Add SH4 support:

	* config/sh/lib1funcs.asm (___movstr_i4_even, ___movstr_i4_odd): Define.
	(___movstrSI12_i4, ___sdivsi3_i4, ___udivsi3_i4): Define.
	* sh.c (reg_class_from_letter, regno_reg_class): Add DF_REGS.
	(fp_reg_names, assembler_dialect): New variables.
	(print_operand_address): Handle SUBREGs.
	(print_operand): Added 'o' case.
	Don't use adj_offsettable_operand on PRE_DEC / POST_INC.
	Name of FP registers depends on mode.
	(expand_block_move): Emit different code for SH4 hardware.
	(prepare_scc_operands): Use emit_sf_insn / emit_df_insn as appropriate.
	(from_compare): Likewise.
	(add_constant): New argument last_value.  Changed all callers.
	(find_barrier): Don't try HImode load for FPUL_REG.
	(machine_dependent_reorg): Likewise.
	(sfunc_uses_reg): A CLOBBER cannot be the address register use.
	(gen_far_branch): Emit a barrier after the new jump.
	(barrier_align): Don't trust instruction lengths before
	fixing up pcloads.
	(machine_dependent_reorg): Add support for FIRST_XD_REG .. LAST_XD_REG.
	Use auto-inc addressing for fp registers if doubles need to
	be loaded in two steps.
	Set sh_flag_remove_dead_before_cse.
	(push): Support for TARGET_FMOVD.  Use gen_push_fpul for fpul.
	(pop): Support for TARGET_FMOVD.  Use gen_pop_fpul for fpul.
	(calc_live_regs): Support for TARGET_FMOVD.  Don't save FPSCR.
	Support for FIRST_XD_REG .. LAST_XD_REG.
	(sh_expand_prologue): Support for FIRST_XD_REG .. LAST_XD_REG.
	(sh_expand_epilogue): Likewise.
	(sh_builtin_saveregs): Use DFmode moves for fp regs on SH4.
	(initial_elimination_offset): Take TARGET_ALIGN_DOUBLE into account.
	(arith_reg_operand): FPUL_REG is OK for SH4.
	(fp_arith_reg_operand, fp_extended_operand) New functions.
	(tertiary_reload_operand, fpscr_operand): Likewise.
	(commutative_float_operator, noncommutative_float_operator): Likewise.
	(binary_float_operator, get_fpscr_rtx, emit_sf_insn): Likewise.
	(emit_df_insn, expand_sf_unop, expand_sf_binop): Likewise.
	(expand_df_unop, expand_df_binop, expand_fp_branch): Likewise.
	(emit_fpscr_use, mark_use, remove_dead_before_cse): Likewise.
	* sh.h (CPP_SPEC): Add support for -m4, m4-single, m4-single-only.
	(CONDITIONAL_REGISTER_USAGE): Likewise.
	(HARD_SH4_BIT, FPU_SINGLE_BIT, SH4_BIT, FMOVD_BIT): Define.
	(TARGET_CACHE32, TARGET_SUPERSCALAR, TARGET_HARWARD): Define.
	(TARGET_HARD_SH4, TARGET_FPU_SINGLE, TARGET_SH4, TARGET_FMOVD): Define.
	(target_flag): Add -m4, m4-single, m4-single-only, -mfmovd.
	(OPTIMIZATION_OPTIONS): If optimizing, set flag_omit_frame_pointer
	to -1 and sh_flag_remove_dead_before_cse to 1.
	(ASSEMBLER_DIALECT): Define to assembler_dialect.
	(assembler_dialect, fp_reg_names): Declare.
	(OVERRIDE_OPTIONS): Add code for TARGET_SH4.
	Hide names of registers that are not accessible.
	(CACHE_LOG): Take TARGET_CACHE32 into account.
	(LOOP_ALIGN): Take TARGET_HARWARD into account.
	(FIRST_XD_REG, LAST_XD_REG, FPSCR_REG): Define.
	(FIRST_PSEUDO_REGISTER: Now 49.
	(FIXED_REGISTERS, CALL_USED_REGISTERS): Include values for registers.
	(HARD_REGNO_NREGS): Special treatment of FIRST_XD_REG .. LAST_XD_REG.
	(HARD_REGNO_MODE_OK): Update.
	(enum reg_class): Add DF_REGS and FPSCR_REGS.
	(REG_CLASS_NAMES, REG_CLASS_CONTENTS, REG_ALLOC_ORDER): Likewise.
	(SECONDARY_OUTPUT_RELOAD_CLASS, SECONDARY_INPUT_RELOAD_CLASS): Update.
	(CLASS_CANNOT_CHANGE_SIZE, DEBUG_REGISTER_NAMES): Define.
	(NPARM_REGS): Eight floating point parameter registers on SH4.
	(BASE_RETURN_VALUE_REG): SH4 also passes double values
	in floating point registers.
	(GET_SH_ARG_CLASS) Likewise.
	Complex float types are also returned in float registers.
	(BASE_ARG_REG): Complex float types are also passes in float registers.
	(FUNCTION_VALUE): Change mode like PROMOTE_MODE does.
	(LIBCALL_VALUE): Remove trailing semicolon.
	(ROUND_REG): Round when double precision value is passed in floating
	point register(s).
	(FUNCTION_ARG_ADVANCE): No change wanted for SH4 when things are
	passed on the stack.
	(FUNCTION_ARG): Little endian adjustment for SH4 SFmode.
	(FUNCTION_ARG_PARTIAL_NREGS): Zero for SH4.
	(TRAMPOLINE_ALIGNMENT): Take TARGET_HARWARD into account.
	(INITIALIZE_TRAMPOLINE): Emit ic_invalidate_line for TARGET_HARWARD.
	(MODE_DISP_OK_8): Not for SH4 DFmode.
	(GO_IF_LEGITIMATE_ADDRESS): No base reg + index reg for SH4 DFmode.
	Allow indexed addressing for PSImode after reload.
	(LEGITIMIZE_ADDRESS): Not for SH4 DFmode.
	(LEGITIMIZE_RELOAD_ADDRESS): Handle SH3E SFmode.
	Don't change SH4 DFmode nor PSImode RELOAD_FOR_INPUT_ADDRESS.
	(DOUBLE_TYPE_SIZE): 64 for SH4.
	(RTX_COSTS): Add PLUS case.
	Increae cost of ASHIFT, ASHIFTRT, LSHIFTRT case.
	(REGISTER_MOVE_COST): Add handling of R0_REGS, FPUL_REGS, T_REGS,
	MAC_REGS, PR_REGS, DF_REGS.
	(REGISTER_NAMES): Use fp_reg_names.
	(enum processor_type): Add PROCESSOR_SH4.
	(sh_flag_remove_dead_before_cse): Declare.
	(rtx_equal_function_value_matters, fpscr_rtx, get_fpscr_rtx): Declare.
	(PREDICATE_CODES): Add binary_float_operator,
	commutative_float_operator, fp_arith_reg_operand, fp_extended_operand,
	fpscr_operand, noncommutative_float_operator.
	(ADJUST_COST): Use different scale for TARGET_SUPERSCALAR.
	(SH_DYNAMIC_SHIFT_COST): Cheaper for SH4.
	* sh.md (attribute cpu): Add value sh4.
	(attrbutes fmovd, issues): Define.
	(attribute type): Add values dfp_arith, dfp_cmp, dfp_conv, dfdiv.
	(function units memory, int, mpy, fp): Make dependent on issue rate.
	(function units issue, single_issue, load_si, load): Define.
	(function units load_store, fdiv, gp_fpul): Define.
	(attribute hit_stack): Provide proper default.
	(use_sfunc_addr+1, udivsi3): Predicated on ! TARGET_SH4.
	(udivsi3_i4, udivsi3_i4_single, divsi3_i4, divsi3_i4_single): New insns.
	(udivsi3, divsi3): Emit special patterns for SH4 hardware,
	(mulsi3_call): Now uses match_operand for function address.
	(mulsi3): Also emit code for SH1 case.  Wrap result in REG_LIBCALL /
	REG_RETVAL notes.
	(push, pop, push_e, pop_e): Now define_expands.
	(push_fpul, push_4, pop_fpul, pop_4, ic_invalidate_line): New expanders.
	(movsi_ie): Added y/i alternative.
	(ic_invalidate_line_i, movdf_i4): New insns.
	(movdf_i4+[123], reload_outdf+[12345], movsi_y+[12]): New splitters.
	(reload_indf, reload_outdf, reload_outsf, reload_insi): New expanders.
	(movdf): Add special code for SH4.
	(movsf_ie, movsf_ie+1, reload_insf, calli): Make use of fpscr visible.
	(call_valuei, calli, call_value): Likewise.
	(movsf): Emit no-op move.
	(mov_nop, movsi_y): New insns.
	(blt, sge): generalize to handle DFmode.
	(return predicate): Call emit_fpscr_use and remove_dead_before_cse.
	(block_move_real, block_lump_real): Predicate on ! TARGET_HARD_SH4.
	(block_move_real_i4, block_lump_real_i4, fpu_switch): New insns.
	(fpu_switch0, fpu_switch1, movpsi): New expanders.
	(fpu_switch+[12], fix_truncsfsi2_i4_2+1): New splitters.
	(toggle_sz): New insn.
	(addsf3, subsf3, mulsf3, divsf3): Now define_expands.
	(addsf3_i, subsf3_i, mulsf3_i4, mulsf3_ie, divsf3_i): New insns.
	(macsf3): Make use of fpscr visible.  Disable for SH4.
	(floatsisf2): Make use of fpscr visible.
	(floatsisf2_i4): New insn.
	(floatsisf2_ie, fixsfsi, cmpgtsf_t, cmpeqsf_t): Disable for SH4.
	(ieee_ccmpeqsf_t): Likewise.
	(fix_truncsfsi2): Emit different code for SH4.
	(fix_truncsfsi2_i4, fix_truncsfsi2_i4_2, cmpgtsf_t_i4): New insns.
	(cmpeqsf_t_i4, ieee_ccmpeqsf_t_4): New insns.
	(negsf2, sqrtsf2, abssf2): Now expanders.
	(adddf3, subdf3i, muldf2, divdf3, floatsidf2): New expanders.
	(negsf2_i, sqrtsf2_i, abssf2_i, adddf3_i, subdf3_i): New insns.
	(muldf3_i, divdf3_i, floatsidf2_i, fix_truncdfsi2_i): New insns.
	(fix_truncdfsi2, cmpdf, negdf2, sqrtdf2, absdf2): New expanders.
	(fix_truncdfsi2_i4, cmpgtdf_t, cmpeqdf_t, ieee_ccmpeqdf_t): New insns.
	(fix_truncdfsi2_i4_2+1): New splitters.
	(negdf2_i, sqrtdf2_i, absdf2_i, extendsfdf2_i4): New insns.
	(extendsfdf2, truncdfsf2): New expanders.
	(truncdfsf2_i4): New insn.
	* t-sh (LIB1ASMFUNCS): Add _movstr_i4, _sdivsi3_i4, _udivsi3_i4.
	(MULTILIB_OPTIONS): Add m4-single-only/m4-single/m4.
	* float-sh.h: When testing for __SH3E__, also test for
	__SH4_SINGLE_ONLY__ .
	* va-sh.h (__va_freg): Define to float.
	(__va_greg, __fa_freg, __gnuc_va_list, va_start):
        Define for __SH4_SINGLE_ONLY__ like for __SH3E__ .
        (__PASS_AS_FLOAT, __TARGET_SH4_P): Likewise.
	(__PASS_AS_FLOAT): Use different definition for __SH4__ and
	 __SH4_SINGLE__.
	(TARGET_SH4_P): Define.
	(va_arg): Use it.
	* sh.md (movdf_k, movsf_i): Tweak the condition so that
	init_expr_once is satisfied about the existence of load / store insns.
	* sh.md (movsi_i, movsi_ie, movsi_i_lowpart, movsf_i, movsf_ie):
        change m constraint in source operand to mr / mf .
	* va-sh.h (__va_arg_sh1): Use __asm instead of asm.
	* (__VA_REEF): Define.
	(__va_arg_sh1): Use it.
	* va-sh.h (va_start, va_arg, va_copy): Add parenteses.

From-SVN: r23777

1 files changed, 63 insertions, 36 deletions

diff --git a/gcc/ginclude/va-sh.h b/gcc/ginclude/va-sh.h
index f1671c7..0bfc84c 100644
--- a/gcc/ginclude/va-sh.h
+++ b/gcc/ginclude/va-sh.h
@@ -6,10 +6,10 @@
 #ifndef __GNUC_VA_LIST
 #define __GNUC_VA_LIST
 
-#ifdef __SH3E__
+#if defined (__SH3E__) || defined (__SH4_SINGLE__) || defined (__SH4__) || defined (__SH4_SINGLE_ONLY__)
 
 typedef long __va_greg;
-typedef double __va_freg;
+typedef float __va_freg;
 
 typedef struct {
   __va_greg * __va_next_o;		/* next available register */
@@ -33,24 +33,24 @@ typedef void *__gnuc_va_list;
 
 #ifdef _STDARG_H
 
-#ifdef __SH3E__
+#if defined (__SH3E__) || defined (__SH4_SINGLE__) || defined (__SH4__) || defined (__SH4_SINGLE_ONLY__)
 
 #define va_start(AP, LASTARG) \
 __extension__ \
   ({ \
-     AP.__va_next_fp = (__va_freg *) __builtin_saveregs (); \
-     AP.__va_next_fp_limit = (AP.__va_next_fp + \
+     (AP).__va_next_fp = (__va_freg *) __builtin_saveregs (); \
+     (AP).__va_next_fp_limit = ((AP).__va_next_fp + \
 			      (__builtin_args_info (1) < 8 ? 8 - __builtin_args_info (1) : 0)); \
-     AP.__va_next_o = (__va_greg *) AP.__va_next_fp_limit; \
-     AP.__va_next_o_limit = (AP.__va_next_o + \
+     (AP).__va_next_o = (__va_greg *) (AP).__va_next_fp_limit; \
+     (AP).__va_next_o_limit = ((AP).__va_next_o + \
 			     (__builtin_args_info (0) < 4 ? 4 - __builtin_args_info (0) : 0)); \
-     AP.__va_next_stack = (__va_greg *) __builtin_next_arg (LASTARG); \
+     (AP).__va_next_stack = (__va_greg *) __builtin_next_arg (LASTARG); \
   })
 
 #else /* ! SH3E */
 
 #define va_start(AP, LASTARG) 						\
- (AP = ((__gnuc_va_list) __builtin_next_arg (LASTARG)))
+ ((AP) = ((__gnuc_va_list) __builtin_next_arg (LASTARG)))
 
 #endif /* ! SH3E */
 
@@ -59,24 +59,26 @@ __extension__ \
 #define va_alist  __builtin_va_alist
 #define va_dcl    int __builtin_va_alist;...
 
-#ifdef __SH3E__
+#if defined (__SH3E__) || defined (__SH4_SINGLE__) || defined (__SH4__) || defined (__SH4_SINGLE_ONLY__)
 
 #define va_start(AP) \
 __extension__ \
   ({ \
-     AP.__va_next_fp = (__va_freg *) __builtin_saveregs (); \
-     AP.__va_next_fp_limit = (AP.__va_next_fp + \
+     (AP).__va_next_fp = (__va_freg *) __builtin_saveregs (); \
+     (AP).__va_next_fp_limit = ((AP).__va_next_fp + \
 			      (__builtin_args_info (1) < 8 ? 8 - __builtin_args_info (1) : 0)); \
-     AP.__va_next_o = (__va_greg *) AP.__va_next_fp_limit; \
-     AP.__va_next_o_limit = (AP.__va_next_o + \
+     (AP).__va_next_o = (__va_greg *) (AP).__va_next_fp_limit; \
+     (AP).__va_next_o_limit = ((AP).__va_next_o + \
 			     (__builtin_args_info (0) < 4 ? 4 - __builtin_args_info (0) : 0)); \
-     AP.__va_next_stack = (__va_greg *) __builtin_next_arg (__builtin_va_alist) \
-       - (__builtin_args_info (0) >= 4 || __builtin_args_info (1) >= 8 ? 1 : 0); \
+     (AP).__va_next_stack \
+       = ((__va_greg *) __builtin_next_arg (__builtin_va_alist) \
+	  - (__builtin_args_info (0) >= 4 || __builtin_args_info (1) >= 8 \
+	     ? 1 : 0)); \
   })
 
 #else /* ! SH3E */
 
-#define va_start(AP)  AP=(char *) &__builtin_va_alist
+#define va_start(AP)  ((AP) = (char *) &__builtin_va_alist)
 
 #endif /* ! SH3E */
 
@@ -136,53 +138,78 @@ enum __va_type_classes {
      We want the MEM_IN_STRUCT_P bit set in the emitted RTL, therefore we
      use unions even when it would otherwise be unnecessary.  */
 
+/* gcc has an extension that allows to use a casted lvalue as an lvalue,
+   But it doesn't work in C++ with -pedantic - even in the presence of
+   __extension__ .  We work around this problem by using a reference type.  */
+#ifdef __cplusplus
+#define __VA_REF &
+#else
+#define __VA_REF
+#endif
+
 #define __va_arg_sh1(AP, TYPE) __extension__ 				\
-__extension__								\
 ({(sizeof (TYPE) == 1							\
    ? ({union {TYPE t; char c;} __t;					\
-       asm(""								\
-	   : "=r" (__t.c)						\
-	   : "0" ((((union { int i, j; } *) (AP))++)->i));		\
+       __asm(""								\
+	     : "=r" (__t.c)						\
+	     : "0" ((((union { int i, j; } *__VA_REF) (AP))++)->i));	\
        __t.t;})								\
    : sizeof (TYPE) == 2							\
    ? ({union {TYPE t; short s;} __t;					\
-       asm(""								\
-	   : "=r" (__t.s)						\
-	   : "0" ((((union { int i, j; } *) (AP))++)->i));		\
+       __asm(""								\
+	     : "=r" (__t.s)						\
+	     : "0" ((((union { int i, j; } *__VA_REF) (AP))++)->i));	\
        __t.t;})								\
    : sizeof (TYPE) >= 4 || __LITTLE_ENDIAN_P				\
-   ? (((union { TYPE t; int i;} *) (AP))++)->t				\
-   : ((union {TYPE t;TYPE u;}*) ((char *)++(int *)(AP) - sizeof (TYPE)))->t);})
+   ? (((union { TYPE t; int i;} *__VA_REF) (AP))++)->t			\
+   : ((union {TYPE t;TYPE u;}*) ((char *)++(int *__VA_REF)(AP) - sizeof (TYPE)))->t);})
 
-#ifdef __SH3E__
+#if defined (__SH3E__) || defined (__SH4_SINGLE__) || defined (__SH4__) || defined (__SH4_SINGLE_ONLY__)
 
 #define __PASS_AS_FLOAT(TYPE_CLASS,SIZE) \
   (TYPE_CLASS == __real_type_class && SIZE == 4)
 
+#define __TARGET_SH4_P 0
+
+#if defined(__SH4__) || defined(__SH4_SINGLE__)
+#undef __PASS_AS_FLOAT
+#define __PASS_AS_FLOAT(TYPE_CLASS,SIZE) \
+  (TYPE_CLASS == __real_type_class && SIZE <= 8 \
+   || TYPE_CLASS == __complex_type_class && SIZE <= 16)
+#undef __TARGET_SH4_P
+#define __TARGET_SH4_P 1
+#endif
+
 #define va_arg(pvar,TYPE)					\
 __extension__							\
 ({int __type = __builtin_classify_type (* (TYPE *) 0);		\
   void * __result_p;						\
   if (__PASS_AS_FLOAT (__type, sizeof(TYPE)))			\
     {								\
-      if (pvar.__va_next_fp < pvar.__va_next_fp_limit)		\
+      if ((pvar).__va_next_fp < (pvar).__va_next_fp_limit)	\
 	{							\
-	  __result_p = &pvar.__va_next_fp;			\
+	  if (((__type == __real_type_class && sizeof (TYPE) > 4)\
+	       || sizeof (TYPE) > 8)				\
+	      && (((int) (pvar).__va_next_fp ^ (int) (pvar).__va_next_fp_limit)\
+		  & 4))						\
+	    (pvar).__va_next_fp++;				\
+	  __result_p = &(pvar).__va_next_fp;			\
 	}							\
       else							\
-	__result_p = &pvar.__va_next_stack;			\
+	__result_p = &(pvar).__va_next_stack;			\
     }								\
   else								\
     {								\
-      if (pvar.__va_next_o + ((sizeof (TYPE) + 3) / 4)		\
-	  <= pvar.__va_next_o_limit) 				\
-	__result_p = &pvar.__va_next_o;				\
+      if ((pvar).__va_next_o + ((sizeof (TYPE) + 3) / 4)	\
+	  <= (pvar).__va_next_o_limit) 				\
+	__result_p = &(pvar).__va_next_o;			\
       else							\
 	{							\
 	  if (sizeof (TYPE) > 4)				\
-	    pvar.__va_next_o = pvar.__va_next_o_limit;		\
+	   if (! __TARGET_SH4_P)				\
+	    (pvar).__va_next_o = (pvar).__va_next_o_limit;	\
 								\
-	  __result_p = &pvar.__va_next_stack;			\
+	  __result_p = &(pvar).__va_next_stack;			\
 	}							\
     } 								\
   __va_arg_sh1(*(void **)__result_p, TYPE);})
@@ -194,6 +221,6 @@ __extension__							\
 #endif /* SH3E */
 
 /* Copy __gnuc_va_list into another variable of this type.  */
-#define __va_copy(dest, src) (dest) = (src)
+#define __va_copy(dest, src) ((dest) = (src))
 
 #endif /* defined (_STDARG_H) || defined (_VARARGS_H) */