3600x 2024 AMD Ryzen 9 3900XT 12-Core testing with a MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) and AMD Radeon RX 56/64 8GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2410197-NE-3600X202416&grs&sro .
3600x 2024 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution a b c AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads) MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) AMD Starship/Matisse 2 x 8GB DDR4-4133MT/s F4-4133C19-8GTZKW 500GB Seagate FireCuda 520 SSD ZP500GM30002 AMD Radeon RX 56/64 8GB AMD Vega 10 HDMI Audio DELL U2723QE Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200 Ubuntu 22.04 6.8.0-47-generic (x86_64) GNOME Shell 42.9 X Server + Wayland 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.57) 1.3.204 GCC 11.4.0 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler 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: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8701021 Graphics Details - a, b: BAR1 / Visible vRAM Size: 256 MB Java Details - a: OpenJDK Runtime Environment (build 11.0.24+8-post-Ubuntu-1ubuntu322.04) Python Details - a: Python 3.10.12 Security Details - 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: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
3600x 2024 glibc-bench: sqrt onednn: IP Shapes 3D - CPU onednn: Deconvolution Batch shapes_1d - CPU glibc-bench: exp blosc: blosclz bitshuffle - 64MB glibc-bench: modf glibc-bench: sinh glibc-bench: pow glibc-bench: log2 onednn: IP Shapes 1D - CPU glibc-bench: pthread_once glibc-bench: cos glibc-bench: atanh xnnpack: FP32MobileNetV1 blosc: blosclz noshuffle - 16MB blosc: blosclz noshuffle - 8MB xnnpack: FP32MobileNetV2 blosc: blosclz bitshuffle - 32MB blosc: blosclz shuffle - 32MB blosc: blosclz shuffle - 16MB glibc-bench: sincos litert: Mobilenet Float blosc: blosclz noshuffle - 32MB litert: Inception V4 blosc: blosclz bitshuffle - 128MB litert: DeepLab V3 namd: ATPase with 327,506 Atoms blosc: blosclz bitshuffle - 16MB xnnpack: FP32MobileNetV3Large blosc: blosclz bitshuffle - 8MB glibc-bench: sin glibc-bench: tanh litert: Inception ResNet V2 xnnpack: FP32MobileNetV3Small glibc-bench: asinh glibc-bench: ffs onednn: Convolution Batch Shapes Auto - CPU litert: Mobilenet Quant blosc: blosclz noshuffle - 64MB glibc-bench: ffsll onednn: Recurrent Neural Network Training - CPU furmark: 1920 x 1080 - FurMark OpenGL - Off onednn: Deconvolution Batch shapes_3d - CPU xnnpack: QS8MobileNetV2 onednn: Recurrent Neural Network Inference - CPU blosc: blosclz noshuffle - 128MB xnnpack: FP16MobileNetV3Large blosc: blosclz shuffle - 8MB xnnpack: FP16MobileNetV1 litert: SqueezeNet blosc: blosclz shuffle - 64MB litert: NASNet Mobile litert: Quantized COCO SSD MobileNet v1 xnnpack: FP16MobileNetV2 xnnpack: FP16MobileNetV3Small blosc: blosclz shuffle - 128MB lczero: BLAS furmark: 1920 x 1080 - Furmark Knot Vulkan - Off furmark: 1920 x 1080 - FurMark Knot OpenGL - Off furmark: 1920 x 1080 - FurMark Vulkan - Off a b c 10.3879 15.9354 7.03818 16.7658 8054.3 6.69978 29.16 42.704 13.463 2.55382 6.03187 81.3098 36.9881 2454 8745 9500 2263 9784 10369.6 11523.1 41.1823 2282.72 6738.3 38445.9 6703.8 3688.37 0.77506 10404.9 2505 10444.6 71.885 39.6167 32634.7 1183 31.7853 6.03612 18.9965 1698.8 5462.1 6.06866 2654.7 42.121109 5.33741 1377 1370.26 4695.4 2178 11575 2493 2548.21 8550.6 12847.8 2646.99 1915 1084 6896.5 63 15.955235 11.254252 38.168106 7.84162 12.0669 5.96129 16.9909 8517.2 6.55046 28.1594 44.6435 13.5004 2.66658 6.03169 78.4383 36.9931 2502 8834.7 9622.5 2220 9540.4 10252.8 11253.3 41.9762 2239.6 6814.6 38646.1 6587.4 3653.79 0.78593 10549.8 2512 10497.1 71.035 40.0893 32941 1194 31.5253 6.08496 18.9056 1689.17 5424.4 6.03505 2666.16 41.91703 5.36237 1371 1364.38 4696.9 2174 11536.1 2485 2553.5 8530.4 2652.69 1911 1082 6893 10.3278 12.2266 6.03743 19.2329 8352.2 6.89904 29.4491 44.6405 12.9174 2.62929 5.78067 81.3725 35.7851 2430 8993.3 9750.8 2206 9643.8 10512.1 11379.4 41.1967 2259.66 6865.3 39144.4 6615.2 3629.77 0.78383 10414.3 2479 10361.2 71.0232 39.6121 32820.2 1189 31.7904 6.07068 18.8464 1686.52 5439.3 6.0688 2651.48 5.35165 1371 1364.68 4715 2170 11542.8 2491 2546.22 8536.4 12877.1 2648.53 1912 1082 6900.4 OpenBenchmarking.org
Glibc Benchmarks Benchmark: sqrt OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: sqrt a b c 3 6 9 12 15 10.38790 7.84162 10.32780 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
oneDNN Harness: IP Shapes 3D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: IP Shapes 3D - Engine: CPU a b c 4 8 12 16 20 15.94 12.07 12.23 MIN: 12.64 MIN: 11.98 MIN: 12.12 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Deconvolution Batch shapes_1d - Engine: CPU a b c 2 4 6 8 10 7.03818 5.96129 6.03743 MIN: 5.34 MIN: 5.08 MIN: 5.15 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
Glibc Benchmarks Benchmark: exp OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: exp a b c 5 10 15 20 25 16.77 16.99 19.23 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
C-Blosc Test: blosclz bitshuffle - Buffer Size: 64MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 64MB a b c 2K 4K 6K 8K 10K 8054.3 8517.2 8352.2 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
Glibc Benchmarks Benchmark: modf OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: modf a b c 2 4 6 8 10 6.69978 6.55046 6.89904 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: sinh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: sinh a b c 7 14 21 28 35 29.16 28.16 29.45 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: pow OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: pow a b c 10 20 30 40 50 42.70 44.64 44.64 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: log2 OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: log2 a b c 3 6 9 12 15 13.46 13.50 12.92 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
oneDNN Harness: IP Shapes 1D - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: IP Shapes 1D - Engine: CPU a b c 0.6 1.2 1.8 2.4 3 2.55382 2.66658 2.62929 MIN: 2.5 MIN: 2.59 MIN: 2.57 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
Glibc Benchmarks Benchmark: pthread_once OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: pthread_once a b c 2 4 6 8 10 6.03187 6.03169 5.78067 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: cos OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: cos a b c 20 40 60 80 100 81.31 78.44 81.37 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: atanh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: atanh a b c 9 18 27 36 45 36.99 36.99 35.79 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
XNNPACK Model: FP32MobileNetV1 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV1 a b c 500 1000 1500 2000 2500 2454 2502 2430 1. (CXX) g++ options: -O3 -lrt -lm
C-Blosc Test: blosclz noshuffle - Buffer Size: 16MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 16MB a b c 2K 4K 6K 8K 10K 8745.0 8834.7 8993.3 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
C-Blosc Test: blosclz noshuffle - Buffer Size: 8MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 8MB a b c 2K 4K 6K 8K 10K 9500.0 9622.5 9750.8 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
XNNPACK Model: FP32MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV2 a b c 500 1000 1500 2000 2500 2263 2220 2206 1. (CXX) g++ options: -O3 -lrt -lm
C-Blosc Test: blosclz bitshuffle - Buffer Size: 32MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 32MB a b c 2K 4K 6K 8K 10K 9784.0 9540.4 9643.8 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
C-Blosc Test: blosclz shuffle - Buffer Size: 32MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 32MB a b c 2K 4K 6K 8K 10K 10369.6 10252.8 10512.1 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
C-Blosc Test: blosclz shuffle - Buffer Size: 16MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 16MB a b c 2K 4K 6K 8K 10K 11523.1 11253.3 11379.4 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
Glibc Benchmarks Benchmark: sincos OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: sincos a b c 10 20 30 40 50 41.18 41.98 41.20 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
LiteRT Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Mobilenet Float a b c 500 1000 1500 2000 2500 2282.72 2239.60 2259.66
C-Blosc Test: blosclz noshuffle - Buffer Size: 32MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 32MB a b c 1500 3000 4500 6000 7500 6738.3 6814.6 6865.3 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
LiteRT Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Inception V4 a b c 8K 16K 24K 32K 40K 38445.9 38646.1 39144.4
C-Blosc Test: blosclz bitshuffle - Buffer Size: 128MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 128MB a b c 1400 2800 4200 5600 7000 6703.8 6587.4 6615.2 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
LiteRT Model: DeepLab V3 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: DeepLab V3 a b c 800 1600 2400 3200 4000 3688.37 3653.79 3629.77
NAMD Input: ATPase with 327,506 Atoms OpenBenchmarking.org ns/day, More Is Better NAMD 3.0 Input: ATPase with 327,506 Atoms a b c 0.1768 0.3536 0.5304 0.7072 0.884 0.77506 0.78593 0.78383
C-Blosc Test: blosclz bitshuffle - Buffer Size: 16MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 16MB a b c 2K 4K 6K 8K 10K 10404.9 10549.8 10414.3 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
XNNPACK Model: FP32MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV3Large a b c 500 1000 1500 2000 2500 2505 2512 2479 1. (CXX) g++ options: -O3 -lrt -lm
C-Blosc Test: blosclz bitshuffle - Buffer Size: 8MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 8MB a b c 2K 4K 6K 8K 10K 10444.6 10497.1 10361.2 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
Glibc Benchmarks Benchmark: sin OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: sin a b c 16 32 48 64 80 71.89 71.04 71.02 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: tanh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: tanh a b c 9 18 27 36 45 39.62 40.09 39.61 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
LiteRT Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Inception ResNet V2 a b c 7K 14K 21K 28K 35K 32634.7 32941.0 32820.2
XNNPACK Model: FP32MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP32MobileNetV3Small a b c 300 600 900 1200 1500 1183 1194 1189 1. (CXX) g++ options: -O3 -lrt -lm
Glibc Benchmarks Benchmark: asinh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: asinh a b c 7 14 21 28 35 31.79 31.53 31.79 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: ffs OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: ffs a b c 2 4 6 8 10 6.03612 6.08496 6.07068 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
oneDNN Harness: Convolution Batch Shapes Auto - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Convolution Batch Shapes Auto - Engine: CPU a b c 5 10 15 20 25 19.00 18.91 18.85 MIN: 18.73 MIN: 18.8 MIN: 18.7 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
LiteRT Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Mobilenet Quant a b c 400 800 1200 1600 2000 1698.80 1689.17 1686.52
C-Blosc Test: blosclz noshuffle - Buffer Size: 64MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 64MB a b c 1200 2400 3600 4800 6000 5462.1 5424.4 5439.3 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
Glibc Benchmarks Benchmark: ffsll OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks 2.39 Benchmark: ffsll a b c 2 4 6 8 10 6.06866 6.03505 6.06880 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
oneDNN Harness: Recurrent Neural Network Training - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Recurrent Neural Network Training - Engine: CPU a b c 600 1200 1800 2400 3000 2654.70 2666.16 2651.48 MIN: 2646.21 MIN: 2649.73 MIN: 2643.75 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
FurMark Resolution: 1920 x 1080 - Demo: FurMark OpenGL - MSAA: Off OpenBenchmarking.org FPS, More Is Better FurMark 2.1 Resolution: 1920 x 1080 - Demo: FurMark OpenGL - MSAA: Off a b 10 20 30 40 50 42.12 41.92 MIN: 41 / MAX: 44 MIN: 41 / MAX: 44
oneDNN Harness: Deconvolution Batch shapes_3d - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Deconvolution Batch shapes_3d - Engine: CPU a b c 1.2065 2.413 3.6195 4.826 6.0325 5.33741 5.36237 5.35165 MIN: 5.23 MIN: 5.26 MIN: 5.26 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
XNNPACK Model: QS8MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: QS8MobileNetV2 a b c 300 600 900 1200 1500 1377 1371 1371 1. (CXX) g++ options: -O3 -lrt -lm
oneDNN Harness: Recurrent Neural Network Inference - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.6 Harness: Recurrent Neural Network Inference - Engine: CPU a b c 300 600 900 1200 1500 1370.26 1364.38 1364.68 MIN: 1357.53 MIN: 1359.36 MIN: 1358.89 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -fcf-protection=full -pie -ldl
C-Blosc Test: blosclz noshuffle - Buffer Size: 128MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 128MB a b c 1000 2000 3000 4000 5000 4695.4 4696.9 4715.0 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
XNNPACK Model: FP16MobileNetV3Large OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV3Large a b c 500 1000 1500 2000 2500 2178 2174 2170 1. (CXX) g++ options: -O3 -lrt -lm
C-Blosc Test: blosclz shuffle - Buffer Size: 8MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 8MB a b c 2K 4K 6K 8K 10K 11575.0 11536.1 11542.8 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
XNNPACK Model: FP16MobileNetV1 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV1 a b c 500 1000 1500 2000 2500 2493 2485 2491 1. (CXX) g++ options: -O3 -lrt -lm
LiteRT Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: SqueezeNet a b c 500 1000 1500 2000 2500 2548.21 2553.50 2546.22
C-Blosc Test: blosclz shuffle - Buffer Size: 64MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 64MB a b c 2K 4K 6K 8K 10K 8550.6 8530.4 8536.4 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
LiteRT Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: NASNet Mobile a c 3K 6K 9K 12K 15K 12847.8 12877.1
LiteRT Model: Quantized COCO SSD MobileNet v1 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Quantized COCO SSD MobileNet v1 a b c 600 1200 1800 2400 3000 2646.99 2652.69 2648.53
XNNPACK Model: FP16MobileNetV2 OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV2 a b c 400 800 1200 1600 2000 1915 1911 1912 1. (CXX) g++ options: -O3 -lrt -lm
XNNPACK Model: FP16MobileNetV3Small OpenBenchmarking.org us, Fewer Is Better XNNPACK b7b048 Model: FP16MobileNetV3Small a b c 200 400 600 800 1000 1084 1082 1082 1. (CXX) g++ options: -O3 -lrt -lm
C-Blosc Test: blosclz shuffle - Buffer Size: 128MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 128MB a b c 1500 3000 4500 6000 7500 6896.5 6893.0 6900.4 1. (CC) gcc options: -std=gnu99 -O3 -ldl -lrt -lm
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.31.1 Backend: BLAS a 14 28 42 56 70 63 1. (CXX) g++ options: -flto -pthread
FurMark Resolution: 1920 x 1080 - Demo: Furmark Knot Vulkan - MSAA: Off OpenBenchmarking.org FPS, More Is Better FurMark 2.1 Resolution: 1920 x 1080 - Demo: Furmark Knot Vulkan - MSAA: Off a 4 8 12 16 20 15.96 MAX: 19
FurMark Resolution: 1920 x 1080 - Demo: FurMark Knot OpenGL - MSAA: Off OpenBenchmarking.org FPS, More Is Better FurMark 2.1 Resolution: 1920 x 1080 - Demo: FurMark Knot OpenGL - MSAA: Off a 3 6 9 12 15 11.25 MAX: 13
FurMark Resolution: 1920 x 1080 - Demo: FurMark Vulkan - MSAA: Off OpenBenchmarking.org FPS, More Is Better FurMark 2.1 Resolution: 1920 x 1080 - Demo: FurMark Vulkan - MSAA: Off a 9 18 27 36 45 38.17 MIN: 38 / MAX: 40
Phoronix Test Suite v10.8.5