[m-rev.] for review: workaround problems with mercury_atomic_ops and gcc -O0

[Peter Wang]

On 2007-10-24, Julien Fischer <juliensf at csse.unimelb.edu.au> wrote:
> 
>  For review by PeterW.
> 
>  Estimated hours taken: 0.2
>  Branches: main
> 
>  Avoid problems with some versions of gcc when compiling the runtime
>  atomic_ops module at -O0 in non low-level .par grades.
> 
>  runtime/mercury_atomic_ops.[hc]:
>  	Implement MR_compare_and_swap_word using the builtin gcc compare
>  	and swap if it is available.  (In particular prefer this to the
>  	handcoded assembler versions on x86 and x86_64.)
> 
>  	Only include the code in these modules if MR_LL_PARALLEL_CONJ
>  	is defined.  This helps to avoid problems with gcc in grades
>  	where atomic operations are not used.
> 
>  Julien.
> 
>  Index: mercury_atomic_ops.c
>  ===================================================================
>  RCS file: 
>  /home/mercury/mercury1/repository/mercury/runtime/mercury_atomic_ops.c,v
>  retrieving revision 1.1
>  diff -u -r1.1 mercury_atomic_ops.c
>  --- mercury_atomic_ops.c	11 Oct 2007 12:18:03 -0000	1.1
>  +++ mercury_atomic_ops.c	24 Oct 2007 04:55:44 -0000
>  @@ -14,6 +14,8 @@
>   #include "mercury_imp.h"
>   #include "mercury_atomic_ops.h"
> 
>  +#if defined(MR_LL_PARALLEL_CON)

MR_LL_PARALLEL_CONJ

>  /*---------------------------------------------------------------------------*/
>   /*
>   ** Provide definitions for functions declared `extern inline'.
>  @@ -28,3 +30,5 @@
>   	MR_COMPARE_AND_SWAP_WORD_BODY;
>       }
>   )
>  +
>  +#endif /* MR_LL_PARALLEL_CONJ */
>  Index: mercury_atomic_ops.h
>  ===================================================================
>  RCS file: 
>  /home/mercury/mercury1/repository/mercury/runtime/mercury_atomic_ops.h,v
>  retrieving revision 1.1
>  diff -u -r1.1 mercury_atomic_ops.h
>  --- mercury_atomic_ops.h	11 Oct 2007 12:18:03 -0000	1.1
>  +++ mercury_atomic_ops.h	24 Oct 2007 04:54:58 -0000
>  @@ -16,6 +16,8 @@
> 
>   #include "mercury_std.h"
> 
>  +#if defined(MR_LL_PARALLEL_CON)

MR_LL_PARALLEL_CONJ

>  @@ -82,4 +85,5 @@
>   ** currently require any atomic ops.
>   */
> 
>  +#endif /* MR_LL_PARALLEL_CONJ */
>   #endif /* not MERCURY_ATOMIC_OPS_H */

What's the convention on #endif comments?

Otherwise it looks fine.

Peter

--------------------------------------------------------------------------
mercury-reviews mailing list
Post messages to:       mercury-reviews at csse.unimelb.edu.au
Administrative Queries: owner-mercury-reviews at csse.unimelb.edu.au
Subscriptions:          mercury-reviews-request at csse.unimelb.edu.au
--------------------------------------------------------------------------