[SH, committed] PR 56529 - Calls to __sdivsi3_i4i and __udivsi3_i4i are generated on SH2

[Oleg Endo <oleg dot endo at t-online dot de>]

Hi,

This is the patch that I posted in the PR and that was pre-approved by
Kaz, with some documentation bits added.

Tested with 'make info dvi pdf' and 'make all'.
Applied as revision 196484.
Will backport it to 4.7 branch.

Cheers,
Oleg

gcc/ChangeLog:

	PR target/56529
	* config/sh/sh.c (sh_option_override): Check for TARGET_DYNSHIFT
	instead of TARGET_SH2 for call-table case.  Do not set 
	sh_div_strategy to SH_DIV_CALL_TABLE for TARGET_SH2.
	* config.gcc (sh_multilibs): Add m2 and m2a to sh*-*-linux* 
	multilib list.
	* doc/invoke.texi (SH options):	Document mdiv= call-div1, 
	call-fp, call-table options.

libgcc/ChangeLog:

	PR target/56529
	* config/sh/lib1funcs.S (udivsi3_i4i, sdivsi3_i4i): Add __SH2A__
	to inclusion list.

Index: gcc/config/sh/sh.c
===================================================================
--- gcc/config/sh/sh.c	(revision 196483)
+++ gcc/config/sh/sh.c	(working copy)
@@ -820,7 +820,7 @@
 		   || (TARGET_HARD_SH4 && TARGET_SH2E)
 		   || (TARGET_SHCOMPACT && TARGET_FPU_ANY)))
 	sh_div_strategy = SH_DIV_CALL_FP;
-      else if (! strcmp (sh_div_str, "call-table") && TARGET_SH2)
+      else if (! strcmp (sh_div_str, "call-table") && TARGET_DYNSHIFT)
 	sh_div_strategy = SH_DIV_CALL_TABLE;
       else
 	/* Pick one that makes most sense for the target in general.
@@ -840,8 +840,6 @@
 	  sh_div_strategy = SH_DIV_CALL_FP;
 	/* SH1 .. SH3 cores often go into small-footprint systems, so
 	   default to the smallest implementation available.  */
-	else if (TARGET_SH2)	/* ??? EXPERIMENTAL */
-	  sh_div_strategy = SH_DIV_CALL_TABLE;
 	else
 	  sh_div_strategy = SH_DIV_CALL_DIV1;
     }
Index: gcc/config.gcc
===================================================================
--- gcc/config.gcc	(revision 196483)
+++ gcc/config.gcc	(working copy)
@@ -2371,7 +2371,7 @@
 		sh[1234]*)	sh_multilibs=${sh_cpu_target} ;;
 		sh64* | sh5*)	sh_multilibs=m5-32media,m5-32media-nofpu,m5-compact,m5-compact-nofpu,m5-64media,m5-64media-nofpu ;;
 		sh-superh-*)	sh_multilibs=m4,m4-single,m4-single-only,m4-nofpu ;;
-		sh*-*-linux*)	sh_multilibs=m1,m3e,m4 ;;
+		sh*-*-linux*)	sh_multilibs=m1,m2,m2a,m3e,m4 ;;
 		sh*-*-netbsd*)	sh_multilibs=m3,m3e,m4 ;;
 		*) sh_multilibs=m1,m2,m2e,m4,m4-single,m4-single-only,m2a,m2a-single ;;
 		esac
Index: gcc/doc/invoke.texi
===================================================================
--- gcc/doc/invoke.texi	(revision 196483)
+++ gcc/doc/invoke.texi	(working copy)
@@ -18749,8 +18749,8 @@
 
 @item -mdiv=@var{strategy}
 @opindex mdiv=@var{strategy}
-Set the division strategy to use for SHmedia code.  @var{strategy} must be
-one of: 
+Set the division strategy to be used for integer division operations.
+For SHmedia @var{strategy} can be one of: 
 
 @table @samp
 
@@ -18808,6 +18808,36 @@
 
 @end table
 
+For targets other than SHmedia @var{strategy} can be one of:
+
+@table @samp
+
+@item call-div1
+Calls a library function that uses the single-step division instruction
+@code{div1} to perform the operation.  Division by zero calculates an
+unspecified result and does not trap.  This is the default except for SH4,
+SH2A and SHcompact.
+
+@item call-fp
+Calls a library function that performs the operation in double precision
+floating point.  Division by zero causes a floating-point exception.  This is
+the default for SHcompact with FPU.  Specifying this for targets that do not
+have a double precision FPU will default to @code{call-div1}.
+
+@item call-table
+Calls a library function that uses a lookup table for small divisors and
+the @code{div1} instruction with case distinction for larger divisors.  Division
+by zero calculates an unspecified result and does not trap.  This is the default
+for SH4.  Specifying this for targets that do not have dynamic shift
+instructions will default to @code{call-div1}.
+
+@end table
+
+When a division strategy has not been specified the default strategy will be
+selected based on the current target.  For SH2A the default strategy is to
+use the @code{divs} and @code{divu} instructions instead of library function
+calls.
+
 @item -maccumulate-outgoing-args
 @opindex maccumulate-outgoing-args
 Reserve space once for outgoing arguments in the function prologue rather
Index: libgcc/config/sh/lib1funcs.S
===================================================================
--- libgcc/config/sh/lib1funcs.S	(revision 196483)
+++ libgcc/config/sh/lib1funcs.S	(working copy)
@@ -3288,8 +3288,8 @@
 	.word	17136
 	.word	16639
 
-#elif defined (__SH3__) || defined (__SH3E__) || defined (__SH4__) || defined (__SH4_SINGLE__) || defined (__SH4_SINGLE_ONLY__) || defined (__SH4_NOFPU__)
-/* This code used shld, thus is not suitable for SH1 / SH2.  */
+#elif defined (__SH2A__) || defined (__SH3__) || defined (__SH3E__) || defined (__SH4__) || defined (__SH4_SINGLE__) || defined (__SH4_SINGLE_ONLY__) || defined (__SH4_NOFPU__)
+/* This code uses shld, thus is not suitable for SH1 / SH2.  */
 
 /* Signed / unsigned division without use of FPU, optimized for SH4.
    Uses a lookup table for divisors in the range -128 .. +128, and