g-32cpu-118mem-4v100-3ssd

g-32cpu-118mem-4v100-3ssd

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2102140-HA-G32CPU11883
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
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
g-32cpu-118mem-4v100-3ssd
February 12 2021
  14 Hours, 52 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

g-32cpu-118mem-4v100-3ssd

Processor: Intel Xeon (16 Cores / 32 Threads), Motherboard: Google Compute Engine n1-standard-32, Memory: 118GB, Disk: 3 x 403GB nvme_card + 137GB PersistentDisk, Graphics: Tesla V100-SXM2-16GB

OS: Ubuntu 20.04, Kernel: 5.4.0-1036-gcp (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.9, Display Driver: NVIDIA, OpenCL: OpenCL 1.2 CUDA 11.2.109, Vulkan: 1.2.155, Compiler: GCC 9.3.0 + CUDA 10.1, File-System: ext4, System Layer: KVM

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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
Disk Notes: NONE / relatime,rw,stripe=384 / raid0 nvme0n3[2] nvme0n2[1] nvme0n1[0] Block Size: 4096
Processor Notes: CPU Microcode: 0x1
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: Not affected + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT Host state unknown + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

g-32cpu-118mem-4v100-3ssdOpenBenchmarking.orgPhoronix Test SuiteIntel Xeon (16 Cores / 32 Threads)Google Compute Engine n1-standard-32118GB3 x 403GB nvme_card + 137GB PersistentDiskTesla V100-SXM2-16GBUbuntu 20.045.4.0-1036-gcp (x86_64)GNOME Shell 3.36.4X Server 1.20.9NVIDIAOpenCL 1.2 CUDA 11.2.1091.2.155GCC 9.3.0 + CUDA 10.1ext4KVMProcessorMotherboardMemoryDiskGraphicsOSKernelDesktopDisplay ServerDisplay DriverOpenCLVulkanCompilerFile-SystemSystem LayerG-32cpu-118mem-4v100-3ssd BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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 - NONE / relatime,rw,stripe=384 / raid0 nvme0n3[2] nvme0n2[1] nvme0n1[0] Block Size: 4096 - CPU Microcode: 0x1- Python 3.8.5- itlb_multihit: Not affected + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT Host state unknown + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

g-32cpu-118mem-4v100-3ssdior: 1024MB - Default Test Directorydbench: 12 Clientsior: 512MB - Default Test Directoryior: 64MB - Default Test Directorysqlite: 128dbench: 1 Clientsior: 256MB - Default Test Directorysqlite: 64tinymembench: Standard Memsettinymembench: Standard Memcpysqlite: 32fs-mark: 5000 Files, 1MB Size, 4 Threadsior: 32MB - Default Test Directorysqlite: 8blender: Barbershop - CPU-Onlyasmfish: 1024 Hash Memory, 26 Depthfio: Rand Write - Linux AIO - No - Yes - 2MB - Default Test Directoryfio: Rand Write - Linux AIO - No - Yes - 2MB - Default Test Directoryfahbench: cachebench: Write Cachecachebench: Read Cachesqlite: 1kvazaar: Bosphorus 4K - Slowkvazaar: Bosphorus 4K - Mediumstockfish: Total Timenamd: ATPase Simulation - 327,506 Atomsramspeed: Add - Floating Pointramspeed: Scale - Floating Pointramspeed: Copy - Floating Pointramspeed: Average - Floating Pointramspeed: Triad - Floating Pointramspeed: Add - Integerramspeed: Copy - Integerramspeed: Average - Integerramspeed: Scale - Integerramspeed: Triad - Integerbuild-linux-kernel: Time To Compilencnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetpostmark: Disk Transaction Performancecompress-7zip: Compress Speed Testior: 16MB - Default Test Directoryplaidml: No - Inference - DenseNet 201 - OpenCLpovray: Trace Timefs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizekvazaar: Bosphorus 4K - Very Fastx265: Bosphorus 4Khashcat: MD5ior: 8MB - Default Test Directoryfio: Seq Read - Linux AIO - No - Yes - 4KB - Default Test Directoryfio: Seq Read - Linux AIO - No - Yes - 4KB - Default Test Directoryfio: Rand Read - Linux AIO - No - Yes - 4KB - Default Test Directoryfio: Rand Read - Linux AIO - No - Yes - 4KB - Default Test Directoryfio: Rand Read - Linux AIO - No - Yes - 2MB - Default Test Directoryfio: Rand Read - 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: Seq Write - Linux AIO - No - Yes - 2MB - Default Test Directoryfio: Seq Write - Linux AIO - No - Yes - 2MB - Default Test Directoryfio: Seq Write - Linux AIO - No - Yes - 4KB - Default Test Directoryfio: Seq 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 - 4KB - Default Test Directorykvazaar: Bosphorus 1080p - Slowkvazaar: Bosphorus 1080p - Mediumt-test1: 1rodinia: OpenMP LavaMDkvazaar: Bosphorus 4K - Ultra Fastmbw: Memory Copy - 1024 MiBmbw: Memory Copy, Fixed Block Size - 1024 MiBopenssl: RSA 4096-bit Performancestream: Copyplaidml: No - Inference - IMDB LSTM - OpenCLior: 4MB - Default Test Directoryrodinia: OpenMP CFD Solverneatbench: GPUclpeak: Integer Compute INTplaidml: Yes - Inference - Mobilenet - OpenCLhashcat: SHA-512x265: Bosphorus 1080phashcat: SHA1hashcat: TrueCrypt RIPEMD160 + XTSkvazaar: Bosphorus 1080p - Very Fastfs-mark: 1000 Files, 1MB Sizeplaidml: No - Inference - Mobilenet - OpenCLior: 2MB - Default Test Directoryrodinia: OpenCL Particle Filterviennacl: OpenCL LU Factorizationsysbench: CPUhashcat: 7-Zipt-test1: 2financebench: Black-Scholes OpenCLarrayfire: Conjugate Gradient OpenCLkvazaar: Bosphorus 1080p - Ultra Fastx264: H.264 Video Encodingclpeak: Double-Precision Doublectx-clock: Context Switch Timecl-mem: Copycl-mem: Writecl-mem: Readclpeak: Global Memory Bandwidthclpeak: Single-Precision Floatfs-mark: 1000 Files, 1MB Size, No Sync/FSyncstream: Addstream: Triadstream: Scaleg-32cpu-118mem-4v100-3ssd767.32314.490648.99400.62867.66869.3050659.87659.49813248.36248.9528.068155.5490.22347.608779.43346360255511109250.966021803.5542432639.300322116.9035.375.49312482161.4396120951.2119048.5117817.2621061.0826355.4723529.4717807.5722226.0323431.2124124.6365.6033.3820.4928.6123.359.4311.5632.8616.653.278.966.576.866.247.1720.89412165536529.27246.7241.43493.314.0615.55140123775000439.141446675662063338051050210710512108577116122666788518900073820.2820.8626.71423.90425.474729.0464793.5612166.089906.1694.93430.8415.62457.315381.473398.66960796666745.0971223333333268976749.6283.83080.79320.232.38346.955726608.859535956339.2981.2242.32589.26100.897771.48763281.9746.0789.5767.6115671.471446.873543.373526.664724.7OpenBenchmarking.org

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: 1024MB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd170340510680850SE +/- 1.72, N = 3767.32MIN: 685.66 / MAX: 800.231. (CC) gcc options: -O2 -lm -pthread -lmpi

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 Clientsg-32cpu-118mem-4v100-3ssd70140210280350SE +/- 4.29, N = 9314.491. (CC) gcc options: -lpopt -O2

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: 512MB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd140280420560700SE +/- 3.29, N = 3648.99MIN: 444.72 / MAX: 722.621. (CC) gcc options: -O2 -lm -pthread -lmpi

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.3.0Block Size: 64MB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd90180270360450SE +/- 5.71, N = 9400.62MIN: 137.16 / MAX: 780.441. (CC) gcc options: -O2 -lm -pthread -lmpi

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: 128g-32cpu-118mem-4v100-3ssd2004006008001000SE +/- 2.72, N = 3867.671. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

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 4.01 Clientsg-32cpu-118mem-4v100-3ssd1530456075SE +/- 0.37, N = 369.311. (CC) gcc options: -lpopt -O2

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 Directoryg-32cpu-118mem-4v100-3ssd140280420560700SE +/- 1.85, N = 3659.87MIN: 529.7 / MAX: 736.391. (CC) gcc options: -O2 -lm -pthread -lmpi

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: 64g-32cpu-118mem-4v100-3ssd140280420560700SE +/- 4.80, N = 3659.501. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

Tinymembench

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

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memsetg-32cpu-118mem-4v100-3ssd3K6K9K12K15KSE +/- 119.19, N = 513248.31. (CC) gcc options: -O2 -lm

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memcpyg-32cpu-118mem-4v100-3ssd13002600390052006500SE +/- 66.88, N = 56248.91. (CC) gcc options: -O2 -lm

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: 32g-32cpu-118mem-4v100-3ssd110220330440550SE +/- 3.04, N = 3528.071. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 5000 Files, 1MB Size, 4 Threadsg-32cpu-118mem-4v100-3ssd306090120150SE +/- 3.57, N = 12155.51. (CC) gcc options: -static

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: 32MB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd110220330440550SE +/- 5.16, N = 12490.22MIN: 125.91 / MAX: 870.331. (CC) gcc options: -O2 -lm -pthread -lmpi

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: 8g-32cpu-118mem-4v100-3ssd80160240320400SE +/- 1.90, N = 3347.611. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: CPU-Onlyg-32cpu-118mem-4v100-3ssd2004006008001000779.43

asmFish

This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depthg-32cpu-118mem-4v100-3ssd7M14M21M28M35MSE +/- 121185.38, N = 334636025

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 Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd120240360480600SE +/- 13.21, N = 155511. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Directoryg-32cpu-118mem-4v100-3ssd2004006008001000SE +/- 26.33, N = 1511091. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

FAHBench

FAHBench is a Folding@Home benchmark on the GPU. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2g-32cpu-118mem-4v100-3ssd50100150200250SE +/- 0.53, N = 3250.97

CacheBench

This is a performance test of CacheBench, which is part of LLCbench. CacheBench is designed to test the memory and cache bandwidth performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchWrite Cacheg-32cpu-118mem-4v100-3ssd5K10K15K20K25KSE +/- 101.96, N = 321803.55MIN: 19538.94 / MAX: 23477.621. (CC) gcc options: -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchRead Cacheg-32cpu-118mem-4v100-3ssd6001200180024003000SE +/- 0.62, N = 32639.30MIN: 2602.47 / MAX: 2654.361. (CC) gcc options: -lrt

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: 1g-32cpu-118mem-4v100-3ssd306090120150SE +/- 0.13, N = 3116.901. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Slowg-32cpu-118mem-4v100-3ssd1.20832.41663.62494.83326.0415SE +/- 0.00, N = 35.371. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Mediumg-32cpu-118mem-4v100-3ssd1.23532.47063.70594.94126.1765SE +/- 0.00, N = 35.491. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Stockfish

This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total Timeg-32cpu-118mem-4v100-3ssd7M14M21M28M35MSE +/- 112367.56, N = 3312482161. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 Atomsg-32cpu-118mem-4v100-3ssd0.32390.64780.97171.29561.6195SE +/- 0.00253, N = 31.43961

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: Add - Benchmark: Floating Pointg-32cpu-118mem-4v100-3ssd4K8K12K16K20KSE +/- 20.27, N = 320951.211. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating Pointg-32cpu-118mem-4v100-3ssd4K8K12K16K20KSE +/- 15.51, N = 319048.511. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating Pointg-32cpu-118mem-4v100-3ssd4K8K12K16K20KSE +/- 22.51, N = 317817.261. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating Pointg-32cpu-118mem-4v100-3ssd5K10K15K20K25KSE +/- 9.59, N = 321061.081. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating Pointg-32cpu-118mem-4v100-3ssd6K12K18K24K30KSE +/- 33.89, N = 326355.471. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Integerg-32cpu-118mem-4v100-3ssd5K10K15K20K25KSE +/- 29.89, N = 323529.471. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Integerg-32cpu-118mem-4v100-3ssd4K8K12K16K20KSE +/- 21.09, N = 317807.571. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Integerg-32cpu-118mem-4v100-3ssd5K10K15K20K25KSE +/- 25.25, N = 322226.031. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Integerg-32cpu-118mem-4v100-3ssd5K10K15K20K25KSE +/- 28.10, N = 323431.211. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Integerg-32cpu-118mem-4v100-3ssd5K10K15K20K25KSE +/- 5.05, N = 324124.631. (CC) gcc options: -O3 -march=native

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 4.18Time To Compileg-32cpu-118mem-4v100-3ssd1530456075SE +/- 0.86, N = 365.60

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400mg-32cpu-118mem-4v100-3ssd816243240SE +/- 0.03, N = 333.38MIN: 32.11 / MAX: 46.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: squeezenet_ssdg-32cpu-118mem-4v100-3ssd510152025SE +/- 0.08, N = 320.49MIN: 19.52 / MAX: 21.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tinyg-32cpu-118mem-4v100-3ssd714212835SE +/- 0.01, N = 328.61MIN: 27.53 / MAX: 42.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet50g-32cpu-118mem-4v100-3ssd612182430SE +/- 0.06, N = 323.35MIN: 22.41 / MAX: 25.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnetg-32cpu-118mem-4v100-3ssd3691215SE +/- 0.30, N = 39.43MIN: 8.45 / MAX: 10.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet18g-32cpu-118mem-4v100-3ssd3691215SE +/- 0.03, N = 311.56MIN: 10.85 / MAX: 14.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg16g-32cpu-118mem-4v100-3ssd816243240SE +/- 0.02, N = 332.86MIN: 31.99 / MAX: 34.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenetg-32cpu-118mem-4v100-3ssd48121620SE +/- 0.18, N = 316.65MIN: 15.54 / MAX: 29.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazefaceg-32cpu-118mem-4v100-3ssd0.73581.47162.20742.94323.679SE +/- 0.01, N = 33.27MIN: 3.01 / MAX: 3.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b0g-32cpu-118mem-4v100-3ssd3691215SE +/- 0.06, N = 38.96MIN: 8.34 / MAX: 9.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnetg-32cpu-118mem-4v100-3ssd246810SE +/- 0.03, N = 36.57MIN: 6.04 / MAX: 7.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v2g-32cpu-118mem-4v100-3ssd246810SE +/- 0.01, N = 36.86MIN: 6.35 / MAX: 7.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3g-32cpu-118mem-4v100-3ssd246810SE +/- 0.03, N = 36.24MIN: 5.77 / MAX: 7.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2g-32cpu-118mem-4v100-3ssd246810SE +/- 0.06, N = 37.17MIN: 6.57 / MAX: 8.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mobilenetg-32cpu-118mem-4v100-3ssd510152025SE +/- 0.19, N = 320.89MIN: 19.65 / MAX: 23.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PostMark

This is a test of NetApp's PostMark benchmark designed to simulate small-file testing similar to the tasks endured by web and mail servers. This test profile will set PostMark to perform 25,000 transactions with 500 files simultaneously with the file sizes ranging between 5 and 512 kilobytes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostMark 1.51Disk Transaction Performanceg-32cpu-118mem-4v100-3ssd9001800270036004500SE +/- 22.67, N = 341211. (CC) gcc options: -O3

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 Testg-32cpu-118mem-4v100-3ssd14K28K42K56K70KSE +/- 215.44, N = 3655361. (CXX) g++ options: -pipe -lpthread

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 Directoryg-32cpu-118mem-4v100-3ssd110220330440550SE +/- 1.49, N = 3529.27MIN: 207.4 / MAX: 878.071. (CC) gcc options: -O2 -lm -pthread -lmpi

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCLg-32cpu-118mem-4v100-3ssd50100150200250SE +/- 0.09, N = 3246.72

POV-Ray

This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Timeg-32cpu-118mem-4v100-3ssd918273645SE +/- 0.12, N = 341.431. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSM -lICE -lX11 -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB Sizeg-32cpu-118mem-4v100-3ssd20406080100SE +/- 0.26, N = 393.31. (CC) gcc options: -static

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very Fastg-32cpu-118mem-4v100-3ssd48121620SE +/- 0.01, N = 314.061. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

x265

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

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4Kg-32cpu-118mem-4v100-3ssd48121620SE +/- 0.08, N = 315.551. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD5g-32cpu-118mem-4v100-3ssd30000M60000M90000M120000M150000MSE +/- 21695480029.52, N = 16140123775000

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: 8MB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd100200300400500SE +/- 3.55, N = 3439.14MIN: 200.18 / MAX: 654.061. (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 Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd30K60K90K120K150KSE +/- 1333.33, N = 31446671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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: 4KB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd120240360480600SE +/- 4.91, N = 35661. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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: 4KB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd40K80K120K160K200KSE +/- 333.33, N = 32063331. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Directoryg-32cpu-118mem-4v100-3ssd2004006008001000SE +/- 1.20, N = 38051. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Directoryg-32cpu-118mem-4v100-3ssd2004006008001000SE +/- 0.88, N = 310501. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Directoryg-32cpu-118mem-4v100-3ssd5001000150020002500SE +/- 1.73, N = 321071. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Directoryg-32cpu-118mem-4v100-3ssd200400600800100010511. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Directoryg-32cpu-118mem-4v100-3ssd500100015002000250021081. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd120240360480600SE +/- 4.73, N = 35771. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Directoryg-32cpu-118mem-4v100-3ssd2004006008001000SE +/- 9.85, N = 311611. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd50K100K150K200K250KSE +/- 1666.67, N = 32266671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Directoryg-32cpu-118mem-4v100-3ssd2004006008001000SE +/- 7.02, N = 38851. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Directoryg-32cpu-118mem-4v100-3ssd40K80K120K160K200KSE +/- 1000.00, N = 31890001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -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 Directoryg-32cpu-118mem-4v100-3ssd160320480640800SE +/- 4.67, N = 37381. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Slowg-32cpu-118mem-4v100-3ssd510152025SE +/- 0.02, N = 320.281. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Mediumg-32cpu-118mem-4v100-3ssd510152025SE +/- 0.03, N = 320.861. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

t-test1

This is a test of t-test1 for basic memory allocator benchmarks. Note this test profile is currently very basic and the overall time does include the warmup time of the custom t-test1 compilation. Improvements welcome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 1g-32cpu-118mem-4v100-3ssd612182430SE +/- 0.11, N = 326.711. (CC) gcc options: -pthread

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDg-32cpu-118mem-4v100-3ssd612182430SE +/- 0.10, N = 323.901. (CXX) g++ options: -O2 -lOpenCL

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra Fastg-32cpu-118mem-4v100-3ssd612182430SE +/- 0.07, N = 325.471. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 1024 MiBg-32cpu-118mem-4v100-3ssd10002000300040005000SE +/- 4.19, N = 34729.051. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiBg-32cpu-118mem-4v100-3ssd10002000300040005000SE +/- 4.00, N = 34793.561. (CC) gcc options: -O3 -march=native

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 Performanceg-32cpu-118mem-4v100-3ssd5001000150020002500SE +/- 9.63, N = 32166.01. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Stream

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

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Copyg-32cpu-118mem-4v100-3ssd20K40K60K80K100KSE +/- 57.93, N = 589906.11. (CC) gcc options: -O3 -march=native -fopenmp

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLg-32cpu-118mem-4v100-3ssd150300450600750SE +/- 0.92, N = 3694.93

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 Directoryg-32cpu-118mem-4v100-3ssd90180270360450SE +/- 3.79, N = 3430.84MIN: 132.24 / MAX: 655.181. (CC) gcc options: -O2 -lm -pthread -lmpi

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD Solverg-32cpu-118mem-4v100-3ssd48121620SE +/- 0.02, N = 315.621. (CXX) g++ options: -O2 -lOpenCL

NeatBench

NeatBench is a benchmark of the cross-platform Neat Video software on the CPU and optional GPU (OpenCL / CUDA) support. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: GPUg-32cpu-118mem-4v100-3ssd1326395265SE +/- 0.23, N = 357.3

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTg-32cpu-118mem-4v100-3ssd3K6K9K12K15KSE +/- 160.92, N = 1515381.471. (CXX) g++ options: -O3 -rdynamic -lOpenCL

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLg-32cpu-118mem-4v100-3ssd7001400210028003500SE +/- 2.19, N = 33398.66

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-512g-32cpu-118mem-4v100-3ssd2000M4000M6000M8000M10000MSE +/- 712585.28, N = 39607966667

x265

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

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pg-32cpu-118mem-4v100-3ssd1020304050SE +/- 0.20, N = 345.091. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA1g-32cpu-118mem-4v100-3ssd15000M30000M45000M60000M75000MSE +/- 1966666.67, N = 371223333333

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTSg-32cpu-118mem-4v100-3ssd600K1200K1800K2400K3000KSE +/- 240.37, N = 32689767

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Very Fastg-32cpu-118mem-4v100-3ssd1122334455SE +/- 0.02, N = 349.621. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Sizeg-32cpu-118mem-4v100-3ssd20406080100SE +/- 0.47, N = 383.81. (CC) gcc options: -static

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLg-32cpu-118mem-4v100-3ssd7001400210028003500SE +/- 23.49, N = 33080.79

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: 2MB - Disk Target: Default Test Directoryg-32cpu-118mem-4v100-3ssd70140210280350SE +/- 3.89, N = 3320.23MIN: 108.66 / MAX: 535.031. (CC) gcc options: -O2 -lm -pthread -lmpi

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL Particle Filterg-32cpu-118mem-4v100-3ssd0.53621.07241.60862.14482.681SE +/- 0.032, N = 142.3831. (CXX) g++ options: -O2 -lOpenCL

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile uses ViennaCL OpenCL support and runs the included computational benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterViennaCL 1.4.2OpenCL LU Factorizationg-32cpu-118mem-4v100-3ssd1122334455SE +/- 0.19, N = 346.961. (CXX) g++ options: -rdynamic -lOpenCL

Sysbench

This is a benchmark of Sysbench with CPU and memory sub-tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPUg-32cpu-118mem-4v100-3ssd6K12K18K24K30KSE +/- 128.90, N = 326608.861. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=haswell -rdynamic -ldl -laio -lm

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-Zipg-32cpu-118mem-4v100-3ssd800K1600K2400K3200K4000KSE +/- 4884.10, N = 33595633

t-test1

This is a test of t-test1 for basic memory allocator benchmarks. Note this test profile is currently very basic and the overall time does include the warmup time of the custom t-test1 compilation. Improvements welcome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 2g-32cpu-118mem-4v100-3ssd3691215SE +/- 0.049, N = 39.2981. (CC) gcc options: -pthread

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Black-Scholes OpenCLg-32cpu-118mem-4v100-3ssd0.27540.55080.82621.10161.377SE +/- 0.008, N = 131.2241. (CXX) g++ options: -O3 -march=native -fopenmp

ArrayFire

ArrayFire is an GPU and CPU numeric processing library, this test uses the built-in CPU and OpenCL ArrayFire benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCLg-32cpu-118mem-4v100-3ssd0.52311.04621.56932.09242.6155SE +/- 0.020, N = 32.3251. (CXX) g++ options: -rdynamic

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Ultra Fastg-32cpu-118mem-4v100-3ssd20406080100SE +/- 0.06, N = 389.261. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 2018-09-25H.264 Video Encodingg-32cpu-118mem-4v100-3ssd20406080100SE +/- 0.15, N = 3100.891. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision Doubleg-32cpu-118mem-4v100-3ssd17003400510068008500SE +/- 85.36, N = 37771.481. (CXX) g++ options: -O3 -rdynamic -lOpenCL

ctx_clock

Ctx_clock is a simple test program to measure the context switch time in clock cycles. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch Timeg-32cpu-118mem-4v100-3ssd160320480640800763

cl-mem

A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Copyg-32cpu-118mem-4v100-3ssd60120180240300SE +/- 0.03, N = 3281.91. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Writeg-32cpu-118mem-4v100-3ssd160320480640800SE +/- 2.32, N = 3746.01. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Readg-32cpu-118mem-4v100-3ssd2004006008001000SE +/- 0.09, N = 3789.51. (CC) gcc options: -O2 -flto -lOpenCL

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory Bandwidthg-32cpu-118mem-4v100-3ssd170340510680850SE +/- 0.03, N = 3767.611. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision Floatg-32cpu-118mem-4v100-3ssd3K6K9K12K15KSE +/- 0.73, N = 315671.471. (CXX) g++ options: -O3 -rdynamic -lOpenCL

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Size, No Sync/FSyncg-32cpu-118mem-4v100-3ssd30060090012001500SE +/- 8.34, N = 31446.81. (CC) gcc options: -static

Stream

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

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Addg-32cpu-118mem-4v100-3ssd16K32K48K64K80KSE +/- 20.58, N = 573543.31. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Triadg-32cpu-118mem-4v100-3ssd16K32K48K64K80KSE +/- 62.01, N = 573526.61. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Scaleg-32cpu-118mem-4v100-3ssd14K28K42K56K70KSE +/- 62.99, N = 564724.71. (CC) gcc options: -O3 -march=native -fopenmp

119 Results Shown

IOR
Dbench
IOR:
  512MB - Default Test Directory
  64MB - Default Test Directory
SQLite
Dbench
IOR
SQLite
Tinymembench:
  Standard Memset
  Standard Memcpy
SQLite
FS-Mark
IOR
SQLite
Blender
asmFish
Flexible IO Tester:
  Rand Write - Linux AIO - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
FAHBench
CacheBench:
  Write Cache
  Read Cache
SQLite
Kvazaar:
  Bosphorus 4K - Slow
  Bosphorus 4K - Medium
Stockfish
NAMD
RAMspeed SMP:
  Add - Floating Point
  Scale - Floating Point
  Copy - Floating Point
  Average - Floating Point
  Triad - Floating Point
  Add - Integer
  Copy - Integer
  Average - Integer
  Scale - Integer
  Triad - Integer
Timed Linux Kernel Compilation
NCNN:
  Vulkan GPU - regnety_400m
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - resnet50
  Vulkan GPU - alexnet
  Vulkan GPU - resnet18
  Vulkan GPU - vgg16
  Vulkan GPU - googlenet
  Vulkan GPU - blazeface
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - mnasnet
  Vulkan GPU - shufflenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - mobilenet
PostMark
7-Zip Compression
IOR
PlaidML
POV-Ray
FS-Mark
Kvazaar
x265
Hashcat
IOR
Flexible IO Tester:
  Seq Read - Linux AIO - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
  Rand Read - Linux AIO - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
  Rand Read - Linux AIO - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
  Seq Read - Linux AIO - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
  Seq Write - Linux AIO - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
  Seq Write - Linux AIO - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
  Rand Write - Linux AIO - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
Kvazaar:
  Bosphorus 1080p - Slow
  Bosphorus 1080p - Medium
t-test1
Rodinia
Kvazaar
MBW:
  Memory Copy - 1024 MiB
  Memory Copy, Fixed Block Size - 1024 MiB
OpenSSL
Stream
PlaidML
IOR
Rodinia
NeatBench
clpeak
PlaidML
Hashcat
x265
Hashcat:
  SHA1
  TrueCrypt RIPEMD160 + XTS
Kvazaar
FS-Mark
PlaidML
IOR
Rodinia
ViennaCL
Sysbench
Hashcat
t-test1
FinanceBench
ArrayFire
Kvazaar
x264
clpeak
ctx_clock
cl-mem:
  Copy
  Write
  Read
clpeak:
  Global Memory Bandwidth
  Single-Precision Float
FS-Mark
Stream:
  Add
  Triad
  Scale

g-32cpu-118mem-4v100-3ssd

Processor: Intel Xeon (16 Cores / 32 Threads), Motherboard: Google Compute Engine n1-standard-32, Memory: 118GB, Disk: 3 x 403GB nvme_card + 137GB PersistentDisk, Graphics: Tesla V100-SXM2-16GB

OS: Ubuntu 20.04, Kernel: 5.4.0-1036-gcp (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.9, Display Driver: NVIDIA, OpenCL: OpenCL 1.2 CUDA 11.2.109, Vulkan: 1.2.155, Compiler: GCC 9.3.0 + CUDA 10.1, File-System: ext4, System Layer: KVM

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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
Disk Notes: NONE / relatime,rw,stripe=384 / raid0 nvme0n3[2] nvme0n2[1] nvme0n1[0] Block Size: 4096
Processor Notes: CPU Microcode: 0x1
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: Not affected + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT Host state unknown + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 12 February 2021 23:21 by user sniklaus.