Re: [rfc] Fix SPU build (Re: [PATCH] Remove basic_block->loop_depth)

[Richard Guenther <rguenther at suse dot de>]

On Wed, 15 Aug 2012, Ulrich Weigand wrote:

> Richard Guenther wrote:
> > On Tue, 14 Aug 2012, Ulrich Weigand wrote:
> > > Looks like this broke SPU build, since spu_machine_dependent_reorg
> > > accesses ->loop_depth.  According to comments in the code, this
> > > was done because of concerns that loop_father may no longer be set up
> > > this late in compilation, so I'm wondering whether just replacing
> > > this by loop_depth (bb->loop_father) would work here ...
> 
> > If SPU md reorg would like to look at loop structures it should
> > compute them.  Simply call flow_loops_find, which hopefully works
> > in CFG RTL mode (which I think is the mode available from md reorg?).
> 
> It seems flow_loops_find by itself is not quite enough, but everything
> necessary to use the loop structures seems to be encapsulated in
> loop_optimizer_init / loop_optimizer_finalize, which are already called
> by a number of optimization passes.  When I do the same in the SPU
> md-reorg pass, loop_father seems to be set up OK.
> 
> Does this look reasonable?

Yes.  You can use bb_loop_depth instead of loop_depth (bb->loop_father).

Richard.

> Thanks,
> Ulrich
> 
> 
> ChangeLog:
> 
> 	* config/spu/spu.c: Include "cfgloop.h".
> 	(spu_machine_dependent_reorg): Call loop_optimizer_init and
> 	loop_optimizer_finalize.  Use loop_father instead of loop_depth.
> 	* config/spu/t-spu-elf (spu.o): Update dependencies.
> 
> Index: gcc/config/spu/spu.c
> ===================================================================
> *** gcc/config/spu/spu.c	(revision 190390)
> --- gcc/config/spu/spu.c	(working copy)
> ***************
> *** 53,58 ****
> --- 53,59 ----
>   #include "timevar.h"
>   #include "df.h"
>   #include "dumpfile.h"
> + #include "cfgloop.h"
>   
>   /* Builtin types, data and prototypes. */
>   
> *************** spu_machine_dependent_reorg (void)
> *** 2458,2463 ****
> --- 2459,2468 ----
>     in_spu_reorg = 1;
>     compute_bb_for_insn ();
>   
> +   /* (Re-)discover loops so that bb->loop_father can be used
> +      in the analysis below.  */
> +   loop_optimizer_init (AVOID_CFG_MODIFICATIONS);
> + 
>     compact_blocks ();
>   
>     spu_bb_info =
> *************** spu_machine_dependent_reorg (void)
> *** 2562,2575 ****
>   	     fallthru block. This catches the cases when it is a simple
>   	     loop or when there is an initial branch into the loop. */
>   	  if (prev && (loop_exit || simple_loop)
> ! 	      && prev->loop_depth <= bb->loop_depth)
>   	    prop = prev;
>   
>   	  /* If there is only one adjacent predecessor.  Don't propagate
> ! 	     outside this loop.  This loop_depth test isn't perfect, but
> ! 	     I'm not sure the loop_father member is valid at this point.  */
>   	  else if (prev && single_pred_p (bb)
> ! 		   && prev->loop_depth == bb->loop_depth)
>   	    prop = prev;
>   
>   	  /* If this is the JOIN block of a simple IF-THEN then
> --- 2567,2580 ----
>   	     fallthru block. This catches the cases when it is a simple
>   	     loop or when there is an initial branch into the loop. */
>   	  if (prev && (loop_exit || simple_loop)
> ! 	      && (loop_depth (prev->loop_father)
> ! 		  <= loop_depth (bb->loop_father)))
>   	    prop = prev;
>   
>   	  /* If there is only one adjacent predecessor.  Don't propagate
> ! 	     outside this loop.  */
>   	  else if (prev && single_pred_p (bb)
> ! 		   && prev->loop_father == bb->loop_father)
>   	    prop = prev;
>   
>   	  /* If this is the JOIN block of a simple IF-THEN then
> *************** spu_machine_dependent_reorg (void)
> *** 2578,2584 ****
>   		   && EDGE_COUNT (bb->preds) == 2
>   		   && EDGE_COUNT (prev->preds) == 1
>   		   && EDGE_PRED (prev, 0)->src == prev2
> ! 		   && prev2->loop_depth == bb->loop_depth
>   		   && GET_CODE (branch_target) != REG)
>   	    prop = prev;
>   
> --- 2583,2589 ----
>   		   && EDGE_COUNT (bb->preds) == 2
>   		   && EDGE_COUNT (prev->preds) == 1
>   		   && EDGE_PRED (prev, 0)->src == prev2
> ! 		   && prev2->loop_father == bb->loop_father
>   		   && GET_CODE (branch_target) != REG)
>   	    prop = prev;
>   
> *************** spu_machine_dependent_reorg (void)
> *** 2600,2606 ****
>   	      if (dump_file)
>   		fprintf (dump_file, "propagate from %i to %i (loop depth %i) "
>   			 "for %i (loop_exit %i simple_loop %i dist %i)\n",
> ! 			 bb->index, prop->index, bb->loop_depth,
>   			 INSN_UID (branch), loop_exit, simple_loop,
>   			 branch_addr - INSN_ADDRESSES (INSN_UID (bbend)));
>   
> --- 2605,2611 ----
>   	      if (dump_file)
>   		fprintf (dump_file, "propagate from %i to %i (loop depth %i) "
>   			 "for %i (loop_exit %i simple_loop %i dist %i)\n",
> ! 			 bb->index, prop->index, loop_depth (bb->loop_father),
>   			 INSN_UID (branch), loop_exit, simple_loop,
>   			 branch_addr - INSN_ADDRESSES (INSN_UID (bbend)));
>   
> *************** spu_machine_dependent_reorg (void)
> *** 2657,2662 ****
> --- 2662,2669 ----
>   
>     spu_var_tracking ();
>   
> +   loop_optimizer_finalize ();
> + 
>     free_bb_for_insn ();
>   
>     in_spu_reorg = 0;
> Index: gcc/config/spu/t-spu-elf
> ===================================================================
> *** gcc/config/spu/t-spu-elf	(revision 190390)
> --- gcc/config/spu/t-spu-elf	(working copy)
> *************** spu.o: $(CONFIG_H) $(SYSTEM_H) coretypes
> *** 23,29 ****
>     real.h insn-config.h conditions.h insn-attr.h flags.h $(RECOG_H) \
>     $(OBSTACK_H) $(TREE_H) $(EXPR_H) $(OPTABS_H) except.h function.h \
>     output.h $(BASIC_BLOCK_H) $(GGC_H) $(HASHTAB_H) \
> !   $(TM_P_H) $(TARGET_H) $(TARGET_DEF_H) langhooks.h reload.h \
>     $(srcdir)/config/spu/spu-protos.h \
>     $(srcdir)/config/spu/spu-builtins.def 
>   
> --- 23,29 ----
>     real.h insn-config.h conditions.h insn-attr.h flags.h $(RECOG_H) \
>     $(OBSTACK_H) $(TREE_H) $(EXPR_H) $(OPTABS_H) except.h function.h \
>     output.h $(BASIC_BLOCK_H) $(GGC_H) $(HASHTAB_H) \
> !   $(TM_P_H) $(TARGET_H) $(TARGET_DEF_H) langhooks.h reload.h $(CFGLOOP_H) \
>     $(srcdir)/config/spu/spu-protos.h \
>     $(srcdir)/config/spu/spu-builtins.def