Questions tagged [gpu]
Anything related to Graphics Processing Units (GPUs), i.e. microprocessors specially designed to efficiently handle all the calculations needed to implement 2D and 3D graphic operations and rendering on modern computer systems.
55
questions
0
votes
1answer
54 views
Damages caused by inversely connected PCI-e power cable?
Recently, I used a 6-pin to 8-pin PCI-e convertor to power a graphics card (see the picture). After installation, each time I turned on the switch on the PSU and pressed the power button on the PC, ...
0
votes
0answers
8 views
T460P Whining when not connected to charger
I have a Thinkpad T460P that whines when performing tasks. This happens mostly when it is not connected to the charger. Has anyone else had this problem, and fixed it (e.g. desolder coils/capacitors ...
0
votes
1answer
104 views
Is it safe to keep using graphics card with blown diode? [closed]
Is it safe to use my GTX 1070 ti with a blown diode? It works as usual. Please see attached image. I don't know much about this, but it looks like d33 has blown.
Thanks in advance.
0
votes
0answers
110 views
Can this component be identified? Top mark is 2B with a sideways F
What do you think, does this look right?
https://www.mouser.com/datasheet/2/916/PMPB215ENEA-1600076.pdf
Short is gone........
This is the 1V rail for a GTX 2060 GPU which is currently shorted. I'm ...
-2
votes
1answer
158 views
A computer architecture joke [closed]
Background
Some months ago, I watched a Youtube video posted by the channel Numberphile. The video was on famous world mathematician Terence Tao, and in the video, he seemed to be struggling with ...
0
votes
1answer
49 views
Is there a way to power a GPU only by external supply?
Actually I don't think so, because I think different components of the GPU are powered by only one of the two sources.
0
votes
2answers
236 views
What happens if the PCI voltage in input to a GPU is different from external power supply voltage?
In particular if there is a difference of one or two volts between the two inputs? Is it safe?
2
votes
2answers
340 views
Low voltage GPU decoupling capacitor longevity
Recently noticed my GPU card (Nvidia 1060) made more coil noise (electrical noise, noise level proportional to frame rate) than usual. I discovered that directly behind the GPU chip one of 2 big 470uF,...
1
vote
0answers
51 views
DC-DC converter cause PC GPU computer to shut down
I am currently trying to power up a edge GPU computer that runs on 12-19 V and is rated for 60 W.
Whenever I start to overclock my computer to run some machine learning stuff, the computer will just ...
5
votes
5answers
1k views
How is quality/damage control done in large circuits?
There is apparently more than 28 billion transistors in the recently released Nvidia GeForce RTX 3080.
First, when you manufacture such a circuit there must be a decent chance of botching some of ...
1
vote
3answers
214 views
Why do displays have limited bit-depth?
As far as I am aware,
HDMI 2.1 does support 12-bit 4K 60fps, Also it doesn't use TMDS, rather FRL. Sends upto 48Gbps
GPUs can do calculation in fp32 and from some reference, I think that it can send ...
0
votes
0answers
67 views
Stacking PCBs seamlessly
Seeing NVIDIA's Massive RTX3090 leaks got me thinking. Would it be possible to almost seamlessly stack PCBs? Like have the small parts on the bottom and bigger parts on the top and put a liquid ...
2
votes
0answers
42 views
Question about component name (DrMOS?)
I'm trying to find the fault on my GTX 970 card and it seems that I have found at least one of the problems. There seems to be a DrMOS(?) that after plugging the power in is getting hot to the touch ...
2
votes
1answer
245 views
Nvidia 1080 ti VRM? SMD Identification
I was hoping that some of you experts could help me identify a SMD on the back of a 1080 ti FE. This item was dropped and it appears has some damage done to it. I would like to replace the missing SMD ...
1
vote
0answers
71 views
How to overclock an embedded TPU?
I am doing a benchmark between 2 EDGE devices: Google Coral and Jetson Tx2.
I have planned to overclock the TPU and GPU respectively.
So far I have overclocked the TPU, from 250MHz (STD) to 500 MHz (...
0
votes
1answer
101 views
STM32MP157 GPU documentation
Reference Manual Chapter 20 of this document describes GPU and basically uses 2 sentences about, it is just present, however it mentions that it supports OpenGL ES 2.1 API. The question is, ST ...
19
votes
5answers
8k views
Why does GPU consume so much power?
I am trying to understand why GPUs consume so much power. For example, the max power consumption of the P100 GPU is 250W.
As I understand power is measures in watts as ...
1
vote
1answer
150 views
Gpu to interface with an arm cpu [closed]
I am building an embedded gaming system to... well to play games. I looked up to the gameboy advance cpu manual and saw that it had some sort of gpu. Where can I find a gpu to use with an arm cpu? I ...
0
votes
3answers
164 views
Why is GPU memory fixed? [closed]
In pretty much all modern computers and mobile devices, the CPU can have varying amounts of memory (either to be configured by the user or fixed at point of assembly). Apart from historical form-...
0
votes
0answers
79 views
Please help me identify the SMD component
I have two nVIDIA Quadro P5000 GPUs. This component got damaged in one of the GPU while I was removing it from the PC. Please help me to identify this SMD component so that I could purchase and solder ...
0
votes
2answers
653 views
Why are GPU dies so much physically bigger than CPU dies?
I understand that the physical sizes of microchips are generally limited by silicon yields. The larger your chip is, the more waste occurs when you hit a defect in the silicon and have to throw it ...
4
votes
1answer
845 views
USB Camera to GPU Memory Directly
There may be several points in this question which may not make sense to a knowledgeable person, so I do thank you for your understanding in advance.
For a computer vision project I wish to process ...
1
vote
3answers
220 views
Would a standardized graphics chip socket be sensible? [closed]
I am not an EE, and so I'm running this conjecture on breaking out the GPU from the CPU by folks who have better knowledge than me. Perhaps you can point out something I don't know about modern CPU ...
0
votes
2answers
1k views
GPU vs CPU on chip memory
There has been a fairly wide ranging discussion as to why it is difficult to combine memory / CPU logic on the same die (yield issue compounding, different processes, different clock-frequency, ...
0
votes
1answer
139 views
GPU Shader Hardware Requirements Question
I have a question which I hope is not out of the scope of this branch of the exchange network and is a fair question (to be fair I have provided a block diagram on what I have so far) on the "basics" ...
2
votes
1answer
563 views
GPU-grade memory bandwidth on low-cost FPGA solutions
I'm designing a custom FPGA board, for something low-cost like a Xilinx Spartan 6. I want to perform research about solving memory-intensive algorithms in an FPGA.
As we all know, memory bandwidth is ...
-1
votes
1answer
76 views
Will a laptop works with missing GPU Power rail? [closed]
I have a skylake laptop with a dedicated graphics, the Mosfets on the buck converter are shorted (at least one of them) so if i cut the 1v gpu power rail will the laptop works again?
Thanks in advance....
0
votes
1answer
126 views
Connecting GPU chips in order to create more powerful graphic card [closed]
I had thoughts about GPU and I came up with an idea. Why not putting more than one GPU chips in order to create a powerful graphic card? Is it possible with ordinary GPU chips or one need custom ...
2
votes
1answer
1k views
Understanding GDDR5 clamshell mode
Let suppose a 256 bit memory controller is installed on a PCB with GDDR5 memory modules.
In normal mode you can split the lines into 8 group of 32 bit and drive 8 modules x 1Gbit (128 MB) = 1 GB of ...
0
votes
1answer
493 views
Intel iGPU die area and power consumption
What is the Intel's iGPU area occupied on the die (or transistor count) and what is the power consumpition of the iGPU alone?
Didnt find any information from Intel, quite odd they dont advertise this ...
1
vote
2answers
69 views
How to discern quality of a breakout board? other than proper soldering on back of board [closed]
I see three different breakout boards for a project I am doing yet I am not sure which one to pick. How would i know which is of higher quality?
I do see a metal circle inserts in board two and ...
0
votes
3answers
156 views
Why does the capacitor exist on this breakout board but not others that have same function?
I am looking at using either of these parts to connect to a server power supply. I realize a capacitor helps to regulate voltage. Why would each of these parts that have similar function not both have ...
0
votes
2answers
706 views
How can I use an Nvidia GPU with an open-source embedded board? [closed]
Is it possible by any means or method, to use an Nvidia GPU with an (probably open-source) embedded board? If yes, how do I go about achieving that? I have a few ideas but I'm just a beginner, hence ...
1
vote
2answers
235 views
How overvoltaging makes graphic processing unit operate faster?
My teacher told me that we are trying to make transistors smaller so that they require less electricity to operate, hence make them faster (because changing form 1 signal to 0 or vice versa need less ...
1
vote
2answers
5k views
Why are there 2 clock rates (core vs memory clock) in the GPU?
I learned at school that the clock rate inside a computer is the signal that keep switching between 0 - 1 (or active - inactive). There's also another delayed clock with the same frequency. These 2 ...
1
vote
2answers
585 views
Standard Interface Between LCD and GPU
Almost all smartphones on the market seem to use a distinct LCD as their display, though most use an ARM processor with a GPU from one of a relatively (compared to the screens) small number of ...
1
vote
2answers
4k views
Is the bracket of a graphics card grounded?
I would guess so, but I want to make sure.
Edit: After measuring with a multimeter, I suspect that brackets (of most graphics cards) are grounded to the graphics card's ground-plane.
I measured 0 ohm ...
-3
votes
1answer
152 views
How to design a Video Card with existing GPU (NVDIA/AMD)? [closed]
I searched on the web if there is any documentation about designing a video card using existing GPU (NVDIA/AMD). Let's say, ASUS, MSI and other brands design GTX 960 cards using the same GPU. I'd like ...
-2
votes
2answers
195 views
What makes a circuit bootable or capable of runnning an OS? [closed]
I posted this on StackOverflow for the premise that any programmer (not an HTML coder, who does not, strictly speaking, do programming, though HTML does require a lot of specific knowledge and bears a ...
1
vote
2answers
418 views
CPUs and GPUs temperature ranges
Every integrated circuit, like any other component, have a working temperature range. The minimum ranges are in the commercial grade (if I did dot forget something), while the military/aersopace grade ...
2
votes
1answer
88 views
Moving beyond high end microcontrollers to high performance computation embedded systems [closed]
I have been working a with relatively fast and high end microcontrollers now, and I want to move beyond them. For example, I've been using the STM32F4 chip, which has something of a 180MHz and a ...
0
votes
1answer
291 views
ESD protection for work with CPU/GPU
I am ready to perform a BGA reballing operation on my ps3's CPU and GPU chips. Should i take into consideration electrostatic discharge or is it not needed?
How can i protect from these dangers? Are ...
0
votes
1answer
213 views
Does NVIDIA Tegra SoC's and AMD Fusion APU's bypass the GPU<->CPU memory transfer bottleneck?
The major limitation in heterogeneous CPU+GPU programming seems to be the slow memory transfer across the PCI-e bus when data needs to be passed back and forth between the Device and Host. I have ...
6
votes
1answer
544 views
Capturing data at 500MHz
I have an ADC sampling at 500MHz (It is collecting data from an Ultrasound sensor). I need to be able to stream this data to my PC (for the time being - this will be done through a wireless unit). I ...
0
votes
2answers
371 views
How much power does a GPU actually use when only doing PCIe I/O, or only compute?
I hope this is the right sight to ask such a question, if not please be kind and direct me elsewhere.
I have some discrete GPU with a TDP figure of X watts. Now, sometimes the GPU does
Only ...
3
votes
2answers
2k views
GPU reflow soldering profile
I've had my ENGTX480/2DI/1536MD5 GPU for 3 and half years now.
Over the past 2 months it started causing trouble. At first, it started seldom displaying big zones with
weird color, but simply ...
3
votes
1answer
853 views
what inside a graphical processor?
Preamble
Due to the super-secret nature of commercial GPU, I didn't find anything interesting yet.The best thing I can do is asking that to someone which has more experience than me (everyone). It's ...
1
vote
1answer
824 views
3D Rotation Using Fixed Point Arithmetic - Rotating Object is Deforming (and Shrinking)
I have an FPGA board (Virtex 5) for which I have created a Wireframe GPU with the ability to rotate a sample object using a 3 Axis Trackball. Additionally, I have connected the board to a PC Monitor.
...
19
votes
2answers
17k views
How does a GPU/CPU communicate with a standard display output? (HDMI/DVI/etc) [closed]
I am interested in how the cpu/gpu presents (to whatever equipment that it does) video data after it has been processed.
I have been told that the video is processed by the CPU/GPU and then sent to ...
6
votes
1answer
2k views
Is CPU/GPGPU heat dissipation quadratic in clock frequency?
In the following article on overclocking a Pentium from 1GHz to 5GHz using liquid nitrogen: The 5GHz Project, there is an assertion that "Heat dissipation rises exponentially during extreme ...
