14299224583043021711. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16gcp-c2-standard-16n2d-standard-163691215SE +/- 0.000, N = 3SE +/- 0.008, N = 3SE +/- 0.004, N = 3SE +/- 0.000, N = 3SE +/- 0.015, N = 1411.7009.8461.2311.2240.6991. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16gcp-c2-standard-16n2d-standard-161428425670SE +/- 0.16, N = 156260464651. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16gcp-c2-standard-16n2d-standard-16306090120150SE +/- 0.33, N = 3SE +/- 0.20, N = 3SE +/- 0.03, N = 3SE +/- 0.27, N = 15131.0128.099.799.514.51. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16gcp-c2-standard-16n2d-standard-161428425670SE +/- 2.47, N = 156261404051. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directoryaws-c5.4xlargeaws-m5.4xlargen2-standard-16gcp-c2-standard-16n2d-standard-16306090120150SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 5.02, N = 15131.0129.086.486.216.01. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

SQLite

This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.30.1Threads / Copies: 1gcp-c2-standard-16n2-standard-16aws-c5.4xlargen2d-standard-16aws-m5.4xlarge20406080100SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.40, N = 3SE +/- 0.14, N = 3SE +/- 7.38, N = 1221.8325.6233.4333.6592.541. (CC) gcc options: -O2 -lm -ldl -lpthread

106 Results Shown

Flexible IO Tester:
  Rand Read - Linux AIO - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
Dbench
Stress-NG:
  NUMA
  Atomic
RAMspeed SMP:
  Scale - Floating Point
  Add - Floating Point
  Triad - Floating Point
IOR:
  16MB - Default Test Directory
  32MB - Default Test Directory
  64MB - Default Test Directory
  8MB - Default Test Directory
RAMspeed SMP:
  Average - Floating Point
  Scale - Integer
Redis
RAMspeed SMP:
  Triad - Integer
  Average - Integer
  Copy - Integer
  Add - Integer
  Copy - Floating Point
Flexible IO Tester:
  Seq Write - Linux AIO - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
Stress-NG
Redis
pmbench:
  8 - 80% Reads 20% Writes
  4 - 80% Reads 20% Writes
Redis
Stress-NG
Compile Bench
Redis:
  GET
  SADD
pmbench:
  8 - 100% Writes
  4 - 50%
Stress-NG
Sockperf
pmbench:
  2 - 50%
  16 - 50%
Stress-NG
Hierarchical INTegration
Multichase Pointer Chaser
pmbench
Stress-NG
pmbench:
  1 - 80% Reads 20% Writes
  1 - 50%
OSBench
Multichase Pointer Chaser:
  1GB Array, 256 Byte Stride
  1GB Array, 256 Byte Stride, 2 Threads
OSBench
Multichase Pointer Chaser
OpenSSL
OSBench
Stress-NG:
  Socket Activity
  MEMFD
  Crypto
  Context Switching
Multichase Pointer Chaser
Stress-NG
Coremark
SQLite Speedtest
pmbench
Stress-NG
pmbench:
  4 - 100% Reads
  8 - 100% Reads
  16 - 100% Reads
Stress-NG
Timed Apache Compilation
x264
7-Zip Compression
Stress-NG
Timed Linux Kernel Compilation
Stress-NG
Flexible IO Tester:
  Seq Read - Linux AIO - No - Yes - 4KB - Default Test Directory:
    MB/s
    IOPS
Stress-NG
IOR:
  256MB - Default Test Directory
  512MB - Default Test Directory
  1024MB - Default Test Directory
Stress-NG:
  RdRand
  CPU Cache
  Forking
OSBench:
  Create Processes
  Create Threads
Sockperf:
  Latency Under Load
  Latency Ping Pong
pmbench:
  16 - 80% Reads 20% Writes
  2 - 80% Reads 20% Writes
  4 - 100% Writes
  2 - 100% Writes
  1 - 100% Writes
  1 - 100% Reads
  8 - 50%
Compile Bench:
  Read Compiled Tree
  Initial Create
IOR:
  4MB - Default Test Directory
  2MB - Default Test Directory
Flexible IO Tester:
  Seq Write - Linux AIO - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
  Seq Read - Linux AIO - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
  Rand Write - Linux AIO - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
  Rand Write - Linux AIO - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
  Rand Read - Linux AIO - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
SQLite