Xeong Linux

2 x Intel Xeon Gold 6138 testing with a TYAN S7106 (V2.00.B20 BIOS) and llvmpipe 93GB on Ubuntu 18.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1910133-AS-XEONGLINU92
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Samsung SSD 860 - 2 x Intel Xeon Gold 6138
October 13 2019
  5 Hours, 49 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):

Samsung SSD 860 - 2 x Intel Xeon Gold 6138

Processor: 2 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads), Motherboard: TYAN S7106 (V2.00.B20 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 96256MB, Disk: 500GB Samsung SSD 860, Graphics: llvmpipe 93GB, Monitor: VE228, Network: 2 x Intel I210 + 2 x QLogic cLOM8214 1/10GbE

OS: Ubuntu 18.04, Kernel: 5.0.0-31-generic (x86_64), Desktop: GNOME Shell 3.28.4, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 3.3 Mesa 19.0.8 (LLVM 8.0 256 bits), Compiler: GCC 7.4.0, File-System: ext4, Screen Resolution: 1920x1080

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++ --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 Notes: MQ-DEADLINE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: intel_pstate powersave
Security Notes: l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled

Xeong LinuxOpenBenchmarking.orgPhoronix Test Suite2 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads)TYAN S7106 (V2.00.B20 BIOS)Intel Sky Lake-E DMI3 Registers96256MB500GB Samsung SSD 860llvmpipe 93GBVE2282 x Intel I210 + 2 x QLogic cLOM8214 1/10GbEUbuntu 18.045.0.0-31-generic (x86_64)GNOME Shell 3.28.4X Server 1.20.4modesetting 1.20.43.3 Mesa 19.0.8 (LLVM 8.0 256 bits)GCC 7.4.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionXeong Linux BenchmarksSystem Logs- --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++ --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 - MQ-DEADLINE / errors=remount-ro,relatime,rw- Scaling Governor: intel_pstate powersave- l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled

Xeong Linuxlibgav1: Chimera 1080p 10-bitmkl-dnn: Convolution Batch conv_all - bf16bf16bf16mkl-dnn: Convolution Batch conv_all - u8s8f32mkl-dnn: Convolution Batch conv_all - f32mkl-dnn: Deconvolution Batch deconv_all - bf16bf16bf16mkl-dnn: Deconvolution Batch deconv_all - f32libgav1: Chimera 1080pospray: San Miguel - Path Tracerlibgav1: Summer Nature 4Kluxcorerender: DLSCluxcorerender: Rainbow Colors and Prismmkl-dnn: Convolution Batch conv_googlenet_v3 - bf16bf16bf16mkl-dnn: Convolution Batch conv_googlenet_v3 - u8s8f32mkl-dnn: Convolution Batch conv_googlenet_v3 - f32ospray: San Miguel - SciVisospray: XFrog Forest - SciVislibgav1: Summer Nature 1080pmkl-dnn: Deconvolution Batch deconv_1d - bf16bf16bf16mkl-dnn: Deconvolution Batch deconv_1d - u8s8f32sqlite-speedtest: Timed Time - Size 1,000ospray: XFrog Forest - Path Tracermkl-dnn: Convolution Batch conv_3d - u8s8f32mkl-dnn: IP Batch All - bf16bf16bf16mkl-dnn: IP Batch All - f32mkl-dnn: IP Batch All - u8s8f32mkl-dnn: Convolution Batch conv_3d - bf16bf16bf16mkl-dnn: Convolution Batch conv_3d - f32mkl-dnn: Recurrent Neural Network Training - f32embree: Pathtracer - Asian Dragon Objospray: NASA Streamlines - SciVisembree: Pathtracer ISPC - Asian Dragon Objtungsten: Water Caustictungsten: Non-Exponentialtungsten: Volumetric Causticospray: Magnetic Reconnection - SciVismkl-dnn: Deconvolution Batch deconv_3d - u8s8f32ospray: NASA Streamlines - Path Tracerembree: Pathtracer - Crownmt-dgemm: Sustained Floating-Point Ratemkl-dnn: Deconvolution Batch deconv_1d - f32mkl-dnn: Convolution Batch conv_alexnet - bf16bf16bf16embree: Pathtracer ISPC - Crownembree: Pathtracer - Asian Dragonopenssl: RSA 4096-bit Performancemkl-dnn: Convolution Batch conv_alexnet - u8s8f32embree: Pathtracer ISPC - Asian Dragonmkl-dnn: Convolution Batch conv_alexnet - f32mkl-dnn: IP Batch 1D - f32mkl-dnn: IP Batch 1D - bf16bf16bf16mkl-dnn: IP Batch 1D - u8s8f32tungsten: Hairn-queens: Elapsed Timeoidn: Memorialmkl-dnn: Deconvolution Batch deconv_3d - bf16bf16bf16mkl-dnn: Deconvolution Batch deconv_3d - f32ospray: Magnetic Reconnection - Path Tracerior: Read Testior: Write TestSamsung SSD 860 - 2 x Intel Xeon Gold 613811.633122.942527.50854.682759.561135.8624.853.8312.181.071.10152.6025.2740.1941.677.0436.036.5519.5465.343.894593.53150.6711.534.5813.026.27256.2030.5955.5635.8524.965.9916.4045.453937.8510.4928.7910.681.75567.9431.9733.667829.7060.3741.4087.002.584.932.1311.275.0430.037.151.96500357.97235.49OpenBenchmarking.org

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Chimera 1080p 10-bitSamsung SSD 860 - 2 x Intel Xeon Gold 61383691215SE +/- 0.05, N = 311.631. (CXX) g++ options: -O3 -lpthread

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_all - Data Type: bf16bf16bf16Samsung SSD 860 - 2 x Intel Xeon Gold 61387001400210028003500SE +/- 0.86, N = 33122.94MIN: 3098.681. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_all - Data Type: u8s8f32Samsung SSD 860 - 2 x Intel Xeon Gold 61385001000150020002500SE +/- 4.88, N = 32527.50MIN: 2501.41. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_all - Data Type: f32Samsung SSD 860 - 2 x Intel Xeon Gold 61382004006008001000SE +/- 0.86, N = 3854.68MIN: 834.931. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_all - Data Type: bf16bf16bf16Samsung SSD 860 - 2 x Intel Xeon Gold 61386001200180024003000SE +/- 1.81, N = 32759.56MIN: 2723.661. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_all - Data Type: f32Samsung SSD 860 - 2 x Intel Xeon Gold 61382004006008001000SE +/- 2.15, N = 31135.86MIN: 1115.561. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Chimera 1080pSamsung SSD 860 - 2 x Intel Xeon Gold 6138612182430SE +/- 0.16, N = 324.851. (CXX) g++ options: -O3 -lpthread

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerSamsung SSD 860 - 2 x Intel Xeon Gold 61380.86181.72362.58543.44724.309SE +/- 0.00, N = 123.83MIN: 2.74 / MAX: 3.86

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Summer Nature 4KSamsung SSD 860 - 2 x Intel Xeon Gold 61383691215SE +/- 0.03, N = 312.181. (CXX) g++ options: -O3 -lpthread

LuxCoreRender

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on the CPU as opposed to the OpenCL version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.2Scene: DLSCSamsung SSD 860 - 2 x Intel Xeon Gold 61380.24080.48160.72240.96321.204SE +/- 0.14, N = 121.07MIN: 0.57 / MAX: 1.97

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.2Scene: Rainbow Colors and PrismSamsung SSD 860 - 2 x Intel Xeon Gold 61380.24750.4950.74250.991.2375SE +/- 0.09, N = 121.10MIN: 0.51 / MAX: 1.54

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_googlenet_v3 - Data Type: bf16bf16bf16Samsung SSD 860 - 2 x Intel Xeon Gold 6138306090120150SE +/- 0.21, N = 3152.60MIN: 150.11. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32Samsung SSD 860 - 2 x Intel Xeon Gold 6138612182430SE +/- 0.04, N = 325.27MIN: 24.471. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32Samsung SSD 860 - 2 x Intel Xeon Gold 6138918273645SE +/- 0.07, N = 340.19MIN: 37.751. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisSamsung SSD 860 - 2 x Intel Xeon Gold 61381020304050SE +/- 0.00, N = 1241.67MIN: 25 / MAX: 43.48

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisSamsung SSD 860 - 2 x Intel Xeon Gold 6138246810SE +/- 0.00, N = 107.04MIN: 5.62 / MAX: 7.09

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Summer Nature 1080pSamsung SSD 860 - 2 x Intel Xeon Gold 6138816243240SE +/- 0.03, N = 336.031. (CXX) g++ options: -O3 -lpthread

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf16Samsung SSD 860 - 2 x Intel Xeon Gold 6138246810SE +/- 0.06, N = 146.55MIN: 6.271. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32Samsung SSD 860 - 2 x Intel Xeon Gold 6138510152025SE +/- 16.62, N = 1219.54MIN: 0.841. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

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 1,000Samsung SSD 860 - 2 x Intel Xeon Gold 61381530456075SE +/- 0.10, N = 365.341. (CC) gcc options: -O2 -ldl -lz -lpthread

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerSamsung SSD 860 - 2 x Intel Xeon Gold 61380.87531.75062.62593.50124.3765SE +/- 0.01, N = 33.89MIN: 3.53 / MAX: 3.92

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_3d - Data Type: u8s8f32Samsung SSD 860 - 2 x Intel Xeon Gold 613810002000300040005000SE +/- 6.67, N = 34593.53MIN: 4569.731. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch All - Data Type: bf16bf16bf16Samsung SSD 860 - 2 x Intel Xeon Gold 6138306090120150SE +/- 1.39, N = 3150.67MIN: 88.281. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch All - Data Type: f32Samsung SSD 860 - 2 x Intel Xeon Gold 61383691215SE +/- 0.01, N = 311.53MIN: 11.091. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch All - Data Type: u8s8f32Samsung SSD 860 - 2 x Intel Xeon Gold 61381.03052.0613.09154.1225.1525SE +/- 0.02, N = 34.58MIN: 4.211. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_3d - Data Type: bf16bf16bf16Samsung SSD 860 - 2 x Intel Xeon Gold 61383691215SE +/- 0.01, N = 313.02MIN: 12.621. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_3d - Data Type: f32Samsung SSD 860 - 2 x Intel Xeon Gold 6138246810SE +/- 0.04, N = 36.27MIN: 5.981. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Recurrent Neural Network Training - Data Type: f32Samsung SSD 860 - 2 x Intel Xeon Gold 613860120180240300SE +/- 3.58, N = 3256.20MIN: 237.441. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian Dragon ObjSamsung SSD 860 - 2 x Intel Xeon Gold 6138714212835SE +/- 0.11, N = 330.59MIN: 30 / MAX: 31.93

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisSamsung SSD 860 - 2 x Intel Xeon Gold 61381224364860SE +/- 0.00, N = 1555.56MIN: 21.74

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian Dragon ObjSamsung SSD 860 - 2 x Intel Xeon Gold 6138816243240SE +/- 0.02, N = 335.85MIN: 35.39 / MAX: 36.48

Tungsten Renderer

Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Water CausticSamsung SSD 860 - 2 x Intel Xeon Gold 6138612182430SE +/- 0.10, N = 324.961. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Non-ExponentialSamsung SSD 860 - 2 x Intel Xeon Gold 61381.34782.69564.04345.39126.739SE +/- 0.18, N = 155.991. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Volumetric CausticSamsung SSD 860 - 2 x Intel Xeon Gold 613848121620SE +/- 0.20, N = 516.401. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisSamsung SSD 860 - 2 x Intel Xeon Gold 61381020304050SE +/- 0.00, N = 1345.45MIN: 16.39 / MAX: 47.62

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32Samsung SSD 860 - 2 x Intel Xeon Gold 61388001600240032004000SE +/- 1.55, N = 33937.85MIN: 3933.051. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerSamsung SSD 860 - 2 x Intel Xeon Gold 61383691215SE +/- 0.04, N = 310.49MIN: 8.62 / MAX: 10.75

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: CrownSamsung SSD 860 - 2 x Intel Xeon Gold 6138714212835SE +/- 0.14, N = 328.79MIN: 28.01 / MAX: 30.06

ACES DGEMM

This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateSamsung SSD 860 - 2 x Intel Xeon Gold 61383691215SE +/- 0.02, N = 310.681. (CC) gcc options: -O3 -march=native -fopenmp

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_1d - Data Type: f32Samsung SSD 860 - 2 x Intel Xeon Gold 61380.39380.78761.18141.57521.969SE +/- 0.00, N = 31.75MIN: 1.661. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_alexnet - Data Type: bf16bf16bf16Samsung SSD 860 - 2 x Intel Xeon Gold 6138120240360480600SE +/- 0.78, N = 3567.94MIN: 563.581. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: CrownSamsung SSD 860 - 2 x Intel Xeon Gold 6138714212835SE +/- 0.01, N = 331.97MIN: 31.38 / MAX: 32.6

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian DragonSamsung SSD 860 - 2 x Intel Xeon Gold 6138816243240SE +/- 0.13, N = 333.66MIN: 32.77 / MAX: 35.15

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 PerformanceSamsung SSD 860 - 2 x Intel Xeon Gold 61382K4K6K8K10KSE +/- 28.11, N = 37829.701. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32Samsung SSD 860 - 2 x Intel Xeon Gold 61381428425670SE +/- 0.06, N = 360.37MIN: 57.421. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian DragonSamsung SSD 860 - 2 x Intel Xeon Gold 6138918273645SE +/- 0.02, N = 341.40MIN: 40.85 / MAX: 42.2

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_alexnet - Data Type: f32Samsung SSD 860 - 2 x Intel Xeon Gold 613820406080100SE +/- 0.08, N = 387.00MIN: 84.241. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch 1D - Data Type: f32Samsung SSD 860 - 2 x Intel Xeon Gold 61380.58051.1611.74152.3222.9025SE +/- 0.02, N = 32.58MIN: 2.251. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch 1D - Data Type: bf16bf16bf16Samsung SSD 860 - 2 x Intel Xeon Gold 61381.10932.21863.32794.43725.5465SE +/- 0.06, N = 34.93MIN: 4.411. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch 1D - Data Type: u8s8f32Samsung SSD 860 - 2 x Intel Xeon Gold 61380.47930.95861.43791.91722.3965SE +/- 0.00, N = 32.13MIN: 1.951. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Tungsten Renderer

Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: HairSamsung SSD 860 - 2 x Intel Xeon Gold 61383691215SE +/- 0.02, N = 311.271. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

N-Queens

This is a test of the OpenMP version of a test that solves the N-queens problem. The board problem size is 18. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed TimeSamsung SSD 860 - 2 x Intel Xeon Gold 61381.1342.2683.4024.5365.67SE +/- 0.01, N = 35.041. (CC) gcc options: -static -fopenmp -O3 -march=native

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.0.0Scene: MemorialSamsung SSD 860 - 2 x Intel Xeon Gold 6138714212835SE +/- 0.11, N = 330.03

MKL-DNN DNNL

This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf16Samsung SSD 860 - 2 x Intel Xeon Gold 6138246810SE +/- 0.01, N = 37.15MIN: 7.041. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_3d - Data Type: f32Samsung SSD 860 - 2 x Intel Xeon Gold 61380.4410.8821.3231.7642.205SE +/- 0.00, N = 31.96MIN: 1.891. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path TracerSamsung SSD 860 - 2 x Intel Xeon Gold 6138110220330440550500MIN: 250

IOR

IOR is a parallel I/O storage benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Read TestSamsung SSD 860 - 2 x Intel Xeon Gold 613880160240320400SE +/- 0.67, N = 3357.97MIN: 341.84 / MAX: 389.631. (CC) gcc options: -O2 -lm -pthread -lmpi

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Write TestSamsung SSD 860 - 2 x Intel Xeon Gold 613850100150200250SE +/- 1.46, N = 3235.49MIN: 130.49 / MAX: 265.321. (CC) gcc options: -O2 -lm -pthread -lmpi

58 Results Shown

libgav1
MKL-DNN DNNL:
  Convolution Batch conv_all - bf16bf16bf16
  Convolution Batch conv_all - u8s8f32
  Convolution Batch conv_all - f32
  Deconvolution Batch deconv_all - bf16bf16bf16
  Deconvolution Batch deconv_all - f32
libgav1
OSPray
libgav1
LuxCoreRender:
  DLSC
  Rainbow Colors and Prism
MKL-DNN DNNL:
  Convolution Batch conv_googlenet_v3 - bf16bf16bf16
  Convolution Batch conv_googlenet_v3 - u8s8f32
  Convolution Batch conv_googlenet_v3 - f32
OSPray:
  San Miguel - SciVis
  XFrog Forest - SciVis
libgav1
MKL-DNN DNNL:
  Deconvolution Batch deconv_1d - bf16bf16bf16
  Deconvolution Batch deconv_1d - u8s8f32
SQLite Speedtest
OSPray
MKL-DNN DNNL:
  Convolution Batch conv_3d - u8s8f32
  IP Batch All - bf16bf16bf16
  IP Batch All - f32
  IP Batch All - u8s8f32
  Convolution Batch conv_3d - bf16bf16bf16
  Convolution Batch conv_3d - f32
  Recurrent Neural Network Training - f32
Embree
OSPray
Embree
Tungsten Renderer:
  Water Caustic
  Non-Exponential
  Volumetric Caustic
OSPray
MKL-DNN DNNL
OSPray
Embree
ACES DGEMM
MKL-DNN DNNL:
  Deconvolution Batch deconv_1d - f32
  Convolution Batch conv_alexnet - bf16bf16bf16
Embree:
  Pathtracer ISPC - Crown
  Pathtracer - Asian Dragon
OpenSSL
MKL-DNN DNNL
Embree
MKL-DNN DNNL:
  Convolution Batch conv_alexnet - f32
  IP Batch 1D - f32
  IP Batch 1D - bf16bf16bf16
  IP Batch 1D - u8s8f32
Tungsten Renderer
N-Queens
Intel Open Image Denoise
MKL-DNN DNNL:
  Deconvolution Batch deconv_3d - bf16bf16bf16
  Deconvolution Batch deconv_3d - f32
OSPray
IOR:
  Read Test
  Write Test

Samsung SSD 860 - 2 x Intel Xeon Gold 6138

Processor: 2 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads), Motherboard: TYAN S7106 (V2.00.B20 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 96256MB, Disk: 500GB Samsung SSD 860, Graphics: llvmpipe 93GB, Monitor: VE228, Network: 2 x Intel I210 + 2 x QLogic cLOM8214 1/10GbE

OS: Ubuntu 18.04, Kernel: 5.0.0-31-generic (x86_64), Desktop: GNOME Shell 3.28.4, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 3.3 Mesa 19.0.8 (LLVM 8.0 256 bits), Compiler: GCC 7.4.0, File-System: ext4, Screen Resolution: 1920x1080

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++ --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 Notes: MQ-DEADLINE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: intel_pstate powersave
Security Notes: l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled

Testing initiated at 13 October 2019 09:49 by user phoronix.