I am using SharpDX and am fairly comfortable with it at the moment, but for an assessment for university, I need to create a demo which utilizes some sort of GPU acceleration. This is an 'independent research' task - what that means is, I assigned myself this task. I am legitimately interested in GPU acceleration in games, but right now it feels like I threw myself way too far into the deep.
I am planning to do a particle system (it will be a very BASIC system, with particles firing/falling/dieing) but I need a starting point.
Can someone point me in the right direction? Articles to read? things to consider? I have googled my heart out on things like "GPU acceleration DirectX", but I can't find any solid results! I wish I had a sort of 'hello world' for GPU acceleration..!
If you want to understand how to build a GPU particle system, I suggest you to read the book "Practical Rendering And Compution with Direct3D11", where you will find an entire chapter dedicated on how to implement a simple GPU particle system.
Then the most trickiest part is probably the sorting algorithm which is not detailed in the previous book, but you can have a look at ComputeShaderSort11 sample from the old DirectX June 2010 that could help you a lot (the implementation is quite efficient).
Also, I did a full particle engine on the GPU with SharpDX at my work, so It is perfectly achievable with SharpDX.
my question is : how can build single board computer like Raspberry Pi for run OS ?
user ARM micro processor and debian arm os , can use USB and etc.
like raspberry pi and other single board computer
i search but find nothing for help me !!! :(
The reason you can find nothing is probably because it is a specialist task undertaken by companies with appropriate resources in terms of expertise, equipment, tools and money.
High-end microprocessors capable of running an OS such as Linux use high-pin-density surface mount packages such as BGA or TQFP, these (especially BGA) require specialist equipment to manufacture and cannot reliably or realistically be assembled by hand. The pin count and density necessitates the use of multi-layer boards, these again require specialist manufacture.
What you would have to do if you wanted your own board, is to design your board, source the components, and then have it manufactured by a contract electronics assembly house. Short runs and one-off's will cost you may times that of just buying a COTS development or application board. It is only cost-effective if you are ultimately manufacturing a product that will sell in high volumes. It is only these volumes that make the RPi so inexpensive (and until recently Chinese manufacture).
Even if you designed and had your own board built, that in itself requires specialist knowledge and skill. The bus speeds on such processors require very specific layout to maintain signal integrity and timing and to avoid EMC problems. The cost of suitable schematic capture and board layout software might also be prohibitive, no doubt there are some reasonably capable open source tools - but you will have to find one that generates output your manufacturer can use to set-up their machinery.
Some lower-end 8 bit microcontrollers with low pin count are suitable for hand soldering or even DIP socketing, using a bread-board or prototyping board, but that is not what you are after.
[Further thoughts added 14 Sep 2012]
This is probably only worth doing if one or more of the following are true:
Your aim is to gain experience in board design, manufacture and bring-up as an academic or career development exercise and you have the necessary financial resources.
You envisage high production volumes where the economies of scale make it less expensive than a COTS board.
You have product requirements for specific features or form-factor not supported by COTS boards.
You have restricted product requirements where a custom board tailored to those and having no redundant features might, in sufficient volumes be cost-effective.
Note that COTS boards come in two types: Application modules intended for integration in a larger system or product, and development boards that tend to have a wide range of peripherals, switches, indicators and connectivity options and often a prototyping area for your own use.
I know this is an old question, but I've been looking into the same thing, possibly for different reasons, and it now comes up at the top of a google search providing more reasons not to ask or even look into it than it provides answers.
For an overview of what it takes to build a linux running board from scratch this link is incredibly useful:
http://hforsten.com/making-embedded-linux-computer.html
It details:
The bare minimum you need in terms of hardware ( ARM processor, NAND flash etc )
The complexities of getting a board designed
The process of programming the new chip on the board to include bootloaders and then pointing them to a linux kernel for the chip to boot.
Whether the OP wishes to pursue every or just some of these challenges, it is useful to know what the challenges are.
And these won't be all of them, adding displays, graphics and other hardware and interfaces is not covered, but this is a start.
Single board computers(SBC) are expected to take more load than normal hobby board and so it has slightly complicated structure in terms of PCB and components. You should be ready to work with BGA packages. Almost all of processors in SBCs are BGA (no DIP/QAFP). Here is the best blogpost that I recently came across. Its very nicely designed and fabricated board running Linux on ARM processor. Author has really done a great job at designing as well as documenting the process. I hope it helps you to understand both hardware and software side of SBCs.
A lot of answers are discouraging. But, I would say you can do it, as I have done it already with imx233. Its not easy, its not a weekend project. My project link is MyIMX233.
It took me about 4-5months
It didn't cost me much, a small fine tip soldering iron is what I used.
The hard part is learning to design PCB.
Next task would be to find a PCB manufacturer with good enough precision, and prototyping price.
Next task would be to source components.
You may not get it right, I got the PCB right by my 3rd iteration. After that I was able to repeatedly produce 3 more boards all of which worked fine.
PCB Design - I used opensource KiCAD. You need to take care in doing impedance matching between RAM and processor buses, and some other high speed buses. I managed to do it in 2 layer board with 5mil/5mil trace space.
Component Sourcing - I got imx233 LQFP once via mouser, and once via element14.
RAM - 64MB tssop.
Soldering - I can say its easy to mess up here, but key is patience. And one caution don't use frying pan and solder past to do reflow soldering. I literally fried my first 2 processors like this. Even hot air soldering by a mobile repair shop was also not good enough.
Boot loading image - I didn't take much chance here, just went with Archlinux image by olimex.
If you want to skip the trouble of circuit designing between RAM & processor, skip imx233 and go for Allwinner V3S. In 2017/2018 this would be easiest approach.
Bottom line is I am a software engineer by profession, and if I can do it, then you can do it.
Why not using an FPGA board?
Something with Zynq like the Zybo board or from Altera like the DE0-Nano SoCKit.
There you already have the ARM core, memory, etc... plus the possibility to add the logic you miss.
I remember reading some time ago that there were cpu cards for systems to add additional processing power to do mass parallelization. Anyone have any experience on this and any resources to get looking into the hardware and software aspects of the project? Is this technology inferior to a traditional cluster? Is it more power conscious?
There are two cool options. one is the use of GPU's as Mitch mentions. The other is to get a PS/3, which has a multicore Cell processor.
You can also set up multiple inexpensive motherboard PCs and run Linux and Beowulf.
GPGPU is probably the most practical option for an enthusiast. However, DSPs are another option, such as those made by Texas Instruments, Freescale, Analog Devices, and NXP Semiconductors. Granted, most of those are probably targeted more towards industrial users, but you might look into the Storm-1 line of DSPs, some of which are supposed to go for as low as $60 a piece.
Another option for data parallelism are Physics Processing Units like the Nvidia (formerly Ageia) PhysX. The most obvious use of these coprocessors are for games, but they're also used for scientific modeling, cryptography, and other vector processing applications.
ClearSpeed Attached Processors are another possibility. These are basically SIMD co-processors designed for HPC applications, so they might be out of your price range, but I'm just guessing here.
All of these suggestions are based around data parallelism since I think that's the area with the most untapped potential. A lot of currently CPU-intensive applications could be performed much faster at much lower clock rates (and using less power) by simply taking advantage of vector processing and more specialized SIMD instruction sets.
Really, most computer users don't need more than an Intel Atom processor for the majority of their casual computing needs: e-mail, browsing the web, and playing music/video. And for the other 10% of computing tasks that actually do require lots of processing power, a general-purpose scalar processor typically isn't the best tool for the job anyway.
Even most people who do have serious processing needs only need it for a narrow range of applications; a physicist doesn't need a PC capable of playing the latest FPS; a sound engineer doesn't need to do scientific modeling or perform statistical analysis; and a graphic designer doesn't need to do digital signal processing. Domain-specific vector processors with highly specialized instruction sets (like modern GPUs for gaming) would be able to handle these tasks much more efficiently than a high power general-purpose CPU.
Cluster computing is no doubt very useful for a lot of high end industrial applications like nuclear research, but I think vector processing has much more practical uses for the average person.
Have you looked at the various GPU Computing options. Nvidia (and probably others) are offering personal supercomputers based around utilising the power of graphics cards.
OpenCL - is an industry wide standard for doing HPC computing across different vendors and processor types, single-core, multi-core, graphics cards, cell, etc... see http://en.wikipedia.org/wiki/OpenCL.
The idea is that using a simple code base you can use all spare processing capacity on the machine regardless of type of processor.
Apple has implemented this standard in its next version Mac OS X. There will also be offerings from nVIDIA, ATI, Intel etc.
Mercury Computing offers a Cell Accelerator Board, it's a PCIe card that has a Cell processor, and runs Yellow Dog Linux, or Mercury's flavor of YDL. Fixstars offers a more powerful Cell PCIe board called the GigaAccel. I called up Mercury, they said their board is about $5000 USD, without software. I'd guess the GigaAccel is up to twice as expensive.
I found one of the Mercury boards used, but it didn't come with a power cable, so I haven't been able to use it yet, sadly.
As it currently stands, this question is not a good fit for our Q&A format. We expect answers to be supported by facts, references, or expertise, but this question will likely solicit debate, arguments, polling, or extended discussion. If you feel that this question can be improved and possibly reopened, visit the help center for guidance.
Closed 10 years ago.
I'm looking to learn about embedded programming (in C mainly, but I hope to brush up on my ASM as well) and I was wondering what the best platform would be. I have some experience in using Atmel AVR's and programming them with the stk500 and found that to be relatively easy. I especially like AVR Studio and the debugger that lets you view that state of registers.
However, If I was to take the time to learn, I would rather learn about something that is prevalent in industry. I am thinking ARM, that is unless someone has a better suggestion.
I would also be looking for some reference material, I have found the books section on the ARM website and if one is a technically better book than another I would appreciate a heads up.
The last thing I would be looking for is a prototyping/programming board like the STK500 that has some buttons and so forth.
Thanks =]
"embedded programming" is a very broad term. AVR is pretty well in that category, but it's a step below ARM, in that it's both simpler to use, as well as less powerful.
If you just want to play around with ARM, buy a Nintendo DS or a Gameboy Advance. These are very cheap compared to the hardware inside (wonders of mass production), and they both have free development toolchains based off of gcc which can compile to them.
If you want to play around with embedded linux, BeagleBoard is looking to be a good option, only $150 and it has a ton of features.
Personally I think AVR is best for the smaller-sized 8-bit platforms, and ARM is best for the larger, more powerful 32-bit based platforms. Like many AVR fans, I don't like PIC. It just seems worse in pretty much every way. Also avoid anything that requires you to write any type of BASIC.
If you just want to play around with it, I'd suggest the Arduino platform (http://www.arduino.cc). It's based on the ATmega168 or ATmega8, depending on the version. It uses a C-like language and has its own IDE.
Myself I've worked in embedded programming for 9 years now and have experience on TI MSP430, Atmel AVR (a couple of flavours) and will be using an ARM soon.
My suggestion is to pickup something that has some extra features in the processor like ethernet controller and CAN controller, even get two or three if you can. Embedded devices are nice to work with, but once they can talk to other similar devices via CAN or get onto a network, they can become much more fun to play with.
ADI's Blackfin is another option since it's quite a straight forward architecture to program, yet can also do some fairly hefty DSP stuff should you choose to go down that route. It helps that the assembly language is quite sane too.
The Blackfin STAMP boards are an inexpensive (~$100 last I checked) way in, and they support the free GCC tools and uClinux.
Whatever architecture you choose I'd definitely recommend first downloading the toolchain\SDK and looking through the sample projects and tutorials - generally having a bit of a play about. You can often get quite acquainted with the architecture through simulation without even touching any hardware.
ARM has the nicest instruction set of the widely used embedded platforms, leaving you free to pick up the general principles of writing software for embedded platforms without getting bogged down in weird details like non-orthogonal registers or branch delay slots. There are plenty of emulators - ARM's own, while not free, is cycle-accurate; and a huge variety of programmable ARM-based hardware is cheap and easy to come by as well.
The TI MSP430 is a great platform for learning how to program microcontrollers. TI has a variety of FREE Tools and some cheap evaluation boards (starting at $20). Plus, it's a low-power, modern microcontroller.
A nice choice would be PIC18 by Microchip
It has quite alot of material, documentation, tutorials and projects on the internet
Free IDE and compiler.
you can pull your own flash writer in a few minutes.
(Although for a debugger to work you'll need to work harder)
If you're a student (or has a student email address) Microchip will send you free sample chips. So basically you can have a full development environment for close to nothing.
PICs are quite prevalent in the industry. Specifically as controllers for robots for some reason although they can do so much more.
Arduino seems to be the platform of choice these days for beginners although there are lots of others. I like the Olimex boards personally but they are not really for beginners.
Microchip's PIC range of CPUs are also excellent for beginners, especially if you want to program in assembler.
BTW, Assembler is not used as much as it used to. The general rule with embedded is if you've got 4k of memory or more, use C. You get portability and you can develop code faster.
I suppose it depends on your skill level and what you want to do with the chip. I usually choose which embedded chip to use by the available peripherals. If you want a USB port, find one with USB built in, if you want analogue-to-digital, find one with an ADC etc. If you've got a simple application, use an 8-bit but if you need serious number crunching, go 32 bits.
I'd like to suggest the beagleboard from TI. It has a Omap3 on it. That's a Cortex-A8 ARM11 CPU, a C64x+ DSP and a video accelerator as well.
The board does not need an expensive jtag device. A serial cable an an SD-Card is all you need to get started. Board costs only $150 and there is a very active community.
www.beagleboard.org
Your question sort of has been answered in this question.
To add to that, the embedded processor industry is very segmented, it doesn't have a major player like Intel/x86 is for the "desktop" processor industry. The ARM processor does have a large share, so does MIPS I believe, and there are many smaller more specific microcontroller like chips available (like the MSP430 etc from TI).
As for documentation, I do embedded development for a day job, and the documentation we have access to (as software developers) is rather sparse. Your best bet is to use the documentation available on the processor manufacturers site.
Take a look at Processing and the associated Arduino and Wiring boards.
If you just want to have fun, then try the Parallax Propeller chip. The HYDRA game platform looks like a blast. There's a $100 C compiler for it now.
I started on BASIC stamps, moved up through SX chips and PICs into 8051s, then 68332s, various DSPs, FPGA soft processors, etc.
8051s are more useful in the real world... the things won't go away. There's TONS of derivatives and crazy stuff for them. (Just stay away from the DS80C400) The energy industry is absolutely full of them.
Start with something tiny. If you have external RAM and plenty of registers... what's the difference between that and a SBC?
Many moons ago I've worked with 8-bitters like 68HC05 and Z80, later AVR and MSP430 (16-bit). However most recent projects were on ARM7. Several manufacturers offer ARM controllers, in all colors and sizes (well, not really color).
ARM(7) is replacing 8-bit architecture: it's more performant (32-bit RISC at faster instruction cycles than most 8-bitters), has more memory and is available with several IO-configurations.
I worked with NXP LPC2000 controllers, which are also inexpensive (< 1 USD for a 32-bitter!).
If you're in Europe http://www.olimex.com/dev/index.html has some nice low-cost development boards. Works in the rest of the world too :-)
For a fun project to test, have a look at xgamestation
But for a more industrial used one chip solution programming, look at PIC
For my Computer Architecture course I had to work with both a PIC and an AVR; in my opinion the PIC was easier to work with, but that's maybe because that's what we worked with the most and we had the most time to get used to. We used the AVR maybe only a couple of times so I couldn't get the hang of it perfectly but it also was nothing overly complicated, or at least not more frustrating than the other.
I think you can also order microprocessor samples from Microchip's website so you could also get started with that?
Second that:
Arduino platform http://www.arduino.cc
HTH
For learning, you can't go past the AVR. The chips are cheap and they'll run with zero external components - they also supply enough current to drive an LED straight from the port.
You can start with a cheap programmer such as lady-ada's USBTinyISP (USD$22 for a kit) which can power your board with 5V from the USB port. Get the free tools WinAVR (GCC based) and AVRStudio and get a small project working in no time.
Yes the AVRs have limitations - but developing software for microcontrollers is largely about managing resources and coping with those problems. It's unlikely that you'll experience problems such as running out of stack space, RAM or ROM when you're making hobbist projects for powerful ARM platforms.
That said, ARM is also a great platform which is widely used in the industry, however, for learning I highly recommend AVRs.
I would suggest Microchip's PIC18F series. I just started developing for them with the RealICE in-circuit emulator, but the pickit2 is a decent debugger for the price. You could say this for the AVR's also, but there is a large following for the device all over the web. I was able to have a - buggy, yet functional - embedded USB device running within days due to all the PIC related chatter.
The only thing I don't like about the PICs is that a lot of the sample code is VERY entwined into the demo boards. That can make it hard to tear out sections that you need and still have an application that will build and run for your application.
Texas Instruments has released a very interesting development kit at a very low price: The eZ430-Chronos Development Tool contains an MSP430 with display and various sensors in a sports watch, including a usb debug programmer and a usb radio access point for 50$
There is also a wiki containing lots and lots of information.
I have already created a stackexchange proposal for the eZ430-Chronos Kit.
You should try and learn from developpers kits provided by Embedded Artists. After you get the kit, check their instructional videos and videos provided by NXP, which are not as detailed as they could be, but they cover a lot of things. Problems with learning ARM as your first architecture and try to do something practicall are:
You need to buy dev. kit.
You need a good book to learn ARM assembly, because sooner or later you will come across ARM startup code, which is quite a deal for a beginner. The book i mentioned allso covers some C programming.
Combine book mentioned above with a user guide for your speciffic processor like this one. Make sure you get this as studying this in combination with above book is the only way to learn your ARM proc. in detail.
If you want to make a transfer from ARM assembly to C programming you will need to read this book, which covers a different ARM processor but is easier for C beginner. The down side is that it doesn't explain any ARM assembly, but this is why you need the first book.
There is no easy way.
mikroElektronika has nice ARM boards and C, Pascal and Basic compilers that might suite your demands.