Re: Reducing RTEMS size to <32KB to fit in Epiphany local memories

2014-12-18 Thread Marcos Díaz
On Thu, Dec 18, 2014 at 6:34 AM, Hesham Moustafa wrote: > > Hi all, > > Thanks for all your helpful replies. I actually tried all the solution > you mentioned: used printk, low-ticker (from example-v2), disabled > newlib reentrancy (part of low-ticker configuration). I managed to get > <32KB ticke

Re: Mutex obtain with timeout

2014-12-18 Thread Peter Dufault
> On Dec 18, 2014, at 11:12 , Gedare Bloom wrote: > > In general, I would suspect any "real-time" application that uses a > mutex with a timeout. I suppose you could construct a valid way to use > them, such as in a low-priority task that could lose the lock, and > thus 'checks' for the conditio

Re: Mutex obtain with timeout

2014-12-18 Thread Joel Sherrill
On 12/18/2014 9:40 AM, Hesham Moustafa wrote: > On Thu, Dec 18, 2014 at 3:38 PM, Joel Sherrill > wrote: >> >> On December 18, 2014 5:18:31 AM PST, Sebastian Huber >> wrote: >>> Hello, >>> >>> I work currently on concepts to implement mutex objects with SMP aware >>> locking protocols. Currentl

Re: Mutex obtain with timeout

2014-12-18 Thread Gedare Bloom
On Thu, Dec 18, 2014 at 8:18 AM, Sebastian Huber wrote: > Hello, > > I work currently on concepts to implement mutex objects with SMP aware > locking protocols. Currently this is MrsP [1] and OMIP [2]. The > implementation should use fine grained locking. It turned out that the > support for tim

Re: Mutex obtain with timeout

2014-12-18 Thread Hesham Moustafa
On Thu, Dec 18, 2014 at 3:38 PM, Joel Sherrill wrote: > > > On December 18, 2014 5:18:31 AM PST, Sebastian Huber > wrote: >>Hello, >> >>I work currently on concepts to implement mutex objects with SMP aware >>locking protocols. Currently this is MrsP [1] and OMIP [2]. The >>implementation shoul

Re: Mutex obtain with timeout

2014-12-18 Thread Joel Sherrill
On December 18, 2014 5:18:31 AM PST, Sebastian Huber wrote: >Hello, > >I work currently on concepts to implement mutex objects with SMP aware >locking protocols. Currently this is MrsP [1] and OMIP [2]. The >implementation should use fine grained locking. It turned out that the > >support f

Mutex obtain with timeout

2014-12-18 Thread Sebastian Huber
Hello, I work currently on concepts to implement mutex objects with SMP aware locking protocols. Currently this is MrsP [1] and OMIP [2]. The implementation should use fine grained locking. It turned out that the support for timeout makes the implementations much more complicated. With tim

Re: Reducing RTEMS size to <32KB to fit in Epiphany local memories

2014-12-18 Thread Sebastian Huber
On 18/12/14 11:22, Hesham Moustafa wrote: PS: > >The unlimited objects feature and the identifier to object translation in >general are also a huge problem for SMP. > Could you provide more details? I may work on this problem alongside some SMP locks implementation part of my research. The _O

Re: Reducing RTEMS size to <32KB to fit in Epiphany local memories

2014-12-18 Thread Hesham Moustafa
On Thu, Dec 18, 2014 at 10:08 AM, Sebastian Huber wrote: > > On 18/12/14 10:34, Hesham Moustafa wrote: >> >> Sebastian, the 32KB is for both code and data. Although there is 32MB >> external memory, it's very slow compared with local memories. The idea >> of getting rid of workspace appeals to me.

Re: Reducing RTEMS size to <32KB to fit in Epiphany local memories

2014-12-18 Thread Sebastian Huber
On 18/12/14 10:34, Hesham Moustafa wrote: Sebastian, the 32KB is for both code and data. Although there is 32MB external memory, it's very slow compared with local memories. The idea of getting rid of workspace appeals to me. Does this include discarding malloc, heap stuff? And how can this be d

Re: Reducing RTEMS size to <32KB to fit in Epiphany local memories

2014-12-18 Thread Hesham Moustafa
Hi all, Thanks for all your helpful replies. I actually tried all the solution you mentioned: used printk, low-ticker (from example-v2), disabled newlib reentrancy (part of low-ticker configuration). I managed to get <32KB ticker with GCC optimization enabled (-Os), but I got some exceptions durin