i386.c (classify_argument): Treat V1xx modes the same as their base modes.

* config/i386/i386.c (classify_argument): Treat V1xx modes the same as
        their base modes. CTImode, TCmode, and XCmode must be passed in memory.
        TFmode (__float128) must be is an SSE/SSEUP pair. V2SImode, V4HImode,
        and V8QI are class SSE. All sufficiently small remaining vector modes
        must be passed in one or two integer registers.
        (ix86_libcall_value): TFmode must be returned in xmm0, XCmode must be
        returned in memory.
        (bdesc_2arg, ix86_init_mmx_sse_builtins): __builtin_ia32_pmuludq and
        __builtin_ia32_pmuludq128 have non-uniform argument and return types
        and must thus be handled explicitly.
        * config/i386/i386.md (*movdi_1_rex64): Add cases for moving between
        MMX and XMM regs.
        (movv8qi_internal, movv4hi_internal, movv2si_internal,
        movv2sf_internal): Permit moving between MMX and XMM registers (since
        MMX areguments and return values are passed in XMM registers).
        (sse2_umulsidi3): Correct type and mode.

From-SVN: r84410

gcc/ChangeLog

@@ -1,3 +1,22 @@
+2004-04-09  Jan Beulich  <jbeulich@novell.com>
+
+	* config/i386/i386.c (classify_argument): Treat V1xx modes the same as
+	their base modes. CTImode, TCmode, and XCmode must be passed in memory.
+	TFmode (__float128) must be is an SSE/SSEUP pair. V2SImode, V4HImode,
+	and V8QI are class SSE. All sufficiently small remaining vector modes
+	must be passed in one or two integer registers.
+	(ix86_libcall_value): TFmode must be returned in xmm0, XCmode must be
+	returned in memory.
+	(bdesc_2arg, ix86_init_mmx_sse_builtins): __builtin_ia32_pmuludq and
+	__builtin_ia32_pmuludq128 have non-uniform argument and return types
+	and must thus be handled explicitly.
+	* config/i386/i386.md (*movdi_1_rex64): Add cases for moving between
+	MMX and XMM regs.
+	(movv8qi_internal, movv4hi_internal, movv2si_internal,
+	movv2sf_internal): Permit moving between MMX and XMM registers (since
+	MMX areguments and return values are passed in XMM registers).
+	(sse2_umulsidi3): Correct type and mode.
+
 2004-04-09  Richard Henderson  <rth@redhat.com>
 
 	* tree-cfg.c (dump_cfg_stats): Fix 64-bit format mismatch errors.

gcc/config/i386/i386.c

@@ -2265,6 +2265,11 @@ classify_argument (enum machine_mode mode, tree type,
 	return 0;
     }
 
+  /* for V1xx modes, just use the base mode */
+  if (VECTOR_MODE_P (mode)
+      && GET_MODE_SIZE (GET_MODE_INNER (mode)) == bytes)
+    mode = GET_MODE_INNER (mode);
+
   /* Classification of atomic types.  */
   switch (mode)
     {
@@ -2285,9 +2290,7 @@ classify_argument (enum machine_mode mode, tree type,
       classes[0] = classes[1] = X86_64_INTEGER_CLASS;
       return 2;
     case CTImode:
-      classes[0] = classes[1] = X86_64_INTEGER_CLASS;
+      return 0;
-      classes[2] = classes[3] = X86_64_INTEGER_CLASS;
-      return 4;
     case SFmode:
       if (!(bit_offset % 64))
 	classes[0] = X86_64_SSESF_CLASS;
@@ -2302,21 +2305,20 @@ classify_argument (enum machine_mode mode, tree type,
       classes[1] = X86_64_X87UP_CLASS;
       return 2;
     case TFmode:
-    case TCmode:
+      classes[0] = X86_64_SSE_CLASS;
-      return 0;
+      classes[1] = X86_64_SSEUP_CLASS;
-    case XCmode:
-      classes[0] = X86_64_X87_CLASS;
-      classes[1] = X86_64_X87UP_CLASS;
-      classes[2] = X86_64_X87_CLASS;
-      classes[3] = X86_64_X87UP_CLASS;
-      return 4;
-    case DCmode:
-      classes[0] = X86_64_SSEDF_CLASS;
-      classes[1] = X86_64_SSEDF_CLASS;
       return 2;
     case SCmode:
       classes[0] = X86_64_SSE_CLASS;
       return 1;
+    case DCmode:
+      classes[0] = X86_64_SSEDF_CLASS;
+      classes[1] = X86_64_SSEDF_CLASS;
+      return 2;
+    case XCmode:
+    case TCmode:
+      /* These modes are larger than 16 bytes.  */
+      return 0;
     case V4SFmode:
     case V4SImode:
     case V16QImode:
@@ -2330,11 +2332,26 @@ classify_argument (enum machine_mode mode, tree type,
     case V2SImode:
     case V4HImode:
     case V8QImode:
-      return 0;
+      classes[0] = X86_64_SSE_CLASS;
+      return 1;
     case BLKmode:
     case VOIDmode:
       return 0;
     default:
+      if (VECTOR_MODE_P (mode))
+	{
+	  if (bytes > 16)
+	    return 0;
+	  if (GET_MODE_CLASS (GET_MODE_INNER (mode)) == MODE_INT)
+	    {
+	      if (bit_offset + GET_MODE_BITSIZE (mode) <= 32)
+		classes[0] = X86_64_INTEGERSI_CLASS;
+	      else
+		classes[0] = X86_64_INTEGER_CLASS;
+	      classes[1] = X86_64_INTEGER_CLASS;
+	      return 1 + (bytes > 8);
+	    }
+	}
       abort ();
     }
 }
@@ -2963,11 +2980,11 @@ ix86_libcall_value (enum machine_mode mode)
 	case SCmode:
 	case DFmode:
 	case DCmode:
+	case TFmode:
 	  return gen_rtx_REG (mode, FIRST_SSE_REG);
 	case XFmode:
-	case XCmode:
 	  return gen_rtx_REG (mode, FIRST_FLOAT_REG);
-	case TFmode:
+	case XCmode:
 	case TCmode:
 	  return NULL;
 	default:
@@ -12856,8 +12873,6 @@ static const struct builtin_description bdesc_2arg[] =
 
   { MASK_SSE2, CODE_FOR_mulv8hi3, "__builtin_ia32_pmullw128", IX86_BUILTIN_PMULLW128, 0, 0 },
   { MASK_SSE2, CODE_FOR_smulv8hi3_highpart, "__builtin_ia32_pmulhw128", IX86_BUILTIN_PMULHW128, 0, 0 },
-  { MASK_SSE2, CODE_FOR_sse2_umulsidi3, "__builtin_ia32_pmuludq", IX86_BUILTIN_PMULUDQ, 0, 0 },
-  { MASK_SSE2, CODE_FOR_sse2_umulv2siv2di3, "__builtin_ia32_pmuludq128", IX86_BUILTIN_PMULUDQ128, 0, 0 },
 
   { MASK_SSE2, CODE_FOR_sse2_andv2di3, "__builtin_ia32_pand128", IX86_BUILTIN_PAND128, 0, 0 },
   { MASK_SSE2, CODE_FOR_sse2_nandv2di3, "__builtin_ia32_pandn128", IX86_BUILTIN_PANDN128, 0, 0 },
@@ -12895,6 +12910,9 @@ static const struct builtin_description bdesc_2arg[] =
   { MASK_SSE2, CODE_FOR_umulv8hi3_highpart, "__builtin_ia32_pmulhuw128", IX86_BUILTIN_PMULHUW128, 0, 0 },
   { MASK_SSE2, CODE_FOR_sse2_psadbw, 0, IX86_BUILTIN_PSADBW128, 0, 0 },
 
+  { MASK_SSE2, CODE_FOR_sse2_umulsidi3, 0, IX86_BUILTIN_PMULUDQ, 0, 0 },
+  { MASK_SSE2, CODE_FOR_sse2_umulv2siv2di3, 0, IX86_BUILTIN_PMULUDQ128, 0, 0 },
+
   { MASK_SSE2, CODE_FOR_ashlv8hi3_ti, 0, IX86_BUILTIN_PSLLW128, 0, 0 },
   { MASK_SSE2, CODE_FOR_ashlv8hi3, 0, IX86_BUILTIN_PSLLWI128, 0, 0 },
   { MASK_SSE2, CODE_FOR_ashlv4si3_ti, 0, IX86_BUILTIN_PSLLD128, 0, 0 },
@@ -13290,9 +13308,15 @@ ix86_init_mmx_sse_builtins (void)
   tree di_ftype_v8qi_v8qi
     = build_function_type_list (long_long_unsigned_type_node,
 				V8QI_type_node, V8QI_type_node, NULL_TREE);
+  tree di_ftype_v2si_v2si
+    = build_function_type_list (long_long_unsigned_type_node,
+				V2SI_type_node, V2SI_type_node, NULL_TREE);
   tree v2di_ftype_v16qi_v16qi
     = build_function_type_list (V2DI_type_node,
 				V16QI_type_node, V16QI_type_node, NULL_TREE);
+  tree v2di_ftype_v4si_v4si
+    = build_function_type_list (V2DI_type_node,
+				V4SI_type_node, V4SI_type_node, NULL_TREE);
   tree int_ftype_v16qi
     = build_function_type_list (integer_type_node, V16QI_type_node, NULL_TREE);
   tree v16qi_ftype_pcchar
@@ -13588,6 +13612,9 @@ ix86_init_mmx_sse_builtins (void)
 
   def_builtin (MASK_SSE, "__builtin_ia32_setzero128", v2di_ftype_void, IX86_BUILTIN_CLRTI);
 
+  def_builtin (MASK_SSE2, "__builtin_ia32_pmuludq", di_ftype_v2si_v2si, IX86_BUILTIN_PMULUDQ);
+  def_builtin (MASK_SSE2, "__builtin_ia32_pmuludq128", v2di_ftype_v4si_v4si, IX86_BUILTIN_PMULUDQ128);
+
   def_builtin (MASK_SSE2, "__builtin_ia32_psllw128", v8hi_ftype_v8hi_v2di, IX86_BUILTIN_PSLLW128);
   def_builtin (MASK_SSE2, "__builtin_ia32_pslld128", v4si_ftype_v4si_v2di, IX86_BUILTIN_PSLLD128);
   def_builtin (MASK_SSE2, "__builtin_ia32_psllq128", v2di_ftype_v2di_v2di, IX86_BUILTIN_PSLLQ128);

gcc/config/i386/i386.md

@@ -1963,14 +1963,19 @@
   "ix86_split_long_move (operands); DONE;")
 
 (define_insn "*movdi_1_rex64"
-  [(set (match_operand:DI 0 "nonimmediate_operand" "=r,r,r,mr,!mr,!*y,!rm,!*y,!*Y,!rm,!*Y")
+  [(set (match_operand:DI 0 "nonimmediate_operand" "=r,r,r,mr,!mr,!*y,!rm,!*y,!*Y,!rm,!*Y,!*Y,!*y")
-	(match_operand:DI 1 "general_operand" "Z,rem,i,re,n,*y,*y,rm,*Y,*Y,rm"))]
+	(match_operand:DI 1 "general_operand" "Z,rem,i,re,n,*y,*y,rm,*Y,*Y,rm,*y,*Y"))]
   "TARGET_64BIT
    && (TARGET_INTER_UNIT_MOVES || optimize_size)
    && (GET_CODE (operands[0]) != MEM || GET_CODE (operands[1]) != MEM)"
 {
   switch (get_attr_type (insn))
     {
+    case TYPE_SSECVT:
+      if (which_alternative == 11)
+	return "movq2dq\t{%1, %0|%0, %1}";
+      else
+	return "movdq2q\t{%1, %0|%0, %1}";
     case TYPE_SSEMOV:
       if (get_attr_mode (insn) == MODE_TI)
 	  return "movdqa\t{%1, %0|%0, %1}";
@@ -2001,6 +2006,8 @@
 	      (const_string "mmxmov")
 	    (eq_attr "alternative" "8,9,10")
 	      (const_string "ssemov")
+	    (eq_attr "alternative" "11,12")
+	      (const_string "ssecvt")
 	    (eq_attr "alternative" "4")
 	      (const_string "multi")
  	    (and (ne (symbol_ref "flag_pic") (const_int 0))
@@ -2008,9 +2015,9 @@
 	      (const_string "lea")
 	   ]
 	   (const_string "imov")))
-   (set_attr "modrm" "*,0,0,*,*,*,*,*,*,*,*")
+   (set_attr "modrm" "*,0,0,*,*,*,*,*,*,*,*,*,*")
-   (set_attr "length_immediate" "*,4,8,*,*,*,*,*,*,*,*")
+   (set_attr "length_immediate" "*,4,8,*,*,*,*,*,*,*,*,*,*")
-   (set_attr "mode" "SI,DI,DI,DI,SI,DI,DI,DI,TI,DI,DI")])
+   (set_attr "mode" "SI,DI,DI,DI,SI,DI,DI,DI,TI,DI,DI,DI,DI")])
 
 (define_insn "*movdi_1_rex64_nointerunit"
   [(set (match_operand:DI 0 "nonimmediate_operand" "=r,r,r,mr,!mr,!*y,!m,!*y,!*Y,!m,!*Y")
@@ -19705,52 +19712,68 @@
 })
 
 (define_insn "movv8qi_internal"
-  [(set (match_operand:V8QI 0 "nonimmediate_operand" "=y,y,m")
+  [(set (match_operand:V8QI 0 "nonimmediate_operand" "=y,y,m,!y,!*Y,?*Y,?m")
-	(match_operand:V8QI 1 "vector_move_operand" "C,ym,y"))]
+	(match_operand:V8QI 1 "vector_move_operand" "C,ym,y,*Y,y,*Ym,*Y"))]
   "TARGET_MMX
    && (GET_CODE (operands[0]) != MEM || GET_CODE (operands[1]) != MEM)"
   "@
     pxor\t%0, %0
     movq\t{%1, %0|%0, %1}
+    movq\t{%1, %0|%0, %1}
+    movdq2q\t{%1, %0|%0, %1}
+    movq2dq\t{%1, %0|%0, %1}
+    movq\t{%1, %0|%0, %1}
     movq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "mmxmov")
+  [(set_attr "type" "mmxmov,mmxmov,mmxmov,ssecvt,ssecvt,ssemov,ssemov")
    (set_attr "mode" "DI")])
 
 (define_insn "movv4hi_internal"
-  [(set (match_operand:V4HI 0 "nonimmediate_operand" "=y,y,m")
+  [(set (match_operand:V4HI 0 "nonimmediate_operand" "=y,y,m,!y,!*Y,?*Y,?m")
-	(match_operand:V4HI 1 "vector_move_operand" "C,ym,y"))]
+	(match_operand:V4HI 1 "vector_move_operand" "C,ym,y,*Y,y,*Ym,*Y"))]
   "TARGET_MMX
    && (GET_CODE (operands[0]) != MEM || GET_CODE (operands[1]) != MEM)"
   "@
     pxor\t%0, %0
     movq\t{%1, %0|%0, %1}
+    movq\t{%1, %0|%0, %1}
+    movdq2q\t{%1, %0|%0, %1}
+    movq2dq\t{%1, %0|%0, %1}
+    movq\t{%1, %0|%0, %1}
     movq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "mmxmov")
+  [(set_attr "type" "mmxmov,mmxmov,mmxmov,ssecvt,ssecvt,ssemov,ssemov")
    (set_attr "mode" "DI")])
 
-(define_insn "movv2si_internal"
+(define_insn "*movv2si_internal"
-  [(set (match_operand:V2SI 0 "nonimmediate_operand" "=y,y,m")
+  [(set (match_operand:V2SI 0 "nonimmediate_operand" "=y,y,m,!y,!*Y,?*Y,?m")
-	(match_operand:V2SI 1 "vector_move_operand" "C,ym,y"))]
+	(match_operand:V2SI 1 "vector_move_operand" "C,ym,y,*Y,y,*Ym,*Y"))]
   "TARGET_MMX
    && (GET_CODE (operands[0]) != MEM || GET_CODE (operands[1]) != MEM)"
   "@
     pxor\t%0, %0
     movq\t{%1, %0|%0, %1}
+    movq\t{%1, %0|%0, %1}
+    movdq2q\t{%1, %0|%0, %1}
+    movq2dq\t{%1, %0|%0, %1}
+    movq\t{%1, %0|%0, %1}
     movq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "mmxcvt")
+  [(set_attr "type" "mmxmov,mmxmov,mmxmov,ssecvt,ssecvt,ssemov,ssemov")
    (set_attr "mode" "DI")])
 
 (define_insn "movv2sf_internal"
-  [(set (match_operand:V2SF 0 "nonimmediate_operand" "=y,y,m")
+  [(set (match_operand:V2SF 0 "nonimmediate_operand" "=y,y,m,!y,!*Y,?*x,?m")
-        (match_operand:V2SF 1 "vector_move_operand" "C,ym,y"))]
+        (match_operand:V2SF 1 "vector_move_operand" "C,ym,y,*Y,y,*xm,*x"))]
   "TARGET_3DNOW
    && (GET_CODE (operands[0]) != MEM || GET_CODE (operands[1]) != MEM)"
   "@
     pxor\t%0, %0
     movq\t{%1, %0|%0, %1}
-    movq\t{%1, %0|%0, %1}"
+    movq\t{%1, %0|%0, %1}
-  [(set_attr "type" "mmxcvt")
+    movdq2q\t{%1, %0|%0, %1}
-   (set_attr "mode" "DI")])
+    movq2dq\t{%1, %0|%0, %1}
+    movlps\t{%1, %0|%0, %1}
+    movlps\t{%1, %0|%0, %1}"
+  [(set_attr "type" "mmxmov,mmxmov,mmxmov,ssecvt,ssecvt,ssemov,ssemov")
+   (set_attr "mode" "DI,DI,DI,DI,DI,V2SF,V2SF")])
 
 (define_expand "movti"
   [(set (match_operand:TI 0 "nonimmediate_operand" "")
@@ -23069,8 +23092,8 @@
 				  (parallel [(const_int 0)])))))]
   "TARGET_SSE2"
   "pmuludq\t{%2, %0|%0, %2}"
-  [(set_attr "type" "sseimul")
+  [(set_attr "type" "mmxmul")
-   (set_attr "mode" "TI")])
+   (set_attr "mode" "DI")])
 
 (define_insn "sse2_umulv2siv2di3"
   [(set (match_operand:V2DI 0 "register_operand" "=x")