vulkan 6800XT

Intel Core i9-13900K testing with a ASUS PRIME Z790-P WIFI (0812 BIOS) and AMD Radeon RX 6800 XT 16GB on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2308019-NE-VULKAN68087&rdt&grs.

vulkan 6800XTProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionabIntel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads)ASUS PRIME Z790-P WIFI (0812 BIOS)Intel Device 7a2732GB1000GB Western Digital WDS100T1X0E-00AFY0 + 2 x 64GB Flash DriveAMD Radeon RX 6800 XT 16GB (2575/1000MHz)Realtek ALC897ASUS VP28UUbuntu 22.045.19.0-50-generic (x86_64)GNOME Shell 42.9X Server + Wayland4.6 Mesa 22.2.5-0ubuntu0.1~22.04.3 (LLVM 15.0.7 DRM 3.47)1.3.224GCC 11.4.0ext43840x2160OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 Processor Details- Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.4.9 Graphics Details- BAR1 / Visible vRAM Size: 16368 MB - vBIOS Version: 113-D4120500-101Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

vulkan 6800XTncnn: CPU - vgg16ncnn: Vulkan GPU - blazefacencnn: CPU - blazefacencnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - vision_transformerncnn: CPU - regnety_400mncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - regnety_400mncnn: CPU - mnasnetncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - yolov4-tinyncnn: CPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - mobilenetncnn: CPU - squeezenet_ssdncnn: CPU - googlenetncnn: CPU - FastestDetncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - vgg16vkpeak: fp32-vec4vkfft: FFT + iFFT C2C multidimensional in single precisionvkfft: FFT + iFFT C2C Bluestein in single precisionncnn: Vulkan GPU - alexnetncnn: CPU - resnet50vkpeak: fp16-scalarvkfft: FFT + iFFT R2C / C2Rvkpeak: int16-scalarncnn: Vulkan GPU - resnet50vkpeak: int16-vec4ncnn: CPU - resnet18ncnn: CPU - yolov4-tinyvkpeak: fp32-scalarvkpeak: fp16-vec4ncnn: CPU - alexnetvkfft: FFT + iFFT C2C 1D batched in half precisionvkpeak: int32-vec4vkpeak: int32-scalarvkfft: FFT + iFFT C2C Bluestein benchmark in double precisionvkpeak: fp64-scalarvkpeak: fp64-vec4vkfft: FFT + iFFT C2C 1D batched in double precisionvkfft: FFT + iFFT C2C 1D batched in single precisionvkfft: FFT + iFFT C2C 1D batched in single precision, no reshufflingvkresample: 2x - Singleab40.260.870.651.771.791336.945.42.246.861.96.3111.193.372.027.225.655.512.172.454.161249.173.691.811.837.512.025.2819.0521484.2145096148113.948.4721527.055931621383.738.2533053.144.110.8422073.2633775.493.841272294477.623834.8969491413.61411.862828565298691168.49219.080.760.912.372.351018.847.072.475.862.385.7913.634.081.798.514.826.352.462.174.181301.133.341.731.777.061.95.618.9822328.1343591143343.948.222233.825747422064.238.2733941.934.1610.721822.4734040.483.871280444497.583850.0369261416.241414.332824265337691378.491OpenBenchmarking.org

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16ab91827364540.2619.08MIN: 19.59 / MAX: 674.5MIN: 18.91 / MAX: 21.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefaceba0.19580.39160.58740.78320.9790.600.87MIN: 0.59 / MAX: 1.1MIN: 0.86 / MAX: 1.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefaceab0.20480.40960.61440.81921.0240.650.91MIN: 0.63 / MAX: 0.75MIN: 0.9 / MAX: 1.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2ab0.53331.06661.59992.13322.66651.772.37MIN: 1.74 / MAX: 2.24MIN: 2.34 / MAX: 3.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3ab0.52881.05761.58642.11522.6441.792.35MIN: 1.76 / MAX: 2.33MIN: 2.33 / MAX: 2.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformerab300600900120015001336.941018.84MIN: 47.96 / MAX: 2057.96MIN: 48.19 / MAX: 2067.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mab2468105.407.07MIN: 5.33 / MAX: 6.69MIN: 6.95 / MAX: 21.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2ba0.55581.11161.66742.22322.7791.902.24MIN: 1.87 / MAX: 2.81MIN: 2.21 / MAX: 3.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mba2468105.366.86MIN: 5.25 / MAX: 7.02MIN: 6.8 / MAX: 8.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetab0.53551.0711.60652.1422.67751.902.38MIN: 1.87 / MAX: 2.73MIN: 2.36 / MAX: 2.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetba2468105.176.31MIN: 5.11 / MAX: 7.16MIN: 6.26 / MAX: 7.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinyba4812162011.4011.19MIN: 11.3 / MAX: 12.68MIN: 11.07 / MAX: 13.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0ab0.9181.8362.7543.6724.593.374.08MIN: 3.33 / MAX: 4.65MIN: 4.04 / MAX: 5.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetba0.45450.9091.36351.8182.27251.682.02MIN: 1.66 / MAX: 2.21MIN: 1.99 / MAX: 3.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetba2468108.047.22MIN: 7.97 / MAX: 10.38MIN: 7.13 / MAX: 8.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdab1.27132.54263.81395.08526.35655.654.82MIN: 5.57 / MAX: 6.77MIN: 4.75 / MAX: 6.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetab2468105.516.35MIN: 5.45 / MAX: 7.83MIN: 6.29 / MAX: 8.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDetab0.55351.1071.66052.2142.76752.172.46MIN: 2.15 / MAX: 2.31MIN: 2.43 / MAX: 3.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetab0.55131.10261.65392.20522.75652.452.17MIN: 2.42 / MAX: 3.92MIN: 2.14 / MAX: 3.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18ba0.94051.8812.82153.7624.70253.724.16MIN: 3.66 / MAX: 4.32MIN: 4.13 / MAX: 5.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerba300600900120015001158.571249.17MIN: 48.54 / MAX: 2061.75MIN: 54.34 / MAX: 2059.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0ba0.83031.66062.49093.32124.15153.293.69MIN: 3.25 / MAX: 4.76MIN: 3.65 / MAX: 4.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3ba0.40730.81461.22191.62922.03651.641.81MIN: 1.61 / MAX: 3.04MIN: 1.78 / MAX: 3.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2ba0.41180.82361.23541.64722.0591.711.83MIN: 1.68 / MAX: 3.37MIN: 1.79 / MAX: 2.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenetab2468107.517.06MIN: 6.7 / MAX: 66.34MIN: 7 / MAX: 8.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2ab0.45450.9091.36351.8182.27252.021.90MIN: 1.99 / MAX: 3.41MIN: 1.86 / MAX: 3.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdba1.262.523.785.046.35.285.28MIN: 5.22 / MAX: 7.15MIN: 5.23 / MAX: 6.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16ba51015202520.0219.05MIN: 19.89 / MAX: 21.08MIN: 18.83 / MAX: 21.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

vkpeak

fp32-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp32-vec4ab5K10K15K20K25K21484.2122328.13

VkFFT

Test: FFT + iFFT C2C multidimensional in single precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C multidimensional in single precisionab10K20K30K40K50K45096435911. (CXX) g++ options: -O3

VkFFT

Test: FFT + iFFT C2C Bluestein in single precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C Bluestein in single precisionab3K6K9K12K15K14811143341. (CXX) g++ options: -O3

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetba0.91581.83162.74743.66324.5794.073.94MIN: 4.03 / MAX: 5.5MIN: 3.89 / MAX: 5.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50ab2468108.478.20MIN: 8.38 / MAX: 10.41MIN: 8.11 / MAX: 10.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

vkpeak

fp16-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp16-scalarab5K10K15K20K25K21527.0522233.82

VkFFT

Test: FFT + iFFT R2C / C2R

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT R2C / C2Rab13K26K39K52K65K59316574741. (CXX) g++ options: -O3

vkpeak

int16-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int16-scalarab5K10K15K20K25K21383.7322064.23

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50ba2468108.498.25MIN: 8.41 / MAX: 9.94MIN: 8.17 / MAX: 9.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

vkpeak

int16-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int16-vec4ab7K14K21K28K35K33053.1433941.93

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18ab0.9361.8722.8083.7444.684.104.16MIN: 4.07 / MAX: 4.6MIN: 4.11 / MAX: 5.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinyab369121510.8410.70MIN: 10.74 / MAX: 12.8MIN: 10.58 / MAX: 12.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

vkpeak

fp32-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp32-scalarab5K10K15K20K25K22073.2621822.47

vkpeak

fp16-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp16-vec4ab7K14K21K28K35K33775.4934040.48

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetab0.87081.74162.61243.48324.3543.843.87MIN: 3.8 / MAX: 4.84MIN: 3.83 / MAX: 4.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

VkFFT

Test: FFT + iFFT C2C 1D batched in half precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in half precisionab30K60K90K120K150K1272291280441. (CXX) g++ options: -O3

vkpeak

int32-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int32-vec4ab100020003000400050004477.624497.58

vkpeak

int32-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int32-scalarab80016002400320040003834.893850.03

VkFFT

Test: FFT + iFFT C2C Bluestein benchmark in double precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C Bluestein benchmark in double precisionab15003000450060007500694969261. (CXX) g++ options: -O3

vkpeak

fp64-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp64-scalarab300600900120015001413.601416.24

vkpeak

fp64-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp64-vec4ab300600900120015001411.861414.33

VkFFT

Test: FFT + iFFT C2C 1D batched in double precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in double precisionab6K12K18K24K30K28285282421. (CXX) g++ options: -O3

VkFFT

Test: FFT + iFFT C2C 1D batched in single precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in single precisionab14K28K42K56K70K65298653371. (CXX) g++ options: -O3

VkFFT

Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in single precision, no reshufflingab15K30K45K60K75K69116691371. (CXX) g++ options: -O3

VkResample

Upscale: 2x - Precision: Single

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Singleab2468108.4928.4911. (CXX) g++ options: -O3


Phoronix Test Suite v10.8.5