WARNING - Most of the benchmarks provide two libraries. Early versions of Android 4, Ice Cream Sandwich, can sometimes fail to select the one to use faster hardware instructions, resulting in extremely slow performance -
See # above.
For maximum and consistent performance, some units might need setting of a CPU Mode (example ICS Settings, Developer Options, CPU Mode, Change Normal to Performance).
Some of these benchmarks produce poor performance, influenced by Power Saving options and short running time. For versions that run for extended periods see Android Long MP Benchmarks.htm.
Roy Longbottom痴 PC Benchmark Collection comprises numerous FREE benchmarks and reliability testing programs, for processors, caches, memory, buses, disks, flash drives, graphics, local area networks and Internet. Original ones run under DOS and later ones under all varieties of Windows. Most have also been converted to run under Linux and now many as Android Apps.
Android Benchmarks.htm provides details, results and links to download the apps and source code. The latter are written in Java or in C with a Java front end. A standard screen layout is used, an example being shown on the right. The same methods and display are being used for the new multithreading programs. So far, the C code for multithreading in the Linux benchmarks compiles and works with Android.
As indicated above, early versions of Android 4, Ice Cream Sandwich, can sometimes fail to select library to use fast vfpv3 hardware, resulting in extremely slow performance. In this case, two versions of the programs have being produced, one to use vfpv3 (v7) and the other for older CPUs (v5).
These benchmarks were developed on a Linux Ubuntu PC, using Eclipse Integrated Development Environment for Java, Android Software Development Kit and compiled C/C++ code from Native Development Kit (all free software). Eclipse projects for the benchmarks, with source code, can be downloaded from www.roylongbottom.org.uk/Android MP Benchmarks.zip.
Versions 1.1 January 2013 - Coloured display instead of black and white,
background image,
wider format for HD displays.
See also www.roylongbottom.org.uk/Android NEON Benchmarks.htm.
T11 Cortex-A15 Android 4.2.2 Linux 3.4.35 P11 Cortex-A9 Android 4.2.2 Linux 3.4.35 T7 Cortex-A9 Android 4.3 Linux 3.1.10
Results are now included for a Tablet (A1) using an Intel Atom CPU. Android versions have a compatibility layer called Houdini that maps ARM instructions into X86 instructions. Phone
On multithreading these processor benchmarks, using a particular device, CPU MHz is expected to be constant at the maximum value, subject to Power Saving settings. This is not always the case on later devices. For example, tablet T11 normally runs at 1700 MHz or 1000 MHz with the Saving option selected but, with some benchmarks, it will not run at the higher frequency when individual test running time is low.
The graph shows measured MHz whilst running MP-RandMem, with longer test times, on three devices, also MP-Whets on T11 where it runs continuously at 1700 MHz.
See results below for more details, particularly MP-RandMem and MP-MFLOPS.
This benchmark uses the same multithreading programming code as my Linux MultiThreading Benchmarks, where the latter executes identical functions as my CUDA and OpenMP performance tests. Details and results of these can be found in Linux CUDA MFLOPS.htm and OpenMP Speeds.htm. The arithmetic operations executed are of the form x[i] = (x[i] + a) * b - (x[i] + c) * d + (x[i] + e) * f with 2, 8 or 32 operations per input data word. Array sizes used are 0.1, 1 or 10 million 4 byte single precision floating point words. The program checks for consistent numeric results, primarily to show that all calculations are carried out and can be run using between 1 and 64 threads. Each thread uses the same calculations but accessing different segments of the data.
The Android version uses the functions with 2 and 32 operations per word with 1, 2, 4 and 8 threads. Data sizes are also limited to three to use L1 cache, L2 cache and RAM at 12.8, 128 and 12800 KB (3200, 32000 and 3200000 single precision floating point words). In a v7 version, for faster hardware, these are accessed 5000, 500 and 5 times respectively (for constant 32 million and 512 million arithmetic operations). This means that numeric results at given data sizes should be the same at all thread sizes. The i5 version, for older CPUs, uses 1000, 100 and 1 repeat passes.
Below is an example of results, with system information as included in Emailed results from all benchmarks. Numeric results are provided for both i7 and i5 versions, showing differences between them due to differing pass counts, but consistent across threads.
Android MP-MFLOPS v7 Benchmark V1.0 28-Sep-2012 18.21 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 183 159 90 588 539 524 2T 340 310 152 1117 1108 1048 4T 348 341 158 1144 1099 1067 8T 330 346 160 1129 1141 1055 Results x 100000, 0 indicates ERRORS 1T 86735 98519 99984 79897 97638 99975 2T 86735 98519 99984 79897 97638 99975 4T 86735 98519 99984 79897 97638 99975 8T 86735 98519 99984 79897 97638 99975 Total Elapsed Time 9.6 seconds ##################################################### Android MP-MFLOPS v5 Benchmark V1.0 Results x 100000 1T 97075 99700 99996 95363 99520 99995 2T 97075 99700 99996 95363 99520 99995 4T 97075 99700 99996 95363 99520 99995 8T 97075 99700 99996 95363 99520 99995 ##################################################### System Information Screen pixels w x h 1024 x 552 Android Build Version 4.0.3 Processor : ARMv7 Processor rev 0 (v7l) processor : 0 BogoMIPS : 2393.70 processor : 1 BogoMIPS : 2393.70 Features : swp half thumb fastmult vfp edsp neon vfpv3 CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x3 CPU part : 0xc09 CPU revision : 0 Hardware : Amlogic Meson6 g04 customer platform Revision : 0020 Serial : 000000000000000c Linux version 3.0.8+ (zuguo.chen@droid02-sz) (gcc version 4.4.1 (Sourcery G++ Lite 2010q1-202) ) #13 SMP PREEMPT Wed Apr 25 20:41:16 CST 2012
For maximum performance Tablet T4 requires the CPU Mode to be set to Performance, via Settings. This has a dual core CPU, where two or more threads produce appropriate performance gains using caches and, surprisingly, also using shared RAM. As for other v7 results, tests using 32 operations per word are CPU limited, with the dual core producing more than 1 GFLOPS. An example of poor initial performance using Normal CPU mode is also shown along with v5 results, not using vfpv3 hardware.
Tablet T2 could be expected to produce the same MFLOPS speeds at all thread sizes using the same data KB. It looks as though this device does not start in the CPU Mode for Performance. No manual settings are available. Tablet T1 has an older CPU, where the v7 benchmark cannot be installed and, maybe, is always running at 300 MHz.
As indicted in Android Benchmarks.htm the Cortex-A9 CPUs in tablets T7 and T4 both appear to be running at around 1200 MHz, lower than that specified. Then T7 appears to use the same frequency with two and four threads, providing a linear increase in performance. Although this benchmark is more CPU limited, P11 still provides a significant performance increase in the two operations tests using RAM. The P11 phone might have some background tasks running as it appears reluctant to fully utilise all CPUs with four threads.
August 2013 - Tablet T11 has a dual core Cortex-A15 CPU (Samsung Exynos 5250) and performs well, compared to P11, with the earlier fastest Cortex-A9. First results indicate that single and dual thread results are 1.9 to 3.0 times faster or 1.5 to 2.5 times faster, assuming the same CPU MHz. However, as T11 system appeared to run twice as fast using four threads, compared to two, further investigation was carried out.
The benchmark was run with Power Saving option enabled, when the CPU runs at 1000 MHz. As shown in the results below, cache based single and two thread results were the same as with the option disabled. Running a variation of my Measure CPU MHz App (100 ms sampling), with this and other benchmarks, showed that multi-threaded programs ran at the lower MHz when elapsed time for test functions was short. Next, MP_MFLOPS was modified to run the tests 100 times longer and results are shown below. This was also run on T4 and T7 where performance was the same as from the unmodified benchmark. Note that the new results on T11 are about 1.7 times faster than the 1000 MHz results, for cached data. Full speed was also confirmed with the MHz program.
The 100x version was also run on P11, where performance also improved, but not as much as T11. With these, T11 is 2.3 to 4.7 times faster, using one or two threads, and 1.9 to 3.9 times faster, assuming the same CPU MHz.
February 2015 - Results for Atom system A1, and others, show that the ARM to Intel mapping conversion takes into account threaded programs, and appropriate gains from using four cores can be demonstrated. Performance is relatively good on the old V5 instructions version but is variable on the V7 variety. It is not good on the CPU limited part, with 32 operations per word, but the fast memory can provide apparent high speeds, on the first part, compared with such as the Nexus 7.
On tablet A1, the later native code ARM/Intel version produced performance gains of up to nearly twice as fast as the ARM converted test run. In both cases, with 2 operations per word, maximum MP gains were on using L2 cache based data, with RAM speed performance limitations, where two threads were needed for maximum speed (See Android Native ARM-Intel Benchmarks.htm).
July 2015 - T21, with the Qualcomm Snapdragon 800, produces the fastest overall performance so far, using four cores. On a single core T11, with a Cortex-A15, is faster, typically by 50% on a per MHz basis.
August 2015 - Results provided for T22, with 64 bit CPU and 64 bit Android 5.0, showing that, at 32 operations per word, it was just over twice as fast at 64 bits, then up to 3.7 times, at 2 operations per word, with cache based data. The reason is that 64 bit vector SIMD instructions were produced, instead of scalars.
October 2015 - T7 Nexus 7, Android 5.0.2, then up to 5.1.1, upgrades, similar speeds (not shown). T22 Android 5.0.2 to 5.1 (ARM-v8 CPU), as with other benchmarks, practically all results were a little faster, average around 3% for both 32 bit and 64 bit compilations (see below).
For a version using NEON functions see www.roylongbottom.org.uk/Android NEON Benchmarks.htm.
***************************************************** A1 Quad Core 1.86 GHz Intel Atom Z3745, Android 4.4 Dual Channel LPDDR3-1066 Bandwidth 17.1 GB/s Android MP-MFLOPS v7 Benchmark V1.1 04-Feb-2015 10.59 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 413 495 467 556 529 562 2T 919 937 888 1141 1148 1084 4T 1513 937 869 1841 2141 2183 8T 1077 1163 910 1983 2066 2175 Total Elapsed Time 6.7 secondsLonger Tests - 100 Times
Android MP-MFLOPS2 Benchmark V2.1 04-Feb-2015 11.03 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 502 501 476 575 575 573 2T 1012 975 921 1133 1140 1115 4T 1571 1627 979 2238 2255 2258 8T 1550 1890 1007 2235 2239 2217 Total Elapsed Time 117.4 seconds Measured CPU MHz - 1862 ARM/Intel MP-MFLOPS2 Benchmark V2.1 28-Apr-2015 17.24 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 695 696 661 1061 1061 1055 2T 1335 1382 1058 2088 2086 2102 4T 1832 2635 979 3993 4125 4145 8T 2026 2557 1007 3842 4044 4110 Total Elapsed Time 65.8 secondsOld V5 Instructions
Android MP-MFLOPS v5 Benchmark V1.1 04-Feb-2015 11.18 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 175 171 190 198 203 192 2T 357 345 379 405 401 393 4T 645 369 441 524 702 698 8T 362 292 339 719 634 688 Total Elapsed Time 4.8 seconds ***************************************************** T11 Samsung EXYNOS 5250 Dual 2.0 GHz Cortex-A15, Android 4.2.2 Android MP-MFLOPS v7 Benchmark V1.1 09-Aug-2013 17.14 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 619 475 429 1106 1481 1438 2T 1195 935 654 2420 2992 2986 4T 2010 1924 635 3054 3134 2573 8T 1128 1197 640 2259 2796 2981 Total Elapsed Time 3.7 seconds Measured CPU MHz - 1700Power Saving Mode - 1000 MHz
FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 616 469 423 917 889 864 2T 1169 943 651 1830 1787 1751 4T 1178 1203 513 1828 1833 1757 8T 1139 1122 645 1800 1836 1756 Total Elapsed Time 5.3 secondsLonger Tests - 100 Times
FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 1004 816 578 1565 1528 1502 2T 1958 1633 643 3151 3060 2757 4T 1467 1152 608 2925 2844 2743 8T 1731 1666 596 2832 2870 2504 Total Elapsed Time 303.3 secondsOld V5 Instructions
Android MP-MFLOPS v5 Benchmark V1.1 04-Feb-2015 11.26 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 42 50 41 59 58 54 2T 86 100 83 122 127 114 4T 126 130 82 113 126 117 8T 142 140 116 123 128 117 Total Elapsed Time 14.4 seconds ***************************************************** T21 Qualcomm Snapdragon 800 2150 MHz, Android 4.4.4 Android MP-MFLOPS v7 Benchmark V1.1 05-Jul-2015 14.56 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 367 754 536 1212 1245 1243 2T 1341 1153 1040 2426 2422 2403 4T 1576 1048 1048 2941 4076 4165 8T 2648 2140 1309 4559 4885 4571 Total Elapsed Time 3.3 secondsLonger Tests
Android MP-MFLOPS2 Benchmark V2.1 05-Jul-2015 15.35 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 718 781 590 1214 1220 1228 2T 1572 1583 1118 2406 2436 2442 4T 2338 2959 1836 4867 4911 4859 8T 3148 3266 1866 4870 4916 4888 Total Elapsed Time 56.4 secondsOld V5 Instructions
Android MP-MFLOPS v5 Benchmark V1.1 05-Jul-2015 14.52 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 49 69 69 63 66 61 2T 147 146 136 129 126 121 4T 122 145 150 221 247 241 8T 262 255 272 261 246 242 Total Elapsed Time 10.8 seconds ********************* T22 32 Bit ******************** T22, Quad Core ARM Cortex-A53 1300 MHz, Android 5.0.2 ARM/Intel MP-MFLOPS2 Benchmark V2.2 09-Aug-2015 21.17 Compiled for 32 bit ARM v7a FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 190 190 184 670 672 664 2T 377 378 370 1343 1345 1329 4T 707 755 725 2657 2669 2621 8T 722 736 714 2640 2672 2631 Total Elapsed Time 113.0 seconds *************** T22 Android 5.1 32 Bit ************** ARM/Intel MP-MFLOPS2 Benchmark V2.2 28-Sep-2015 21.11 Compiled for 32 bit ARM v7a FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 196 196 190 692 692 687 2T 391 393 385 1387 1387 1371 4T 683 768 745 2746 2754 2705 8T 752 763 742 2724 2743 2705 Total Elapsed Time 109.6 seconds ********************* T22 64 Bit ******************** ARM/Intel MP-MFLOPS2 Benchmark V2.2 09-Aug-2015 21.24 Compiled for 64 bit ARM v8a FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 705 701 636 1398 1394 1362 2T 1376 1395 942 2794 2797 2757 4T 2063 2602 962 5491 5546 5336 8T 2474 2611 957 5367 5500 5417 Total Elapsed Time 51.6 seconds *************** T22 Android 5.1 64 Bit ************** ARM/Intel MP-MFLOPS2 Benchmark V2.2 28-Sep-2015 22.16 Compiled for 64 bit ARM v8a FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 730 727 668 1436 1440 1411 2T 1411 1434 963 2884 2889 2840 4T 1959 2749 979 5614 5460 5606 8T 2540 2661 1024 5583 5700 5576 Total Elapsed Time 50.1 seconds ***************************************************** P11 Galaxy SIII, Quad Cortex-A9 1.4 GHz, Android 4.0.4 Android MP-MFLOPS v7 Benchmark V1.0 23-Dec-2012 14.12 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 208 188 172 588 675 643 2T 392 375 302 1323 1342 1311 4T 472 439 321 1824 1758 1645 8T 619 608 381 2666 2537 2645 Total Elapsed Time 6.7 secondsLonger Tests - 100 Times
FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 212 191 186 692 626 664 2T 311 380 367 1390 1365 1051 4T 615 771 520 2678 2678 2600 8T 836 817 536 2692 2261 2595 Total Elapsed Time 580.8 seconds Measured CPU MHz - 1400Old V5 Instructions
Android MP-MFLOPS v5 Benchmark V1.0 23-Dec-2012 14.48 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 38 44 35 38 38 37 2T 88 88 77 76 76 74 4T 92 90 78 98 103 145 8T 177 174 146 153 148 148 Total Elapsed Time 18.6 seconds ***************************************************** P20 MediaTec MT6589, Quad Cortex A7 1.5 GHz, Android 4.2.1 Android MP-MFLOPS v7 Benchmark V1.1 05-11-2013 10.17 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 270 268 223 740 737 701 2T 541 531 447 1478 1476 1393 4T 1070 1035 633 2935 2912 2773 8T 1051 1075 579 2909 2946 2636 Total Elapsed Time 5.4 seconds ***************************************************** T7 Nexus 7 Quad 1300 MHz Cortex-A9, Android 4.1.2 Android MP-MFLOPS v7 Benchmark V1.0 17-Oct-2012 16.49 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 180 170 118 643 581 573 2T 365 323 199 1193 1164 1145 4T 726 700 241 2355 2374 2280 8T 623 724 229 2178 2385 2182 Total Elapsed Time 7.2 secondsLonger Tests - Similar speed Android 5.0.2
Android MP-MFLOPS2 Benchmark V2.1 05-Feb-2015 11.37 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 182 156 114 598 578 572 2T 365 321 194 1194 1163 1141 4T 716 655 233 2367 2316 2240 8T 717 682 233 2347 2371 2246 Total Elapsed Time 135.5 secondsOld V5 Instructions
Android MP-MFLOPS v5 Benchmark V1.0 17-Oct-2012 14.00 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 36 37 34 33 33 32 2T 77 75 68 66 66 65 4T 157 157 134 133 129 127 8T 128 122 111 130 122 128 Total Elapsed Time 20.5 seconds Measured CPU MHz - 1200 ***************************************************** T4 Miumiu w17 Pro 7 inch tablet, dual 1500 MHz Cortex-A9 Android MP-MFLOPS v7 Benchmark V1.0 28-Sep-2012 18.21 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 183 159 90 588 539 524 2T 340 310 152 1117 1108 1048 4T 348 341 158 1144 1099 1067 8T 330 346 160 1129 1141 1055 Total Elapsed Time 9.6 seconds Settings CPU Mode Normal, not Performance 1T 23 67 65 307 135 172 2T 99 128 136 800 1015 1017 4T 345 343 153 1133 1150 1069 8T 348 351 159 1134 1148 1054 Total Elapsed Time 17.6 seconds Android MP-MFLOPS v5 Benchmark V1.0 28-Sep-2012 17.50 1T 39 36 31 32 32 32 2T 74 71 57 63 62 60 4T 75 71 63 64 64 61 8T 75 75 61 64 64 62 Total Elapsed Time 26.3 seconds Measured CPU MHz - 1200 ***************************************************** P15 Lava Xolo A1000 1GHz Dual-core Cortex A9 processor Android MP-MFLOPS v7 Benchmark V1.1 14-Mar-2013 07.49 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 139 133 134 487 477 471 2T 299 280 215 977 937 939 4T 289 279 194 974 970 910 8T 297 298 221 975 963 936 Total Elapsed Time 10.3 seconds ***************************************************** T2 WayTeq xTAB-70 7 inch tablet, 800 MHz Cortex-A9 Android MP-MFLOPS v7 Benchmark V1.0 28-Sep-2012 18.38 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 70 94 69 393 388 386 2T 113 113 67 395 386 384 4T 116 118 67 390 390 384 8T 120 114 68 389 392 377 Total Elapsed Time 21.0 seconds Android MP-MFLOPS v5 Benchmark V1.0 28-Sep-2012 18.35 1T 10 25 23 21 21 21 2T 25 24 22 22 22 21 4T 26 26 23 22 22 21 8T 26 26 22 21 21 21 Total Elapsed Time 60.9 seconds ***************************************************** T1 TTFone M013S 10.1 inch tablet, 300-800 MHz VIA 8650 Android MP-MFLOPS v5 Benchmark V1.0 28-Sep-2012 18.34 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 10 9 9 10 10 10 2T 10 9 9 10 10 10 4T 10 9 9 10 9 10 8T 10 10 9 10 10 10 Total Elapsed Time 132.1 seconds ***************************************************** T9 ARM 926EJ 800 MHz, Android 2.2 Android MP-MFLOPS v5 Benchmark V1.1 09-jul-2013 22.44 FPU Add & Multiply using 1, 2, 4 and 8 Threads 2 Ops/Word 32 Ops/Word KB 12.8 128 12800 12.8 128 12800 MFLOPS 1T 10 9 9 10 9 10 2T 10 9 9 10 10 10 4T 10 9 9 10 10 9 8T 10 10 9 10 10 9 Total Elapsed Time 134,9 seconds
The Whetstone programs, initially used in 1972, were the first general purpose benchmarks that set industry standards of computer system performance. Details and performance of early to modern systems can be found in Whetstone Benchmark History And Results and Results On PCs. The overall performance rating is in Millions of Whetstone Instructions Per Second (MWIPS). Later, it was found necessary to measure the speed of the eight different test functions used, to demonstrate that compilers were not over optimising and to allow code tweaks to avoid this situation. The additional measurements are in terms of Millions of Operations Per Second (MOPS) or MFLOPS for straight floating point calculations. As the design authority, nominated by the original author, I have to say that versions that do not provide these separate measurements cannot be taken as valid.
This multithreading benchmark runs using 1, 2, 4 and 8 threads, executing multiple copies of the same program. An initial calibration, using a single thread, determines the number of passes needed for an overall execution time of 5 seconds. Then all threads are run using the same pass count, running time being extended when there are more threads than CPUs. The same calculations are carried out on each thread but using dedicated variables. The numeric results of calculations are noted for the first thread with others checked for the same values and an error message displayed if they are inconsistent.
An example of displayed results is shown below. Configuration details, as shown above for the first MP program, are included in Emailed details.
Android MP-Whetstone Benchmark V1.0 02-Oct-2012 17.11 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 985.5 209.9 219.5 245.5 23.9 15.0 442.1 556.0 479.8 2T 2005.9 445.8 449.9 512.4 49.7 29.1 869.0 1158.6 987.2 4T 2060.7 445.8 463.6 523.1 51.8 29.5 885.2 1282.8 1005.9 8T 2036.8 461.0 469.1 513.6 50.7 29.4 890.8 1181.8 998.0 Overall Seconds 4.83 1T, 4.88 2T, 9.46 4T, 18.90 8T All calculations produced consistent numeric results Total Elapsed Time 38.6 seconds
This benchmark works on both v7 vfpv3 floating point and older v5 hardware, using the two different libraries generated on compilation. Note the slow floating point performance on Tablet T1. Tablets T7 and T4 again appear to be running slower than expected. The first two MFLOPS tests use limited cached data and, unlike the other tests, might be why P11's four thread performance is lower than expected.
August 2013 - Results for Tablet T11, with the dual core Cortex-A15 CPU, are disappointing, as with the single processor Whetstone Benchmark. P11痴 Cortex-A9 is faster on some test functions on a per MHz basis. On the first time of running, performance was even worse, but this was with the CPU running at 1000 MHz due to the Power Saving option being on (see results below). On T11, the timer with 100 ms sampling, showed that the CPU was running at 1700 MHz virtually all of the time.
February 2015 - Atom system A1 performed quite well on the simple floating point calculations but fell down using mathematical functions.
The new ARM/Intel version, running on the Intel Atom tablet, is rated at twice the speed of the original, due to the use of native code. The fixed point results indicate overoptimisation, but the test uses little of the overall time, this being mainly dependent on the Cos, Exp and third MFLOPS tests (See Android Native ARM-Intel Benchmarks.htm).
July 2015 - T21, with the Qualcomm Snapdragon 800, obtains similar performance as the native code version running on tablet A1, with the Intel Atom CPU.
August 2015 - Results provided for 64 bit T22 showing that, at 64 bits, the Fixpt test was clearly nearly optimised out, but this makes little difference to the overall MWIPS rating, at 2.25 times faster than the 32 bit benchmark.
October 2015 - T7 Nexus 7, Android 5.0.2, up to 5.1.1, upgrades produced similar speeds as via Android 4. As for the stand alone version, the ARM/Intel compilation, via the later gcc 4.8 compilation, produced a slower overall rating. This was due to excessive time taken by the Exp test. T7 example from Android 5.1.1 provided below. T22 Android 5.0.2 to 5.1 (ARM-v8 CPU), as with other benchmarks, practically all results were a little faster, average around 6% for both 32 bit and 64 bit compilations (see below).
Each thread executes the same test functions at the same time, running time and speed calculations being based on the last thread to finish. As with the later MP-RandMem program, Mutex functions are used to avoid the updating conflict by only allowing one thread at a time to access common data. This has little effect and performance of each test can be proportional to the number of cores.
***************************************************** A1 Quad Core 1.86 GHz Intel Atom Z3745, Android 4.4 Dual Channel LPDDR3-1066 Bandwidth 17.1 GB/s Android MP-Whetstone Benchmark V1.1 04-Feb-2015 11.39 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 953.7 363.0 382.4 267.8 21.0 13.2 413.1 1842.4 392.3 2T 1921.2 726.0 663.5 541.4 42.6 27.0 816.1 3662.6 793.3 4T 3820.6 1419.2 1514.6 1081.5 84.1 54.0 1543.8 6292.4 1588.5 8T 4003.8 1912.9 1872.4 1114.1 86.5 56.4 2053.1 8292.6 1599.7 Overall Seconds 4.88 1T, 4.87 2T, 4.96 4T, 10.05 8T #################### A1 ARM-Intel ###################### ARM/Intel MP-Whetstone Benchmark V1.1 30-Apr-2015 17.35 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 1916.9 691.4 691.3 497.2 35.3 27.6 10209.8 2787.3 1351.8 2T 3800.3 1377.6 1381.2 980.0 70.1 54.7 20248.0 5252.8 2748.7 4T 7604.9 2713.2 2711.8 1977.1 140.2 110.0 33906.3 9526.5 5550.8 8T 7798.1 3141.5 3627.2 2064.2 141.2 110.2 59590.6 12743.7 5711.5 Overall Seconds 4.94 1T, 5.00 2T, 5.06 4T, 10.11 8T ***************************************************** P23 Huawei ?? Octa-core Cortex A17, ?? GHz, Android 4.2.2 Android MP-Whetstone Benchmark V1.1 24-9 ?-2014 10.53 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 1129.8 282.6 286.2 340.4 24.6 15.6 600.3 1360.1 509.7 2T 2251.0 553.9 569.8 680.0 48.9 31.1 1201.4 2722.3 1017.2 4T 4516.5 956.9 1145.5 1361.5 98.7 62.4 2402.0 5441.9 2038.8 8T 8982.5 1713.2 2262.3 2716.7 196.9 123.9 4788.410771.3 4070.7 Overall Seconds 4.93 1T, 4.97 2T, 5.03 4T, 5.20 8T ***************************************************** T11 Samsung EXYNOS 5250 Dual 2.0 GHz Cortex-A15, Android 4.2.2 Android MP-Whetstone Benchmark V1.1 06-Sep-2013 12.49 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 1308.2 345.9 379.0 294.1 30.8 17.2 1351.4 1265.7 843.1 2T 2886.6 782.1 782.6 614.0 80.1 34.3 2775.2 2463.7 1667.5 4T 3086.0 998.6 788.1 610.6 79.2 44.5 3472.0 2526.4 2191.4 8T 2930.0 788.2 843.5 616.5 80.5 35.0 2846.0 2799.1 1686.2 Overall Seconds 3.54 1T, 3.30 2T, 6.62 4T, 13.16 8T Measured CPU MHz - 1700Power Saving On
Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 840.7 228.7 224.7 178.2 23.4 10.0 822.1 740.9 488.6 2T 1676.3 448.5 443.4 357.2 46.5 19.9 1642.8 1483.0 978.8 4T 1716.7 445.4 448.7 365.6 47.5 20.3 2092.6 1667.0 990.8 8T 1695.9 459.7 463.0 358.9 46.8 20.1 1647.9 1484.5 1116.2 Overall Seconds 4.92 1T, 4.94 2T, 9.94 4T, 19.68 8T Measured CPU MHz - 1000 ***************************************************** T21 Qualcomm Snapdragon 800 2150 MHz, Android 4.4.4 Android MP-Whetstone Benchmark V1.1 06-Jul-2015 10.42 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 1877.1 645.2 642.6 524.1 44.0 22.3 1364.7 1572.1 898.9 2T 3668.6 1220.2 1262.4 1021.9 85.9 43.8 2663.5 3078.4 1753.4 4T 7426.9 2375.5 2474.7 2097.7 175.7 88.2 5052.6 6240.4 3555.0 8T 7706.6 2692.2 2746.2 2186.9 180.1 90.3 5822.5 6902.7 3681.3 Overall Seconds 4.44 1T, 4.62 2T, 4.64 4T, 9.00 8T Total Elapsed Time 24.1 seconds ********************* T22 32 Bit ******************** T22, Quad Core ARM Cortex-A53 1300 MHz, Android 5.0.2 ARM/Intel MP-Whetstone Benchmark V1.2 10-Aug-2015 11.30 Compiled for 32 bit ARM v7a Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 676.4 275.9 281.9 147.9 35.4 5.3 600.3 901.0 285.5 2T 1362.5 533.8 561.7 298.0 70.9 10.8 1203.1 1838.9 574.0 4T 2698.6 903.9 1071.7 594.4 141.2 21.5 2346.1 3305.5 1138.5 8T 2830.1 1463.2 1393.0 614.2 152.5 21.9 3243.9 4418.3 1171.4 Overall Seconds 4.95 1T, 4.94 2T, 5.11 4T, 10.09 8T *************** T22 Andoid 5.1 32 Bit *************** ARM/Intel MP-Whetstone Benchmark V1.2 28-Sep-2015 21.18 Compiled for 32 bit ARM v7a Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 706.1 284.7 286.8 154.2 37.6 5.6 618.9 1114.8 294.0 2T 1411.9 552.0 553.1 307.6 75.3 11.2 1240.1 2362.1 592.5 4T 2779.8 948.4 1140.7 613.4 147.4 21.8 2418.0 4651.7 1170.3 8T 2913.1 1386.6 1434.9 631.2 157.2 22.6 3142.5 5860.6 1187.8 Overall Seconds 4.91 1T, 4.91 2T, 5.12 4T, 10.02 8T ********************* T22 64 Bit ******************** ARM/Intel MP-Whetstone Benchmark V1.2 10-Aug-2015 11.34 Compiled for 64 bit ARM v8a Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 1524.8 328.6 348.8 297.6 37.3 19.9 1462579 1867.2 1238.0 2T 3062.5 688.8 697.9 596.0 75.5 39.8 2097113 3726.7 2481.3 4T 6085.4 1214.9 1360.5 1185.4 150.5 79.4 2449153 7055.0 4951.8 8T 6222.4 1495.2 1545.6 1204.2 152.2 80.6 3869846 9218.8 5154.1 Overall Seconds 4.92 1T, 4.90 2T, 5.05 4T, 9.97 8T *************** T22 Andoid 5.1 64 Bit *************** ARM/Intel MP-Whetstone Benchmark V1.2 28-Sep-2015 22.22 Compiled for 64 bit ARM v8a Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 1634.8 360.2 360.0 307.0 41.9 21.31708797.2 1923.6 1278.3 2T 3270.5 713.8 720.1 615.2 83.7 42.62426910.3 3847.3 2563.3 4T 6466.7 1312.0 1395.8 1224.3 167.6 83.13224807.7 7403.4 5078.8 8T 6683.1 1466.7 1485.2 1253.2 171.4 86.74732245.1 9177.6 5315.0 Overall Seconds 4.90 1T, 4.91 2T, 5.08 4T, 10.06 8T ***************************************************** P11 Galaxy SIII, Quad Cortex-A9 1.4 GHz, Android 4.0.4 Android MP-Whetstone Benchmark V1.0 23-Dec-2012 14.36 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 1206.4 266.3 269.4 310.1 30.1 17.6 522.8 551.8 597.9 2T 2411.7 520.5 530.0 619.1 60.0 35.1 1026.4 1359.2 1195.9 4T 4719.0 874.2 881.7 1231.1 119.1 69.6 2072.8 2779.4 2369.0 8T 4676.4 1227.1 1105.1 1182.4 120.0 63.2 2254.4 2821.8 2299.5 Overall Seconds 4.84 1T, 4.82 2T, 5.14 4T, 10.25 8T ***************************************************** T7 Nexus 7 Quad 1300 MHz Cortex-A9, Android 4.1.2 Android MP-Whetstone Benchmark V1.0 17-Oct-2012 13.49 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 1033.7 247.4 235.4 266.0 25.3 15.0 448.4 630.9 513.5 2T 2058.1 456.3 473.0 532.4 50.0 30.1 898.1 1198.4 1026.6 4T 4122.8 831.9 944.7 1064.6 100.7 60.1 1797.0 2392.2 2053.4 8T 4163.2 1016.0 948.2 1069.5 101.8 60.9 1808.0 2414.2 2051.5 Overall Seconds 5.28 1T, 5.34 2T, 5.42 4T, 10.81 8T Later GCC 4.8 Compilation ARM/Intel MP-Whetstone Benchmark V1.1 01-Oct-2015 12.45 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 621.0 235.6 238.6 139.2 27.9 5.3 479.5 1415.1 235.7 2T 1253.5 483.8 483.6 281.6 56.3 10.6 969.6 2863.6 478.2 4T 2489.3 826.2 963.1 560.7 112.8 21.0 1933.3 5709.1 934.9 8T 2497.9 980.7 973.1 562.7 112.9 20.9 1961.2 5771.0 959.7 Overall Seconds 4.96 1T, 4.92 2T, 5.08 4T, 9.96 8T Measured CPU MHz - 1200 ***************************************************** T4 Miumiu w17 Pro 7 inch tablet, dual 1500 MHz Cortex-A9 Android MP-Whetstone Benchmark V1.0 02-Oct-2012 17.11 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 985.5 209.9 219.5 245.5 23.9 15.0 442.1 556.0 479.8 2T 2005.9 445.8 449.9 512.4 49.7 29.1 869.0 1158.6 987.2 4T 2060.7 445.8 463.6 523.1 51.8 29.5 885.2 1282.8 1005.9 8T 2036.8 461.0 469.1 513.6 50.7 29.4 890.8 1181.8 998.0 Overall Seconds 4.83 1T, 4.88 2T, 9.46 4T, 18.90 8T Measured CPU MHz - 1200 ***************************************************** T2 WayTeq xTAB-70 7 inch tablet, 800 MHz Cortex-A9 Android MP-Whetstone Benchmark V1.0 02-Oct-2012 17.14 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 607.9 143.3 132.4 151.3 15.2 8.8 277.5 367.0 301.2 2T 631.8 144.1 136.4 164.1 15.7 9.1 272.1 369.3 316.0 4T 643.3 144.6 141.0 168.5 15.7 9.3 282.4 376.5 323.9 8T 627.5 132.7 130.5 153.1 15.7 9.4 287.1 353.1 313.1 Overall Seconds 4.86 1T, 9.38 2T, 18.44 4T, 38.08 8T ***************************************************** T1 TTFone M013S 10.1 inch tablet, 300-800 MHz VIA 8650 Android MP-Whetstone Benchmark V1.0 02-Oct-2012 17.19 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 30.2 9.6 10.1 11.4 0.6 0.3 77.1 193.9 145.7 2T 30.4 9.8 9.9 11.4 0.6 0.3 78.9 174.2 146.3 4T 30.5 9.9 10.5 11.5 0.6 0.3 77.9 214.6 147.4 8T 30.9 9.9 10.4 11.2 0.6 0.3 78.7 200.7 147.8 Overall Seconds 4.71 1T, 9.40 2T, 18.81 4T, 37.16 8T ***************************************************** ET1 Device ARM Emulator 2.4 GHz Core 2 Duo Android MP-Whetstone Benchmark V1.0 02-Oct-2012 15.27 Using 1, 2, 4 and 8 Threads MWIPS MFLOPS MFLOPS MFLOPS Cos Exp Fixpt If Equal 1 2 3 MOPS MOPS MOPS MOPS MOPS 1T 90.7 28.2 27.5 34.9 1.5 1.2 143.4 214.4 174.5 2T 90.4 27.3 27.8 34.9 1.5 1.2 145.8 216.4 174.2 4T 89.5 28.6 27.7 34.8 1.5 1.2 145.1 213.4 173.8 8T 89.6 28.4 27.8 35.0 1.5 1.2 145.6 213.8 174.7 Overall Seconds 4.86 1T, 9.78 2T, 19.69 4T, 39.42 8T
The Dhrystone "C" benchmark provides a measure of integer performance (no floating point instructions). It became the key standard benchmark from 1984. Speed was originally measured in Dhrystones per second. This was later changed to VAX MIPS by dividing Dhrystones per second by 1757, the DEC VAX 11/780 result, the latter being regarded as the first 1 MIPS minicomputer. Details and results from Windows and Linux based PCs, can be found in Dhrystone Results.htm.
This multithreading benchmark runs using 1, 2, 4 and 8 threads, executing multiple copies of the same program. An initial calibration, using a single thread, determines the number of passes needed for an overall execution time of 1 second. Then all threads are run using the same pass count, running time being extended when there are more threads than CPUs. The same calculations are carried out on each thread. Some variables can be used by all threads and it might be foreseen that this could cause the program to crash. Data arrays have been moved so that different RAM will be allocated for each thread. One of the locations is used to count the number passes used be each thread and these are checked for consistency.
An example of displayed results is shown below. Configuration details, as shown above for the first MP program, are included in Emailed details.
Android MP-Dhrystone 2 Benchmark V1.0 06-Oct-2012 12.40 Using 1, 2, 4 and 8 Threads Threads 1 2 4 8 Seconds 0.91 1.01 2.01 4.06 Dhrystones per Second 2185814 3970026 3975949 3938332 VAX MIPS rating 1244 2260 2263 2242 Internal pass count correct all threads Total Elapsed Time 8.5 seconds
This benchmark also works on both v7 and v5 hardware, using the two different libraries generated on compilation. Again, tablet T4 demonstrates a significant performance gain of up to 1.82 times, using two cores. Tablet T7 gains are 1.74 times with two cores and 2.42 using all four cores. It seems that these are degraded by shared data forced to reside in RAM or L2 cache. Again, P11 has lower gains using four cores.
Results from emulators include some from the newer BlueStack software. This and the Android NDK tool only use one of multiple cores and each typically runs at 5% speed of Windows or Linux natively compiled versions of the same benchmark, or sometimes 10% of a 1.5 GHz Cortex-A9 tablet CPU. On the other hand, all Java benchmarks can run at the same speed as the 1.5 GHz tablet. - See Android Benchmarks.htm. Using BlueStacks, this Dhrystone benchmark can produce results at 38% of the speed of a single 1.5 GHz Cortex-A9 CPU.
Below are results from http://gamma0burst.tistory.com in Korea (including some of mine). These provide better identification of the processors used. There are wide variations in results of what should be identical CPUs but, as with all benchmarks reported here, the systems might not be running at the specified clock frequency or might need a Setting to run at maximum speed.
August 2013 - Results for Tablet T11, with the dual core Cortex-A15 CPU, are the best so far running this MP-Dhrystone Benchmark. Note, results are provided for this CPU running at 1.0 and 1.7 GHz. Continuous 1.7 MHz was confirmed with the 100 ms timer.
February 2015 - The benchmark failed run on Atom system A1 but, for some reason, ran later. Unlike other systems, performance was worse using multiple threads. The later conversion, to a native ARM/Intel version, produced similar speeds on all Android devices tested. Then, running on a PC, via the BlueStacks emulator, showed that Intel native code ran ten times faster (See Android Native ARM-Intel Benchmarks.htm).
July 2015 - T21, with the Qualcomm Snapdragon 800, sometimes crashes running this benchmark and apparently every time, trying the ARM-Intel version. When running, the eight thread performance is also highly suspect.
August 2015 - Results provided for 64 bit T22 showing that the 64 bit version was much faster than via the 32 bit variety.
October 2015 - T7 Nexus 7, Android 5.0.2 and up to 5.1.1 upgrades produced similar speeds (not shown).
T22 Android 5.0.2 to 5.1 (ARM-v8 CPU), all results were a little faster, average around 3% for both 32 bit and 64 bit compilations (see below).
VAX MIPS Rating Threads 1 2 4 8 T11 Dual ARM-A15 1700 MHz 3086 4371 4335 4341 T11 Dual ARM-A15 1000 MHz 2271 4281 4326 4171 T11$ Dual ARM-A15 1000 MHz 2295 4057 3902 4096 P22 Quad ARM-A9 1600 MHz 2044 3762 5973 5682 P11 Quad ARM-A92 1400 MHz 1814 3178 3399 4775 P12 Dual QU-S4 1500 MHz 1737 3719 3308 3729 T7 Quad ARM-A9 1300 MHz 1584 2749 3836 3569 T7 $ Quad ARM-A9 1300 MHz 1464 2399 3575 3737 P13 Dual ARM-A9 1200 MHz 1572 2749 2778 2744 P23 Octa AER-A17 ???? MHz 1491 2554 2040 1505 T4 Dual ARM-A9 1500 MHz 1244 2260 2263 2242 T2 ARM-A9 800 MHz 767 790 790 807 T1 ARM926E 300-800 MHz 336 321 338 328 T9 ARM926E 800 MHz 296 291 326 324 A1 Atom Z3745 1866 MHz 2360 1394 1334 1321 A1$ Atom Z3745 1866 MHz 2365 1322 1323 1319 P19 Dual QU-S4 1500 MHz? 2404 4564 4544 4895 T21 Quad QU-800 2150 MHz 2850 4395 7736 11821 32 bit T22 ARM v8-A53 1300 MHz 1412 2559 4038 4291 T22+ ARM v8-A53 1300 MHz 1449 2610 4264 4442 64 bit T22 ARM v8-A53 1300 MHz 2548 4311 5560 5613 T22+ ARM v8-A53 1300 MHz 2623 4477 5734 5797 ET1 Emul Core2D 2400 MHz 255 253 255 254 BS1 Emul Phenx4 3000 MHz 474 465 453 449 BS1$ Emul Phenx4 3000 MHz 4844 4670 4623 4724 QU = Qualcomm CPU. $ ARM/Intel Version, + Android 5.1 Measured CPU MHz - T4 and T7 1200, T11 spec 2000 VAX MIPS via threads Processor CPUs x MHz 1 2 4 8 Sam Exynos 4210 Cortex-A9 2x1200 1588 2771 2778 2733 1784 3209 3137 3165 Sam Exynos 4412 Cortex-A9 4x1400 1838 3108 4492 5244 4x1600 2065 3656 4619 5903 TI OMAP4460 Cortex-A9 2x1200 1328 2420 2594 2689 2x1200 1558 2779 2800 2708 nV Tegra 3 Cortex-A9 4x1400 1511 1951 3581 5154 Sam Exynos 5250 Cortex-A15 2x1700 3078 4342 4382 4396 QSn S3 MSM 8660 Scorpian 2x1500 1633 2339 2365 2419 QSn S4 MSM8960 Krait 2x1500 2105 3918 3517 4419 QSn S4 APQ8064 Krait 4x1500 2177 3868 6783 7242 QSn S4 Snap600 Krait300 4x1700 2353 3702 5954 5231 QSn - Qualcomm Snapdragon, Sam - Samsung, Aml - Amlogic, Ti - Texas Instruments, nV - nVidia
This uses the same calculations as my original BusSpeed2K Benchmark , the link providing data and results, including Windows and Linux MP varieties. Data is read using AND instructions at a range of data sizes covering caches and RAM. The program starts by reading words with 32 word address increments, then reduces the increment to eventually read all words sequentially. Speed reductions of around 50% at each higher increment suggests reading in bursts over the bus. This is normal for reading from RAM and is sometimes found reading cached data. In this case, only 12.3 KB, 123KB and 12.3 MB memory sizes are used via 1, 2, 4 and 8 threads.
Two versions are provided again for separate vfpv3 (v7) hardware and older CPUs (v5). An initial calibration phase for each test normally results in about 13 seconds overall running time. All threads read the same data sequentially. The results of all tests and all threads should be identical (Hex 55555555, where 5 is binary 0101) and this is checked and reported if incorrect.
An example of displayed results is shown below. Configuration details, as shown above for the first MP program, are included in Emailed details.
Android MP-BusSpd v7 Benchmark V1.0 11-Oct-2012 20.02 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 2790 3123 3464 3516 3384 3250 2T 3948 5858 6466 6641 6764 6832 4T 5165 5915 6405 6097 6805 6700 8T 5444 5585 6488 6729 6876 6977 122.9 1T 484 497 481 579 644 1028 2T 927 929 923 1201 1264 1930 4T 916 940 926 1197 1175 1772 8T 932 929 937 1214 1285 1892 12288 1T 34 34 60 124 237 435 2T 49 47 85 162 295 650 4T 46 55 79 174 306 509 8T 46 50 103 176 345 698 No Errors Found Total Elapsed Time 12.7 seconds
This benchmark is intended to demonstrate maximum speeds executing integer arithmetic, using the AND instruction. As explained in details for the single processor BusSpeed, the RdAll tests at 12.3 KB provide measures of CPU speed and of RAM speed at 12.288 MB. Also, a measure of maximum possible data transfer rate can be estimated from burst measurements, typically 16 times the Inc16 results. Calculated estimates of CPU and maximum potential RAM speeds are provided below for the quad core devices P11 and T7. On measured RAM speeds, both show that multiple cores are needed to obtain the highest throughput and the dual channel P11 performance is quite good. As reflected in single processor BusSpeed results, the upgraded Cortex-A9 CPU in P11 provides significant performance gains using L2 cache and RAM.
August 2013 - Comparing Cortex-A15 Tablet T11 results, with those for Cortex-A9 Phone P11, suggests a difference in burst reading from L2 cache, reducing relative speed of T11 with the larger address increments. Other than this, cache based reading data is generally faster on T11 by 20% to 30%, after assuming the same MHz. In both cases, memory throughput can be doubled, using two cores, with P11痴 improvement continuing with four cores. In this case, T11 was running at 1700 MHz for most of the time.
February 2015 - Results for Atom system A1 are the best so far, the Intel to ARM instruction mapping not appearing to impose severe performance degradation. The Atom has a 64 bit memory bus, where maximum speed is 533 (MHz) x 2 (DDR) x 16 (bus bytes) = 17.06 GB/second.
The new ARM/Intel version, running on tablet A1, produced some gains using four threads and on estimated maximum RAM speed (See Android Native ARM-Intel Benchmarks.htm).
July 2015 - T21, with the Qualcomm Snapdragon 800, has similar L1 cache based performance characteristic as Cortex-A9, assuming the same clock MHz, but significantly faster using L2 cache and RAM. Then, on the same basis, Cortex-A15 is faster from L1 but otherwise slower, particularly using RAM data trannsfers. The A1 Atom tablet is the closest match, via native Intel code.
August 2015 - Results included for T22 with 64 bit CPU and 64 bit Android 5.0. Just considering the Read All data tests, A53 64/32 bit L1 cache, L2 cache and RAM performance ratios averaged 2.2, 1.8 and 1.0.
October 2015 - T7 Nexus 7, Android 5.0.2 and up to 5.1.1 upgrades indicated similar speeds (not shown). T22 Android 5.0.2 to 5.1 (ARM-v8 CPU), reading all data with 64 bit compilation indicated that most results were a little faster, average around 3%. Results were not as good at 32 bits, particularly with data in RAM (see below).
Tests via BlueStacks Emulator, and the one that installs with Eclipse, do not use multiple cores but the faster RAM on PCs can produce much better performance than Android devices at the 12.3 MB level, with BlueStacks being the quickest, but in turn, much slower than Windows and Linux versions reported on in BusSpeed2K Results.htm.
NOTE: Originally, an estimate of maximum RAM data transfer speed could be calculated from such as Inc32 MB/second x 32 or Inc16 speed x 16. With the latest systems, this could indicate throughput faster than the specified maximum bandwidth. The reason for this that shared L2 caches are now being provided. In the benchmark, each thread reads all the data, starting a the beginning, whereby some will be read from L2 cache, rather than RAM. This also occurred on desktop PCs with shared L3 caches, where a revised version was produced with staggered starting addresses.
MP-BusSpd2i.apk is a similar revised version for Android and can be found in
Android Native ARM-Intel Benchmarks.htm.
***************************************************** A1 Quad Core 1.86 GHz Intel Atom Z3745, Android 4.4 Dual Channel LPDDR3-1066 Bandwidth 17.1 GB/s 4 x 24 KB L1 cache, 2 x 1024 KB shared L2 caches Android MP-BusSpd v7 Benchmark V1.1 04-Feb-2015 10.38 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 4218 4461 6019 6448 6116 6474 2T 3917 5061 7652 8058 11346 12554 4T 4190 6955 11380 12327 15436 16020 8T 4254 7528 12364 16735 17407 16880 122.9 1T 1306 1598 2278 2667 3740 5017 2T 2560 3149 4490 5370 7468 10154 4T 3990 4052 5542 6504 10279 16331 8T 3070 5106 6376 9289 11898 17355 12288 1T 196 267 599 1199 2315 3815 2T 248 447 843 1658 3312 6625 4T 352 716 741 2114 4024 7280 8T 376 454 835 1780 3414 6622 Total Elapsed Time 13.6 seconds Max CPU estimate 16880/1.92 = 8792 MIPS #################### A1 ARM-Intel ###################### ARM/Intel MP-BusSpd v7 Benchmark V1.1 05-May-2015 14.28 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 5925 6494 6778 6979 7047 7026 2T 3966 7029 9689 11689 12856 13654 4T 4438 8698 16739 22057 23946 25729 8T 4455 8619 15787 19934 22576 20804 122.9 1T 1490 1975 2360 2802 3818 5330 2T 2881 3798 4647 5531 7536 10546 4T 4452 6338 5910 10217 14650 19903 8T 4096 5075 6264 9213 12610 15821 12288 1T 206 273 593 1198 2343 3935 2T 276 455 842 1821 3319 6591 4T 445 730 1401 2076 4457 7525 8T 424 539 954 1829 3688 7064 Total Elapsed Time 13.0 second Max CPU estimate 25729/1.92 = 13400 MIPS ########## A1 New Long Version ARM/Intel MP-BusSpd2 Benchmark V1.0 24-Jul-2015 15.50 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 5431 6110 6780 6262 6655 7313 2T 3550 4464 7375 9825 11777 12442 4T 2027 4442 4399 8841 17611 23509 8T 983 2477 5063 4433 8568 15867 122.9 1T 1499 1991 2357 2839 3818 5382 2T 2816 3808 4708 5592 7557 10677 4T 4316 6313 7991 9816 14335 19993 8T 4235 5610 7917 8791 12828 19661 49152 1T 215 275 611 1183 2328 3922 2T 276 435 787 1671 3323 6507 4T 398 455 884 1754 3490 6971 8T 376 511 867 1746 3512 7510 Total Elapsed Time 48.6 seconds ***************************************************** T11 Samsung EXYNOS 5250 Dual 2.0 GHz Cortex-A15, Android 4.2.2 RAM 12.8 GB/sec, L1 2 x 32 KB, L2 shared 1024 KB Android MP-BusSpd v7 Benchmark V1.1 09-Aug-2013 17.16 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 3192 4183 3734 4797 5393 6190 2T 9165 10043 11654 12215 12606 12926 4T 7811 9174 10998 12110 12584 11769 8T 7009 9026 11033 12043 12587 12791 122.9 1T 667 776 1198 2916 3164 2028 2T 419 938 2036 4556 5943 6111 4T 593 1011 1899 4250 5955 5829 8T 472 1015 2031 4499 5872 5460 12288 1T 125 134 197 582 988 1382 2T 277 281 349 1097 1377 2347 4T 180 228 335 795 1524 2411 8T 274 243 354 824 1467 2468 Total Elapsed Time 12.5 seconds Measured CPU MHz - 1700 Android MP-BusSpd2 Benchmark V2.1 24-Sep-2013 12.00 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 5505 4738 4318 6406 6492 6569 2T 9163 9897 11365 11924 12137 12524 4T 7532 8876 11093 12046 12199 12328 8T 7164 9020 11451 12037 12384 12689 122.9 1T 692 898 1191 2684 2612 3325 2T 606 1010 2029 4569 6066 6312 4T 604 923 2063 4396 6234 6361 8T 600 1024 2059 4613 6269 6460 12288 1T 128 134 185 548 926 1335 2T 280 278 346 1103 1385 2445 4T 239 239 353 828 1362 2410 8T 236 245 354 810 1416 2418 Total Elapsed Time 49.8 seconds ARM/Intel MP-BusSpd v7 Benchmark V1.1 05-May-2015 14.45 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 2165 3591 4256 5587 5998 6109 2T 4121 6469 9530 11381 11846 11936 4T 4106 6438 8827 6793 9802 12080 8T 4098 6390 9534 10141 10996 11603 122.9 1T 464 740 1173 2395 3276 3340 2T 579 989 1934 3994 5431 5792 4T 579 988 1930 3873 5469 5821 8T 580 985 1915 3999 5408 5812 12288 1T 134 172 211 462 602 1904 2T 269 343 387 934 1217 2685 4T 252 231 374 768 991 2625 8T 231 254 367 781 1104 2782 Total Elapsed Time 12.1 seconds ########## T11 New Long Version ARM/Intel MP-BusSpd2 Benchmark V1.0 24-Jul-2015 17.07 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 3499 4539 5499 5505 6134 6045 2T 3775 7202 8377 10605 10457 11319 4T 3982 6676 7687 9326 9707 10807 8T 2546 3643 7891 8003 10725 11097 122.9 1T 672 901 1336 2784 3274 3334 2T 568 969 1931 3894 5427 5221 4T 574 971 1912 3831 5256 4811 8T 559 971 1917 3878 5387 5162 49152 1T 140 142 193 575 989 1499 2T 221 223 342 769 1379 2355 4T 228 223 344 783 1382 2376 8T 223 223 342 787 1385 2352 Total Elapsed Time 49.9 secondBusSpd v7 Power Saving Mode - 1000 MHz
MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 3238 3528 3740 3831 3807 3851 2T 5515 5930 6866 7126 7403 6979 4T 4197 5291 6901 7132 7383 7349 8T 4209 5207 6898 6662 7258 7538 122.9 1T 411 450 699 1692 1964 1970 2T 354 542 1171 2645 3525 3897 4T 353 586 1160 2750 3777 3874 8T 354 595 1110 2733 3742 3668 12288 1T 124 131 184 483 870 1118 2T 229 255 336 771 1351 2120 4T 207 220 344 749 1249 2084 8T 204 229 333 753 1331 2056 Total Elapsed Time 12.7 seconds ***************************************************** T21 Qualcomm Snapdragon 800 2150 MHz, Android 4.4.4 Dual Channel 32 Bit LPDDR3-1866 RAM 14.9 GB/s L1 caches 4 x 32 KB, L2 cache shared 2048 KB Android MP-BusSpd v7 Benchmark V1.1 29-Jun-2015 18.37 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 2580 2206 5048 5176 5679 5989 2T 4062 5175 9340 9868 10971 11281 4T 4688 10324 16552 17196 21714 23708 8T 8467 9834 16698 18183 21936 23693 122.9 1T 1152 1052 2068 3035 3927 5723 2T 1710 1840 3094 5001 7963 11475 4T 2047 2002 5031 9267 14698 22920 8T 2235 2275 5223 9348 14234 21783 12288 1T 262 382 508 867 1466 2661 2T 464 766 1049 1754 3186 5735 4T 612 1018 1796 3149 5892 9095 8T 575 680 1277 2308 4987 7948 Total Elapsed Time 12.7 seconds Android MP-BusSpd2 Benchmark V2.1 08-Jul-2015 16.31 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 2439 2540 4468 5029 5108 5906 2T 4815 5217 9151 9909 10915 11830 4T 8621 9985 16468 18446 21068 22775 8T 9162 10268 16345 18483 21565 23821 122.9 1T 1171 1239 2220 3084 4024 5762 2T 1865 1828 3317 5545 7924 11479 4T 2181 2334 5305 9126 14409 21786 8T 2294 2321 5211 9064 14322 22029 12288 1T 249 393 534 904 1619 2839 2T 449 595 1083 1747 3266 5872 4T 895 1102 1904 3206 6116 11116 8T 721 871 1548 2805 4860 9417 Total Elapsed Time 52.0 seconds ARM/Intel MP-BusSpd v7 Benchmark V1.1 23-May-2015 17.05 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 1840 2073 3512 3554 4829 5243 2T 3432 4591 7128 7651 9120 9821 4T 4398 7855 13752 15428 18530 20235 8T 6692 9507 13857 16110 18143 18796 122.9 1T 860 753 2011 2841 3205 5282 2T 1505 1609 3076 5038 8089 10421 4T 1924 1981 4299 7588 14614 20754 8T 1909 1988 4264 7980 13884 19027 12288 1T 270 379 538 856 1626 2859 2T 471 677 1098 1849 3304 5924 4T 549 787 1066 1874 6274 10781 8T 713 853 1649 2258 4664 8321 Total Elapsed Time 13.1 seconds ########## T21 New Long Version ARM/Intel MP-BusSpd2 Benchmark V1.0 24-Jul-2015 15.39 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 2247 2616 4010 4443 4909 5614 2T 3558 4725 7241 9048 9747 10892 4T 6074 8303 13442 16937 18525 21068 8T 3998 5106 14314 13615 18200 20740 122.9 1T 874 1198 2024 2935 4529 5345 2T 1686 1702 3174 5357 7688 10545 4T 1988 2139 4465 8171 14969 21169 8T 1972 2139 4468 8195 15261 21132 49152 1T 292 406 516 899 1663 2929 2T 449 541 962 1569 2851 4776 4T 495 605 1109 2439 4161 8243 8T 530 564 1156 2149 4172 7907 Total Elapsed Time 48.0 seconds Android MP-BusSpd v5 Benchmark V1.1 28-Jun-2015 16.22 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 1580 2111 2197 2423 2106 2983 2T 3126 4066 4337 4906 4304 5978 4T 2973 7669 8596 9524 7180 12217 8T 6187 7529 8588 9479 8503 12328 122.9 1T 1240 1056 2030 2351 2234 3063 2T 2128 2064 3482 4645 4465 6350 4T 2292 2017 4843 7664 8769 12642 8T 2513 2283 5301 8989 7723 12660 12288 1T 273 393 495 876 1499 2133 2T 414 622 1011 1597 3043 4974 4T 500 1178 1696 3074 5668 9861 8T 678 834 1526 2586 4359 7446 Total Elapsed Time 13.3 seconds ********************* T22 32 Bit ******************** T22, Tab 2 A8-50, 1.3 GHz quad core 64 bit ARM Cortex-A53 Single Channel RAM, LPDDR3 666 MHz, 5.3 GB/second ARM/Intel MP-BusSpd2 Benchmark V1.2 12-Aug-2015 16.14 Compiled for 32 bit ARM v7a MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 1877 2124 2176 2266 2296 2343 2T 3625 4198 4341 4468 4536 4613 4T 5733 7541 8293 8830 8024 9042 8T 2985 3829 7438 6117 8108 8923 122.9 1T 604 625 1142 1846 2150 2284 2T 924 950 1793 3277 4270 4504 4T 962 989 1939 3765 6798 8862 8T 965 993 1933 3748 6651 8239 49152 1T 165 175 344 677 1285 1979 2T 234 238 482 961 1907 3547 4T 266 298 562 1224 2296 4478 8T 272 275 538 1098 2149 4282 Total Elapsed Time 48.8 seconds *************** T22 Android 5.1 32 Bit ************** ARM/Intel MP-BusSpd2 Benchmark V1.2 28-Sep-2015 21.14 Compiled for 32 bit ARM v7a MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 1949 2228 2244 2314 2370 2415 2T 3747 4316 4471 4528 4644 4772 4T 6289 7870 8486 8892 9079 9217 8T 2986 3811 7641 6447 8594 8995 122.9 1T 622 612 1181 1897 2202 2352 2T 947 980 1871 3376 4396 4652 4T 992 1024 2001 3912 6836 8790 8T 996 1022 1998 3852 6916 8770 49152 1T 163 174 344 680 1293 2050 2T 264 245 487 937 1912 3613 4T 294 288 547 1105 2223 4216 8T 277 285 603 1082 2180 4103 Total Elapsed Time 49.9 seconds ********************* T22 64 Bit ******************** ARM/Intel MP-BusSpd2 Benchmark V1.2 12-Aug-2015 16.18 Compiled for 64 bit ARM v8a MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 2610 2472 2586 2727 2748 5841 2T 4404 4681 4994 5369 5420 11297 4T 6546 8125 9105 10243 10319 20610 8T 3380 4023 7919 7146 9871 19852 122.9 1T 604 621 1110 1872 2446 5100 2T 919 948 1855 3433 4853 10037 4T 961 974 1984 3924 7491 14935 8T 963 942 1931 3915 7572 14689 49152 1T 173 177 340 692 1300 2653 2T 266 241 479 968 1883 3724 4T 304 277 556 1130 2126 4328 8T 279 278 544 1138 2179 4275 Total Elapsed Time 49.4 seconds *************** T22 Android 5.1 64 Bit ************** ARM/Intel MP-BusSpd2 Benchmark V1.2 28-Sep-2015 22.18 Compiled for 64 bit ARM v8a MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 2675 2586 2661 2787 2833 6014 2T 4705 4816 5023 5508 5603 11702 4T 6808 8393 9504 10556 10844 21329 8T 3518 4058 8373 7451 9900 19970 122.9 1T 625 639 1149 1955 2532 5265 2T 953 976 1906 3536 4986 10405 4T 991 999 2037 4048 7754 15457 8T 991 1000 2045 3987 7604 15243 49152 1T 171 177 343 673 1259 2602 2T 251 252 500 1132 1993 3877 4T 294 297 555 1021 2250 4424 8T 277 279 572 1117 2204 4501 Total Elapsed Time 48.8 seconds ***************************************************** P11 Galaxy SIII, Quad Cortex-A9 1.4 GHz, Android 4.0.4 LPDDR2 1066 MHz RAM, dual channel, 8.53 GB/sec Android MP-BusSpd v7 Benchmark V1.0 23-Dec-2012 14.42 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 3452 3697 4088 4122 3860 4183 2T 6616 7251 8016 8179 8307 8191 4T 8108 7430 10052 8511 8305 8404 8T 8729 10701 11687 12938 15297 15116 122.9 1T 747 762 746 966 992 1401 2T 1132 1161 1155 1554 1873 2668 4T 1127 1133 1137 2193 2987 4614 8T 1134 1145 1133 2210 3153 4231 12288 1T 82 89 200 376 739 1184 2T 204 179 407 797 1449 2205 4T 399 359 334 1227 1183 4038 8T 134 123 226 502 1378 3718 Total Elapsed Time 13.4 seconds Max RAM estimate 359*16 = 5744 MB/second Max CPU estimate 15116/1.92 = 7873 MIPS Android MP-BusSpd v5 Benchmark V1.0 23-Dec-2012 14.45 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 1041 1008 1308 1321 1836 2090 2T 2028 2010 2558 2649 3650 4213 4T 2185 2431 3019 3111 3960 4684 8T 2900 3928 4829 5289 7141 7866 122.9 1T 244 253 265 425 731 1118 2T 467 485 501 784 1237 2139 4T 794 834 842 1341 2103 3914 8T 789 830 809 1331 2308 3581 12288 1T 79 108 185 311 547 955 2T 157 219 238 603 1027 1812 4T 278 124 346 1013 1064 3383 8T 202 111 308 443 1081 2680 Total Elapsed Time 13.5 seconds ***************************************************** T7 Nexus 7 Quad 1300 MHz Cortex-A9, Android 4.1.2 DDR3L-1333 MHz RAM, single channel, 5.3 GB/sec Android MP-BusSpd v7 Benchmark V1.0 17-Oct-2012 13.53 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 2967 3169 3497 3535 3595 3567 2T 5729 6277 6857 6995 7030 7175 4T 7326 12132 13295 13757 14133 13780 8T 9770 12362 12224 12470 12259 12466 122.9 1T 351 353 337 544 637 980 2T 540 543 518 733 1260 1901 4T 642 750 753 1188 1542 2729 8T 728 748 746 1186 1459 2553 12288 1T 57 57 83 125 174 337 2T 111 114 186 250 346 673 4T 82 216 334 228 695 1351 8T 108 103 326 302 561 1127 Total Elapsed Time 13.6 seconds Max RAM estimate 216*16 = 3456 MB/second Max CPU estimate 12466/1.92 = 6492 MIPS ARM/Intel MP-BusSpd v7 Benchmark V1.1 05-May-2015 14.35 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 2853 3392 3376 3511 3551 3494 2T 2857 3389 3542 5540 5730 5595 4T 7257 10326 10289 10997 11373 11100 8T 6584 10325 10485 11175 11322 11189 122.9 1T 362 379 347 546 623 978 2T 516 530 508 726 1227 1840 4T 598 658 548 1181 1556 2657 8T 721 733 736 1181 1548 2653 12288 1T 58 57 84 123 173 334 2T 111 111 182 248 348 664 4T 87 85 276 463 687 1290 8T 154 107 147 429 441 1242 Total Elapsed Time 12.7 seconds ########## T7 New Long Version ARM/Intel MP-BusSpd2 Benchmark V1.0 24-Jul-2015 15.59 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 2166 2774 3181 3307 3377 3263 2T 3924 5188 5207 5754 5759 5805 4T 7570 10011 10252 11165 11375 11777 8T 3510 4786 9011 8318 11351 11544 122.9 1T 383 409 359 558 663 983 2T 525 541 520 741 1241 1814 4T 739 752 753 1219 1590 2776 8T 735 741 753 1218 1607 2737 49152 1T 56 51 81 126 172 330 2T 65 67 107 196 335 620 4T 70 68 108 215 426 835 8T 70 68 109 215 428 851 Total Elapsed Time 48.2 seconds Android MP-BusSpd v5 Benchmark V1.0 17-Oct-2012 13.58 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 966 941 1211 1267 1692 1922 2T 1739 1725 2236 2257 3141 3624 4T 3427 3406 4011 4611 6200 4553 8T 3033 2790 3896 4588 6256 6347 122.9 1T 153 159 165 280 499 812 2T 300 312 309 515 872 1512 4T 372 453 399 717 1344 2592 8T 410 452 388 715 1240 2595 12288 1T 27 28 46 86 168 322 2T 54 56 93 175 331 645 4T 68 112 186 306 645 882 8T 68 114 190 360 675 1126 Total Elapsed Time 12.8 seconds Measured CPU MHz - 1200 ***************************************************** T4 Miumiu w17 Pro 7 inch tablet, dual 1500 MHz Cortex-A9 Android MP-BusSpd v7 Benchmark V1.0 11-Oct-2012 20.02 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 2790 3123 3464 3516 3384 3250 2T 3948 5858 6466 6641 6764 6832 4T 5165 5915 6405 6097 6805 6700 8T 5444 5585 6488 6729 6876 6977 122.9 1T 484 497 481 579 644 1028 2T 927 929 923 1201 1264 1930 4T 916 940 926 1197 1175 1772 8T 932 929 937 1214 1285 1892 12288 1T 34 34 60 124 237 435 2T 49 47 85 162 295 650 4T 46 55 79 174 306 509 8T 46 50 103 176 345 698 Total Elapsed Time 12.7 seconds Android MP-BusSpd v5 Benchmark V1.0 11-Oct-2012 20.04 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 838 817 1052 1045 1474 1688 2T 1590 1618 2082 2102 2953 3411 4T 1654 1664 1783 2159 2855 3408 8T 1671 1667 2131 2197 2987 3458 122.9 1T 154 155 166 271 455 803 2T 308 318 332 518 865 1523 4T 299 317 339 519 876 1552 8T 314 322 338 528 883 1522 12288 1T 16 17 53 99 178 338 2T 37 38 75 154 363 596 4T 35 30 90 192 462 802 8T 37 36 101 171 325 791 Total Elapsed Time 12.9 seconds Measured CPU MHz - 1200 ***************************************************** T2 WayTeq xTAB-70 7 inch tablet, 800 MHz Cortex-A9 Android MP-BusSpd v7 Benchmark V1.0 11-Oct-2012 20.35 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 1857 1791 2061 2031 2003 2264 2T 1739 2005 1896 2230 2239 2254 4T 1776 2016 2151 2011 2254 2270 8T 1866 1875 2194 1981 2244 2270 122.9 1T 229 197 222 267 245 537 2T 211 217 191 296 314 534 4T 222 228 220 294 312 519 8T 205 226 215 257 300 503 12288 1T 32 33 59 62 59 132 2T 37 32 59 69 66 130 4T 36 36 56 68 65 127 8T 36 37 58 69 66 133 Total Elapsed Time 15.1 seconds Android MP-BusSpd v5 Benchmark V1.0 11-Oct-2012 20.36 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 129 551 709 738 991 1170 2T 562 552 707 728 983 1179 4T 564 557 522 722 967 1189 8T 562 512 685 719 966 1161 122.9 1T 76 70 72 131 230 410 2T 76 75 67 129 222 403 4T 75 75 72 128 224 400 8T 75 72 56 121 193 387 12288 1T 15 17 18 35 65 115 2T 16 18 19 38 64 130 4T 17 18 19 37 65 131 8T 18 17 19 38 65 132 Total Elapsed Time 15.7 seconds ***************************************************** T1 TTFone M013S 10.1 inch tablet, 300-800 MHz VIA 8650 Android MP-BusSpd v5 Benchmark V1.0 11-Oct-2012 20.47 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 383 393 387 458 489 523 2T 397 404 407 460 495 490 4T 396 388 395 450 491 472 8T 386 393 395 444 478 500 122.9 1T 28 25 29 55 99 177 2T 29 28 29 53 103 165 4T 28 28 27 55 102 174 8T 26 28 28 54 100 171 12288 1T 27 27 28 55 99 177 2T 27 28 29 54 97 173 4T 26 28 28 53 101 172 8T 27 28 28 54 100 174 Total Elapsed Time 13.8 seconds ***************************************************** BS1 BlueStacks Emulator on 3 GHz Phenom Android MP-BusSpd v7 Benchmark V1.0 11-Oct-2012 23.12 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 1600 1714 1714 1745 1706 1828 2T 1600 1745 1745 1745 1706 1755 4T 1535 1706 1745 1828 1755 1861 8T 1600 1600 1687 1778 1861 1862 122.9 1T 1090 1246 1477 1745 1714 1688 2T 1054 1154 1477 1746 1746 1755 4T 1025 1163 1476 1688 1638 1720 8T 1026 1164 1477 1538 1644 1762 12288 1T 349 403 744 1172 1512 1638 2T 345 403 726 1141 1563 1720 4T 363 446 716 1117 1445 1638 8T 354 390 716 1075 1445 1552 Total Elapsed Time 13.2 seconds ***************************************************** ET1 Emulator on 2.4 GHz Core 2 Duo Android MP-BusSpd v7 Benchmark V1.0 11-Oct-2012 16.34 MB/Second Reading Data, 1, 2, 4 and 8 Threads KB Inc32 Inc16 Inc8 Inc4 Inc2 RdAll 12.3 1T 753 699 846 860 863 864 2T 750 700 820 864 724 854 4T 750 685 828 862 850 853 8T 738 669 826 843 824 847 122.9 1T 656 600 756 817 844 848 2T 645 590 753 810 832 847 4T 634 596 750 804 826 314 8T 428 313 591 738 789 626 12288 1T 98 204 342 499 460 765 2T 98 202 339 499 675 757 4T 96 199 318 498 654 743 8T 94 171 334 491 660 738 Total Elapsed Time 12.8 seconds
RandMem benchmark carries out four tests at increasing data sizes to produce data transfer speeds in MBytes Per Second from caches and memory. Serial and random address selections are employed, using the same program structure, with read and read/write tests using 32 bit integers. The main purpose is to demonstrate how much slower performance can be through using random access. Here, speed can be considerably influenced by reading and writing in bursts, where much of the data is not used, and by the size of preceding caches. Details and results for Windows and Linux versions can be found in RandMem Results.htm.
This benchmark uses data from the same array for all threads, but starting at different points. Again, two versions are provided again for separate vfpv3 (v7) hardware and older CPUs (v5). Results of the Serial Reading tests are checked for the same result on all threads. An example of displayed results is shown below. Configuration details, as shown above for the first MP program, are included in Emailed details.
Android MP-RndMem v7 Benchmark V1.0 16-Oct-2012 12.25 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 3098 2998 3107 3032 2T 5245 2942 5287 2954 4T 4889 2834 3536 2528 8T 4849 2720 5570 2415 122.9 1T 871 978 758 745 2T 1393 1006 1487 468 4T 1517 960 1291 721 8T 1484 941 1407 631 12288 1T 352 225 48 47 2T 560 233 71 44 4T 568 228 72 45 8T 581 233 72 44 Total Elapsed Time 10.0 seconds
The original Windows version produces extremely slow speeds with read/write tests, particularly with random access. Later Linux varieties included Mutex, or mutual exclusion, functions avoid the updating conflict by only allowing one thread at a time to access common data. This can still lead to using multiple threads being slower than one but, with random access, there can be a significant improvement compared with untethered multiple thread speeds, except when accessing RAM (see linux%20multithreading%20benchmarks.htm).
These Android benchmarks also use Mutex and some speeds continue to be unpredictable. The surprise is that there is little variation using an increasing number of threads.
Tablet T2, again, sometimes seems to start running at a slower (power saving?) mode and BlueStacks performance is relatively fast using RAM.
August 2013 - T11 with the Cortex-A15 was tested with the Power Saving option on and off, with corresponding expected CPU speeds of 1000 and 1700 MHz. A surprise was that measured MB/second results were virtually the same for the two runs. The benchmark was modified to spend five times longer on each test, producing some results 1.7 times faster than those at 1000 MHz (see MHz graph). Then, a further modification for 100 times longer lead to all cache based tests effectively running at 1700 MHz.
Phone P11 also suffered from the same short test effects, but not to the same extent, with some tests being faster than T11, using the unmodified benchmark. On running tests five times longer, T11/P11 one and two thread cache based performance ratios averaged a mere 1.25 times, after adjusting for the same MHz. T7 also suffered from the slowdown, but ran continuously at 1200 MHz, with the 5 times longer running time, but comparisons with this did not help much as L2 and RAM speeds are much slower than those in P11. The extended running time made little difference on tablet T4.
February 2015 - Atom system A1 produced more difficult to explain strange results. The new ARM/Intel version produced btter performance, with cache based speeds up to 3.6 times faster on reading tests and 1.3 times with reading/writing (See Android Native ARM-Intel Benchmarks.htm).
July 2015 - The ARM/Intel compilation for T21, with the Qualcomm Snapdragon 800, is slower than the original version by an average of 14%. It is also slower than tablet A1, with the Intel Atom, on the 122.9 KB L2 cache tests but can be faster in other areas, on read only functions.
August 2015 - Results provided for 64 bit T22 with Cortex-A53 CPU. Probably as performance is dependent on the complex indexing used, performance is not significantly faster at 64 bits.
October 2015 - T7 Nexus 7, Android 5.0.2 and up to 5.1.1 upgrades produced similar speeds (not shown).
T22 Android 5.0.2 to 5.1 (ARM-v8 CPU) produced average performance increases of more than 2%, with some RAM based results no faster.
***************************************************** A1 Quad Core 1.86 GHz Intel Atom Z3745, Android 4.4 Dual Channel LPDDR3-1066 Bandwidth 17.1 GB/s Android MP-RndMem v7 Benchmark V1.1 04-Feb-2015 11.54 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 1069 1935 842 1895 2T 1516 2063 1809 2056 4T 1035 1959 1659 1453 8T 1204 665 800 763 122.9 1T 531 972 470 839 2T 1034 1181 971 1691 4T 2435 2155 1770 1614 8T 2548 2057 2009 1428 12288 1T 1147 1842 101 231 2T 1750 1926 187 222 4T 1787 1757 311 210 8T 2176 1840 302 212 Total Elapsed Time 5.2 secondsLonger Tests
Android MP-RndMem2 Benchmark V2.1 04-Feb-2015 12.27 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 1337 2397 1348 2555 2T 2735 2410 2534 2508 4T 3552 2398 3379 2426 8T 3175 2321 3052 2360 122.9 1T 1299 2248 956 1721 2T 2630 2250 1852 1733 4T 3406 2143 2825 1728 8T 3114 2212 2718 1715 12288 1T 1243 1960 101 212 2T 2479 1871 180 212 4T 3431 1924 297 212 8T 3105 1907 292 205 Total Elapsed Time 43.4 secondsARM/Intel Version
ARM/Intel MP-RndMem Benchmark V1.1 06-May-2015 11.54 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 4643 3593 4710 3641 2T 8583 3552 8761 3564 4T 12707 3450 12496 3384 8T 10410 3389 10796 3408 122.9 1T 3733 2874 2408 2150 2T 7259 2871 4781 2165 4T 11726 2897 7656 2133 8T 11673 2853 7100 2113 12288 1T 3153 2087 226 238 2T 5782 2073 327 238 4T 6451 1997 447 236 8T 6471 2071 446 233 Total Elapsed Time 41.5 secondsOld V5 Instructions
Android MP-RndMem v5 Benchmark V1.1 04-Feb-2015 12.06 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 2364 2585 2261 3688 2T 5218 2757 4833 2783 4T 4909 2218 3799 1873 8T 2579 912 2316 1158 122.9 1T 1543 1866 791 913 2T 2121 1004 1745 861 4T 3083 928 2110 720 8T 1838 711 730 462 12288 1T 2316 2068 202 184 2T 2258 1624 307 209 4T 3692 1802 361 197 8T 3203 1823 385 208 Total Elapsed Time 6.3 seconds ***************************************************** T11 Samsung EXYNOS 5250 Dual 2.0 GHz Cortex-A15, Android 4.2.2 Android MP-RndMem v7 Benchmark V1.1 09-Aug-2013 23.19 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 3906 2582 3742 2599 2T 7107 2469 6813 2520 4T 7231 2482 6825 2475 8T 6909 2366 6705 2361 122.9 1T 1979 1651 969 1003 2T 3555 1679 1107 932 4T 3549 1654 1146 983 8T 3577 1617 1150 969 12288 1T 1184 940 119 121 2T 1644 966 218 119 4T 1842 957 208 120 8T 1675 951 217 121 Total Elapsed Time 4.4 seconds Not running at expected 1700 MHzPower Saving Mode - 1000 MHz
MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 3733 2600 3882 2542 2T 7321 2473 7287 2501 4T 7071 2442 7176 2486 8T 5725 2400 6380 2394 122.9 1T 1934 1677 945 1012 2T 3530 1667 941 997 4T 3585 1655 1166 974 8T 3608 1617 1171 974 12288 1T 1129 894 122 122 2T 1866 943 219 121 4T 1855 906 217 121 8T 1959 956 218 120 Total Elapsed Time 4.3 secondsLonger Tests - 5 Times
MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 4169 2869 6407 4422 2T 12250 2680 12325 2804 4T 11023 2660 10793 2388 8T 12287 3034 12046 2860 122.9 1T 2187 2653 1582 1679 2T 6118 1786 2008 974 4T 6136 1828 1725 1036 8T 6353 1778 1784 1179 12288 1T 1372 1040 123 130 2T 2174 915 251 122 4T 2269 925 273 123 8T 2185 957 243 130 Total Elapsed Time 22.7 secondsLongest Tests - 100 Times
MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 6527 4454 6618 4475 2T 12829 4163 12880 4067 4T 12796 4082 12870 4119 8T 12749 4047 12465 4042 122.9 1T 3385 2888 1673 1751 2T 6277 2760 2059 1648 4T 6249 2734 2055 1357 8T 6356 1668 2064 1473 12288 1T 1316 921 145 113 2T 2141 963 264 139 4T 2160 892 262 137 8T 2202 938 267 137 Total Elapsed Time 415.6 seconds CPU MHz mainly 1700 ARM/Intel MP-RndMem Benchmark V1.1 06-May-2015 12.07 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 6315 4486 6345 4484 2T 11837 2910 11846 3112 4T 11864 2835 11553 2858 8T 11821 3003 11805 3198 122.9 1T 3963 2681 1670 1704 2T 6672 1782 2040 1125 4T 6493 1817 2033 1218 8T 6673 1738 2038 1303 12288 1T 1805 1081 177 145 2T 2543 1066 279 137 4T 2600 1065 276 136 8T 2662 1073 281 138 Total Elapsed Time 43.7 secondsOld V5 Instructions
Android MP-RndMem v5 Benchmark V1.1 04-Feb-2015 12.08 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 1942 1552 1943 1532 2T 3686 1488 3652 1524 4T 3676 1495 3639 1505 8T 3512 1460 2889 1411 122.9 1T 1140 1120 729 908 2T 2204 1108 923 913 4T 2177 1098 1031 894 8T 2101 1073 1014 859 12288 1T 876 755 82 127 2T 1490 705 149 125 4T 1517 749 175 129 8T 1916 771 182 140 Total Elapsed Time 6.4 seconds ***************************************************** T21 Qualcomm Snapdragon 800 2150 MHz, Android 4.4.4 Dual Channel 32 Bit LPDDR3-1866 RAM 14.9 GB/s Android MP-RndMem v7 Benchmark V1.1 29-Jun-2015 18.40 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 4586 3050 2867 2886 2T 4859 4681 4409 4357 4T 4530 4327 8776 4283 8T 8746 4706 11130 3761 122.9 1T 2726 2461 1515 2129 2T 3750 2010 2408 1548 4T 7593 2288 2996 1760 8T 4981 2279 2608 1901 12288 1T 1657 799 166 176 2T 2827 814 287 181 4T 2605 884 339 188 8T 3097 897 436 185 Total Elapsed Time 3.1 seconds Android MP-RndMem2 Benchmark V2.1 08-Jul-2015 16.33 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 5088 5325 4262 4711 2T 9752 4902 8895 4570 4T 17379 4653 17434 4096 8T 19771 4698 17358 4424 122.9 1T 2714 2578 1923 2163 2T 5614 2502 3483 2107 4T 10859 2219 4835 1972 8T 10654 2410 4904 1923 12288 1T 1798 952 186 204 2T 3489 974 341 195 4T 6515 943 563 196 8T 6218 922 563 187 Total Elapsed Time 42.3 seconds ARM/Intel MP-RndMem Benchmark V1.1 09-Jul-2015 11.48 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 4186 3777 4055 3933 2T 9324 3541 7710 3619 4T 16594 3350 15731 3142 8T 18117 3291 16187 3262 122.9 1T 2423 2043 1610 1683 2T 5235 2029 3013 1641 4T 10148 1935 4662 1565 8T 10015 1834 4611 1474 12288 1T 1363 886 171 186 2T 2643 845 325 187 4T 5197 823 534 184 8T 4801 835 542 184 Total Elapsed Time 42.6 seconds Android MP-RndMem v5 Benchmark V1.1 08-Jul-2015 16.28 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 1035 786 645 3547 2T 3137 3532 2641 3122 4T 5280 3565 3163 3341 8T 5859 3705 4347 3516 122.9 1T 1859 2012 741 1720 2T 1671 1982 1348 1817 4T 3594 1949 1050 1651 8T 2846 1862 1037 1639 12288 1T 984 739 84 187 2T 1989 873 145 166 4T 2107 840 213 181 8T 2072 901 248 182 Total Elapsed Time 5.3 seconds ********************* T22 32 Bit ******************** T22, Quad Core ARM Cortex-A53 1300 MHz, Android 5.0.2 ARM/Intel MP-RndMem Benchmark V1.2 12-Aug-2015 17.13 Compiled for 32 bit ARM v7a MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 2894 2438 2887 2433 2T 5665 2402 5663 2403 4T 10922 2369 11100 2310 8T 10065 2293 10648 2265 122.9 1T 2681 2368 757 758 2T 5351 2360 1398 769 4T 10056 2308 2121 772 8T 8838 2351 1916 742 12288 1T 2309 1662 80 78 2T 3986 1683 164 73 4T 5419 1684 283 82 8T 4658 1694 279 82 Total Elapsed Time 44.6 seconds *************** T22 Android 5.1 32 Bit ************** ARM/Intel MP-RndMem Benchmark V1.2 28-Sep-2015 21.17 Compiled for 32 bit ARM v7a MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 2897 2503 2973 2513 2T 5840 2481 5841 2388 4T 11351 2439 9284 2411 8T 11264 2369 9121 2365 122.9 1T 2829 2426 774 781 2T 5519 2402 1438 759 4T 10003 2429 2174 797 8T 9768 2424 2153 793 12288 1T 2403 1705 82 84 2T 3901 1679 166 83 4T 6020 1703 285 83 8T 4632 1690 274 83 Total Elapsed Time 46.7 seconds ********************* T22 64 Bit ******************** ARM/Intel MP-RndMem Benchmark V1.2 12-Aug-2015 17.15 Compiled for 64 bit ARM v8a MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 4445 3109 4455 3089 2T 8010 3100 8072 3105 4T 15909 3057 14711 3040 8T 14764 3036 14570 3037 122.9 1T 3457 2888 842 876 2T 6537 2924 1524 876 4T 11095 2892 2119 861 8T 11729 2916 2080 874 12288 1T 2475 1679 81 78 2T 4155 1713 163 73 4T 5503 1711 285 89 8T 4519 1717 281 89 Total Elapsed Time 48.1 seconds *************** T22 Android 5.1 64 Bit ************** ARM/Intel MP-RndMem Benchmark V1.2 28-Sep-2015 22.21 Compiled for 64 bit ARM v8a MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 4620 3220 4637 3206 2T 8183 3193 8343 3147 4T 16205 3146 16692 3150 8T 15950 3130 14491 3129 122.9 1T 3568 2979 871 888 2T 6743 2985 1553 892 4T 11639 2990 2178 896 8T 11401 3015 2186 889 12288 1T 2524 1691 82 80 2T 3863 1656 160 89 4T 4786 1701 283 91 8T 4821 1705 276 90 Total Elapsed Time 46.8 seconds ***************************************************** P11 Galaxy SIII, Quad Cortex-A9 1.4 GHz, Android 4.0.4 Android MP-RndMem v7 Benchmark V1.0 23-Dec-2012 14.40 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 2043 2028 2066 2027 2T 6788 3058 6835 3346 4T 6251 3104 6478 3376 8T 6635 3244 5408 3242 122.9 1T 1365 1392 1150 1151 2T 2415 1386 1927 1159 4T 2495 1374 1870 1117 8T 2470 1352 1772 1013 12288 1T 581 351 71 77 2T 1674 934 143 96 4T 1675 882 143 95 8T 1838 939 142 96 Total Elapsed Time 5.5 secondsLonger Tests - 5 Times
MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 2858 2844 3419 3044 2T 4162 2861 6614 3360 4T 8352 3082 9055 3352 8T 10021 3209 9708 3272 122.9 1T 1389 1315 1151 1137 2T 2513 1357 1890 1122 4T 3070 1375 1941 1134 8T 3548 1276 2000 951 12288 1T 1046 928 96 96 2T 1732 926 141 94 4T 1610 938 163 94 8T 1654 942 163 95 Total Elapsed Time 22.6 secondsOld V5 Instructions
Android MP-RndMem v5 Benchmark V1.0 23-Dec-2012 14.41 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 761 817 625 811 2T 2742 1779 3262 2268 4T 3429 2224 2920 2231 8T 3324 2169 3354 2160 122.9 1T 980 1154 661 1051 2T 1911 1136 1052 1011 4T 1788 1053 1139 1047 8T 1881 1117 1220 1064 12288 1T 354 352 53 83 2T 854 883 114 84 4T 1623 879 108 91 8T 1611 911 115 95 Total Elapsed Time 8.1 seconds ***************************************************** T7 Nexus 7 Quad 1300 MHz Cortex-A9, Android 4.1.2 Android MP-RndMem v7 Benchmark V1.0 22-Oct-2012 21.04 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 2019 3243 3347 3266 2T 3098 3155 3252 2981 4T 3160 2875 3167 2816 8T 2934 2862 2984 2811 122.9 1T 966 971 678 649 2T 948 988 685 708 4T 937 956 685 642 8T 980 983 624 538 12288 1T 311 304 87 79 2T 329 288 103 80 4T 640 286 123 80 8T 795 288 129 80 Total Elapsed Time 6.6 secondsLonger Tests - 5 Times
MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 3190 3123 3113 3069 2T 5923 3000 5937 3002 4T 11435 2761 11207 2888 8T 11400 2855 11371 2797 122.9 1T 952 955 652 670 2T 1737 953 988 673 4T 2526 947 1239 665 8T 2575 955 1473 668 12288 1T 329 279 85 77 2T 621 279 105 77 4T 934 275 113 77 8T 879 277 125 77 Total Elapsed Time 23.1 seconds ARM/Intel MP-RndMem Benchmark V1.1 06-May-2015 11.59 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 3060 2001 2867 1904 2T 5459 1879 5463 1867 4T 10797 1852 10537 1856 8T 10090 1802 10608 1813 122.9 1T 968 823 588 547 2T 1749 785 902 618 4T 2716 812 1328 672 8T 2733 810 1407 673 12288 1T 329 274 90 82 2T 636 272 112 82 4T 849 271 128 82 8T 869 271 126 81 Total Elapsed Time 45.4 secondsOld V5 Instructions
Android MP-RndMem v5 Benchmark V1.0 22-Oct-2012 21.06 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 1283 2113 1528 2116 2T 1602 2070 1487 2064 4T 1604 2031 1591 1895 8T 1149 1804 1450 1914 122.9 1T 781 905 458 722 2T 799 879 431 714 4T 791 870 408 704 8T 759 835 440 680 12288 1T 316 289 69 80 2T 592 267 102 81 4T 818 275 113 80 8T 815 272 115 81 Total Elapsed Time 9.2 seconds 12.29 1T 658 2120 1616 2133 2T 1618 2076 1606 2071 Measured CPU MHz - 1200 ***************************************************** T4 Miumiu w17 Pro 7 inch tablet, dual 1500 MHz Cortex-A9 Android MP-RndMem v7 Benchmark V1.0 16-Oct-2012 12.25 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 3098 2998 3107 3032 2T 5245 2942 5287 2954 4T 4889 2834 3536 2528 8T 4849 2720 5570 2415 122.9 1T 871 978 758 745 2T 1393 1006 1487 468 4T 1517 960 1291 721 8T 1484 941 1407 631 12288 1T 352 225 48 47 2T 560 233 71 44 4T 568 228 72 45 8T 581 233 72 44 Total Elapsed Time 10.0 secondsLonger Tests - 5 Times
MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 3069 3040 3097 3039 2T 5520 2900 5556 2896 4T 5623 2783 5713 2799 8T 5672 2719 5695 2761 122.9 1T 900 1023 768 767 2T 1595 978 1430 752 4T 1651 980 1445 763 8T 1659 956 1458 728 12288 1T 363 223 48 48 2T 609 226 72 48 4T 593 224 73 47 8T 603 235 73 47 Total Elapsed Time 24.8 seconds Android MP-RndMem v5 Benchmark V1.0 16-Oct-2012 12.27 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 1513 1967 1497 1973 2T 2703 1924 2969 1264 4T 2677 1860 1997 1879 8T 2607 1833 2329 1602 122.9 1T 774 767 407 660 2T 1481 838 836 723 4T 1340 841 828 709 8T 1402 822 791 585 12288 1T 316 238 43 43 2T 550 227 63 47 4T 587 227 66 46 8T 605 220 66 47 Total Elapsed Time 12.6 seconds Measured CPU MHz - 1200 ***************************************************** T2 WayTeq xTAB-70 7 inch tablet, 800 MHz Cortex-A9 Android MP-RndMem v7 Benchmark V1.0 16-Oct-2012 13.53 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 1969 1801 1995 1995 2T 1781 1863 962 1850 4T 1863 1863 1863 1720 8T 1572 1048 1656 1613 122.9 1T 358 357 279 102 2T 294 335 266 290 4T 280 312 223 223 8T 245 196 210 210 12288 1T 133 122 51 50 2T 133 115 53 50 4T 127 127 53 49 8T 130 126 53 50 Total Elapsed Time 13.3 seconds 12.29 1T 409 427 427 427 2T 386 372 403 395 4T 1903 1708 1863 1863 8T 1810 1613 1712 1613 122.9 1T 333 357 266 290 Android MP-RndMem v5 Benchmark V1.0 16-Oct-2012 12.36 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 646 1281 877 1117 2T 602 1181 931 1181 4T 790 1187 921 1183 8T 884 1081 925 1081 122.9 1T 170 419 234 396 2T 357 389 225 389 4T 223 286 131 357 8T 226 226 163 268 12288 1T 119 130 45 45 2T 127 132 43 50 4T 133 126 44 50 8T 132 129 44 49 Total Elapsed Time 17.9 seconds ***************************************************** T1 TTFone M013S 10.1 inch tablet, 300-800 MHz VIA 8650 Android MP-RndMem v5 Benchmark V1.0 16-Oct-2012 14.11 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 619 887 593 818 2T 521 862 570 751 4T 638 728 538 693 8T 521 500 325 509 122.9 1T 166 173 47 57 2T 180 172 45 55 4T 168 158 38 53 8T 152 137 44 49 12288 1T 190 176 19 23 2T 189 173 19 23 4T 189 180 19 22 8T 191 178 19 23 Total Elapsed Time 38.6 seconds ***************************************************** T9 ARM 926EJ 800 MHz, Android 2.2 Android MP-RndMem v5 Benchmark V1.1 09-jul-2013 22.54 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 0 909 620 796 2T 580 825 589 734 4T 228 722 540 685 8T 27 592 456 497 122.9 1T 102 183 48 5 2T 182 164 47 57 4T 165 107 43 24 8T 152 143 43 51 12288 1T 145 188 16 19 2T 193 164 17 20 4T 187 106 18 20 8T 178 158 19 19 Total Elapsed Time 43,9 seconds ***************************************************** BS1 BlueStacks Emulator on 3 GHz Phenom Android MP-RndMem v7 Benchmark V1.0 16-Oct-2012 14.31 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 2048 1921 1921 1755 2T 1921 1228 2457 1228 4T 1638 1638 1638 1638 8T 1528 1946 1528 1218 122.9 1T 2211 2047 1523 1935 2T 1228 1548 1548 1548 4T 1638 1638 1638 1638 8T 1825 1638 1638 1376 12288 1T 1843 1755 307 409 2T 1638 1638 351 351 4T 1638 2457 327 378 8T 1966 1966 327 393 Total Elapsed Time 11.1 seconds ***************************************************** ET1 Emulator on 2.4 GHz Core 2 Duo Android MP-RndMem v7 Benchmark V1.0 16-Oct-2012 12.44 MB/Second Using 1, 2, 4 and 8 Threads KB SerRD SerRDWR RndRD RndRDWR 12.29 1T 737 853 744 884 2T 707 815 709 796 4T 634 772 644 728 8T 508 476 440 483 122.9 1T 738 864 704 840 2T 709 835 753 805 4T 666 720 611 726 8T 517 290 483 559 12288 1T 682 778 41 48 2T 696 773 41 47 4T 690 785 41 48 8T 707 783 41 48 Total Elapsed Time 20.3 seconds
T1 Device TTFone M013S 10.1 inch tablet, 300-800 MHz VIA 8650 Screen pixels w x h 600 x 1024 Android Build Version 2.2 Processor : ARM926EJ-S rev 5 (v5l) BogoMIPS : 797.97 Features : swp half thumb fastmult edsp java CPU part : 0x926 Linux version 2.6.32.9 T2 Device WayTeq xTAB-70 7 inch tablet, 800 MHz Cortex-A9 Screen pixels w x h 600 x 800 Android Build Version 2.3.4 Processor : ARMv7 Processor rev 1 (v7l) BogoMIPS : 2035.71 Features : swp half thumb fastmult vfp edsp neon vfpv3 CPU part : 0xc09 - Cortex-A9 Linux version 2.6.34 T4 Device Miumiu w17 Pro 7 inch tablet, dual 1500 MHz Cortex-A9 Screen pixels w x h 600 x 976 Android Build Version 4.0.3 - Ice Cream Sandwich Processor : ARMv7 Processor rev 0 (v7l) processor : 0 BogoMIPS : 2393.70 processor : 1 BogoMIPS : 2393.70 Features : swp half thumb fastmult vfp edsp neon vfpv3 CPU part : 0xc09 - Cortex-A9 Hardware : Amlogic Meson6 g04 customer platform Linux version 3.0.8 T7 Device Google Nexus 7 quad core CPU 1.3, GHz 1.2 GHz> 1 core RAM 1 GB DDR3L-1333 Bandwidth 5.3 GB/sec Screen pixels w x h 1280 x 736 MHz Twelve-core Nvidia GeForce ULP graphics 416 MHz Android Build Version 4.1.2 Processor : ARMv7 Processor rev 9 (v7l) processor : 0 BogoMIPS : 1993.93 processor : 1 BogoMIPS : 1993.93 processor : 2 BogoMIPS : 1993.93 processor : 3 BogoMIPS : 1993.93 Features : swp half thumb fastmult vfp edsp neon vfpv3 tls CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x2 CPU part : 0xc09 - Cortex-A9 CPU revision : 9 Hardware : grouper - nVidia Tegra 3 T30L Revision : 0000 Linux version 3.1.10 T9 Device WM8650 800 MHz Screen pixels w x h 800 x 480 Android Build Version 2.2 Processor : ARM926EJ-S rev 5 (v5l) BogoMIPS : 797.97 Features : swp half thumb fastmult edsp java CPU implementer : 0x41 CPU architecture: 5TEJ CPU variant : 0x0 CPU part : 0x926 Hardware : WMT Linux version 2.6.32.9 T11 Voyo A15, Samsung EXYNOS 5250 Dual core 2.0 GHz Cortex-A15, Mali-T604 GPU, 2 GB DDR3-1600 RAM, dual channel, 12.8 GB/s Screen pixels w x h 1920 x 1032 Android Build Version 4.2.2 - Jelly Bean Processor : ARMv7 Processor rev 4 (v7l) processor : 0 BogoMIPS : 992.87 processor : 1 BogoMIPS : 997.78 Features : swp half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x0 CPU part : 0xc0f CPU revision : 4 Hardware : SMDK5250 Linux version 3.4.35Ut T21 Kindle Fire HDX 7, 2.2 GHz Quad Core Qualcomm Snapdragon 800 (Krait 400) 2 x 32 Bit LPDDR3-1866 Memory, 14.9 GB/s, GPU Qualcomm Adreno 330, 578 MHz Device Amazon KFTHWI Screen pixels w x h 1200 x 1803 Android Build Version 4.4.3 Processor : ARMv7 Processor rev 0 (v7l) processor : 0, 1, 2, 3 BogoMIPS : 38.40 Features : swp half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt CPU implementer : 0x51 CPU architecture: 7 CPU variant : 0x2 CPU part : 0x06f CPU revision : 0 Hardware : Qualcomm MSM8974 Revision : 0000 Linux version 3.4.0-perf (gcc version 4.7) T22 Lenovo Tab 2 A8-50, 1.3 GHz quad core 64 bit MediaTek ARM Cortex-A53 1 GB LPDDR3, GPU Mali T720 MP2 Device LENOVO Lenovo TAB 2 A8-50F Screen pixels w x h 800 x 1216 Android Build Version 5.0.2 Processor : AArch64 Processor rev 3 (aarch64) processor : 0, 1, 2 BogoMIPS : 26.0 Features : fp asimd aes pmull sha1 sha2 crc32 CPU implementer : 0x41 CPU architecture: AArch64 CPU variant : 0x0 CPU part : 0xd03 CPU revision : 3 Hardware : MT8161 Linux version 3.10.65 P11 Samsung Galaxy SIII, Quad Core 1.4 GHz Cortex-A9 Dual Channel DDR2 RAM Screen pixels w x h 720 x 1280 Android Build Version 4.0.4 Processor : ARMv7 Processor rev 0 (v7l) processor : 0 BogoMIPS : 1592.52 processor : 1 BogoMIPS : 2786.91 processor : 3 BogoMIPS : 398.13 Features : swp half thumb fastmult vfp edsp neon vfpv3 tls CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x3 CPU part : 0xc09 CPU revision : 0 Hardware : SMDK4x12 Revision : 000c Serial : 3b065f3d4df1bb2d Linux version 3.0.15 P12 Qualcomm Snapdragon S4, 1500 MHz Device Vega S5 - Dual Core CPU MSM8960 Screen pixels w x h 720 x 1184 Android Build Version 4.0.3 Processor : ARMv7 Processor rev 0 (v7l) processor : 0 BogoMIPS : 13.53 processor : 1 BogoMIPS : 13.53 Features : swp half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 CPU implementer : 0x51 CPU architecture: 7 CPU variant : 0x1 CPU part : 0x04d CPU revision : 0 Hardware : QCT MSM8960 EF44S Revision : 0000 Linux version 3.0.8 P13 Samsung Galaxy GT-I9100 SII Dual core 1.2 GHz Cortex-A9 Screen pixels w x h 480 x 800 Android Build Version 4.1.2 Processor : ARMv7 Processor rev 1 (v7l) processor : 0 BogoMIPS : 1592.52 processor : 1 BogoMIPS : 2388.78 Features : swp half thumb fastmult vfp edsp neon vfpv3 tls CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x2 CPU part : 0xc09 CPU revision : 1 Hardware : SHW-M250K Revision : 000a Linux version 3.0.31 P15 Lava Xolo A1000 1GHz Dual-core MT6577 Cortex A9 processor Screen pixels w x h 720 x 1280 Android Build Version 4.1.1 Processor : ARMv7 Processor rev 0 (v7l) processor : 0 BogoMIPS : 1993.93 Features : swp half thumb fastmult vfp edsp thumbee neon vfpv3 tls CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x3 CPU part : 0xc09 CPU revision : 0 Hardware : MT6577 Linux version 3.4.0 P19? Device not given Qualcomm Snapdragon S4 Dual Core Screen pixels w x h 720 x 1184 Android Build Version 4.3 Processor : ARMv7 Processor rev 0 (v7l) processor : 0 and 1 BogoMIPS : 13.53 Features : swp half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 CPU implementer : 0x51 CPU architecture: 7 CPU variant : 0x2 CPU part : 0x04d CPU revision : 0 Hardware : msm8960dt Revision : 81b2 Device : ghost Radio : 1 Linux version 3.4.42 P20 MediaTec MT6589, Quad Core Cortex A7 1.5 GHz Screen pixels w x h 720 x 1280 Android Build Version 4.2.1 Processor ARMv7 Processor rev 2 (v7l) processor : 0, 1, 2, 3 BogoMIPS : 3043.37 Features : swp half thumb fastmult vfp edsp thumbee neon vfpv3 tls vfpv4 idiva idivt CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x0 CPU part : 0xc07 CPU revision : 2 Hardware : MT6589 Linux version 3.4.5 P22 Samsung Galaxy Note II N7100 Quad-core 1.6 GHz Cortex-A9 Screen pixels w x h 720 x 1280 Android Build Version 4.1.2 Processor : ARMv7 Processor rev 0 (v7l) processor : 0, 1, 2, 3 BogoMIPS : 1592.52 Features : swp half thumb fastmult vfp edsp neon vfpv3 tls CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x3 CPU part : 0xc09 CPU revision : 0 Chip revision : 0020 Hardware : SMDK4x12 Revision : 000b Linux version 3.0.97 P23 Huawei ?? Octa-core Cortex A17 Screen pixels w x h 1280 x 720 Android Build Version 4.2.2 Processor : ARMv7 Processor rev 4 (v7l) processor : 0, 1, 2, 3, 4, 5, 6, 7 BogoMIPS : 2723.39 Features : swp half thumb fastmult vfp edsp thumbee neon vfpv3 tls vfpv4 idiva idivt CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x0 CPU part : 0xc07 CPU revision : 4 Hardware : MT6592 Revision : 0000 Linux version 3.4.39 A1 Asus MemoPad 7 ME176CEX, 1.86 GHz Atom Intel Atom Z3745 Screen pixels w x h 800 x 1216 Android Build Version 4.4.2 Processor : ARMv7 processor rev 1 (v7l) BogoMIPS : 1500.0 Features : neon vfp swp half thumb fastmult edsp vfpv3 CPU implementer : 0x69 CPU architecture: 7 CPU variant : 0x1 CPU part : 0x001 CPU revision : 1 Hardware : placeholder Revision : 0001 Linux version 3.10.20 ET1 Device Emulator 2.4 GHz Core 2 Duo Screen pixels w x h 600 x 1024 Android Build Version 4.0.4 Processor : ARMv7 Processor rev 0 (v7l) BogoMIPS : 292.45 Features : swp half thumb fastmult vfp edsp neon vfpv3 CPU implementer : 0x41 CPU part : 0xc08 Linux version 2.6.29 BS1 BlueStacks Emulator on 3 GHz Phenom Screen pixels w x h 1024 x 600 Android Build Version 2.3.4 processor : 0 vendor_id : AuthenticAMD cpu family : 16 model : 4 model name : AMD Phenom(tm) II X4 945 Processor stepping : 2 cpu MHz : 3013.000 cache size : 512 KB - - bogomips : 26686.25 Linux version 2.6.38
