Compared with ARM architecture, Intel x86 architecture has stronger performance but higher power consumption, which is a well-known fact. So how much stronger is the CPU performance of Intel x86 architecture than that of ARM architecture? Let's do a simple evaluation of a single Core.
My PC CPU: Intel Pentium Dual-Core CPU E5300 2.60GHz (Launched 2008Q1 x86)
My phone's CPU: Qualcomm Snapdragon S2 MSM8255 1.0GHz (Launched 2010Q2 ARMv7)
From the above description, it can be seen that Intel CPU was launched two years earlier than Qualcomm CPU.
We use the Whetstone benchmark (Whetstone: floating-point arithmetic performance) to test the CPU performance. The general steps are as follows:
1. Download Whetstone source code
2. Use gcc to compile Windows PC version executable program in MinGW environment
3. Use arm-none-linux-gnueabi-gcc to compile Android Native C version executable program in Linux cross-compilation environment
4. Run the test program in Windows
5. Run the test program in Android ARM Linux
6. Summarize the running time
1. Download Whetstone source code
You can download the source code file directly at the following address:
http://www.netlib.org/benchmark/whetstone.c
2. Use gcc to compile Windows PC version executable programs in MinGW environment
Compile in MinGW using the following command line: gcc -static whetstone.c –O0 -o whetstone -lm
Note: -O0 is used to prevent gcc from optimizing the code to ensure the accuracy of the comparison test
3. Use arm-none-linux-gnueabi-gcc to compile Android Native C version executable program in Linux cross-compilation environment
Use the following command line to compile in the Linux cross-compilation environment: arm-none-linux-gnueabi-gcc -static whetstone.c –O0 -o whetstone -lm
For more information about how to set up a Linux cross-compilation environment, see my other article: "Setting up an ARM cross-compilation environment in Ubuntu 10.04"
http://blog.csdn.net/xt_xiaotian/article/details/6836739
4. Run the test program in MinGW
Run the program 100 times and observe the output.
$ time ./whetstone.exe 100
Loops: 100, Iterations: 1, Duration: 8 sec.
C Converted Double Precision Whetstones: 1250.0 MIPS
real 0m8.698s
user 0m0.s
sys 0m0.015s
5. Run the test program in Android ARM Linux
Assume that adb (Android Debug Bridge) has been configured in the system. Connect the phone to the USB data cable and turn on USB debugging. Enter adb shell in the cmd window to enter the Android adb shell. Then configure as follows:
1. Use mount –o remount,rw /system to mount the /system directory as writable. Press Ctrl + C to exit the Android adb shell and return to the cmd window.
2. Use adb push C:\whetstone /system to copy the whetstone program compiled in the Linux cross-compilation environment to the /system folder in Android Linux.
3. Use chmod whetstone to set the program as executable
4. Run the program using time ./whetstone 100 and observe the output.
The output is:
Loops: 100, Iterations: 1, Duration: 148 sec.
C Converted Double Precision Whetstones: 67.6 MIPS
real 2m 28.88s
user 2m 28.25s
sys 0m 0.02s
6. Summary of running time
The same program, with the same number of loops, takes 8.698 seconds to run on an Intel CPU and 148.88 seconds to run on a Qualcomm CPU.
It can be concluded that in terms of floating point operations, the Intel Pentium Dual-Core CPU E5300 2.60GHz is 17 times more powerful than the Qualcomm Snapdragon S2 MSM8255 1.0GHz. According to Intel's Moore's Law, CPU performance will double every 18 months. It can be roughly calculated that the Intel CPU is 42 times more powerful than the Qualcomm CPU of the same grade and time.
The test may not be accurate, but it does reflect the performance gap between the two different types of CPUs to a certain extent. Everyone is welcome to reply and tell us the test values of your own ARM CPU and PC CPU.
--This
comparison is not scientific.
The main reason is that you run too few cycles. The user time of Windows is ignored. The user time of Android is about the same as the running time.
The difference can be seen only when the number of cycles is increased. The difference should be close to 1 times, not 42 times.
--In
comparison, Qualcomm MSM8255 is only equivalent to an Intel Pentium III Mobile 750MHz. Link: http://ark.intel.com/products/27410/Mobile-Intel-Pentium-III-Processor-750-MHz-256K-Cache-100-MHz-FSB
Previous article:ARM CPU architecture and classification description
Next article:Comparison of ARM and X86 architecture terminal features
Recommended ReadingLatest update time:2024-11-16 14:46
- Popular Resources
- Popular amplifiers
- Siemens PLC Programming Technology and Application Cases (Edited by Liu Zhenquan, Wang Hanzhi, Yang Kun, etc.)
- Siemens PLC from Beginner to Mastery with Color Illustrations (Yang Rui)
- Experience and skills in using Siemens S7-200PLC (Shang Baoxing)
- Siemens S7-1200-PLC Programming and Application Tutorial (3rd Edition) (Edited by Shi Shouyong)
Professor at Beihang University, dedicated to promoting microcontrollers and embedded systems for over 20 years.
- Innolux's intelligent steer-by-wire solution makes cars smarter and safer
- 8051 MCU - Parity Check
- How to efficiently balance the sensitivity of tactile sensing interfaces
- What should I do if the servo motor shakes? What causes the servo motor to shake quickly?
- 【Brushless Motor】Analysis of three-phase BLDC motor and sharing of two popular development boards
- Midea Industrial Technology's subsidiaries Clou Electronics and Hekang New Energy jointly appeared at the Munich Battery Energy Storage Exhibition and Solar Energy Exhibition
- Guoxin Sichen | Application of ferroelectric memory PB85RS2MC in power battery management, with a capacity of 2M
- Analysis of common faults of frequency converter
- In a head-on competition with Qualcomm, what kind of cockpit products has Intel come up with?
- Dalian Rongke's all-vanadium liquid flow battery energy storage equipment industrialization project has entered the sprint stage before production
- Allegro MicroSystems Introduces Advanced Magnetic and Inductive Position Sensing Solutions at Electronica 2024
- Car key in the left hand, liveness detection radar in the right hand, UWB is imperative for cars!
- After a decade of rapid development, domestic CIS has entered the market
- Aegis Dagger Battery + Thor EM-i Super Hybrid, Geely New Energy has thrown out two "king bombs"
- A brief discussion on functional safety - fault, error, and failure
- In the smart car 2.0 cycle, these core industry chains are facing major opportunities!
- The United States and Japan are developing new batteries. CATL faces challenges? How should China's new energy battery industry respond?
- Murata launches high-precision 6-axis inertial sensor for automobiles
- Ford patents pre-charge alarm to help save costs and respond to emergencies
- New real-time microcontroller system from Texas Instruments enables smarter processing in automotive and industrial applications
- Interrupt-Based Ambient Light and Environment Sensor Node Reference Design for Sub-1 GHz Networks
- STM32CUbe usage issues
- Low-power MCUs and smart buildings
- STM32F103C8T6 low power consumption issue
- [D-Gesture Recognition Device] D_Gesture Recognition
- The difference between continuous wave power and pulse power
- About the memory FRAM of msp430fr2000!!
- Optimal control of solar panel position based on GD32E231
- STM32F103C8T6 low power consumption problem
- ADAFRUIT PYBADGE LC CAN RUNNING MAKECODE ARCADE, CIRCUITPYTHON AND ARDUINO