Intel Tiger Lake Mitigation COmparison Tests for a possible future article by Michael Larabel. The "Ice Lake" and "Tiger Lake" numbers are from prior article testing. The "TGL ReRun 58" is from re-testing on Ubuntu 20.10 with all latest stable updates as of latest testing (notable significant update since then is newer Firefox as worth mentioning for any Firefox changes compared to original numbers, due to their new Warp JS). The "TGL Linux 5.10" results are when using the Linux 5.10 Git kernel from the Ubuntu Mainline Kernel PPA. Linux 5.10 results more in line with expectations.
HTML result view exported from: https://openbenchmarking.org/result/2102245-HA-2012136HA60&sor .
Intel Tiger Lake Mitigation COmparison Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution OpenCL Ice Lake: Default Ice Lake: mitigations=off Tiger Lake: Default Tiger Lake: mitigations=off TGL ReRun 58: Default TGL ReRun 58: mitigations=off TGL Linux 5.10: Default TGL Linux 5.10: mitigations=off my tiger lake, default my tiger lake, unmitigated Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads) Dell 06CDVY (1.0.9 BIOS) Intel Device 34ef 16GB Toshiba KBG40ZPZ512G NVMe 512GB Intel Iris Plus G7 3GB (1100MHz) Realtek ALC289 Intel Killer Wi-Fi 6 AX1650i 160MHz Ubuntu 20.10 5.8.0-25-generic (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 modesetting 1.20.9 4.6 Mesa 20.2.1 1.2.145 GCC 10.2.0 ext4 1920x1200 Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads) Dell 0GG9PT (1.0.3 BIOS) Intel Tiger Lake-LP Kioxia KBG40ZNS256G NVMe 256GB Intel UHD 3GB (1300MHz) Intel Wi-Fi 6 AX201 5.8.0-31-generic (x86_64) 5.10.0-051000rc7daily20201213-generic (x86_64) 20201212 LENOVO LNVNB161216 (FBCN23WW BIOS) 8GB 512GB SAMSUNG MZVL2512HCJQ-00BL2 Intel Iris Xe 3GB (1300MHz) Realtek ALC287 ManjaroLinux 20.2.1 5.11.1-1-MANJARO (x86_64) GNOME Shell 3.38.3 X Server 1.20.10 intel 4.6 Mesa 20.3.4 OpenCL 3.0 GCC 10.2.0 + Clang 11.1.0 1600x900 OpenBenchmarking.org Compiler Details - Ice Lake: Default, Ice Lake: mitigations=off, Tiger Lake: Default, Tiger Lake: mitigations=off, TGL ReRun 58: Default, TGL ReRun 58: mitigations=off, TGL Linux 5.10: Default, TGL Linux 5.10: mitigations=off: --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/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 Disk Details - Ice Lake: Default: NONE / errors=remount-ro,relatime,rw - Ice Lake: mitigations=off: NONE / errors=remount-ro,relatime,rw - Tiger Lake: Default: NONE / errors=remount-ro,relatime,rw - Tiger Lake: mitigations=off: NONE / errors=remount-ro,relatime,rw - TGL ReRun 58: Default: NONE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - Ice Lake: Default: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x78 - Thermald 2.3 - Ice Lake: mitigations=off: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x78 - Thermald 2.3 - Tiger Lake: Default: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3 - Tiger Lake: mitigations=off: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3 - TGL ReRun 58: Default: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3 - TGL ReRun 58: mitigations=off: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3 - TGL Linux 5.10: Default: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3 - TGL Linux 5.10: mitigations=off: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3 - my tiger lake, default: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x66 - Thermald 2.4.2 - my tiger lake, unmitigated: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x66 - Thermald 2.4.2 Java Details - Ice Lake: Default: OpenJDK Runtime Environment (build 11.0.9+10-post-Ubuntu-0ubuntu1) - Ice Lake: mitigations=off: OpenJDK Runtime Environment (build 11.0.9+10-post-Ubuntu-0ubuntu1) - Tiger Lake: Default: OpenJDK Runtime Environment (build 11.0.9+10-post-Ubuntu-0ubuntu1) - Tiger Lake: mitigations=off: OpenJDK Runtime Environment (build 11.0.9+10-post-Ubuntu-0ubuntu1) - TGL ReRun 58: Default: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10) - TGL ReRun 58: mitigations=off: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10) - TGL Linux 5.10: Default: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10) - TGL Linux 5.10: mitigations=off: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10) Python Details - Ice Lake: Default: Python 3.8.6 - Ice Lake: mitigations=off: Python 3.8.6 - Tiger Lake: Default: Python 3.8.6 - Tiger Lake: mitigations=off: Python 3.8.6 - TGL ReRun 58: Default: Python 3.8.6 - TGL ReRun 58: mitigations=off: Python 3.8.6 - TGL Linux 5.10: Default: Python 3.8.6 - TGL Linux 5.10: mitigations=off: Python 3.8.6 - my tiger lake, default: Python 3.9.1 - my tiger lake, unmitigated: Python 3.9.1 Security Details - Ice Lake: Default: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - Ice Lake: mitigations=off: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + 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: Not affected + tsx_async_abort: Not affected - Tiger Lake: Default: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - Tiger Lake: mitigations=off: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + 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: Not affected + tsx_async_abort: Not affected - TGL ReRun 58: Default: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - TGL ReRun 58: mitigations=off: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + 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: Not affected + tsx_async_abort: Not affected - TGL Linux 5.10: Default: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - TGL Linux 5.10: mitigations=off: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + 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: Not affected + tsx_async_abort: Not affected - my tiger lake, default: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - my tiger lake, unmitigated: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + 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: Not affected + tsx_async_abort: Not affected Kernel Details - my tiger lake, default, my tiger lake, unmitigated: Transparent Huge Pages: madvise
Intel Tiger Lake Mitigation COmparison sockperf: Throughput dacapobench: Jython renaissance: Twitter HTTP Requests tensorflow-lite: SqueezeNet tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Quant tensorflow-lite: Inception ResNet V2 sqlite-speedtest: Timed Time - Size 1,000 gimp: auto-levels gimp: unsharp-mask caffe: AlexNet - CPU - 100 caffe: GoogleNet - CPU - 100 mnn: resnet-v2-50 mnn: inception-v3 ncnn: CPU - vgg16 ncnn: CPU - resnet18 ncnn: CPU - alexnet ncnn: CPU - yolov4-tiny rocksdb: Rand Read pyperformance: pathlib selenium: Kraken - Firefox selenium: WebXPRT - Firefox selenium: Jetstream 2 - Firefox selenium: ARES-6 - Google Chrome selenium: Kraken - Google Chrome selenium: Octane - Google Chrome selenium: WebXPRT - Google Chrome selenium: Jetstream - Google Chrome selenium: CanvasMark - Google Chrome selenium: StyleBench - Google Chrome selenium: Jetstream 2 - Google Chrome selenium: WASM imageConvolute - Google Chrome gimp: auto-levels gimp: unsharp-mask mnn: SqueezeNetV1.0 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 ncnn: CPU - squeezenet ncnn: CPU - mobilenet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - efficientnet-b0 ncnn: CPU - blazeface ncnn: CPU - googlenet ncnn: CPU - resnet50 Ice Lake: Default Ice Lake: mitigations=off Tiger Lake: Default Tiger Lake: mitigations=off TGL ReRun 58: Default TGL ReRun 58: mitigations=off TGL Linux 5.10: Default TGL Linux 5.10: mitigations=off my tiger lake, default my tiger lake, unmitigated 554537 5101 3842.164 674153 494187 455175 8917553 61.215 13.008 15.709 66912 179934 66.588 80.481 80.68 25.02 22.05 47.55 12925515 16.8 830.7 241 91.648 19.76 799.3 53717 225 242.78 14994 33.5 138.439 32.6245 582151 4414 3525.294 646988 495179 456401 8905090 59.986 12.313 15.740 64140 176908 63.444 77.032 75.59 24.33 21.47 46.83 13732080 16.1 752.7 264 99.720 19.77 806.0 53635 227 250.94 15149 34.0 140.146 32.6082 767117 3843 2487.367 564437 406430 372045 7382540 51.251 11.266 13.345 84931 216420 54.541 68.288 71.04 21.30 18.64 40.44 15791136 13.9 671.9 288 108.423 16.60 668.2 61608 281 289.55 17698 39.6 165.909 28.2575 738032 4113 2533.808 588506 430449 394514 7765500 53.138 11.670 13.990 89846 226788 57.668 73.116 75.98 23.20 20.15 43.82 15304072 14.2 610.5 299 115.080 17.32 701.8 58235 269 276.88 16864 38.5 158.473 29.2972 773590 3425 2515.071 567661 409558 376005 7434223 51.006 11.160 13.415 84246 214784 53.954 67.671 70.42 21.21 18.6 40.02 15871303 13.7 1005.7 267 86.921 16.19 661.7 61369 279 289.93 20485 42.6 165.154 28.699 741680.92 3630.21 2593.01 581732.98611111 411997.95918367 378435.37414966 7525608.8435374 53.13 11.180 13.486 85939.795918367 225830.52631579 56.10 70.12 72.64 21.93 19.21 41.28 15589035.71 14.26 938.67 292 93.32499 17.80 680.40 57008 253 272.2531 19667 39.576 153.70846 29.38 760189 3471 2540.388 559412 404421 369926 7349897 50.848 11.087 13.317 84009 213883 53.814 67.698 69.82 21.15 18.47 39.89 16151167 13.9 1004.1 268 87.346 16.16 656.8 62304 278 292.24 21237 42.9 164.687 28.6120 733327 3460 2443.830 558600 403126 368982 7352977 50.685 11.068 13.326 83965 213543 53.201 66.247 70.11 21.20 18.57 40.29 15900784 13.9 886.9 296 96.285 16.07 678.0 62405 277 292.30 21010 43.0 166.769 28.2868 644502 395875 286649 270998 5231100 49.886 35.891 44.125 70.45 15.63 20.28 29.58 24236402 12.8 890.0 97.481 10.970 12.691 7.354 4.018 5.555 19.12 22.17 5.63 4.79 3.75 5.19 7.49 1.52 16.42 33.42 636293 396356 289256 272762 5268597 49.294 36.059 43.627 69.68 15.63 19.32 29.11 24016638 13.0 796.8 106.771 10.666 12.290 7.222 4.012 5.567 18.77 21.95 5.56 4.70 3.75 5.18 7.44 1.53 16.41 33.64 OpenBenchmarking.org
Sockperf Test: Throughput OpenBenchmarking.org Messages Per Second, More Is Better Sockperf 3.4 Test: Throughput TGL ReRun 58: Default Tiger Lake: Default TGL Linux 5.10: Default TGL ReRun 58: mitigations=off Tiger Lake: mitigations=off TGL Linux 5.10: mitigations=off my tiger lake, default my tiger lake, unmitigated Ice Lake: mitigations=off Ice Lake: Default 170K 340K 510K 680K 850K SE +/- 5771.94, N = 11 SE +/- 9040.07, N = 25 SE +/- 5678.70, N = 5 SE +/- 9852.43, N = 20 SE +/- 8183.20, N = 5 SE +/- 6828.62, N = 25 SE +/- 2778.53, N = 5 SE +/- 3620.61, N = 5 SE +/- 6985.56, N = 5 SE +/- 2421.79, N = 5 773590.00 767117.00 760189.00 741680.92 738032.00 733327.00 644502.00 636293.00 582151.00 554537.00 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
DaCapo Benchmark Java Test: Jython TGL ReRun 58 TGL Linux 5.10 Tiger Lake Ice Lake OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Default mitigations=off 1100 2200 3300 4400 5500 SE +/- 7.95, N = 4 SE +/- 25.57, N = 4 SE +/- 33.94, N = 5 SE +/- 39.09, N = 4 SE +/- 38.95, N = 20 SE +/- 50.55, N = 5 SE +/- 45.07, N = 4 SE +/- 93.22, N = 16 3425.00 3630.21 3460.00 3471.00 3843.00 4113.00 4414.00 5101.00
Renaissance Test: Twitter HTTP Requests TGL Linux 5.10 Tiger Lake TGL ReRun 58 Ice Lake OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Twitter HTTP Requests mitigations=off Default 800 1600 2400 3200 4000 SE +/- 11.73, N = 5 SE +/- 14.45, N = 5 SE +/- 10.30, N = 5 SE +/- 11.39, N = 5 SE +/- 16.33, N = 5 SE +/- 18.14, N = 5 SE +/- 33.64, N = 25 SE +/- 45.02, N = 5 2443.83 2540.39 2487.37 2533.81 2515.07 2593.01 3525.29 3842.16
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet my tiger lake, default my tiger lake, unmitigated TGL Linux 5.10: mitigations=off TGL Linux 5.10: Default Tiger Lake: Default TGL ReRun 58: Default TGL ReRun 58: mitigations=off Tiger Lake: mitigations=off Ice Lake: mitigations=off Ice Lake: Default 140K 280K 420K 560K 700K SE +/- 2335.83, N = 3 SE +/- 2537.13, N = 3 SE +/- 4682.82, N = 3 SE +/- 4476.17, N = 3 SE +/- 4132.54, N = 3 SE +/- 3215.23, N = 3 SE +/- 4523.41, N = 3 SE +/- 6328.07, N = 3 SE +/- 12430.05, N = 14 SE +/- 5183.16, N = 15 395875.00 396356.00 558600.00 559412.00 564437.00 567661.00 581732.99 588506.00 646988.00 674153.00
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile my tiger lake, default my tiger lake, unmitigated TGL Linux 5.10: mitigations=off TGL Linux 5.10: Default Tiger Lake: Default TGL ReRun 58: Default TGL ReRun 58: mitigations=off Tiger Lake: mitigations=off Ice Lake: Default Ice Lake: mitigations=off 110K 220K 330K 440K 550K SE +/- 960.49, N = 3 SE +/- 1561.84, N = 3 SE +/- 2843.05, N = 3 SE +/- 2967.19, N = 3 SE +/- 2818.20, N = 3 SE +/- 3076.30, N = 3 SE +/- 3203.98, N = 3 SE +/- 3141.38, N = 3 SE +/- 3688.05, N = 3 SE +/- 2851.71, N = 3 286649.00 289256.00 403126.00 404421.00 406430.00 409558.00 411997.96 430449.00 494187.00 495179.00
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant my tiger lake, default my tiger lake, unmitigated TGL Linux 5.10: mitigations=off TGL Linux 5.10: Default Tiger Lake: Default TGL ReRun 58: Default TGL ReRun 58: mitigations=off Tiger Lake: mitigations=off Ice Lake: Default Ice Lake: mitigations=off 100K 200K 300K 400K 500K SE +/- 670.99, N = 3 SE +/- 677.12, N = 3 SE +/- 2493.36, N = 3 SE +/- 2976.32, N = 3 SE +/- 2509.46, N = 3 SE +/- 2667.17, N = 3 SE +/- 2912.75, N = 3 SE +/- 2832.59, N = 3 SE +/- 3093.36, N = 3 SE +/- 3375.54, N = 3 270998.00 272762.00 368982.00 369926.00 372045.00 376005.00 378435.37 394514.00 455175.00 456401.00
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 my tiger lake, default my tiger lake, unmitigated TGL Linux 5.10: Default TGL Linux 5.10: mitigations=off Tiger Lake: Default TGL ReRun 58: Default TGL ReRun 58: mitigations=off Tiger Lake: mitigations=off Ice Lake: mitigations=off Ice Lake: Default 2M 4M 6M 8M 10M SE +/- 10551.93, N = 3 SE +/- 5371.66, N = 3 SE +/- 6529.42, N = 3 SE +/- 7453.09, N = 3 SE +/- 5564.33, N = 3 SE +/- 8367.51, N = 3 SE +/- 6570.47, N = 3 SE +/- 1537.93, N = 3 SE +/- 14703.15, N = 3 SE +/- 2473.50, N = 3 5231100.00 5268597.00 7349897.00 7352977.00 7382540.00 7434223.00 7525608.84 7765500.00 8905090.00 8917553.00
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 my tiger lake, unmitigated my tiger lake, default TGL Linux 5.10: mitigations=off TGL Linux 5.10: Default TGL ReRun 58: Default Tiger Lake: Default TGL ReRun 58: mitigations=off Tiger Lake: mitigations=off Ice Lake: mitigations=off Ice Lake: Default 14 28 42 56 70 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.33, N = 3 SE +/- 0.53, N = 3 SE +/- 0.28, N = 3 SE +/- 0.29, N = 3 SE +/- 0.56, N = 3 SE +/- 0.50, N = 3 SE +/- 0.22, N = 3 SE +/- 0.96, N = 3 49.29 49.89 50.69 50.85 51.01 51.25 53.13 53.14 59.99 61.22 1. (CC) gcc options: -O2 -ldl -lz -lpthread
GIMP Test: auto-levels TGL Linux 5.10 TGL ReRun 58 Tiger Lake Ice Lake OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: auto-levels mitigations=off Default 3 6 9 12 15 SE +/- 0.10, N = 3 SE +/- 0.14, N = 3 SE +/- 0.10, N = 8 SE +/- 0.11, N = 6 SE +/- 0.11, N = 9 SE +/- 0.12, N = 8 SE +/- 0.12, N = 3 SE +/- 0.15, N = 7 11.07 11.09 11.16 11.18 11.27 11.67 12.31 13.01
GIMP Test: unsharp-mask TGL Linux 5.10 Tiger Lake TGL ReRun 58 Ice Lake OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: unsharp-mask Default mitigations=off 4 8 12 16 20 SE +/- 0.12, N = 12 SE +/- 0.10, N = 12 SE +/- 0.13, N = 9 SE +/- 0.14, N = 9 SE +/- 0.09, N = 15 SE +/- 0.14, N = 12 SE +/- 0.21, N = 5 SE +/- 0.16, N = 15 13.32 13.33 13.35 13.99 13.42 13.49 15.71 15.74
Caffe Model: AlexNet - Acceleration: CPU - Iterations: 100 Ice Lake TGL Linux 5.10 TGL ReRun 58 Tiger Lake OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 100 mitigations=off Default 20K 40K 60K 80K 100K SE +/- 873.74, N = 3 SE +/- 396.22, N = 3 SE +/- 455.74, N = 3 SE +/- 593.84, N = 3 SE +/- 380.75, N = 3 SE +/- 414.84, N = 3 SE +/- 561.91, N = 3 SE +/- 434.17, N = 3 64140.00 66912.00 83965.00 84009.00 84246.00 85939.80 84931.00 89846.00 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
Caffe Model: GoogleNet - Acceleration: CPU - Iterations: 100 Ice Lake TGL Linux 5.10 TGL ReRun 58 Tiger Lake OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 100 mitigations=off Default 50K 100K 150K 200K 250K SE +/- 739.79, N = 3 SE +/- 269.90, N = 3 SE +/- 455.98, N = 3 SE +/- 553.87, N = 3 SE +/- 543.36, N = 3 SE +/- 626.06, N = 3 SE +/- 393.32, N = 3 SE +/- 351.65, N = 3 176908.00 179934.00 213543.00 213883.00 214784.00 225830.53 216420.00 226788.00 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: resnet-v2-50 my tiger lake, default my tiger lake, unmitigated TGL Linux 5.10: mitigations=off TGL Linux 5.10: Default TGL ReRun 58: Default Tiger Lake: Default TGL ReRun 58: mitigations=off Tiger Lake: mitigations=off Ice Lake: mitigations=off Ice Lake: Default 15 30 45 60 75 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.19, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.20, N = 3 SE +/- 0.34, N = 3 35.89 36.06 53.20 53.81 53.95 54.54 56.10 57.67 63.44 66.59 MIN: 34.72 / MAX: 48.94 MIN: 35.06 / MAX: 48.88 MIN: 51.25 / MAX: 70.06 MIN: 52.22 / MAX: 69.59 MIN: 51.83 / MAX: 69.79 MIN: 52.47 / MAX: 71.35 MIN: 52.17 / MAX: 88 MIN: 56.81 / MAX: 91.45 MIN: 62.42 / MAX: 109.96 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
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: inception-v3 my tiger lake, unmitigated my tiger lake, default TGL Linux 5.10: mitigations=off TGL ReRun 58: Default TGL Linux 5.10: Default Tiger Lake: Default TGL ReRun 58: mitigations=off Tiger Lake: mitigations=off Ice Lake: mitigations=off Ice Lake: Default 20 40 60 80 100 SE +/- 0.31, N = 3 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.17, N = 3 SE +/- 0.29, N = 3 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.72, N = 3 SE +/- 0.50, N = 3 43.63 44.13 66.25 67.67 67.70 68.29 70.12 73.12 77.03 80.48 MIN: 40.55 / MAX: 67.13 MIN: 41.39 / MAX: 57.22 MIN: 64.97 / MAX: 87.52 MIN: 65.82 / MAX: 84.07 MIN: 65.66 / MAX: 83.26 MIN: 66.59 / MAX: 84.15 MIN: 68.33 / MAX: 117.84 MIN: 70.4 / MAX: 108.37 MIN: 77.49 / MAX: 99.85 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 Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: vgg16 my tiger lake, unmitigated TGL Linux 5.10: Default TGL Linux 5.10: mitigations=off TGL ReRun 58: Default my tiger lake, default Tiger Lake: Default TGL ReRun 58: mitigations=off Ice Lake: mitigations=off Tiger Lake: mitigations=off Ice Lake: Default 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.23, N = 3 SE +/- 0.05, N = 3 SE +/- 0.24, N = 3 SE +/- 0.12, N = 3 SE +/- 0.14, N = 3 SE +/- 1.31, N = 4 SE +/- 0.19, N = 3 SE +/- 0.11, N = 3 69.68 69.82 70.11 70.42 70.45 71.04 72.64 75.59 75.98 80.68 MIN: 68.86 / MAX: 80.75 MIN: 66.13 / MAX: 82.99 MIN: 65.99 / MAX: 84.04 MIN: 66.85 / MAX: 83.65 MIN: 69.47 / MAX: 79.89 MIN: 67.45 / MAX: 85.82 MIN: 70.5 / MAX: 95.89 MIN: 71.7 / MAX: 102.99 MIN: 76.5 / MAX: 103.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet18 my tiger lake, default my tiger lake, unmitigated TGL Linux 5.10: Default TGL Linux 5.10: mitigations=off TGL ReRun 58: Default Tiger Lake: Default TGL ReRun 58: mitigations=off Tiger Lake: mitigations=off Ice Lake: mitigations=off Ice Lake: Default 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.51, N = 4 SE +/- 0.04, N = 3 15.63 15.63 21.15 21.20 21.21 21.30 21.93 23.20 24.33 25.02 MIN: 15.35 / MAX: 17.48 MIN: 15.31 / MAX: 17.59 MIN: 18.49 / MAX: 32.54 MIN: 18.49 / MAX: 34.99 MIN: 18.54 / MAX: 23.48 MIN: 18.47 / MAX: 34.83 MIN: 20.27 / MAX: 38 MIN: 20.42 / MAX: 41.66 MIN: 22.42 / MAX: 37.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: alexnet TGL Linux 5.10: Default TGL Linux 5.10: mitigations=off TGL ReRun 58: Default Tiger Lake: Default TGL ReRun 58: mitigations=off my tiger lake, unmitigated Tiger Lake: mitigations=off my tiger lake, default Ice Lake: mitigations=off Ice Lake: Default 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.38, N = 4 SE +/- 0.02, N = 3 18.47 18.57 18.60 18.64 19.21 19.32 20.15 20.28 21.47 22.05 MIN: 17.18 / MAX: 24.96 MIN: 17.14 / MAX: 25.33 MIN: 17.18 / MAX: 27.55 MIN: 17.18 / MAX: 29.18 MIN: 18.89 / MAX: 28.54 MIN: 18.45 / MAX: 58.96 MIN: 19.88 / MAX: 30.06 MIN: 19.64 / MAX: 34.78 MIN: 20.64 / MAX: 34.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: yolov4-tiny my tiger lake, unmitigated my tiger lake, default TGL Linux 5.10: Default TGL ReRun 58: Default TGL Linux 5.10: mitigations=off Tiger Lake: Default TGL ReRun 58: mitigations=off Tiger Lake: mitigations=off Ice Lake: mitigations=off Ice Lake: Default 11 22 33 44 55 SE +/- 0.08, N = 3 SE +/- 0.41, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.16, N = 3 SE +/- 0.19, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.64, N = 4 SE +/- 0.04, N = 3 29.11 29.58 39.89 40.02 40.29 40.44 41.28 43.82 46.83 47.55 MIN: 28.66 / MAX: 31.99 MIN: 28.89 / MAX: 32.82 MIN: 38.41 / MAX: 50.73 MIN: 38.59 / MAX: 48.41 MIN: 38.49 / MAX: 52.32 MIN: 38.52 / MAX: 52.97 MIN: 41.38 / MAX: 88.84 MIN: 42.33 / MAX: 59.43 MIN: 45.86 / MAX: 62.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read my tiger lake, default my tiger lake, unmitigated TGL Linux 5.10: Default TGL Linux 5.10: mitigations=off TGL ReRun 58: Default Tiger Lake: Default TGL ReRun 58: mitigations=off Tiger Lake: mitigations=off Ice Lake: mitigations=off Ice Lake: Default 5M 10M 15M 20M 25M SE +/- 240154.22, N = 3 SE +/- 172073.57, N = 3 SE +/- 228211.34, N = 3 SE +/- 127649.37, N = 9 SE +/- 113483.52, N = 12 SE +/- 224908.53, N = 3 SE +/- 120229.46, N = 10 SE +/- 150814.30, N = 3 SE +/- 208149.62, N = 15 SE +/- 123171.35, N = 15 24236402.00 24016638.00 16151167.00 15900784.00 15871303.00 15791136.00 15589035.71 15304072.00 13732080.00 12925515.00 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
PyPerformance Benchmark: pathlib OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pathlib my tiger lake, default my tiger lake, unmitigated TGL ReRun 58: Default Tiger Lake: Default TGL Linux 5.10: Default TGL Linux 5.10: mitigations=off Tiger Lake: mitigations=off TGL ReRun 58: mitigations=off Ice Lake: mitigations=off Ice Lake: Default 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.15, N = 5 SE +/- 0.09, N = 3 SE +/- 0.17, N = 3 SE +/- 0.19, N = 3 SE +/- 0.15, N = 3 SE +/- 0.17, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 12.80 13.00 13.70 13.90 13.90 13.90 14.20 14.26 16.10 16.80
Selenium Benchmark: Kraken - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: Kraken - Browser: Firefox Tiger Lake: mitigations=off Tiger Lake: Default Ice Lake: mitigations=off my tiger lake, unmitigated Ice Lake: Default TGL Linux 5.10: mitigations=off my tiger lake, default TGL ReRun 58: mitigations=off TGL Linux 5.10: Default TGL ReRun 58: Default 200 400 600 800 1000 SE +/- 0.73, N = 3 SE +/- 1.35, N = 3 SE +/- 1.72, N = 3 SE +/- 3.47, N = 3 SE +/- 1.20, N = 3 SE +/- 2.55, N = 3 SE +/- 5.50, N = 3 SE +/- 1.19, N = 3 SE +/- 2.10, N = 3 SE +/- 2.62, N = 3 610.50 671.90 752.70 796.80 830.70 886.90 890.00 938.67 1004.10 1005.70 1. Tiger Lake: mitigations=off: firefox 81.0.2 2. Tiger Lake: Default: firefox 81.0.2 3. Ice Lake: mitigations=off: firefox 82.0 4. my tiger lake, unmitigated: firefox 86.0 5. Ice Lake: Default: firefox 82.0 6. TGL Linux 5.10: mitigations=off: firefox 83.0 7. my tiger lake, default: firefox 86.0 8. TGL ReRun 58: mitigations=off: firefox 83.0 9. TGL Linux 5.10: Default: firefox 83.0 10. TGL ReRun 58: Default: firefox 83.0
Selenium Benchmark: WebXPRT - Browser: Firefox Tiger Lake TGL Linux 5.10 TGL ReRun 58 Ice Lake OpenBenchmarking.org Score, More Is Better Selenium Benchmark: WebXPRT - Browser: Firefox mitigations=off Default 70 140 210 280 350 SE +/- 0.33, N = 3 SE +/- 1.00, N = 2 SE +/- 0.58, N = 3 SE +/- 2.03, N = 3 SE +/- 1.53, N = 3 SE +/- 0.88, N = 3 299 288 296 268 292 267 264 241 1. firefox 82.0
Selenium Benchmark: Jetstream 2 - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream 2 - Browser: Firefox Tiger Lake: mitigations=off Tiger Lake: Default my tiger lake, unmitigated Ice Lake: mitigations=off my tiger lake, default TGL Linux 5.10: mitigations=off TGL ReRun 58: mitigations=off Ice Lake: Default TGL Linux 5.10: Default TGL ReRun 58: Default 30 60 90 120 150 SE +/- 1.47, N = 5 SE +/- 0.86, N = 3 SE +/- 0.55, N = 3 SE +/- 0.55, N = 3 SE +/- 1.19, N = 4 SE +/- 0.42, N = 3 SE +/- 1.14, N = 3 SE +/- 0.36, N = 3 SE +/- 0.14, N = 3 SE +/- 0.76, N = 3 115.08 108.42 106.77 99.72 97.48 96.29 93.32 91.65 87.35 86.92 1. Tiger Lake: mitigations=off: firefox 81.0.2 2. Tiger Lake: Default: firefox 81.0.2 3. my tiger lake, unmitigated: firefox 86.0 4. Ice Lake: mitigations=off: firefox 82.0 5. my tiger lake, default: firefox 86.0 6. TGL Linux 5.10: mitigations=off: firefox 83.0 7. TGL ReRun 58: mitigations=off: firefox 83.0 8. Ice Lake: Default: firefox 82.0 9. TGL Linux 5.10: Default: firefox 83.0 10. TGL ReRun 58: Default: firefox 83.0
Selenium Benchmark: ARES-6 - Browser: Google Chrome TGL Linux 5.10 TGL ReRun 58 Tiger Lake Ice Lake OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: ARES-6 - Browser: Google Chrome mitigations=off Default 5 10 15 20 25 SE +/- 0.14, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.14, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 16.07 16.16 16.19 17.80 16.60 17.32 19.76 19.77 1. chrome 86.0.4240.111
Selenium Benchmark: Kraken - Browser: Google Chrome TGL Linux 5.10 TGL ReRun 58 Tiger Lake Ice Lake OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: Kraken - Browser: Google Chrome Default mitigations=off 200 400 600 800 1000 SE +/- 3.01, N = 3 SE +/- 4.40, N = 3 SE +/- 1.95, N = 3 SE +/- 1.46, N = 3 SE +/- 1.55, N = 3 SE +/- 9.46, N = 3 SE +/- 2.47, N = 3 SE +/- 3.34, N = 3 656.80 678.00 661.70 680.40 668.20 701.80 799.30 806.00 1. chrome 86.0.4240.111
Selenium Benchmark: Octane - Browser: Google Chrome TGL Linux 5.10 Tiger Lake TGL ReRun 58 Ice Lake OpenBenchmarking.org Geometric Mean, More Is Better Selenium Benchmark: Octane - Browser: Google Chrome mitigations=off Default 13K 26K 39K 52K 65K SE +/- 817.53, N = 3 SE +/- 780.90, N = 3 SE +/- 1033.11, N = 3 SE +/- 745.81, N = 5 SE +/- 422.22, N = 13 SE +/- 605.64, N = 5 SE +/- 67.56, N = 3 SE +/- 159.67, N = 3 62405 62304 61608 58235 61369 57008 53717 53635 1. chrome 86.0.4240.111
Selenium Benchmark: WebXPRT - Browser: Google Chrome Tiger Lake TGL ReRun 58 TGL Linux 5.10 Ice Lake OpenBenchmarking.org Score, More Is Better Selenium Benchmark: WebXPRT - Browser: Google Chrome Default mitigations=off 60 120 180 240 300 SE +/- 0.58, N = 3 SE +/- 1.00, N = 3 SE +/- 2.91, N = 3 SE +/- 1.86, N = 3 SE +/- 2.08, N = 3 SE +/- 3.06, N = 3 SE +/- 2.08, N = 3 281 269 279 253 278 277 227 225 1. chrome 86.0.4240.111
Selenium Benchmark: Jetstream - Browser: Google Chrome TGL Linux 5.10 TGL ReRun 58 Tiger Lake Ice Lake OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream - Browser: Google Chrome mitigations=off Default 60 120 180 240 300 SE +/- 0.18, N = 3 SE +/- 0.43, N = 3 SE +/- 0.22, N = 3 SE +/- 0.75, N = 3 SE +/- 1.20, N = 3 SE +/- 0.73, N = 3 SE +/- 0.84, N = 3 SE +/- 0.87, N = 3 292.30 292.24 289.93 272.25 289.55 276.88 250.94 242.78 1. chrome 86.0.4240.111
Selenium Benchmark: CanvasMark - Browser: Google Chrome TGL Linux 5.10 TGL ReRun 58 Tiger Lake Ice Lake OpenBenchmarking.org Score, More Is Better Selenium Benchmark: CanvasMark - Browser: Google Chrome Default mitigations=off 5K 10K 15K 20K 25K SE +/- 209.48, N = 3 SE +/- 293.33, N = 3 SE +/- 254.54, N = 4 SE +/- 145.83, N = 3 SE +/- 200.87, N = 12 SE +/- 151.73, N = 10 SE +/- 107.22, N = 3 SE +/- 144.97, N = 9 21237 21010 20485 19667 17698 16864 15149 14994 1. chrome 86.0.4240.111
Selenium Benchmark: StyleBench - Browser: Google Chrome TGL Linux 5.10 TGL ReRun 58 Tiger Lake Ice Lake OpenBenchmarking.org Runs / Minute, More Is Better Selenium Benchmark: StyleBench - Browser: Google Chrome mitigations=off Default 10 20 30 40 50 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.13, N = 3 43.00 42.90 42.60 39.58 39.60 38.50 34.00 33.50 1. chrome 86.0.4240.111
Selenium Benchmark: Jetstream 2 - Browser: Google Chrome TGL Linux 5.10 Tiger Lake TGL ReRun 58 Ice Lake OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream 2 - Browser: Google Chrome mitigations=off Default 40 80 120 160 200 SE +/- 1.14, N = 3 SE +/- 0.37, N = 3 SE +/- 0.51, N = 3 SE +/- 0.72, N = 3 SE +/- 2.37, N = 3 SE +/- 0.42, N = 3 SE +/- 0.64, N = 3 SE +/- 0.40, N = 3 166.77 164.69 165.91 158.47 165.15 153.71 140.15 138.44 1. chrome 86.0.4240.111
Selenium Benchmark: WASM imageConvolute - Browser: Google Chrome Tiger Lake TGL Linux 5.10 TGL ReRun 58 Ice Lake OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM imageConvolute - Browser: Google Chrome Default mitigations=off 8 16 24 32 40 SE +/- 0.10, N = 3 SE +/- 0.25, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.34, N = 3 28.26 29.30 28.29 28.61 28.70 29.38 32.61 32.62 1. chrome 86.0.4240.111
GIMP Test: auto-levels OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.22 Test: auto-levels my tiger lake, unmitigated my tiger lake, default 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 10.67 10.97
GIMP Test: unsharp-mask OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.22 Test: unsharp-mask my tiger lake, unmitigated my tiger lake, default 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 12.29 12.69
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 my tiger lake, unmitigated my tiger lake, default 2 4 6 8 10 SE +/- 0.029, N = 3 SE +/- 0.047, N = 3 7.222 7.354 MIN: 7 / MAX: 20.12 MIN: 7.11 / MAX: 19.8 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
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 my tiger lake, unmitigated my tiger lake, default 0.9041 1.8082 2.7123 3.6164 4.5205 SE +/- 0.021, N = 3 SE +/- 0.003, N = 3 4.012 4.018 MIN: 3.87 / MAX: 16.89 MIN: 3.9 / MAX: 16.8 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
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 my tiger lake, default my tiger lake, unmitigated 1.2526 2.5052 3.7578 5.0104 6.263 SE +/- 0.005, N = 3 SE +/- 0.026, N = 3 5.555 5.567 MIN: 5.35 / MAX: 17.38 MIN: 5.36 / MAX: 18.02 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 Target: CPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet my tiger lake, unmitigated my tiger lake, default 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.19, N = 3 18.77 19.12 MIN: 18.46 / MAX: 20.95 MIN: 18.68 / MAX: 21.45 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenet my tiger lake, unmitigated my tiger lake, default 5 10 15 20 25 SE +/- 0.12, N = 3 SE +/- 0.30, N = 3 21.95 22.17 MIN: 21.45 / MAX: 31.62 MIN: 21.51 / MAX: 31.99 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v2-v2 - Model: mobilenet-v2 my tiger lake, unmitigated my tiger lake, default 1.2668 2.5336 3.8004 5.0672 6.334 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 5.56 5.63 MIN: 5.47 / MAX: 7.25 MIN: 5.55 / MAX: 7.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v3-v3 - Model: mobilenet-v3 my tiger lake, unmitigated my tiger lake, default 1.0778 2.1556 3.2334 4.3112 5.389 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.70 4.79 MIN: 4.61 / MAX: 6.48 MIN: 4.69 / MAX: 6.7 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: shufflenet-v2 my tiger lake, default my tiger lake, unmitigated 0.8438 1.6876 2.5314 3.3752 4.219 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 3.75 3.75 MIN: 3.68 / MAX: 5.17 MIN: 3.69 / MAX: 5.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mnasnet my tiger lake, unmitigated my tiger lake, default 1.1678 2.3356 3.5034 4.6712 5.839 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 5.18 5.19 MIN: 5.09 / MAX: 7.04 MIN: 5.11 / MAX: 7.11 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: efficientnet-b0 my tiger lake, unmitigated my tiger lake, default 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 7.44 7.49 MIN: 7.3 / MAX: 9.87 MIN: 7.39 / MAX: 9.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: blazeface my tiger lake, default my tiger lake, unmitigated 0.3443 0.6886 1.0329 1.3772 1.7215 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.52 1.53 MIN: 1.51 / MAX: 3.02 MIN: 1.5 / MAX: 3.52 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: googlenet my tiger lake, unmitigated my tiger lake, default 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 16.41 16.42 MIN: 16.04 / MAX: 19.41 MIN: 16.19 / MAX: 18.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet50 my tiger lake, default my tiger lake, unmitigated 8 16 24 32 40 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 33.42 33.64 MIN: 32.84 / MAX: 43 MIN: 32.82 / MAX: 43.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Phoronix Test Suite v10.8.4