Re: [partial-reconfig] FPGAs Demystifying

[John Williams <jwilliams@xxxxxxxxxxxxxx>]

Dear Guillaume,

I've spoken to you privately (and politely) about this, and you ignored 
that.  So, apologies, but this one is going public.

This is enough.  You have been spamming every newsgroup, every mailing 
list, me, people at Xilinx and elsewhere, with your stuff.

I'm pleased that you have an interest in FPGAs, and open flight linux, 
and whatever else.  The world is big enough for all of these different 
projects.

My suggestion is that you stop spamming, and actually do some work, get 
some code and designs up on your page, then if it's any good, people 
will use it.

You know, I agree with your main complaint that a closed bitstream 
format inhibits innovation.  However, it is behaviour such as yours 
which discourages companies like Xilinx from engaging more openly with 
the community.

Please don't email me, or the lists I administer, any more, unless you 
have something positive and concrete to contribute.

John


Guillaume FORTAINE wrote:
> Misters,
>
> I will be rude with you, but this is definitely truth : there no FPGA 
> expert on the place , even worse for partial reconfiguration. So, please 
> be nice, do your homeworks and let's go the basics : to hack the 
> bitstream format, then develop a Linux Device Driver for Reconfigurable 
> Computing , instead of smoky publications => "OS for dynamically 
> reconfigurable hardware" , "intrinsic evolution" : all this stuff are 
> definitely buzzwords.
>
>
> *Let's do the real people, do real code*
>
>
> *To quote * :
>
> http://groups.google.com/group/comp.arch.fpga/browse_thread/thread/fda609f68c199c55/2c33ce4ced68b3bc?lnk=st&q=What+would+you+say%2C+if+a+CPU+manufacturer+doesn%27t+make+available%0D%0Athe+processor+documentation+(instruction+set%2C+instruction+encoding).%0D%0AHe+only+gives+you+a+C+compiler+to+design+your+software+and%0D%0Aanything+below+is+the+secret+of+the+company.+Nobody+would+buy+such%0D%0Aa+processor%2C+but+that%27s+exactly+the+situation+with+FPGA%27s.+&rnum=1#2c33ce4ced68b3bc 
>
>
> What would you say, if a CPU manufacturer doesn't make available
> the processor documentation (instruction set, instruction encoding).
> He only gives you a C compiler to design your software and
> anything below is the secret of the company. Nobody would buy such
> a processor, but that's exactly the situation with FPGA's.
>
>
>
>
>
>
> http://xwt.org/research/megacz-fccm07.pdf
>
>
> In the world of FPGAs, the situation is quite dif-
> ferent. Since the discontinuation of the XC6200 series
> in 1998[17], the trend has been overwhelmingly in the
> direction of bitstream secrecy. Currently no major vendor
> discloses the bitstream format of their device. This has
> had the effect of stunting research in several areas, in-
> cluding partial reconfiguration, evolvable hardware, and
> fault recovery. Additionally, alternative design method-
> ologies such as self-timed circuitry or pausible clocks[18]
> become difficult to implement properly if the manufac-
> turer’s tools do not support them
>
>
>
>
>
>
> So here is my starting point : A common philosophy ( OpenFlightLinux ), 
> An Open Source hardware kit ( Elphel ) and a Linux Kernel Driver for 
> Reconfigurable Hardware ( KAD )
>
>
> http://openflightlinux.org/helpforum/index.php?topic=65.0
>
>
>
> I look forward to your answer,
>
> Best Regards,
>
> Guillaume

___________________________
partial-reconfig mailing list
partial-reconfig@xxxxxxxxxxxxxx
Mailing List Archive : http://www.itee.uq.edu.au/~listarch/partial-reconfig/