Differences

This shows you the differences between two versions of the page.

--- en:xu4_benchmark_xu4_xu4q [2017/04/26 16:55]
luke.go [[ Benchmark (2) - Android AnTuTu ]]
+++ en:xu4_benchmark_xu4_xu4q [2017/04/27 12:56] (current)
john1117 [Benchmark of XU4 with Active Cooler and XU4Q with Passive Cooler]
@@ Line 1: / Line 1: @@
-====== Benchmark of ODROID-XU4 with Active Cooler and Passive Cooler (XU4Q) ======
+====== Benchmark of XU4 with Active Cooler and XU4Q with Passive Cooler ======
 This wiki page shows benchmark test results to analysis and compare their system performance\\
 with ODROID-XU4 and ODROID-XU4Q that equips with a passive cooler.\\
+{{:en:201704250351126731.jpg?423|}}
   * [[en:xu4_benchmark_xu4_xu4q&#benchmark_1_-_thermal_and_performance_using_sysbench| 1. Thermal and Frequency Performance Comparison]]
   * [[en:xu4_benchmark_xu4_xu4q&#benchmark_2_-_android_antutu | 2. AnTuTu Performance Comparison ]]
   * [[en:xu4_benchmark_xu4_xu4q&#benchmark_3_-_kernel_build_time| 3. Kernel Build Time Performance Comparison]]
+We've tested three categories of benchmarking utilities and here is a brief result for each test cases.\\
+**sysbench**\\
+- to investigate and compare thermal/cpu frequency performance\\
+- Sysbench running time increased by 16% and 6% for each cases of cpu max 2GHz and 1.8GHz\\
+**AnTuTu**\\
+- for examining a variety of categories performance\\
+- The decreasing score value of XU4Q from XU4 is just 2% \\
+**Kernel build**\\
+- to check the hardest stress case\\
+- About 5m 17s increase of the total execution time (20%)\\
+Except the hardest case like kernel build, the differences are under just 10% or lower.\\
 ==== [ Benchmark (1) - Thermal and Frequency Performance Comparison ]====
@@ Line 59: / Line 75: @@
 Here is sysbench test result in case of max cpu frequency 2.0GHz.\\
-  * Running Time : about 1.16% increase - XU4Q / XU4 = 420 / 362 = 1.16%
+  * Running Time : about 16% increase - XU4Q / XU4 = 420 / 362 = **116%**
-  * Average CPU Frequency : about 0.78% loss - XU4Q / XU4 = 1.48 / 1.89 = 0.78%
+  * Average CPU Frequency : about 22% loss - XU4Q / XU4 = 1.48 / 1.89 = **78%**
-{{:en:1_xu4_max_2ghz.png?700}}
+{{:en:1_xu4_max_2ghz.png?700}}{{:en:2_xu4q_max_2ghz.png?700}}
-{{:en:2_xu4q_max_2ghz.png?700}}
 === Test Case 2 - Max CPU Frequency 1.8GHz case ===
-  * Running Time : about 1.06% increase - XU4Q / XU4 = 392  / 368 = 1.06%
+  * Running Time : about 6% increase - XU4Q / XU4 = 392  / 368 = **106%**
-  * Average CPU Frequency : about 0.89% loss - XU4Q / XU4 = 1.61 / 1.8 = 0.89%
+  * Average CPU Frequency : about 11% loss - XU4Q / XU4 = 1.61 / 1.8 = **89%**
-{{:en:3_xu4_max_1_8ghz.png?700}}
+{{:en:3_xu4_max_1_8ghz.png?700}}{{:en:4_xu4q_max_1_8ghz.png?700}}
-{{:en:4_xu4q_max_1_8ghz.png?700}}
 === Test Case 3 - Finding the threshold not to drop under max frequency ===
@@ Line 76: / Line 90: @@
 ==== [ Benchmark (2) - Android AnTuTu ] ====
+Here is Android AnTuTu benchmark result for examining common and a variety of categories' score.
 === Environment ===
@@ Line 90: / Line 106: @@
 {{:en:screen-xu4q_1.png?direct&600|}}\\
 \\
-=== Conclusion ===
+=== Detail score ===
-^ Category         ^ XU4      ^ XU4Q     ^ %      ^
+^ Category         ^  XU4      ^  XU4Q     ^      % ^
-| 3D               | 9823     | 9843.5   | 0.21   |
+| 3D               |  9823     |  9843.5   |   0.21 |
-| Marooned         | 6337     | 6347     | 0.16   |
+| Marooned         |  6337     |  6347     |   0.16 |
-| Garden           | 3486     | 3496.5   | 0.30   |
+| Garden           |  3486     |  3496.5   |   0.30 |
-| UX               | 21681    | 21443    | -1.11  |
+| UX               |  21681    |  21443    |  -1.11 |
-| Data secure      | 4976.5   | 4975     | -0.03  |
+| Data secure      |  4976.5   |  4975     |  -0.03 |
-| Data process     | 3517.5   | 3496.5   | -0.60  |
+| Data process     |  3517.5   |  3496.5   |  -0.60 |
-| Strategy games   | 5677.5   | 5751.5   | 1.29   |
+| Strategy games   |  5677.5   |  5751.5   |   1.29 |
-| Image process    | 4787.5   | 4505     | -6.27  |
+| Image process    |  4787.5   |  4505     |  -6.27 |
-| I/O performance  | 2722     | 2715     | -0.26  |
+| I/O performance  |  2722     |  2715     |  -0.26 |
-| CPU              | 23933.5  | 22774    | -5.09  |
+| CPU              |  23933.5  |  22774    |  -5.09 |
-| Mathematics      | 5245     | 5248.5   | 0.07   |
+| Mathematics      |  5245     |  5248.5   |   0.07 |
-| Common use       | 7798     | 7621     | -2.32  |
+| Common use       |  7798     |  7621     |  -2.32 |
-| Multi-Core       | 10890.5  | 9904.5   | -9.96  |
+| Multi-Core       |  10890.5  |  9904.5   |  -9.96 |
-| RAM              | 5791     | 5543     | -4.47  |
+| RAM              |  5791     |  5543     |  -4.47 |
-| Result           | 61228.5  | 59603.5  | -2.73  |
+| Result           |  61228.5  |  59603.5  |  -2.73 |
 \\
 {{:en:xu4vsxu4q_antutu.png?direct&700|}}
 {{:en:xu4vxxu4q_percentage.png?direct&600|}}
@@ Line 116: / Line 134: @@
 ==== [ Benchmark (3) - Kernel Build Time ] ====
-TODO
+To check the hardest stress case, we did put kernel build test on XU4 and XU4Q.\\
+The test instruction is as following.
+<code>
+$ make odroidxu3_defconfig
+$ time make -j8
+</code>
+Based on the result, in this case, the kernel build time on XU4Q gets **around 20%** increase from XU4's one.
+^  time   ^  XU4  ^  XU4Q  ^
+|  real  |   25m 1.43s   |  30m 18.36s    |
+|  user  |   149m 58.72s   |  184m 44.36s   |
+|  sys   |   22m 54.96s    |   27m 21.55s   |