Benchmark Intel Intel Core Ultra 9 285K testing with a MSI MEG Z890 UNIFY-X (MS-7E20) v1.0 (1.A10 BIOS) and MSI Intel ARL 15GB on Ubuntu 24.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2412063-NE-BENCHMARK61&grr .
Benchmark Intel Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution Intel Arc A750 Intel Core Ultra 9 285K @ 5.10GHz (24 Cores) MSI MEG Z890 UNIFY-X (MS-7E20) v1.0 (1.A10 BIOS) Intel Device ae7f 2 x 16GB DDR5-6000MT/s Corsair CMH32GX5M2B6000Z30 1024GB Wodposit NVMe SSD MSI Intel ARL 15GB Intel DG2 Audio PiKVM V3 Realtek Device 5000 + Intel Wi-Fi 7 Ubuntu 24.10 6.12.1-061201-generic (x86_64) GNOME Shell 47.0 X Server + Wayland 4.6 Mesa 24.3.1 kisak-mesa PPA GCC 14.2.0 ext4 1920x1080 OpenBenchmarking.org - Transparent Huge Pages: madvise - --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,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/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 - Scaling Governor: intel_pstate powersave (EPP: performance) - CPU Microcode: 0x110 - Thermald 2.5.8 - Python 3.12.7 - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Benchmark Intel ncnn: Vulkan GPU - FastestDet ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3 ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - mobilenet vkfft: FFT + iFFT C2C 1D batched in half precision realsr-ncnn: 4x - Yes vkpeak: fp16-vec4 vkpeak: fp16-scalar vkpeak: fp32-vec4 vkpeak: fp32-scalar vkfft: FFT + iFFT C2C 1D batched in single precision vkfft: FFT + iFFT C2C 1D batched in single precision, no reshuffling vkfft: FFT + iFFT C2C multidimensional in single precision vkfft: FFT + iFFT R2C / C2R vkfft: FFT + iFFT C2C Bluestein in single precision realsr-ncnn: 4x - No vkresample: 2x - Single waifu2x-ncnn: 2x - 3 - Yes betsy: ETC1 - Highest Intel Arc A750 61.47 116.35 243.66 89.54 48.77 76.44 87.56 22.00 43.81 45.54 93.10 11.51 54.56 12.00 5.04 9.37 38.33 76.44 70571 66.066 22840.73 21379.22 13898.32 16868.93 58625 63113 31532 31218 5425 10.356 18.894 5.291 OpenBenchmarking.org
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: FastestDet Intel Arc A750 14 28 42 56 70 SE +/- 4.25, N = 3 61.47 MIN: 5.39 / MAX: 102 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer Intel Arc A750 30 60 90 120 150 SE +/- 0.39, N = 3 116.35 MIN: 49.89 / MAX: 125.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m Intel Arc A750 50 100 150 200 250 SE +/- 13.66, N = 3 243.66 MIN: 23.78 / MAX: 525.86 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd Intel Arc A750 20 40 60 80 100 SE +/- 1.33, N = 3 89.54 MIN: 7.64 / MAX: 108.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny Intel Arc A750 11 22 33 44 55 SE +/- 0.09, N = 3 48.77 MIN: 16.94 / MAX: 52.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 Intel Arc A750 20 40 60 80 100 SE +/- 0.84, N = 3 76.44 MIN: 9.56 / MAX: 84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet50 Intel Arc A750 20 40 60 80 100 SE +/- 1.03, N = 3 87.56 MIN: 10.81 / MAX: 101.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: alexnet Intel Arc A750 5 10 15 20 25 SE +/- 0.16, N = 3 22.00 MIN: 3.54 / MAX: 25.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet18 Intel Arc A750 10 20 30 40 50 SE +/- 0.87, N = 3 43.81 MIN: 5.02 / MAX: 51.96 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vgg16 Intel Arc A750 10 20 30 40 50 SE +/- 0.12, N = 3 45.54 MIN: 23.39 / MAX: 48.99 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: googlenet Intel Arc A750 20 40 60 80 100 SE +/- 2.20, N = 3 93.10 MIN: 8.42 / MAX: 113.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: blazeface Intel Arc A750 3 6 9 12 15 SE +/- 2.95, N = 3 11.51 MIN: 2.57 / MAX: 56.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 Intel Arc A750 12 24 36 48 60 SE +/- 2.82, N = 3 54.56 MIN: 6.64 / MAX: 119.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mnasnet Intel Arc A750 3 6 9 12 15 SE +/- 0.84, N = 3 12.00 MIN: 4.04 / MAX: 70.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 Intel Arc A750 1.134 2.268 3.402 4.536 5.67 SE +/- 0.19, N = 3 5.04 MIN: 4.69 / MAX: 90.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 Intel Arc A750 3 6 9 12 15 SE +/- 3.80, N = 3 9.37 MIN: 4.43 / MAX: 84.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 Intel Arc A750 9 18 27 36 45 SE +/- 2.78, N = 3 38.33 MIN: 4.08 / MAX: 72.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet Intel Arc A750 20 40 60 80 100 SE +/- 0.84, N = 3 76.44 MIN: 9.56 / MAX: 84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
VkFFT Test: FFT + iFFT C2C 1D batched in half precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.3.4 Test: FFT + iFFT C2C 1D batched in half precision Intel Arc A750 15K 30K 45K 60K 75K SE +/- 2534.09, N = 15 70571 1. (CXX) g++ options: -O3
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes Intel Arc A750 15 30 45 60 75 SE +/- 0.01, N = 3 66.07
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp16-vec4 Intel Arc A750 5K 10K 15K 20K 25K SE +/- 0.55, N = 3 22840.73
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp16-scalar Intel Arc A750 5K 10K 15K 20K 25K SE +/- 1.00, N = 3 21379.22
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp32-vec4 Intel Arc A750 3K 6K 9K 12K 15K SE +/- 0.79, N = 3 13898.32
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20240505 fp32-scalar Intel Arc A750 4K 8K 12K 16K 20K SE +/- 26.85, N = 3 16868.93
VkFFT Test: FFT + iFFT C2C 1D batched in single precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.3.4 Test: FFT + iFFT C2C 1D batched in single precision Intel Arc A750 13K 26K 39K 52K 65K SE +/- 70.72, N = 3 58625 1. (CXX) g++ options: -O3
VkFFT Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.3.4 Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling Intel Arc A750 14K 28K 42K 56K 70K SE +/- 527.31, N = 3 63113 1. (CXX) g++ options: -O3
VkFFT Test: FFT + iFFT C2C multidimensional in single precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.3.4 Test: FFT + iFFT C2C multidimensional in single precision Intel Arc A750 7K 14K 21K 28K 35K SE +/- 251.38, N = 12 31532 1. (CXX) g++ options: -O3
VkFFT Test: FFT + iFFT R2C / C2R OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.3.4 Test: FFT + iFFT R2C / C2R Intel Arc A750 7K 14K 21K 28K 35K SE +/- 232.00, N = 15 31218 1. (CXX) g++ options: -O3
VkFFT Test: FFT + iFFT C2C Bluestein in single precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.3.4 Test: FFT + iFFT C2C Bluestein in single precision Intel Arc A750 1200 2400 3600 4800 6000 SE +/- 58.43, N = 3 5425 1. (CXX) g++ options: -O3
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No Intel Arc A750 3 6 9 12 15 SE +/- 0.01, N = 3 10.36
VkResample Upscale: 2x - Precision: Single OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single Intel Arc A750 5 10 15 20 25 SE +/- 0.04, N = 3 18.89 1. (CXX) g++ options: -O3
Waifu2x-NCNN Vulkan Scale: 2x - Denoise: 3 - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes Intel Arc A750 1.1905 2.381 3.5715 4.762 5.9525 SE +/- 0.006, N = 3 5.291
Phoronix Test Suite v10.8.5