Re: [fedora-arm] On ARM atomics

2012-11-14 Thread Leif Lindholm
Hi Jon, The description of the ARM barrier operations is not entirely accurate. The DMB does not guarantee completion of anything - it only enforces ordering. I.e. --- ldr access to clear an interrupt source DMB CPSIE i --- does not guarantee that the interrupt line is not still live when the

Re: [fedora-arm] On ARM atomics

2012-11-13 Thread Jon Masters
On 11/13/2012 01:24 AM, Nicolas Pitre wrote: There are several serious mistakes in your assembly example. Thanks for the feedback! Appreciated. Comments below... |START_FUNC(opal_atomic_add_32) | push{r4-r7} Why r4 to r7? You're using only r4 below. Ah. Because in the rest of

Re: [fedora-arm] On ARM atomics

2012-11-13 Thread Michael Hope
On 14 November 2012 06:21, Jon Masters j...@redhat.com wrote: On 11/13/2012 01:24 AM, Nicolas Pitre wrote: There are several serious mistakes in your assembly example. Thanks for the feedback! Appreciated. Comments below... |START_FUNC(opal_atomic_add_32) | push{r4-r7} Why r4

[fedora-arm] On ARM atomics

2012-11-12 Thread Jon Masters
Hi everyone, I wrote the following little summary of ARM atomics: http://www.jonmasters.org/blog/2012/11/13/arm-atomic-operations/ It's not terribly comprehensive, but you could use it to understand what I did in OpenMPI, and how to poke at other packages. Jon.