Tests for a future article.
Linux 5.19 Default Kernel Notes: Transparent Huge Pages: madviseCompiler 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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=auto --with-tune=generic --without-cuda-driver -vDisk Notes: MQ-DEADLINE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf0 - Thermald 1.9.1Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04)Python Notes: Python 3.8.10Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of IBRS IBPB: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable
retbleed=off Kernel Notes: Transparent Huge Pages: madviseCompiler 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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=auto --with-tune=generic --without-cuda-driver -vDisk Notes: MQ-DEADLINE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf0 - Thermald 1.9.1Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04)Python Notes: Python 3.8.10Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Vulnerable + 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 IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable
mitigations=off Processor: Intel Xeon E3-1245 v5 @ 3.90GHz (4 Cores / 8 Threads), Motherboard: MSI C236A WORKSTATION (MS-7998) v1.0 (2.90 BIOS), Chipset: Intel Xeon E3-1200 v5/E3-1500, Memory: 32GB, Disk: 120GB Samsung SSD 850, Graphics: MSI Intel HD P530 SKL GT2 3GB (1150MHz), Audio: Realtek ALC1150, Monitor: VA2431, Network: Intel I219-V
OS: Ubuntu 20.04, Kernel: 5.19.0-051900rc7daily20220723-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.9, OpenGL: 4.6 Mesa 20.2.6, Vulkan: 1.2.145, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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=auto --with-tune=generic --without-cuda-driver -vDisk Notes: MQ-DEADLINE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf0 - Thermald 1.9.1Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04)Python Notes: Python 3.8.10Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + mmio_stale_data: Vulnerable + retbleed: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + srbds: Vulnerable + tsx_async_abort: Mitigation of TSX disabled
Skylake Xeon E3 v5 Retbleed Mitigations OpenBenchmarking.org Phoronix Test Suite Intel Xeon E3-1245 v5 @ 3.90GHz (4 Cores / 8 Threads) MSI C236A WORKSTATION (MS-7998) v1.0 (2.90 BIOS) Intel Xeon E3-1200 v5/E3-1500 32GB 120GB Samsung SSD 850 MSI Intel HD P530 SKL GT2 3GB (1150MHz) Realtek ALC1150 VA2431 Intel I219-V Ubuntu 20.04 5.19.0-051900rc7daily20220723-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.9 4.6 Mesa 20.2.6 1.2.145 GCC 9.3.0 ext4 1920x1080 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution Skylake Xeon E3 V5 Retbleed Mitigations Performance System Logs - Transparent Huge Pages: madvise - --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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=auto --with-tune=generic --without-cuda-driver -v - MQ-DEADLINE / errors=remount-ro,relatime,rw / Block Size: 4096 - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf0 - Thermald 1.9.1 - OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04) - Python 3.8.10 - Linux 5.19 Default: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of IBRS IBPB: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable - retbleed=off: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Vulnerable + 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 IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable - mitigations=off: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + mmio_stale_data: Vulnerable + retbleed: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + srbds: Vulnerable + tsx_async_abort: Mitigation of TSX disabled
Linux 5.19 Default retbleed=off mitigations=off Result Overview Phoronix Test Suite 100% 121% 141% 162% 183% KeyDB PostMark Stress-NG Sockperf SQLite Speedtest Ethr Apache Cassandra Mobile Neural Network Facebook RocksDB JPEG XL Decoding libjxl JPEG XL libjxl SVT-AV1 RAR Compression NCNN yquake2 Renaissance Timed Linux Kernel Compilation SVT-VP9 Timed Node.js Compilation CLOMP Timed MPlayer Compilation x264 C-Blosc Etcpak Basis Universal 7-Zip Compression Parallel BZIP2 Compression VP9 libvpx Encoding Zstd Compression
Skylake Xeon E3 v5 Retbleed Mitigations stress-ng: MMAP stress-ng: NUMA stress-ng: Futex stress-ng: MEMFD stress-ng: Malloc stress-ng: Forking stress-ng: SENDFILE stress-ng: CPU Cache stress-ng: Socket Activity stress-ng: Context Switching stress-ng: System V Message Passing yquake2: Vulkan - On - Off - 1920 x 1080 yquake2: Vulkan - Off - Off - 1920 x 1080 yquake2: OpenGL 3.x - On - On - 1920 x 1080 yquake2: OpenGL 3.x - Off - On - 1920 x 1080 yquake2: OpenGL 3.x - On - Off - 1920 x 1080 yquake2: OpenGL 3.x - Off - Off - 1920 x 1080 svt-av1: Preset 12 - Bosphorus 4K svt-vp9: VMAF Optimized - Bosphorus 4K vpxenc: Speed 0 - Bosphorus 4K vpxenc: Speed 5 - Bosphorus 4K x264: Bosphorus 4K x264: Bosphorus 1080p ethr: TCP - Bandwidth - 1 ethr: TCP - Bandwidth - 2 ethr: TCP - Bandwidth - 8 blosc: blosclz compress-zstd: 3 - Compression Speed sockperf: Throughput compress-7zip: Compression Rating jpegxl: PNG - 5 jpegxl: PNG - 7 jpegxl: PNG - 8 jpegxl: JPEG - 5 jpegxl: JPEG - 7 jpegxl: JPEG - 8 jpegxl-decode: 1 jpegxl-decode: All etcpak: Multi-Threaded - ETC2 etcpak: Single-Threaded - ETC2 cassandra: Writes rocksdb: Update Rand rocksdb: Read While Writing rocksdb: Read Rand Write Rand keydb: ethr: UDP - Bandwidth - 1 ethr: UDP - Bandwidth - 2 ethr: UDP - Bandwidth - 8 clomp: Static OMP Speedup postmark: Disk Transaction Performance renaissance: Apache Spark PageRank renaissance: Finagle HTTP Requests renaissance: In-Memory Database Shootout mnn: mobilenetV3 mnn: squeezenetv1.1 mnn: resnet-v2-50 mnn: SqueezeNetV1.0 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 mnn: inception-v3 ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - blazeface ncnn: CPU - regnety_400m build-linux-kernel: defconfig build-mplayer: Time To Compile build-nodejs: Time To Compile compress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compression basis: ETC1S basis: UASTC Level 0 sqlite-speedtest: Timed Time - Size 1,000 compress-rar: Linux Source Tree Archiving To RAR ethr: TCP - Latency - 1 ethr: TCP - Latency - 2 ethr: TCP - Latency - 8 sockperf: Latency Ping Pong sockperf: Latency Under Load Linux 5.19 Default retbleed=off mitigations=off 27.92 83.65 659940.43 213.73 380875.88 20251.89 51950.93 132.56 2628.78 882682.35 2092963.81 236.8 249.2 111.5 110.3 282.5 289.1 41.577 25.03 2.84 8.44 10.55 45.07 21.49 39.96 70.94 8703.6 1446.2 352872 27714 18.88 5.26 0.58 49.81 49.17 21.41 41.29 127.93 899.45 192.837 33705 203623 729380 628801 280920.38 182086 366048 1007423 1.8 3787 4279.7 4428.1 4513.8 2.806 4.811 44.167 6.922 4.735 4.577 52.492 5.06 5.9 2.08 13.4 257.376 98.336 1559.124 22.977 38.442 11.699 90.469 75.362 28.442 28.988 28.481 4.852 24.077 33.83 93.45 948191.27 248.72 679810.25 24994.19 54773.70 130.33 3763.22 1160982.48 3689357.82 236.7 250.3 114.0 114.8 323.1 337.0 46.273 26.51 2.88 8.68 11.16 46.80 28.37 48.99 79.86 8959.7 1467.0 540467 28513 19.30 5.76 0.64 55.22 54.95 22.29 45.40 141.42 918.617 199.007 37171 230509 721294 693163 383558.08 219141 438766 1261867 1.8 5245 4054.6 4123.4 4277.6 2.681 4.662 43.713 6.765 4.628 4.531 51.707 4.88 5.67 1.93 12.18 241.926 95.032 1586.295 22.658 37.592 11.362 73.143 71.229 25.590 24.793 24.974 4.157 20.541 37.90 97.60 1225963.43 270.40 1514613.88 28615.95 71825.97 135.90 5099.80 1470831.10 6886225.00 243.7 259.0 115.1 115.5 334.5 359.5 46.629 26.65 2.88 8.72 11.18 46.75 33.31 51.31 88.39 9105.9 1463.5 705601 28665 19.54 6.01 0.66 58.57 58.35 23.07 47.82 147.82 934.327 201.437 40163 262794 743750 750798 513729.13 257991 507280 1506400 1.9 6697 4074.1 3992.6 3930.6 2.102 3.842 36.047 6.039 4.195 4.388 45.675 4.77 5.57 1.91 11.41 236.734 93.699 1497.928 22.370 37.188 11.190 60.068 67.799 22.811 22.022 21.821 3.544 17.843 OpenBenchmarking.org
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: MMAP Linux 5.19 Default retbleed=off mitigations=off 9 18 27 36 45 SE +/- 0.33, N = 3 SE +/- 0.47, N = 15 27.92 33.83 37.90 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: NUMA Linux 5.19 Default retbleed=off mitigations=off 20 40 60 80 100 SE +/- 0.70, N = 3 SE +/- 0.52, N = 3 83.65 93.45 97.60 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Futex Linux 5.19 Default retbleed=off mitigations=off 300K 600K 900K 1200K 1500K SE +/- 32808.49, N = 15 SE +/- 38696.53, N = 15 659940.43 948191.27 1225963.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: MEMFD Linux 5.19 Default retbleed=off mitigations=off 60 120 180 240 300 SE +/- 0.64, N = 3 SE +/- 0.40, N = 3 213.73 248.72 270.40 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Malloc Linux 5.19 Default retbleed=off mitigations=off 300K 600K 900K 1200K 1500K SE +/- 2743.76, N = 3 SE +/- 15095.53, N = 3 380875.88 679810.25 1514613.88 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Forking Linux 5.19 Default retbleed=off mitigations=off 6K 12K 18K 24K 30K SE +/- 62.22, N = 3 SE +/- 89.46, N = 3 20251.89 24994.19 28615.95 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: SENDFILE Linux 5.19 Default retbleed=off mitigations=off 15K 30K 45K 60K 75K SE +/- 16.52, N = 3 SE +/- 22.27, N = 3 51950.93 54773.70 71825.97 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: CPU Cache retbleed=off Linux 5.19 Default mitigations=off 30 60 90 120 150 SE +/- 1.14, N = 15 SE +/- 1.17, N = 15 130.33 132.56 135.90 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Socket Activity Linux 5.19 Default retbleed=off mitigations=off 1100 2200 3300 4400 5500 SE +/- 8.93, N = 3 SE +/- 0.73, N = 3 2628.78 3763.22 5099.80 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Context Switching Linux 5.19 Default retbleed=off mitigations=off 300K 600K 900K 1200K 1500K SE +/- 5784.90, N = 3 SE +/- 2107.33, N = 3 882682.35 1160982.48 1470831.10 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: System V Message Passing Linux 5.19 Default retbleed=off mitigations=off 1.5M 3M 4.5M 6M 7.5M SE +/- 1519.25, N = 3 SE +/- 5285.94, N = 3 2092963.81 3689357.82 6886225.00 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lapparmor -latomic -lbsd -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
yquake2 This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: Vulkan - AF: On - MSAA: Off - Resolution: 1920 x 1080 retbleed=off Linux 5.19 Default mitigations=off 50 100 150 200 250 SE +/- 0.46, N = 3 SE +/- 0.54, N = 3 236.7 236.8 243.7 1. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: Vulkan - AF: Off - MSAA: Off - Resolution: 1920 x 1080 Linux 5.19 Default retbleed=off mitigations=off 60 120 180 240 300 SE +/- 0.26, N = 3 SE +/- 0.12, N = 3 249.2 250.3 259.0 1. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: OpenGL 3.x - AF: On - MSAA: On - Resolution: 1920 x 1080 Linux 5.19 Default retbleed=off mitigations=off 30 60 90 120 150 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 111.5 114.0 115.1 1. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: OpenGL 3.x - AF: Off - MSAA: On - Resolution: 1920 x 1080 Linux 5.19 Default retbleed=off mitigations=off 30 60 90 120 150 SE +/- 0.15, N = 3 SE +/- 0.12, N = 3 110.3 114.8 115.5 1. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: OpenGL 3.x - AF: On - MSAA: Off - Resolution: 1920 x 1080 Linux 5.19 Default retbleed=off mitigations=off 70 140 210 280 350 SE +/- 1.75, N = 3 SE +/- 1.04, N = 3 282.5 323.1 334.5 1. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: OpenGL 3.x - AF: Off - MSAA: Off - Resolution: 1920 x 1080 Linux 5.19 Default retbleed=off mitigations=off 80 160 240 320 400 SE +/- 0.51, N = 3 SE +/- 0.53, N = 3 289.1 337.0 359.5 1. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Linux 5.19 Default retbleed=off mitigations=off 11 22 33 44 55 SE +/- 0.12, N = 3 SE +/- 0.10, N = 3 41.58 46.27 46.63 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 4K Linux 5.19 Default retbleed=off mitigations=off 6 12 18 24 30 SE +/- 0.28, N = 5 SE +/- 0.20, N = 11 25.03 26.51 26.65 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 4K Linux 5.19 Default retbleed=off mitigations=off 0.648 1.296 1.944 2.592 3.24 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 2.84 2.88 2.88 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 4K Linux 5.19 Default retbleed=off mitigations=off 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 8.44 8.68 8.72 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
x264 This is a multi-threaded test of the x264 video encoder run on the CPU with a choice of 1080p or 4K video input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x264 2022-02-22 Video Input: Bosphorus 4K Linux 5.19 Default retbleed=off mitigations=off 3 6 9 12 15 SE +/- 0.11, N = 5 SE +/- 0.09, N = 9 10.55 11.16 11.18 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -flto
OpenBenchmarking.org Frames Per Second, More Is Better x264 2022-02-22 Video Input: Bosphorus 1080p Linux 5.19 Default mitigations=off retbleed=off 11 22 33 44 55 SE +/- 0.63, N = 3 SE +/- 0.65, N = 3 45.07 46.75 46.80 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -flto
Ethr Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and conducting different measurements. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Gbits/sec, More Is Better Ethr 1.0 Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 1 Linux 5.19 Default retbleed=off mitigations=off 8 16 24 32 40 SE +/- 0.10, N = 3 SE +/- 0.23, N = 3 21.49 28.37 33.31 MIN: 18.72 / MAX: 23.73 MIN: 25.84 / MAX: 30.69 MIN: 29.98 / MAX: 35.56
OpenBenchmarking.org Gbits/sec, More Is Better Ethr 1.0 Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 2 Linux 5.19 Default retbleed=off mitigations=off 12 24 36 48 60 SE +/- 0.51, N = 3 SE +/- 0.90, N = 12 39.96 48.99 51.31 MIN: 39.19 / MAX: 40.44 MIN: 35.21 / MAX: 56.69 MIN: 39.62 / MAX: 62.42
OpenBenchmarking.org Gbits/sec, More Is Better Ethr 1.0 Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 8 Linux 5.19 Default retbleed=off mitigations=off 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 70.94 79.86 88.39 MIN: 69.72 / MAX: 72.22 MIN: 78.51 / MAX: 81.08 MIN: 85.37 / MAX: 89.96
Zstd Compression This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3 - Compression Speed Linux 5.19 Default mitigations=off retbleed=off 300 600 900 1200 1500 SE +/- 0.81, N = 3 SE +/- 7.22, N = 3 1446.2 1463.5 1467.0 1. *** zstd command line interface 64-bits v1.4.4, by Yann Collet ***
Sockperf This is a network socket API performance benchmark developed by Mellanox. This test profile runs both the client and server on the local host for evaluating individual system performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Messages Per Second, More Is Better Sockperf 3.7 Test: Throughput Linux 5.19 Default retbleed=off mitigations=off 150K 300K 450K 600K 750K SE +/- 4860.01, N = 25 SE +/- 7001.62, N = 25 352872 540467 705601 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
JPEG XL libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: PNG - Encode Speed: 5 Linux 5.19 Default retbleed=off mitigations=off 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 18.88 19.30 19.54 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: PNG - Encode Speed: 7 Linux 5.19 Default retbleed=off mitigations=off 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 5.26 5.76 6.01 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: PNG - Encode Speed: 8 Linux 5.19 Default retbleed=off mitigations=off 0.1485 0.297 0.4455 0.594 0.7425 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.58 0.64 0.66 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: JPEG - Encode Speed: 5 Linux 5.19 Default retbleed=off mitigations=off 13 26 39 52 65 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 49.81 55.22 58.57 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: JPEG - Encode Speed: 7 Linux 5.19 Default retbleed=off mitigations=off 13 26 39 52 65 SE +/- 0.14, N = 3 SE +/- 0.07, N = 3 49.17 54.95 58.35 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: JPEG - Encode Speed: 8 Linux 5.19 Default retbleed=off mitigations=off 6 12 18 24 30 SE +/- 0.25, N = 3 SE +/- 0.06, N = 3 21.41 22.29 23.07 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
JPEG XL Decoding libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is suited for JPEG XL decode performance testing to PNG output file, the pts/jpexl test is for encode performance. The JPEG XL encoding/decoding is done using the libjxl codebase. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding libjxl 0.6.1 CPU Threads: 1 Linux 5.19 Default retbleed=off mitigations=off 11 22 33 44 55 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 41.29 45.40 47.82
Etcpak Etcpack is the self-proclaimed "fastest ETC compressor on the planet" with focused on providing open-source, very fast ETC and S3 texture compression support. The test profile uses a 8K x 8K game texture as a sample input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mpx/s, More Is Better Etcpak 1.0 Benchmark: Multi-Threaded - Configuration: ETC2 Linux 5.19 Default retbleed=off mitigations=off 200 400 600 800 1000 SE +/- 1.61, N = 3 SE +/- 0.84, N = 3 899.45 918.62 934.33 1. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread
OpenBenchmarking.org Mpx/s, More Is Better Etcpak 1.0 Benchmark: Single-Threaded - Configuration: ETC2 Linux 5.19 Default retbleed=off mitigations=off 40 80 120 160 200 SE +/- 0.14, N = 3 SE +/- 0.28, N = 3 192.84 199.01 201.44 1. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Update Random Linux 5.19 Default retbleed=off mitigations=off 60K 120K 180K 240K 300K SE +/- 1127.33, N = 3 SE +/- 537.35, N = 3 203623 230509 262794 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read While Writing retbleed=off Linux 5.19 Default mitigations=off 160K 320K 480K 640K 800K SE +/- 6644.05, N = 7 SE +/- 7501.81, N = 3 721294 729380 743750 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read Random Write Random Linux 5.19 Default retbleed=off mitigations=off 160K 320K 480K 640K 800K SE +/- 4369.92, N = 3 SE +/- 3806.18, N = 3 628801 693163 750798 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
KeyDB A benchmark of KeyDB as a multi-threaded fork of the Redis server. The KeyDB benchmark is conducted using memtier-benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ops/sec, More Is Better KeyDB 6.2.0 Linux 5.19 Default retbleed=off mitigations=off 110K 220K 330K 440K 550K SE +/- 1072.15, N = 3 SE +/- 273.79, N = 3 280920.38 383558.08 513729.13 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Ethr Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and conducting different measurements. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Packets/sec, More Is Better Ethr 1.0 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 1 Linux 5.19 Default retbleed=off mitigations=off 60K 120K 180K 240K 300K SE +/- 863.96, N = 3 SE +/- 1161.95, N = 3 182086 219141 257991 MIN: 172740 / MAX: 194630 MIN: 208860 / MAX: 237030 MIN: 232250 / MAX: 274270
OpenBenchmarking.org Packets/sec, More Is Better Ethr 1.0 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 2 Linux 5.19 Default retbleed=off mitigations=off 110K 220K 330K 440K 550K SE +/- 4908.47, N = 15 SE +/- 13984.18, N = 15 366048 438766 507280 MIN: 360050 / MAX: 371810 MIN: 282820 / MAX: 479710 MIN: 315290 / MAX: 562960
OpenBenchmarking.org Packets/sec, More Is Better Ethr 1.0 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 8 Linux 5.19 Default retbleed=off mitigations=off 300K 600K 900K 1200K 1500K SE +/- 742.37, N = 3 SE +/- 4460.19, N = 3 1007423 1261867 1506400 MIN: 980210 / MAX: 1040000 MIN: 1190000 / MAX: 1320000 MIN: 1430000 / MAX: 1560000
CLOMP CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Speedup, More Is Better CLOMP 1.2 Static OMP Speedup Linux 5.19 Default retbleed=off mitigations=off 0.4275 0.855 1.2825 1.71 2.1375 SE +/- 0.01, N = 15 SE +/- 0.00, N = 3 1.8 1.8 1.9 1. (CC) gcc options: -fopenmp -O3 -lm
PostMark This is a test of NetApp's PostMark benchmark designed to simulate small-file testing similar to the tasks endured by web and mail servers. This test profile will set PostMark to perform 25,000 transactions with 500 files simultaneously with the file sizes ranging between 5 and 512 kilobytes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance Linux 5.19 Default retbleed=off mitigations=off 1400 2800 4200 5600 7000 SE +/- 37.00, N = 3 SE +/- 59.33, N = 3 3787 5245 6697 1. (CC) gcc options: -O3
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark PageRank Linux 5.19 Default mitigations=off retbleed=off 900 1800 2700 3600 4500 SE +/- 45.41, N = 5 SE +/- 25.28, N = 3 4279.7 4074.1 4054.6 MIN: 3988.08 / MAX: 4350.95 MIN: 3678.77 / MAX: 4418.88 MIN: 3702.58 / MAX: 4344.5
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Finagle HTTP Requests Linux 5.19 Default retbleed=off mitigations=off 900 1800 2700 3600 4500 SE +/- 10.79, N = 3 SE +/- 28.18, N = 3 4428.1 4123.4 3992.6 MIN: 3967.12 / MAX: 5385.47 MIN: 3676.67 / MAX: 4967.91 MIN: 3521.83 / MAX: 5140.33
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: In-Memory Database Shootout Linux 5.19 Default retbleed=off mitigations=off 1000 2000 3000 4000 5000 SE +/- 48.98, N = 3 SE +/- 44.45, N = 3 4513.8 4277.6 3930.6 MIN: 3966.76 / MAX: 4778.05 MIN: 3848.14 / MAX: 4583.34 MIN: 3501.45 / MAX: 4438.71
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 Linux 5.19 Default retbleed=off mitigations=off 0.6314 1.2628 1.8942 2.5256 3.157 SE +/- 0.007, N = 3 SE +/- 0.002, N = 3 2.806 2.681 2.102 MIN: 2.78 / MAX: 2.9 MIN: 2.64 / MAX: 3.87 MIN: 2.08 / MAX: 2.46 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 Linux 5.19 Default retbleed=off mitigations=off 1.0825 2.165 3.2475 4.33 5.4125 SE +/- 0.030, N = 3 SE +/- 0.013, N = 3 4.811 4.662 3.842 MIN: 4.77 / MAX: 4.89 MIN: 4.54 / MAX: 50.1 MIN: 3.8 / MAX: 7.22 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: resnet-v2-50 Linux 5.19 Default retbleed=off mitigations=off 10 20 30 40 50 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 44.17 43.71 36.05 MIN: 44.04 / MAX: 49 MIN: 43.43 / MAX: 63.96 MIN: 35.9 / MAX: 52.69 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: SqueezeNetV1.0 Linux 5.19 Default retbleed=off mitigations=off 2 4 6 8 10 SE +/- 0.019, N = 3 SE +/- 0.014, N = 3 6.922 6.765 6.039 MIN: 6.87 / MAX: 8.38 MIN: 6.68 / MAX: 7.35 MIN: 5.98 / MAX: 6.41 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 Linux 5.19 Default retbleed=off mitigations=off 1.0654 2.1308 3.1962 4.2616 5.327 SE +/- 0.038, N = 3 SE +/- 0.009, N = 3 4.735 4.628 4.195 MIN: 4.66 / MAX: 26.36 MIN: 4.49 / MAX: 7.66 MIN: 4.14 / MAX: 5.74 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 Linux 5.19 Default retbleed=off mitigations=off 1.0298 2.0596 3.0894 4.1192 5.149 SE +/- 0.039, N = 3 SE +/- 0.008, N = 3 4.577 4.531 4.388 MIN: 4.52 / MAX: 21.04 MIN: 4.44 / MAX: 48.78 MIN: 4.35 / MAX: 21.29 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: inception-v3 Linux 5.19 Default retbleed=off mitigations=off 12 24 36 48 60 SE +/- 0.49, N = 3 SE +/- 0.32, N = 3 52.49 51.71 45.68 MIN: 52.33 / MAX: 56.69 MIN: 50.57 / MAX: 72.42 MIN: 44.91 / MAX: 62.77 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: shufflenet-v2 Linux 5.19 Default retbleed=off mitigations=off 1.1385 2.277 3.4155 4.554 5.6925 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 5.06 4.88 4.77 MIN: 5.02 / MAX: 5.19 MIN: 4.82 / MAX: 6.42 MIN: 4.7 / MAX: 16.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet Linux 5.19 Default retbleed=off mitigations=off 1.3275 2.655 3.9825 5.31 6.6375 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 5.90 5.67 5.57 MIN: 5.85 / MAX: 6.25 MIN: 5.61 / MAX: 7.54 MIN: 5.49 / MAX: 5.9 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: blazeface Linux 5.19 Default retbleed=off mitigations=off 0.468 0.936 1.404 1.872 2.34 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 2.08 1.93 1.91 MIN: 2.05 / MAX: 2.78 MIN: 1.91 / MAX: 2.05 MIN: 1.82 / MAX: 2.12 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m Linux 5.19 Default retbleed=off mitigations=off 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 13.40 12.18 11.41 MIN: 13.36 / MAX: 13.75 MIN: 12.12 / MAX: 12.49 MIN: 11.34 / MAX: 11.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Basis Universal Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: ETC1S Linux 5.19 Default retbleed=off mitigations=off 9 18 27 36 45 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 38.44 37.59 37.19 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 0 Linux 5.19 Default retbleed=off mitigations=off 3 6 9 12 15 SE +/- 0.10, N = 3 SE +/- 0.08, N = 11 11.70 11.36 11.19 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Ethr Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and conducting different measurements. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org us, Fewer Is Better Ethr 1.0 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 1 Linux 5.19 Default retbleed=off mitigations=off 7 14 21 28 35 SE +/- 0.29, N = 3 SE +/- 0.22, N = 3 28.44 25.59 22.81 MIN: 24.35 / MAX: 37.5 MIN: 21.4 / MAX: 35.49 MIN: 18.55 / MAX: 29.37
OpenBenchmarking.org us, Fewer Is Better Ethr 1.0 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 2 Linux 5.19 Default retbleed=off mitigations=off 7 14 21 28 35 SE +/- 0.24, N = 6 SE +/- 0.12, N = 3 28.99 24.79 22.02 MIN: 23.83 / MAX: 37.87 MIN: 20.81 / MAX: 51.31 MIN: 17.9 / MAX: 29.29
OpenBenchmarking.org us, Fewer Is Better Ethr 1.0 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 8 Linux 5.19 Default retbleed=off mitigations=off 7 14 21 28 35 SE +/- 0.18, N = 15 SE +/- 0.24, N = 4 28.48 24.97 21.82 MIN: 24.47 / MAX: 37 MIN: 20.73 / MAX: 35.83 MIN: 18.05 / MAX: 29.87
Sockperf This is a network socket API performance benchmark developed by Mellanox. This test profile runs both the client and server on the local host for evaluating individual system performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.7 Test: Latency Ping Pong Linux 5.19 Default retbleed=off mitigations=off 1.0917 2.1834 3.2751 4.3668 5.4585 SE +/- 0.014, N = 5 SE +/- 0.031, N = 5 4.852 4.157 3.544 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.7 Test: Latency Under Load Linux 5.19 Default retbleed=off mitigations=off 6 12 18 24 30 SE +/- 1.57, N = 20 SE +/- 1.15, N = 25 24.08 20.54 17.84 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
Linux 5.19 Default Kernel Notes: Transparent Huge Pages: madviseCompiler 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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=auto --with-tune=generic --without-cuda-driver -vDisk Notes: MQ-DEADLINE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf0 - Thermald 1.9.1Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04)Python Notes: Python 3.8.10Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of IBRS IBPB: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable
Testing initiated at 24 July 2022 12:39 by user phoronix.
retbleed=off Kernel Notes: Transparent Huge Pages: madviseCompiler 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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=auto --with-tune=generic --without-cuda-driver -vDisk Notes: MQ-DEADLINE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf0 - Thermald 1.9.1Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04)Python Notes: Python 3.8.10Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Vulnerable + 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 IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable
Testing initiated at 24 July 2022 19:36 by user phoronix.
mitigations=off Processor: Intel Xeon E3-1245 v5 @ 3.90GHz (4 Cores / 8 Threads), Motherboard: MSI C236A WORKSTATION (MS-7998) v1.0 (2.90 BIOS), Chipset: Intel Xeon E3-1200 v5/E3-1500, Memory: 32GB, Disk: 120GB Samsung SSD 850, Graphics: MSI Intel HD P530 SKL GT2 3GB (1150MHz), Audio: Realtek ALC1150, Monitor: VA2431, Network: Intel I219-V
OS: Ubuntu 20.04, Kernel: 5.19.0-051900rc7daily20220723-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.9, OpenGL: 4.6 Mesa 20.2.6, Vulkan: 1.2.145, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --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=auto --with-tune=generic --without-cuda-driver -vDisk Notes: MQ-DEADLINE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf0 - Thermald 1.9.1Java Notes: OpenJDK Runtime Environment (build 11.0.11+9-Ubuntu-0ubuntu2.20.04)Python Notes: Python 3.8.10Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + mmio_stale_data: Vulnerable + retbleed: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + srbds: Vulnerable + tsx_async_abort: Mitigation of TSX disabled
Testing initiated at 25 July 2022 20:54 by user phoronix.