Intel OpenCL Neo vs. Beignet Linux Open-Source OpenCL

Intel OpenCL NEO vs. Beignet OpenCL open-source compute testing on Intel Coffee Lake for a future article on Phoronix.com.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1803069-FO-OPENCLNEO41
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

Limit displaying results to tests within:

CPU Massive 2 Tests
Creator Workloads 2 Tests
NVIDIA GPU Compute 4 Tests
OpenCL 6 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
Disable Color Branding
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
Beignet 1.4 Git
March 04 2018
 
Intel NEO OpenCL 2.1
March 05 2018
 
Invert Hiding All Results Option
 
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):

Beignet 1.4 Git

Processor: Intel Core i7-8700K @ 4.70GHz (6 Cores / 12 Threads), Motherboard: ASUS PRIME Z370-A (0607 BIOS), Chipset: Intel Device 3ec2, Memory: 15360MB, Disk: 525GB Crucial_CT525MX3 + Samsung SSD 950 PRO 256GB, Graphics: Intel UHD 630 3072MB (1200MHz), Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel Connection

OS: Ubuntu 16.04, Kernel: 4.15.7-041507-generic (x86_64), Desktop: Unity 7.4.5, Display Driver: modesetting 1.19.5, OpenGL: 4.5 Mesa 18.1.0-devel- padoka PPA, OpenCL: OpenCL 1.2 beignet 1.4 (git-7e181af), Vulkan: 1.0.61, Compiler: GCC 5.4.0 20160609 + LLVM 5.0.0, File-System: ext4, Screen Resolution: 3840x2160

Compiler Notes: --build=x86_64-linux-gnu --disable-browser-plugin --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-arch-directory=amd64 --with-default-libstdcxx-abi=new --with-multilib-list=m32,m64,mx32 --with-tune=generic -v
Processor Notes: Scaling Governor: intel_pstate powersave
Security Notes: KPTI + __user pointer sanitization + Full generic retpoline Protection

Intel NEO OpenCL 2.1

OS: Ubuntu 16.04, Kernel: 4.15.7-041507-generic (x86_64), Desktop: Unity 7.4.5, Display Driver: modesetting 1.19.5, OpenGL: 4.5 Mesa 18.1.0-devel- padoka PPA, OpenCL: OpenCL 2.1, Vulkan: 1.0.61, Compiler: GCC 5.4.0 20160609 + LLVM 5.0.0, File-System: ext4, Screen Resolution: 3840x2160

Intel OpenCL Neo vs. Beignet Linux Open-Source OpenCLOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-8700K @ 4.70GHz (6 Cores / 12 Threads)ASUS PRIME Z370-A (0607 BIOS)Intel Device 3ec215360MB525GB Crucial_CT525MX3 + Samsung SSD 950 PRO 256GBIntel UHD 630 3072MB (1200MHz)Realtek ALC1220DELL P2415QIntel ConnectionUbuntu 16.044.15.7-041507-generic (x86_64)Unity 7.4.5modesetting 1.19.54.5 Mesa 18.1.0-devel- padoka PPAOpenCL 1.2 beignet 1.4 (git-7e181af)OpenCL 2.11.0.61GCC 5.4.0 20160609 + LLVM 5.0.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay DriverOpenGLOpenCLsVulkanCompilerFile-SystemScreen ResolutionIntel OpenCL Neo Vs. Beignet Linux Open-Source OpenCL BenchmarksSystem Logs- --build=x86_64-linux-gnu --disable-browser-plugin --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-arch-directory=amd64 --with-default-libstdcxx-abi=new --with-multilib-list=m32,m64,mx32 --with-tune=generic -v - Scaling Governor: intel_pstate powersave- KPTI + __user pointer sanitization + Full generic retpoline Protection

Beignet 1.4 Git vs. Intel NEO OpenCL 2.1 ComparisonPhoronix Test SuiteBaseline+12.6%+12.6%+25.2%+25.2%+37.8%+37.8%+50.4%+50.4%24.2%13.1%8.8%2.9%OpenCL - Bus Speed Readback50.5%OpenCL - Bus Speed DownloadPabellon Barcelona - OpenCLBMW27 - OpenCLMasskrug - OpenCLSHOC Scalable HeterOgeneous ComputingSHOC Scalable HeterOgeneous ComputingBlenderBlenderDarktableBeignet 1.4 GitIntel NEO OpenCL 2.1

Intel OpenCL Neo vs. Beignet Linux Open-Source OpenCLshoc: OpenCL - Triadshoc: OpenCL - FFT SPshoc: OpenCL - MD5 Hashshoc: OpenCL - Max SP Flopsshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Texture Read Bandwidthviennacl: OpenCL LU Factorizationcl-mem: Copycl-mem: Readcl-mem: Writedarktable: Boat - OpenCLdarktable: Masskrug - OpenCLdarktable: Server Room - OpenCLblender: BMW27 - OpenCLblender: Classroom - OpenCLblender: Fishy Cat - OpenCLblender: Barbershop - OpenCLblender: Pabellon Barcelona - OpenCLjuliagpu: GPUluxmark: GPU - Hotelluxmark: GPU - Microphoneluxmark: GPU - Luxball HDRBeignet 1.4 GitIntel NEO OpenCL 2.114.7313.620.37466.5819.8438.7860.8917.5855.2350.4256.6521.830.350.33462.11681.691004.471357.421047.5738087166.6055456272824.6525.7721.560.340.33424.63676.47995.621360.23926.47OpenBenchmarking.org

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: TriadBeignet 1.4 Git48121620SE +/- 0.18, N = 314.731. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPBeignet 1.4 Git48121620SE +/- 0.00, N = 313.621. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: MD5 HashBeignet 1.4 Git0.08330.16660.24990.33320.4165SE +/- 0.00, N = 30.371. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Max SP FlopsBeignet 1.4 Git100200300400500SE +/- 0.02, N = 3466.581. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed DownloadBeignet 1.4 GitIntel NEO OpenCL 2.1612182430SE +/- 0.37, N = 3SE +/- 0.09, N = 319.8424.651. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed DownloadBeignet 1.4 GitIntel NEO OpenCL 2.1612182430Min: 19.16 / Avg: 19.84 / Max: 20.43Min: 24.5 / Avg: 24.65 / Max: 24.811. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed ReadbackBeignet 1.4 GitIntel NEO OpenCL 2.1918273645SE +/- 0.06, N = 3SE +/- 0.11, N = 338.7825.771. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed ReadbackBeignet 1.4 GitIntel NEO OpenCL 2.1816243240Min: 38.66 / Avg: 38.78 / Max: 38.84Min: 25.66 / Avg: 25.77 / Max: 25.991. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Texture Read BandwidthBeignet 1.4 Git1428425670SE +/- 0.03, N = 360.891. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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 FactorizationBeignet 1.4 Git48121620SE +/- 0.15, N = 317.581. (CXX) g++ options: -rdynamic -lOpenCL

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: CopyBeignet 1.4 Git1224364860SE +/- 4.55, N = 655.231. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadBeignet 1.4 Git1122334455SE +/- 3.37, N = 650.421. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteBeignet 1.4 Git1326395265SE +/- 4.52, N = 656.651. (CC) gcc options: -O2 -flto -lOpenCL

Darktable

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.0.3Test: Boat - Acceleration: OpenCLBeignet 1.4 GitIntel NEO OpenCL 2.1510152025SE +/- 0.03, N = 3SE +/- 0.03, N = 321.8321.56
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.0.3Test: Boat - Acceleration: OpenCLBeignet 1.4 GitIntel NEO OpenCL 2.1510152025Min: 21.8 / Avg: 21.83 / Max: 21.9Min: 21.5 / Avg: 21.56 / Max: 21.58

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.0.3Test: Masskrug - Acceleration: OpenCLBeignet 1.4 GitIntel NEO OpenCL 2.10.07880.15760.23640.31520.394SE +/- 0.00, N = 3SE +/- 0.00, N = 30.350.34
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.0.3Test: Masskrug - Acceleration: OpenCLBeignet 1.4 GitIntel NEO OpenCL 2.112345Min: 0.34 / Avg: 0.35 / Max: 0.35Min: 0.34 / Avg: 0.34 / Max: 0.34

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.0.3Test: Server Room - Acceleration: OpenCLBeignet 1.4 GitIntel NEO OpenCL 2.10.07430.14860.22290.29720.3715SE +/- 0.00, N = 3SE +/- 0.00, N = 30.330.33
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.0.3Test: Server Room - Acceleration: OpenCLBeignet 1.4 GitIntel NEO OpenCL 2.112345Min: 0.33 / Avg: 0.33 / Max: 0.33Min: 0.33 / Avg: 0.33 / Max: 0.33

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: BMW27 - Compute: OpenCLBeignet 1.4 GitIntel NEO OpenCL 2.1100200300400500462.11424.63

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Classroom - Compute: OpenCLBeignet 1.4 GitIntel NEO OpenCL 2.1150300450600750681.69676.47

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Fishy Cat - Compute: OpenCLBeignet 1.4 GitIntel NEO OpenCL 2.120040060080010001004.47995.62

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: OpenCLBeignet 1.4 GitIntel NEO OpenCL 2.1300600900120015001357.421360.23

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Pabellon Barcelona - Compute: OpenCLBeignet 1.4 GitIntel NEO OpenCL 2.120040060080010001047.57926.47

JuliaGPU

OpenBenchmarking.orgSamples/sec, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPUBeignet 1.4 Git8M16M24M32M40MSE +/- 41486.36, N = 338087166.601. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm

LuxMark

LuxMark is a multi-platform OpenGL benchmark using LuxRender. LuxMark supports targeting different OpenCL devices and has multiple scenes available for rendering. LuxMark is a fully open-source OpenCL program with real-world rendering examples. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: HotelBeignet 1.4 Git120240360480600SE +/- 1.67, N = 3554

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: MicrophoneBeignet 1.4 Git132639526556

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: Luxball HDRBeignet 1.4 Git6001200180024003000SE +/- 5.00, N = 32728

Beignet 1.4 Git

Processor: Intel Core i7-8700K @ 4.70GHz (6 Cores / 12 Threads), Motherboard: ASUS PRIME Z370-A (0607 BIOS), Chipset: Intel Device 3ec2, Memory: 15360MB, Disk: 525GB Crucial_CT525MX3 + Samsung SSD 950 PRO 256GB, Graphics: Intel UHD 630 3072MB (1200MHz), Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel Connection

OS: Ubuntu 16.04, Kernel: 4.15.7-041507-generic (x86_64), Desktop: Unity 7.4.5, Display Driver: modesetting 1.19.5, OpenGL: 4.5 Mesa 18.1.0-devel- padoka PPA, OpenCL: OpenCL 1.2 beignet 1.4 (git-7e181af), Vulkan: 1.0.61, Compiler: GCC 5.4.0 20160609 + LLVM 5.0.0, File-System: ext4, Screen Resolution: 3840x2160

Compiler Notes: --build=x86_64-linux-gnu --disable-browser-plugin --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-arch-directory=amd64 --with-default-libstdcxx-abi=new --with-multilib-list=m32,m64,mx32 --with-tune=generic -v
Processor Notes: Scaling Governor: intel_pstate powersave
Security Notes: KPTI + __user pointer sanitization + Full generic retpoline Protection

Testing initiated at 4 March 2018 19:19 by user pts.

Intel NEO OpenCL 2.1

Processor: Intel Core i7-8700K @ 4.70GHz (6 Cores / 12 Threads), Motherboard: ASUS PRIME Z370-A (0607 BIOS), Chipset: Intel Device 3ec2, Memory: 15360MB, Disk: 525GB Crucial_CT525MX3 + Samsung SSD 950 PRO 256GB, Graphics: Intel UHD 630 3072MB (1200MHz), Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel Connection

OS: Ubuntu 16.04, Kernel: 4.15.7-041507-generic (x86_64), Desktop: Unity 7.4.5, Display Driver: modesetting 1.19.5, OpenGL: 4.5 Mesa 18.1.0-devel- padoka PPA, OpenCL: OpenCL 2.1, Vulkan: 1.0.61, Compiler: GCC 5.4.0 20160609 + LLVM 5.0.0, File-System: ext4, Screen Resolution: 3840x2160

Compiler Notes: --build=x86_64-linux-gnu --disable-browser-plugin --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-arch-directory=amd64 --with-default-libstdcxx-abi=new --with-multilib-list=m32,m64,mx32 --with-tune=generic -v
Processor Notes: Scaling Governor: intel_pstate powersave
Security Notes: KPTI + __user pointer sanitization + Full generic retpoline Protection

Testing initiated at 5 March 2018 07:51 by user pts.