GPUs in DSP

I heard somewhere that PC GPUs can be used to do say FFTs. They are
cheap and very powerful (though not that easy to prorgam). You can get
up to 1000 processors on a GPU so it could have all manner of
applications. However, the I/O would slow things down I expect unless
the CPU and GPU were on the same chip (lets say). Has anybody linked
GPUs with FPGA I/O?


Hardy

HardySpicer wrote:

> I heard somewhere that PC GPUs can be used to do say FFTs. They are
> cheap and very powerful (though not that easy to prorgam). You can get
> up to 1000 processors on a GPU so it could have all manner of
> applications. However, the I/O would slow things down I expect unless
> the CPU and GPU were on the same chip (lets say). Has anybody linked
> GPUs with FPGA I/O?

Hardy, can you do anything other then babbling nonsense? If you can, 
download a library for ATI or NVIDIA, compile it and see for youself.

On Jun 18, 4:02&#4294967295;pm, Vladimir Vassilevsky <nos...@nowhere.com> wrote:
> HardySpicer wrote:
> > I heard somewhere that PC GPUs can be used to do say FFTs. They are
> > cheap and very powerful (though not that easy to prorgam). You can get
> > up to 1000 processors on a GPU so it could have all manner of
> > applications. However, the I/O would slow things down I expect unless
> > the CPU and GPU were on the same chip (lets say). Has anybody linked
> > GPUs with FPGA I/O?
>
> Hardy, can you do anything other then babbling nonsense? If you can,
> download a library for ATI or NVIDIA, compile it and see for youself.

That wasn't the question. Clearly English is not your first language
so I understand your confusion.
My question was, has anybody interfaced their own FPGA board with a
GPU so that I/O can be speeded up.
Don't bother answering Vlad if you just want to flame.

Hardy

HardySpicer <gyansorova@gmail.com> wrote:

(snip)

> That wasn't the question. Clearly English is not your 
> first language so I understand your confusion.
> My question was, has anybody interfaced their own FPGA 
> board with a GPU so that I/O can be speeded up.
(snip)

I suppose you could do that, but would it help?

As FPGAs aren't so good for floating point, it might be that
GPU attached to an FPGA (possibly as a coprocessor for a more
common system) would be useful.  Otherwise, you can do a lot
of processing inside an FPGA.  

-- glen

On 18 Jun, 03:25, HardySpicer <gyansor...@gmail.com> wrote:
> I heard somewhere that PC GPUs can be used to do say FFTs. They are
> cheap and very powerful (though not that easy to prorgam).

I have seen people  come up with this 'brilliant' idea
every couple of years for a couple of decades, already.
The common factor is that people look exclusively at the
number of FLOPS / gates / processing units, and forget that
the GPUs are intensely tuned to highly specialized tasks.

Which means that it easily takes at least as much work to
re-formulate the generic task at hand to fit the special
structure of the GPU pipeline (which might not be possible
at all), as would be required doing the job with a generic
FPU in the first place.

Rune

Rune Allnor <allnor@tele.ntnu.no> wrote:
> On 18 Jun, 03:25, HardySpicer <gyansor...@gmail.com> wrote:
>> I heard somewhere that PC GPUs can be used to do say FFTs. They are
>> cheap and very powerful (though not that easy to prorgam).
 
> I have seen people  come up with this 'brilliant' idea
> every couple of years for a couple of decades, already.
> The common factor is that people look exclusively at the
> number of FLOPS / gates / processing units, and forget that
> the GPUs are intensely tuned to highly specialized tasks.

Especially tasks that can be done using single precision
floating point.  
 
> Which means that it easily takes at least as much work to
> re-formulate the generic task at hand to fit the special
> structure of the GPU pipeline (which might not be possible
> at all), as would be required doing the job with a generic
> FPU in the first place.

Well, I believe that there are now compilers that speed
up the process, though it still takes more work than
normal programming.

-- glen

HardySpicer wrote:

> On Jun 18, 4:02 pm, Vladimir Vassilevsky <nos...@nowhere.com> wrote:
> 
>>HardySpicer wrote:
>>
>>>I heard somewhere that PC GPUs can be used to do say FFTs. They are
>>>cheap and very powerful (though not that easy to prorgam). You can get
>>>up to 1000 processors on a GPU so it could have all manner of
>>>applications. However, the I/O would slow things down I expect unless
>>>the CPU and GPU were on the same chip (lets say). Has anybody linked
>>>GPUs with FPGA I/O?
>>
>>Hardy, can you do anything other then babbling nonsense? If you can,
>>download a library for ATI or NVIDIA, compile it and see for youself.
> 
> 
> That wasn't the question. Clearly English is not your first language
> so I understand your confusion.
> My question was, has anybody interfaced their own FPGA board with a
> GPU so that I/O can be speeded up.
> Don't bother answering Vlad if you just want to flame.

Hardy, what do you know about FFT, GPU, FPGA ? Do you at least 
understand the difference between them? Have you ever made anything 
practical, or at least can you write a "hello world" program ?
Why don't you try doing anything yourself, instead of casting utter 
nonsense ?

VLV

On Jun 17, 9:25&#4294967295;pm, HardySpicer <gyansor...@gmail.com> wrote:
> I heard somewhere that PC GPUs can be used to do say FFTs. They are
> cheap and very powerful (though not that easy to prorgam). You can get
> up to 1000 processors on a GPU so it could have all manner of
> applications. However, the I/O would slow things down I expect unless
> the CPU and GPU were on the same chip (lets say). Has anybody linked
> GPUs with FPGA I/O?
>
> Hardy

Why even bother with FPGAs ?

GPUs are much cheaper (funded by millions of hard-core gamers who
shell out big bucks to NVidia and AMD) and CUDA is rather well
standardized and adopted programming framework with future path

The only reason to use FPGA might be reducing latency to absolute
minimum. As for data throughput I suspect GPU will beat FPGA hands
down

Of course, if your problem cannot be formulated as SIMD program to run
same computational routine on many pieces of data at the same time
there is no benefit in using massively-parallel GPUs at all

On Jun 18, 7:01&#4294967295;am, Rune Allnor <all...@tele.ntnu.no> wrote:
> On 18 Jun, 03:25, HardySpicer <gyansor...@gmail.com> wrote:
>
> > I heard somewhere that PC GPUs can be used to do say FFTs. They are
> > cheap and very powerful (though not that easy to prorgam).
>
> I have seen people &#4294967295;come up with this 'brilliant' idea
> every couple of years for a couple of decades, already.
> The common factor is that people look exclusively at the
> number of FLOPS / gates / processing units, and forget that
> the GPUs are intensely tuned to highly specialized tasks.
>
> Which means that it easily takes at least as much work to
> re-formulate the generic task at hand to fit the special
> structure of the GPU pipeline (which might not be possible
> at all), as would be required doing the job with a generic
> FPU in the first place.
>
> Rune

You don't have to know anything about GPU architecture to do GPU
computing nowadays

Matlab + Jacket will get you started in no time (if you don't mind
shelling out some bucks)

http://www.accelereyes.com/

The only requirement is that your problem has to be formulated in SIMD
fashion (e.g. doing multidimensional FFT) to see a benefit

>On Jun 18, 7:01=A0am, Rune Allnor <all...@tele.ntnu.no> wrote:
>> On 18 Jun, 03:25, HardySpicer <gyansor...@gmail.com> wrote:
>>
>> > I heard somewhere that PC GPUs can be used to do say FFTs. They are
>> > cheap and very powerful (though not that easy to prorgam).
>>
>> I have seen people =A0come up with this 'brilliant' idea
>> every couple of years for a couple of decades, already.
>> The common factor is that people look exclusively at the
>> number of FLOPS / gates / processing units, and forget that
>> the GPUs are intensely tuned to highly specialized tasks.
>>
>> Which means that it easily takes at least as much work to
>> re-formulate the generic task at hand to fit the special
>> structure of the GPU pipeline (which might not be possible
>> at all), as would be required doing the job with a generic
>> FPU in the first place.
>>
>> Rune
>
>You don't have to know anything about GPU architecture to do GPU
>computing nowadays
>
>Matlab + Jacket will get you started in no time (if you don't mind
>shelling out some bucks)
>
>http://www.accelereyes.com/
>
>The only requirement is that your problem has to be formulated in SIMD
>fashion (e.g. doing multidimensional FFT) to see a benefit

.. and the vectors need to be big. A lot of small FFTs, for example, works
out slower on a GPU than on an i7. A lot of big FFTs can work out several
times as fast on the GPU.

Steve