Add sparc VIS 2.0 builtins, intrinsics, and option to control them.

gcc/ * config/sparc/sparc.opt (VIS2): New option. * doc/invoke.texi: Document it. * config/sparc/sparc.md (UNSPEC_EDGE8N, UNSPEC_EDGE8LN, UNSPEC_EDGE16N, UNSPEC_EDGE16LN, UNSPEC_EDGE32N, UNSPEC_EDGE32LN, UNSPEC_BSHUFFLE): New unspecs. (define_attr type): New insn type 'edgen'. (bmask<P:mode>_vis, bshuffle<V64I:mode>_vis, edge8n<P:mode>_vis, edge8ln<P:mode>_vis, edge16n<P:mode>_vis, edge16ln<P:mode>_vis, edge32n<P:mode>_vis, edge32ln<P:mode>_vis): New insn VIS 2.0 patterns. * niagara.md: Handle edgen. * niagara2.md: Likewise. * ultra1_2.md: Likewise. * ultra3.md: Likewise. * config/sparc/sparc-c.c (sparc_target_macros): Define __VIS__ to 0x200 when TARGET_VIS2. * config/sparc/sparc.c (sparc_option_override): Set MASK_VIS2 by default when targetting capable cpus. TARGET_VIS2 implies TARGET_VIS, clear and it when TARGET_FPU is disabled. (sparc_vis_init_builtins): Emit new VIS 2.0 builtins. (sparc_expand_builtin): Fix predicate indexing when builtin returns void. (sparc_fold_builtin): Do not eliminate bmask when result is ignored. * config/sparc/visintrin.h (__vis_bmask, __vis_bshuffledi, __vis_bshufflev2si, __vis_bshufflev4hi, __vis_bshufflev8qi, __vis_edge8n, __vis_edge8ln, __vis_edge16n, __vis_edge16ln, __vis_edge32n, __vis_edge32ln): New VIS 2.0 interfaces. * doc/extend.texi: Document new VIS 2.0 builtins. gcc/testsuite/ * gcc.target/sparc/bmaskbshuf.c: New test. * gcc.target/sparc/edgen.c: New test. From-SVN: r179376
2011-09-30 07:54:07 +00:00 · 2011-09-30 07:54:07 +00:00 · c4728c6b20
commit c4728c6b20
parent 3aaedee021
15 changed files with 382 additions and 19 deletions
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@ -1,3 +1,34 @@
+2011-09-30  David S. Miller  <davem@davemloft.net>
+
+	* config/sparc/sparc.opt (VIS2): New option.
+	* doc/invoke.texi: Document it.
+	* config/sparc/sparc.md (UNSPEC_EDGE8N, UNSPEC_EDGE8LN,
+	UNSPEC_EDGE16N, UNSPEC_EDGE16LN, UNSPEC_EDGE32N,
+	UNSPEC_EDGE32LN, UNSPEC_BSHUFFLE): New unspecs.
+	(define_attr type): New insn type 'edgen'.
+	(bmask<P:mode>_vis, bshuffle<V64I:mode>_vis, edge8n<P:mode>_vis,
+	edge8ln<P:mode>_vis, edge16n<P:mode>_vis, edge16ln<P:mode>_vis,
+	edge32n<P:mode>_vis, edge32ln<P:mode>_vis): New insn VIS 2.0
+	patterns.
+	* niagara.md: Handle edgen.
+	* niagara2.md: Likewise.
+	* ultra1_2.md: Likewise.
+	* ultra3.md: Likewise.
+	* config/sparc/sparc-c.c (sparc_target_macros): Define __VIS__
+	to 0x200 when TARGET_VIS2.
+	* config/sparc/sparc.c (sparc_option_override): Set MASK_VIS2 by
+	default when targetting capable cpus.  TARGET_VIS2 implies
+	TARGET_VIS, clear and it when TARGET_FPU is disabled.
+	(sparc_vis_init_builtins): Emit new VIS 2.0 builtins.
+	(sparc_expand_builtin): Fix predicate indexing when builtin returns
+	void.
+	(sparc_fold_builtin): Do not eliminate bmask when result is ignored.
+	* config/sparc/visintrin.h (__vis_bmask, __vis_bshuffledi,
+	__vis_bshufflev2si, __vis_bshufflev4hi, __vis_bshufflev8qi,
+	__vis_edge8n, __vis_edge8ln, __vis_edge16n, __vis_edge16ln,
+	__vis_edge32n, __vis_edge32ln): New VIS 2.0 interfaces.
+	* doc/extend.texi: Document new VIS 2.0 builtins.
+
 2011-09-29  Nick Clifton  <nickc@redhat.com>
 	    Bernd Schmidt  <bernds@codesourcery.com>

--- a/gcc/config/sparc/niagara.md
+++ b/gcc/config/sparc/niagara.md
@ -114,5 +114,5 @@
 */
 (define_insn_reservation "niag_vis" 8
  (and (eq_attr "cpu" "niagara")
-    (eq_attr "type" "fga,fgm_pack,fgm_mul,fgm_cmp,fgm_pdist,edge,gsr,array"))
+    (eq_attr "type" "fga,fgm_pack,fgm_mul,fgm_cmp,fgm_pdist,edge,edgen,gsr,array"))
  "niag_pipe*8")
--- a/gcc/config/sparc/niagara2.md
+++ b/gcc/config/sparc/niagara2.md
@ -111,10 +111,10 @@

 (define_insn_reservation "niag2_vis" 6
  (and (eq_attr "cpu" "niagara2")
-    (eq_attr "type" "fga,fgm_pack,fgm_mul,fgm_cmp,fgm_pdist,edge,array,gsr"))
+    (eq_attr "type" "fga,fgm_pack,fgm_mul,fgm_cmp,fgm_pdist,edge,edgen,array,gsr"))
  "niag2_pipe*6")

 (define_insn_reservation "niag3_vis" 9
  (and (eq_attr "cpu" "niagara3")
-    (eq_attr "type" "fga,fgm_pack,fgm_mul,fgm_cmp,fgm_pdist,edge,array,gsr"))
+    (eq_attr "type" "fga,fgm_pack,fgm_mul,fgm_cmp,fgm_pdist,edge,edgen,array,gsr"))
  "niag2_pipe*9")
--- a/gcc/config/sparc/sparc-c.c
+++ b/gcc/config/sparc/sparc-c.c
@ -45,7 +45,12 @@ sparc_target_macros (void)
      cpp_assert (parse_in, "machine=sparc");
    }

-  if (TARGET_VIS)
+  if (TARGET_VIS2)
+    {
+      cpp_define (parse_in, "__VIS__=0x200");
+      cpp_define (parse_in, "__VIS=0x200");
+    }
+  else if (TARGET_VIS)
    {
      cpp_define (parse_in, "__VIS__=0x100");
      cpp_define (parse_in, "__VIS=0x100");
--- a/gcc/config/sparc/sparc.c
+++ b/gcc/config/sparc/sparc.c
@ -769,16 +769,16 @@ sparc_option_override (void)
    /* UltraSPARC III */
    /* ??? Check if %y issue still holds true.  */
    { MASK_ISA,
-      MASK_V9|MASK_DEPRECATED_V8_INSNS},
+      MASK_V9|MASK_DEPRECATED_V8_INSNS|MASK_VIS2},
    /* UltraSPARC T1 */
    { MASK_ISA,
      MASK_V9|MASK_DEPRECATED_V8_INSNS},
    /* UltraSPARC T2 */
-    { MASK_ISA, MASK_V9},
+    { MASK_ISA, MASK_V9|MASK_VIS2},
    /* UltraSPARC T3 */
-    { MASK_ISA, MASK_V9 | MASK_FMAF},
+    { MASK_ISA, MASK_V9|MASK_VIS2|MASK_FMAF},
    /* UltraSPARC T4 */
-    { MASK_ISA, MASK_V9 | MASK_FMAF},
+    { MASK_ISA, MASK_V9|MASK_VIS2|MASK_FMAF},
  };
  const struct cpu_table *cpu;
  unsigned int i;
@ -857,9 +857,13 @@ sparc_option_override (void)
  if (target_flags_explicit & MASK_FPU)
    target_flags = (target_flags & ~MASK_FPU) | fpu;

-  /* Don't allow -mvis or -mfmaf if FPU is disabled.  */
+  /* -mvis2 implies -mvis */
+  if (TARGET_VIS2)
+    target_flags |= MASK_VIS;
+
+  /* Don't allow -mvis, -mvis2, or -mfmaf if FPU is disabled.  */
  if (! TARGET_FPU)
-    target_flags &= ~(MASK_VIS | MASK_FMAF);
+    target_flags &= ~(MASK_VIS | MASK_VIS2 | MASK_FMAF);

  /* -mvis assumes UltraSPARC+, so we are sure v9 instructions
     are available.
@ -9300,6 +9304,21 @@ sparc_vis_init_builtins (void)
 			 di_ftype_ptr_ptr);
      def_builtin_const ("__builtin_vis_edge32l", CODE_FOR_edge32ldi_vis,
 			 di_ftype_ptr_ptr);
+      if (TARGET_VIS2)
+	{
+	  def_builtin_const ("__builtin_vis_edge8n", CODE_FOR_edge8ndi_vis,
+			     di_ftype_ptr_ptr);
+	  def_builtin_const ("__builtin_vis_edge8ln", CODE_FOR_edge8lndi_vis,
+			     di_ftype_ptr_ptr);
+	  def_builtin_const ("__builtin_vis_edge16n", CODE_FOR_edge16ndi_vis,
+			     di_ftype_ptr_ptr);
+	  def_builtin_const ("__builtin_vis_edge16ln", CODE_FOR_edge16lndi_vis,
+			     di_ftype_ptr_ptr);
+	  def_builtin_const ("__builtin_vis_edge32n", CODE_FOR_edge32ndi_vis,
+			     di_ftype_ptr_ptr);
+	  def_builtin_const ("__builtin_vis_edge32ln", CODE_FOR_edge32lndi_vis,
+			     di_ftype_ptr_ptr);
+	}
    }
  else
    {
@ -9315,6 +9334,21 @@ sparc_vis_init_builtins (void)
 			 si_ftype_ptr_ptr);
      def_builtin_const ("__builtin_vis_edge32l", CODE_FOR_edge32lsi_vis,
 			 si_ftype_ptr_ptr);
+      if (TARGET_VIS2)
+	{
+	  def_builtin_const ("__builtin_vis_edge8n", CODE_FOR_edge8nsi_vis,
+			     si_ftype_ptr_ptr);
+	  def_builtin_const ("__builtin_vis_edge8ln", CODE_FOR_edge8lnsi_vis,
+			     si_ftype_ptr_ptr);
+	  def_builtin_const ("__builtin_vis_edge16n", CODE_FOR_edge16nsi_vis,
+			     si_ftype_ptr_ptr);
+	  def_builtin_const ("__builtin_vis_edge16ln", CODE_FOR_edge16lnsi_vis,
+			     si_ftype_ptr_ptr);
+	  def_builtin_const ("__builtin_vis_edge32n", CODE_FOR_edge32nsi_vis,
+			     si_ftype_ptr_ptr);
+	  def_builtin_const ("__builtin_vis_edge32ln", CODE_FOR_edge32lnsi_vis,
+			     si_ftype_ptr_ptr);
+	}
    }

  /* Pixel compare.  */
@ -9394,6 +9428,25 @@ sparc_vis_init_builtins (void)
      def_builtin_const ("__builtin_vis_array32", CODE_FOR_array32si_vis,
 			 si_ftype_si_si);
  }
+
+  if (TARGET_VIS2)
+    {
+      /* Byte mask and shuffle */
+      if (TARGET_ARCH64)
+	def_builtin ("__builtin_vis_bmask", CODE_FOR_bmaskdi_vis,
+		     di_ftype_di_di);
+      else
+	def_builtin ("__builtin_vis_bmask", CODE_FOR_bmasksi_vis,
+		     si_ftype_si_si);
+      def_builtin ("__builtin_vis_bshufflev4hi", CODE_FOR_bshufflev4hi_vis,
+		   v4hi_ftype_v4hi_v4hi);
+      def_builtin ("__builtin_vis_bshufflev8qi", CODE_FOR_bshufflev8qi_vis,
+		   v8qi_ftype_v8qi_v8qi);
+      def_builtin ("__builtin_vis_bshufflev2si", CODE_FOR_bshufflev2si_vis,
+		   v2si_ftype_v2si_v2si);
+      def_builtin ("__builtin_vis_bshuffledi", CODE_FOR_bshuffledi_vis,
+		   di_ftype_di_di);
+    }
 }

 /* Handle TARGET_EXPAND_BUILTIN target hook.
@ -9428,16 +9481,18 @@ sparc_expand_builtin (tree exp, rtx target,
  FOR_EACH_CALL_EXPR_ARG (arg, iter, exp)
    {
      const struct insn_operand_data *insn_op;
+      int idx;

      if (arg == error_mark_node)
 	return NULL_RTX;

      arg_count++;
-      insn_op = &insn_data[icode].operand[arg_count - !nonvoid];
+      idx = arg_count - !nonvoid;
+      insn_op = &insn_data[icode].operand[idx];
      op[arg_count] = expand_normal (arg);

-      if (! (*insn_data[icode].operand[arg_count].predicate) (op[arg_count],
-							      insn_op->mode))
+      if (! (*insn_data[icode].operand[idx].predicate) (op[arg_count],
+							insn_op->mode))
 	op[arg_count] = copy_to_mode_reg (insn_op->mode, op[arg_count]);
    }

@ -9556,7 +9611,9 @@ sparc_fold_builtin (tree fndecl, int n_args ATTRIBUTE_UNUSED,
  if (ignore
      && icode != CODE_FOR_alignaddrsi_vis
      && icode != CODE_FOR_alignaddrdi_vis
-      && icode != CODE_FOR_wrgsr_vis)
+      && icode != CODE_FOR_wrgsr_vis
+      && icode != CODE_FOR_bmasksi_vis
+      && icode != CODE_FOR_bmaskdi_vis)
    return build_zero_cst (rtype);

  switch (icode)
--- a/gcc/config/sparc/sparc.md
+++ b/gcc/config/sparc/sparc.md
@ -72,6 +72,14 @@

   (UNSPEC_SP_SET		60)
   (UNSPEC_SP_TEST		61)
+
+   (UNSPEC_EDGE8N		70)
+   (UNSPEC_EDGE8LN		71)
+   (UNSPEC_EDGE16N		72)
+   (UNSPEC_EDGE16LN		73)
+   (UNSPEC_EDGE32N		74)
+   (UNSPEC_EDGE32LN		75)
+   (UNSPEC_BSHUFFLE		76)
  ])

 (define_constants
@ -240,7 +248,7 @@
   fpcmp,
   fpmul,fpdivs,fpdivd,
   fpsqrts,fpsqrtd,
-   fga,fgm_pack,fgm_mul,fgm_pdist,fgm_cmp,edge,gsr,array,
+   fga,fgm_pack,fgm_mul,fgm_pdist,fgm_cmp,edge,edgen,gsr,array,
   cmove,
   ialuX,
   multi,savew,flushw,iflush,trap"
@ -8188,4 +8196,79 @@
  "array32\t%r1, %r2, %0"
  [(set_attr "type" "array")])

+(define_insn "bmask<P:mode>_vis"
+  [(set (match_operand:P 0 "register_operand" "=r")
+        (plus:P (match_operand:P 1 "register_operand" "rJ")
+                (match_operand:P 2 "register_operand" "rJ")))
+   (clobber (reg:SI GSR_REG))]
+  "TARGET_VIS2"
+  "bmask\t%r1, %r2, %0"
+  [(set_attr "type" "array")])
+
+(define_insn "bshuffle<V64I:mode>_vis"
+  [(set (match_operand:V64I 0 "register_operand" "=e")
+        (unspec:V64I [(match_operand:V64I 1 "register_operand" "e")
+	              (match_operand:V64I 2 "register_operand" "e")]
+                     UNSPEC_BSHUFFLE))
+   (use (reg:SI GSR_REG))]
+  "TARGET_VIS2"
+  "bshuffle\t%1, %2, %0"
+  [(set_attr "type" "fga")
+   (set_attr "fptype" "double")])
+
+;; VIS 2.0 adds edge variants which do not set the condition codes
+(define_insn "edge8n<P:mode>_vis"
+  [(set (match_operand:P 0 "register_operand" "=r")
+        (unspec:P [(match_operand:P 1 "register_operand" "rJ")
+	           (match_operand:P 2 "register_operand" "rJ")]
+                  UNSPEC_EDGE8N))]
+  "TARGET_VIS2"
+  "edge8n\t%r1, %r2, %0"
+  [(set_attr "type" "edgen")])
+
+(define_insn "edge8ln<P:mode>_vis"
+  [(set (match_operand:P 0 "register_operand" "=r")
+        (unspec:P [(match_operand:P 1 "register_operand" "rJ")
+	           (match_operand:P 2 "register_operand" "rJ")]
+                  UNSPEC_EDGE8LN))]
+  "TARGET_VIS2"
+  "edge8ln\t%r1, %r2, %0"
+  [(set_attr "type" "edgen")])
+
+(define_insn "edge16n<P:mode>_vis"
+  [(set (match_operand:P 0 "register_operand" "=r")
+        (unspec:P [(match_operand:P 1 "register_operand" "rJ")
+                   (match_operand:P 2 "register_operand" "rJ")]
+                  UNSPEC_EDGE16N))]
+  "TARGET_VIS2"
+  "edge16n\t%r1, %r2, %0"
+  [(set_attr "type" "edgen")])
+
+(define_insn "edge16ln<P:mode>_vis"
+  [(set (match_operand:P 0 "register_operand" "=r")
+        (unspec:P [(match_operand:P 1 "register_operand" "rJ")
+                   (match_operand:P 2 "register_operand" "rJ")]
+                  UNSPEC_EDGE16LN))]
+  "TARGET_VIS2"
+  "edge16ln\t%r1, %r2, %0"
+  [(set_attr "type" "edgen")])
+
+(define_insn "edge32n<P:mode>_vis"
+  [(set (match_operand:P 0 "register_operand" "=r")
+        (unspec:P [(match_operand:P 1 "register_operand" "rJ")
+                   (match_operand:P 2 "register_operand" "rJ")]
+                  UNSPEC_EDGE32N))]
+  "TARGET_VIS2"
+  "edge32n\t%r1, %r2, %0"
+  [(set_attr "type" "edgen")])
+
+(define_insn "edge32ln<P:mode>_vis"
+  [(set (match_operand:P 0 "register_operand" "=r")
+        (unspec:P [(match_operand:P 1 "register_operand" "rJ")
+                   (match_operand:P 2 "register_operand" "rJ")]
+                  UNSPEC_EDGE32LN))]
+  "TARGET_VIS2"
+  "edge32ln\t%r1, %r2, %0"
+  [(set_attr "type" "edge")])
+
 (include "sync.md")
--- a/gcc/config/sparc/sparc.opt
+++ b/gcc/config/sparc/sparc.opt
@ -59,7 +59,11 @@ Compile for V8+ ABI

 mvis
 Target Report Mask(VIS)
-Use UltraSPARC Visual Instruction Set extensions
+Use UltraSPARC Visual Instruction Set version 1.0 extensions
+
+mvis2
+Target Report Mask(VIS2)
+Use UltraSPARC Visual Instruction Set version 2.0 extensions

 mfmaf
 Target Report Mask(FMAF)
--- a/gcc/config/sparc/ultra1_2.md
+++ b/gcc/config/sparc/ultra1_2.md
@ -94,7 +94,7 @@

 (define_insn_reservation "us1_simple_ieu1" 1
  (and (eq_attr "cpu" "ultrasparc")
-    (eq_attr "type" "compare,edge,array"))
+    (eq_attr "type" "compare,edge,edgen,array"))
  "us1_ieu1 + us1_slot012")

 (define_insn_reservation "us1_ialuX" 1
--- a/gcc/config/sparc/ultra3.md
+++ b/gcc/config/sparc/ultra3.md
@ -56,7 +56,7 @@

 (define_insn_reservation "us3_array" 2
  (and (eq_attr "cpu" "ultrasparc3")
-    (eq_attr "type" "array"))
+    (eq_attr "type" "array,edgen"))
  "us3_ms + us3_slotany, nothing")

 ;; ??? Not entirely accurate.
--- a/gcc/config/sparc/visintrin.h
+++ b/gcc/config/sparc/visintrin.h
@ -354,4 +354,81 @@ __vis_array32 (long __A, long __B)
  return __builtin_vis_array32 (__A, __B);
 }

+extern __inline long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__vis_bmask (long __A, long __B)
+{
+  return __builtin_vis_bmask (__A, __B);
+}
+
+extern __inline __i64
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__vis_bshuffledi (__i64 __A, __i64 __B)
+{
+  return __builtin_vis_bshuffledi (__A, __B);
+}
+
+extern __inline __v2si
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__vis_bshufflev2si (__v2si __A, __v2si __B)
+{
+  return __builtin_vis_bshufflev2si (__A, __B);
+}
+
+extern __inline __v4hi
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__vis_bshufflev4hi (__v4hi __A, __v4hi __B)
+{
+  return __builtin_vis_bshufflev4hi (__A, __B);
+}
+
+extern __inline __v8qi
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__vis_bshufflev8qi (__v8qi __A, __v8qi __B)
+{
+  return __builtin_vis_bshufflev8qi (__A, __B);
+}
+
+extern __inline long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__vis_edge8n (void *__A, void *__B)
+{
+  return __builtin_vis_edge8n (__A, __B);
+}
+
+extern __inline long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__vis_edge8ln (void *__A, void *__B)
+{
+  return __builtin_vis_edge8ln (__A, __B);
+}
+
+extern __inline long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__vis_edge16n (void *__A, void *__B)
+{
+  return __builtin_vis_edge16n (__A, __B);
+}
+
+extern __inline long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__vis_edge16ln (void *__A, void *__B)
+{
+  return __builtin_vis_edge16ln (__A, __B);
+}
+
+extern __inline long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__vis_edge32n (void *__A, void *__B)
+{
+  return __builtin_vis_edge32n (__A, __B);
+}
+
+extern __inline long
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+__vis_edge32ln (void *__A, void *__B)
+{
+  return __builtin_vis_edge32ln (__A, __B);
+}
+
 #endif  /* _VISINTRIN_H_INCLUDED */
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@ -13016,6 +13016,24 @@ long __builtin_vis_array16 (long, long);
 long __builtin_vis_array32 (long, long);
@end smallexample

+Additionally, when you use the @option{-mvis2} switch, the VIS version
+2.0 built-in functions become available:
+
+@smallexample
+long __builtin_vis_bmask (long, long);
+int64_t __builtin_vis_bshuffledi (int64_t, int64_t);
+v2si __builtin_vis_bshufflev2si (v2si, v2si);
+v4hi __builtin_vis_bshufflev2si (v4hi, v4hi);
+v8qi __builtin_vis_bshufflev2si (v8qi, v8qi);
+
+long __builtin_vis_edge8n (void *, void *);
+long __builtin_vis_edge8ln (void *, void *);
+long __builtin_vis_edge16n (void *, void *);
+long __builtin_vis_edge16ln (void *, void *);
+long __builtin_vis_edge32n (void *, void *);
+long __builtin_vis_edge32ln (void *, void *);
+@end smallexample
+
@node SPU Built-in Functions
@subsection SPU Built-in Functions

--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@ -880,7 +880,7 @@ See RS/6000 and PowerPC Options.
 -mstack-bias  -mno-stack-bias @gol
 -munaligned-doubles  -mno-unaligned-doubles @gol
 -mv8plus  -mno-v8plus  -mvis  -mno-vis @gol
-mfmaf -mno-fmaf}
+-mvis2 -mno-vis2 -mfmaf -mno-fmaf}

@emph{SPU Options}
@gccoptlist{-mwarn-reloc -merror-reloc @gol
@ -17430,6 +17430,16 @@ mode for all SPARC-V9 processors.
 With @option{-mvis}, GCC generates code that takes advantage of the UltraSPARC
 Visual Instruction Set extensions.  The default is @option{-mno-vis}.

+@item -mvis2
+@itemx -mno-vis2
+@opindex mvis2
+@opindex mno-vis2
+With @option{-mvis2}, GCC generates code that takes advantage of
+version 2.0 of the UltraSPARC Visual Instruction Set extensions.  The
+default is @option{-mvis2} when targetting a cpu that supports such
+instructions, such as UltraSPARC-III and later.  Setting @option{-mvis2}
+also sets @option{-mvis}.
+
@item -mfmaf
@itemx -mno-fmaf
@opindex mfmaf
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@ -1,3 +1,8 @@
+2011-09-30  David S. Miller  <davem@davemloft.net>
+
+	* gcc.target/sparc/bmaskbshuf.c: New test.
+	* gcc.target/sparc/edgen.c: New test.
+
 2011-09-29  Janus Weil  <janus@gcc.gnu.org>

 	PR fortran/50547
--- a/gcc/testsuite/gcc.target/sparc/bmaskbshuf.c
+++ b/gcc/testsuite/gcc.target/sparc/bmaskbshuf.c
@ -0,0 +1,34 @@
+/* { dg-do compile } */
+/* { dg-options "-O -mcpu=ultrasparc3 -mvis -mvis2" } */
+typedef long long int64_t;
+typedef int vec32 __attribute__((vector_size(8)));
+typedef short vec16 __attribute__((vector_size(8)));
+typedef unsigned char vec8 __attribute__((vector_size(8)));
+
+long test_bmask (long x, long y)
+{
+  return __builtin_vis_bmask (x, y);
+}
+
+vec16 test_bshufv4hi (vec16 x, vec16 y)
+{
+  return __builtin_vis_bshufflev4hi (x, y);
+}
+
+vec32 test_bshufv2si (vec32 x, vec32 y)
+{
+  return __builtin_vis_bshufflev2si (x, y);
+}
+
+vec8 test_bshufv8qi (vec8 x, vec8 y)
+{
+  return __builtin_vis_bshufflev8qi (x, y);
+}
+
+int64_t test_bshufdi (int64_t x, int64_t y)
+{
+  return __builtin_vis_bshuffledi (x, y);
+}
+
+/* { dg-final { scan-assembler "bmask\t%" } } */
+/* { dg-final { scan-assembler "bshuffle\t%" } } */
--- a/gcc/testsuite/gcc.target/sparc/edgen.c
+++ b/gcc/testsuite/gcc.target/sparc/edgen.c
@ -0,0 +1,39 @@
+/* { dg-do compile } */
+/* { dg-options "-O -mcpu=ultrasparc3 -mvis" } */
+
+long test_edge8n (void *p1, void *p2)
+{
+  return __builtin_vis_edge8n (p1, p2);
+}
+
+long test_edge8ln (void *p1, void *p2)
+{
+  return __builtin_vis_edge8ln (p1, p2);
+}
+
+long test_edge16n (void *p1, void *p2)
+{
+  return __builtin_vis_edge16n (p1, p2);
+}
+
+long test_edge16ln (void *p1, void *p2)
+{
+  return __builtin_vis_edge16ln (p1, p2);
+}
+
+long test_edge32n (void *p1, void *p2)
+{
+  return __builtin_vis_edge32n (p1, p2);
+}
+
+long test_edge32ln (void *p1, void *p2)
+{
+  return __builtin_vis_edge32ln (p1, p2);
+}
+
+/* { dg-final { scan-assembler "edge8n\t%" } } */
+/* { dg-final { scan-assembler "edge8ln\t%" } } */
+/* { dg-final { scan-assembler "edge16n\t%" } } */
+/* { dg-final { scan-assembler "edge16ln\t%" } } */
+/* { dg-final { scan-assembler "edge32n\t%" } } */
+/* { dg-final { scan-assembler "edge32ln\t%" } } */