invoke.texi (-mveclibabi): Document new target option.

2007-08-30  Richard Guenther  <rguenther@suse.de>

	* doc/invoke.texi (-mveclibabi): Document new target option.
	* config/i386/i386.opt (-mveclibabi): New target option.
	* config/i386/i386.c (ix86_veclib_handler): Handler for
	vectorization library support.
	(override_options): Handle the -mveclibabi option, initialize
	the vectorization library handler.
	(ix86_builtin_vectorized_function): As fallback call the
	vectorization library handler, if set.
	(ix86_veclibabi_acml): New static function for ACML ABI style
	vectorization support.

	* gcc.target/i386/vectorize5.c: New testcase.

From-SVN: r127926

6 files changed, 159 insertions, 5 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index f025459..e5d5249 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,16 @@
+2007-08-30  Richard Guenther  <rguenther@suse.de>
+
+	* doc/invoke.texi (-mveclibabi): Document new target option.
+	* config/i386/i386.opt (-mveclibabi): New target option.
+	* config/i386/i386.c (ix86_veclib_handler): Handler for
+	vectorization library support.
+	(override_options): Handle the -mveclibabi option, initialize
+	the vectorization library handler.
+	(ix86_builtin_vectorized_function): As fallback call the
+	vectorization library handler, if set.
+	(ix86_veclibabi_acml): New static function for ACML ABI style
+	vectorization support.
+
 2007-08-30  Jakub Jelinek  <jakub@redhat.com>
 
 	* config/rs6000/rs6000.c (rs6000_emit_sync): For QI or HI mode
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 7fdae6c..a98dcfb 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -1620,6 +1620,10 @@ static int ix86_isa_flags_explicit;
 
 #define OPTION_MASK_ISA_SSE4A_UNSET OPTION_MASK_ISA_SSE4
 
+/* Vectorization library interface and handlers.  */
+tree (*ix86_veclib_handler)(enum built_in_function, tree, tree) = NULL;
+static tree ix86_veclibabi_acml (enum built_in_function, tree, tree);
+
 /* Implement TARGET_HANDLE_OPTION.  */
 
 static bool
@@ -2409,6 +2413,16 @@ override_options (void)
   if (!TARGET_80387)
     target_flags &= ~MASK_FLOAT_RETURNS;
 
+  /* Use external vectorized library in vectorizing intrinsics.  */
+  if (ix86_veclibabi_string)
+    {
+      if (strcmp (ix86_veclibabi_string, "acml") == 0)
+	ix86_veclib_handler = ix86_veclibabi_acml;
+      else
+	error ("unknown vectorization library ABI type (%s) for "
+	       "-mveclibabi= switch", ix86_veclibabi_string);
+    }
+
   if ((x86_accumulate_outgoing_args & ix86_tune_mask)
       && !(target_flags_explicit & MASK_ACCUMULATE_OUTGOING_ARGS)
       && !optimize_size)
@@ -19934,33 +19948,122 @@ ix86_builtin_vectorized_function (unsigned int fn, tree type_out,
       if (out_mode == DFmode && out_n == 2
 	  && in_mode == DFmode && in_n == 2)
 	return ix86_builtins[IX86_BUILTIN_SQRTPD];
-      return NULL_TREE;
+      break;
 
     case BUILT_IN_SQRTF:
       if (out_mode == SFmode && out_n == 4
 	  && in_mode == SFmode && in_n == 4)
 	return ix86_builtins[IX86_BUILTIN_SQRTPS];
-      return NULL_TREE;
+      break;
 
     case BUILT_IN_LRINT:
       if (out_mode == SImode && out_n == 4
 	  && in_mode == DFmode && in_n == 2)
 	return ix86_builtins[IX86_BUILTIN_VEC_PACK_SFIX];
-      return NULL_TREE;
+      break;
 
     case BUILT_IN_LRINTF:
       if (out_mode == SImode && out_n == 4
 	  && in_mode == SFmode && in_n == 4)
 	return ix86_builtins[IX86_BUILTIN_CVTPS2DQ];
-      return NULL_TREE;
+      break;
 
     default:
       ;
     }
 
+  /* Dispatch to a handler for a vectorization library.  */
+  if (ix86_veclib_handler)
+    return (*ix86_veclib_handler)(fn, type_out, type_in);
+
   return NULL_TREE;
 }
 
+/* Handler for an ACML-style interface to a library with vectorized
+   intrinsics.  */
+
+static tree
+ix86_veclibabi_acml (enum built_in_function fn, tree type_out, tree type_in)
+{
+  char name[20] = "__vr.._";
+  tree fntype, new_fndecl, args;
+  unsigned arity;
+  const char *bname;
+  enum machine_mode el_mode, in_mode;
+  int n, in_n;
+
+  /* The ACML is 64bits only and suitable for unsafe math only as
+     it does not correctly support parts of IEEE with the required
+     precision such as denormals.  */
+  if (!TARGET_64BIT
+      || !flag_unsafe_math_optimizations)
+    return NULL_TREE;
+
+  el_mode = TYPE_MODE (TREE_TYPE (type_out));
+  n = TYPE_VECTOR_SUBPARTS (type_out);
+  in_mode = TYPE_MODE (TREE_TYPE (type_in));
+  in_n = TYPE_VECTOR_SUBPARTS (type_in);
+  if (el_mode != in_mode
+      || n != in_n)
+    return NULL_TREE;
+
+  switch (fn)
+    {
+    case BUILT_IN_SIN:
+    case BUILT_IN_COS:
+    case BUILT_IN_EXP:
+    case BUILT_IN_LOG:
+    case BUILT_IN_LOG2:
+    case BUILT_IN_LOG10:
+      name[4] = 'd';
+      name[5] = '2';
+      if (el_mode != DFmode
+	  || n != 2)
+	return NULL_TREE;
+      break;
+
+    case BUILT_IN_SINF:
+    case BUILT_IN_COSF:
+    case BUILT_IN_EXPF:
+    case BUILT_IN_POWF:
+    case BUILT_IN_LOGF:
+    case BUILT_IN_LOG2F:
+    case BUILT_IN_LOG10F:
+      name[4] = 's';
+      name[5] = '4';
+      if (el_mode != SFmode
+	  || n != 4)
+	return NULL_TREE;
+      break;
+    
+    default:
+      return NULL_TREE;
+    }
+
+  bname = IDENTIFIER_POINTER (DECL_NAME (implicit_built_in_decls[fn]));
+  sprintf (name + 7, "%s", bname+10);
+
+  arity = 0;
+  for (args = DECL_ARGUMENTS (implicit_built_in_decls[fn]); args;
+       args = TREE_CHAIN (args))
+    arity++;
+
+  if (arity == 1)
+    fntype = build_function_type_list (type_out, type_in, NULL);
+  else
+    fntype = build_function_type_list (type_out, type_in, type_in, NULL);
+
+  /* Build a function declaration for the vectorized function.  */
+  new_fndecl = build_decl (FUNCTION_DECL, get_identifier (name), fntype);
+  TREE_PUBLIC (new_fndecl) = 1;
+  DECL_EXTERNAL (new_fndecl) = 1;
+  DECL_IS_NOVOPS (new_fndecl) = 1;
+  TREE_READONLY (new_fndecl) = 1;
+
+  return new_fndecl;
+}
+
+
 /* Returns a decl of a function that implements conversion of the
    input vector of type TYPE, or NULL_TREE if it is not available.  */
 
diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
index a8e6da6..f32193d 100644
--- a/gcc/config/i386/i386.opt
+++ b/gcc/config/i386/i386.opt
@@ -182,6 +182,10 @@ mtune=
 Target RejectNegative Joined Var(ix86_tune_string)
 Schedule code for given CPU
 
+mveclibabi=
+Target RejectNegative Joined Var(ix86_veclibabi_string)
+Vector library ABI to use
+
 ;; ISA support
 
 m32
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 1c12d20..1646df3 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -557,7 +557,7 @@ Objective-C and Objective-C++ Dialects}.
 -mthreads  -mno-align-stringops  -minline-all-stringops @gol
 -mpush-args  -maccumulate-outgoing-args  -m128bit-long-double @gol
 -m96bit-long-double  -mregparm=@var{num}  -msseregparm @gol
--mpc32 -mpc64 -mpc80 mstackrealign @gol
+-mveclibabi=@var{type} -mpc32 -mpc64 -mpc80 -mstackrealign @gol
 -momit-leaf-frame-pointer  -mno-red-zone -mno-tls-direct-seg-refs @gol
 -mcmodel=@var{code-model} @gol
 -m32  -m64 -mlarge-data-threshold=@var{num}}
@@ -10440,6 +10440,19 @@ vectorized variants RCPPS and RSQRTPS) instead of DIVSS and SQRTSS (and their
 vectorized variants).  These instructions will be generated only when
 @option{-funsafe-math-optimizations} is enabled.
 
+@item -mveclibabi=@var{type}
+@opindex mveclibabi
+Specifies the ABI type to use for vectorizing intrinsics using an
+external library.  Supported types are @code{acml} for the AMD
+math core library style of interfacing.  GCC will currently emit
+calls to @code{__vrd2_sin}, @code{__vrd2_cos}, @code{__vrd2_exp},
+@code{__vrd2_log}, @code{__vrd2_log2}, @code{__vrd2_log10},
+@code{__vrs4_sinf}, @code{__vrs4_cosf}, @code{__vrs4_expf},
+@code{__vrs4_logf}, @code{__vrs4_log2f}, @code{__vrs4_log10f}
+and @code{__vrs4_powf} when using this type and @option{-ftree-vectorize}
+is enabled.  A ACML ABI compatible library will have to be specified
+at link time.
+
 @item -mpush-args
 @itemx -mno-push-args
 @opindex mpush-args
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index aa86266..476fc5f 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,7 @@
+2007-08-30  Richard Guenther  <rguenther@suse.de>
+
+	* gcc.target/i386/vectorize5.c: New testcase.
+
 2007-08-30  Tobias Burnus  <burnus@net-b.de>
 
 	PR fortran/33228
diff --git a/gcc/testsuite/gcc.target/i386/vectorize5.c b/gcc/testsuite/gcc.target/i386/vectorize5.c
new file mode 100644
index 0000000..3894240
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/vectorize5.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -ftree-vectorize -mveclibabi=acml -ffast-math" } */
+
+double x[256];
+
+extern double sin(double);
+
+void foo(void)
+{
+  int i;
+
+  for (i=0; i<256; ++i)
+    x[i] = sin(x[i]);
+}
+
+/* { dg-final { scan-assembler "__vrd2_sin" } } */