How to obtain GPU computing power

Publish: 2021-05-18 05:44:59

1. You can refer to the following, according to some commonly used graphics cards in the Internet bar market, sort out the price and calculation power of a related graphics card, as well as the expected return to the current period, It can be used as a reference:
power consumption: 243w
computing power: 22.4m
price of graphics card: 1999 yuan
number of eth g every 24 hours: 0.015
revenue generated every 24 hours: 24.48 yuan
expected payback time: 81.66 days
power consumption: 159w
computing power: 24.3m
price of graphics card: 1599 yuan
price of graphics card: 1599 yuan
every 24 hours Number of time digging eth: 0.017
revenue generated every 24 hours: 27.9 yuan
expected payback time: 57.31 days
video card of radon RX 480

AI studio's notebook is equipped with instry class NVIDIA Tesla V100 resources. Now AI studio has launched the computing support program to apply. Application link: webpage link. After the application information is verified by AI studio operators, if it meets the qualification, it will be notified by e-mail to give an invitation code for free GPU computing power exchange. On the other hand, those who fail can wait for other activities. AI studio will hold operation activities from time to time to win GPU power card

3. Mali
GPU can be taken from / sys / devices / platform / gpusysfs, including minimum and maximum frequency, current frequency and GPU utilization rate
Adreno
GPU can be found in the folder with kgsl in / sys / class / devfreq / directory. This is a link. The actual location is in / sys / devices / directory.

4. The main reason for GPU's strong computing power is that most of its circuits are arithmetic units. In fact, adders and multipliers are relatively small circuits. Even if they do many such operation units, they will not occupy too much chip area. And because other parts of GPU occupy a small area, it can also have more registers and caches to store data.

Latest gray position

BTC -- total holding: 653561btc, 24h position change: - 36.0032btc, gray position proportion: 3.11%

LTC -- total holding: 1503032ltc, 24h position change: - 102.9583ltc, gray position proportion: 1.79%

eth -- total holding: 3167456eth, 24h position change: - 217.1109eth, Gray position proportion: 2.74%

BCH -- total holding: 293618bch, 24h position change: - 20.0843bch, gray position proportion: 1.40%

etc -- total holding: 12404188etc, 24h position change: - 1019.6023etc, Gray position proportion: 5.89%

{rrrrrrr}

the Xueshuo innovation blockchain Technology Workstation of Lianqiao ecation online is the only approved "blockchain Technology Specialty" pilot workstation of "smart learning workshop 2020 Xueshuo innovation workstation" launched by the school planning, construction and Development Center of the Ministry of ecation of China. Based on providing diversified growth paths for students, the professional station promotes the reform of the training mode of the combination of professional degree research, proction, learning and research, and constructs the applied and compound talent training system

6. Through the search and autopsy of the file, Android ' s GPU information needs access to OpenGL, and android framework providing GL10 with appropriate parameters to obtain GL10, while GL10 is available only at the time of the use of automatic Views, as examples of access to GPUInformation:
1. Examination of RenderType

[java] view plain
class DemoRenderer > Log.d(" System Info ", " " GL_VENDOR = " + gl.glGetString(GL10.GL_VENDOR); > Log.d(" System Info ", " " GL_VERSION = " + gl.glGetString(GL10.GL_VERSION); > Log.i (" System Info ", " " GL_EXTENSIONS = " + gl.glGetString(GL10.GL_EXTENSIONS); 
@Override
/public void onDrawFrame(GL10 arg0) {
/ / / TODO Auto generated method stub

@Override
/public void onSurface Changed (GL10 arg0, int arg1, int arg2) ) { /br /
<

int arg2) {

[java] view plain
ClaCla/> /DemoRenderer mRenderer; < Browse / > > Public DemoGLSurfaceView(Context context) {
< super(context); setEGLConfigChooser(8, 8, 8, 8, 0, 0); < Renderer = new DemoRender(); < < br/ / >

<
<
<
<

< super.onCreate(savedInstanceState); > GLSurfaceView glView = new DemoGLSurfaceView(this); / /this.setContentView(glView); }
}

7. GPU is the display core of graphics card, similar to the concept of CPU. We don't need to know the GPU code, we just need to distinguish it by GPU model. General GPU can be known when you buy a graphics card, such as hd6670, hd6750, hd6770 / gts450, gtx550ti, gtx460, etc. we usually use this to distinguish the classification of graphics cards. For specific internal models, you can use the software gpu-z to view the specific information of graphics cards.

8. CPU-Z software can do that. In the sensors option, GPU load is the utilization rate of GPU, and memory usage is the occupied capacity of video memory.

9. The simplest way, Master Lu has a hardware situation, which do you want to see.

Hot content

Inn digger Publish: 2021-05-29 20:04:36 Views: 341

Purchase of virtual currency in trust contract dispute Publish: 2021-05-29 20:04:33 Views: 942

Blockchain trust machine Publish: 2021-05-29 20:04:26 Views: 720

Brief introduction of ant mine Publish: 2021-05-29 20:04:25 Views: 848

Will digital currency open in November Publish: 2021-05-29 19:56:16 Views: 861

Global digital currency asset exchange Publish: 2021-05-29 19:54:29 Views: 603

Mining chip machine S11 Publish: 2021-05-29 19:54:26 Views: 945

Ethereum algorithm Sha3 Publish: 2021-05-29 19:52:40 Views: 643

Talking about blockchain is not reliable Publish: 2021-05-29 19:52:26 Views: 754

Mining machine node query Publish: 2021-05-29 19:36:37 Views: 750

How to obtain GPU computing power

Related to How to obtain GPU computing power