defaults.h (UNITS_PER_SIMD_WORD): Add scalar mode as argument.

2008-05-22  H.J. Lu  <hongjiu.lu@intel.com>

	* defaults.h (UNITS_PER_SIMD_WORD): Add scalar mode as argument.
	* doc/tm.texi (UNITS_PER_SIMD_WORD): Likewise.

	* tree-vect-analyze.c (vect_compute_data_ref_alignment): Replace
	UNITS_PER_SIMD_WORD with GET_MODE_SIZE (TYPE_MODE (vectype)).
	(vect_update_misalignment_for_peel): Likewise.
	(vector_alignment_reachable_p): Likewise.
	* tree-vect-transform.c (vectorizable_load): Likewise.
	* tree-vectorizer.c (vect_supportable_dr_alignment): Likewise.

	* tree-vectorizer.c (get_vectype_for_scalar_type): Pass mode of
	scalar_type to UNITS_PER_SIMD_WORD.

	* config/arm/arm.h (UNITS_PER_SIMD_WORD): Updated.
	* config/i386/i386.h (UNITS_PER_SIMD_WORD): Likewise.
	* config/mips/mips.h (UNITS_PER_SIMD_WORD): Likewise.
	* config/rs6000/rs6000.h (UNITS_PER_SIMD_WORD): Likewise.
	* config/sparc/sparc.h (UNITS_PER_SIMD_WORD): Likewise.

From-SVN: r135759

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index eda2ea21c1cb42c324b5519540629166bcc2a5a0..50754f75dbe398552588030a18bbb09fb7d6fd6d 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,24 @@
+2008-05-22  H.J. Lu  <hongjiu.lu@intel.com>
+
+       * defaults.h (UNITS_PER_SIMD_WORD): Add scalar mode as argument.
+       * doc/tm.texi (UNITS_PER_SIMD_WORD): Likewise.
+
+       * tree-vect-analyze.c (vect_compute_data_ref_alignment): Replace
+       UNITS_PER_SIMD_WORD with GET_MODE_SIZE (TYPE_MODE (vectype)).
+       (vect_update_misalignment_for_peel): Likewise.
+       (vector_alignment_reachable_p): Likewise.
+       * tree-vect-transform.c (vectorizable_load): Likewise.
+       * tree-vectorizer.c (vect_supportable_dr_alignment): Likewise.
+
+       * tree-vectorizer.c (get_vectype_for_scalar_type): Pass mode of
+       scalar_type to UNITS_PER_SIMD_WORD.
+
+       * config/arm/arm.h (UNITS_PER_SIMD_WORD): Updated.
+       * config/i386/i386.h (UNITS_PER_SIMD_WORD): Likewise.
+       * config/mips/mips.h (UNITS_PER_SIMD_WORD): Likewise.
+       * config/rs6000/rs6000.h (UNITS_PER_SIMD_WORD): Likewise.
+       * config/sparc/sparc.h (UNITS_PER_SIMD_WORD): Likewise.
+
 2008-05-22  Ira Rosen  <irar@il.ibm.com>
 
        PR tree-optimization/36293

diff --git a/gcc/config/arm/arm.h b/gcc/config/arm/arm.h
index 7f10a5797d8ff2f5393e971284b3406070a76ad5..b77a2ac5b8f7ef6e1b7dde6029b8731552519ab4 100644 (file)
--- a/gcc/config/arm/arm.h
+++ b/gcc/config/arm/arm.h
@@ -506,7 +506,7 @@ extern int arm_arch_hwdiv;
 /* Use the option -mvectorize-with-neon-quad to override the use of doubleword
    registers when autovectorizing for Neon, at least until multiple vector
    widths are supported properly by the middle-end.  */
-#define UNITS_PER_SIMD_WORD \
+#define UNITS_PER_SIMD_WORD(MODE) \
   (TARGET_NEON ? (TARGET_NEON_VECTORIZE_QUAD ? 16 : 8) : UNITS_PER_WORD)
 
 /* True if natural alignment is used for doubleword types.  */

diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 9d36a1ff49fdd929cd70270d16d1d8375b24fb26..72ead0795c2dc1714c4f9e7c33200eafe2065145 100644 (file)
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -1132,7 +1132,7 @@ do {                                                                      \
 
 /* ??? No autovectorization into MMX or 3DNOW until we can reliably
    place emms and femms instructions.  */
-#define UNITS_PER_SIMD_WORD (TARGET_SSE ? 16 : UNITS_PER_WORD)
+#define UNITS_PER_SIMD_WORD(MODE) (TARGET_SSE ? 16 : UNITS_PER_WORD)
 
 #define VALID_DFP_MODE_P(MODE) \
   ((MODE) == SDmode || (MODE) == DDmode || (MODE) == TDmode)

diff --git a/gcc/config/mips/mips.h b/gcc/config/mips/mips.h
index 765552778b5d4b2586d792eb2568d2bd5799bbeb..6d3c18feb466918dda45d5c512aeaec7494a54dc 100644 (file)
--- a/gcc/config/mips/mips.h
+++ b/gcc/config/mips/mips.h
@@ -1193,7 +1193,8 @@ enum mips_code_readable_setting {
 /* The number of bytes in a double.  */
 #define UNITS_PER_DOUBLE (TYPE_PRECISION (double_type_node) / BITS_PER_UNIT)
 
-#define UNITS_PER_SIMD_WORD (TARGET_PAIRED_SINGLE_FLOAT ? 8 : UNITS_PER_WORD)
+#define UNITS_PER_SIMD_WORD(MODE) \
+  (TARGET_PAIRED_SINGLE_FLOAT ? 8 : UNITS_PER_WORD)
 
 /* Set the sizes of the core types.  */
 #define SHORT_TYPE_SIZE 16

diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index 269a6021c9695cd2e692006cdec300fe33fa2fba..442f72708b0c9a8ce101515eae2c1866586bc4ea 100644 (file)
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -899,7 +899,7 @@ extern enum rs6000_nop_insertion rs6000_sched_insert_nops;
 #define PAIRED_VECTOR_MODE(MODE)        \
          ((MODE) == V2SFmode)            
 
-#define UNITS_PER_SIMD_WORD                                         \
+#define UNITS_PER_SIMD_WORD(MODE)                                   \
        (TARGET_ALTIVEC ? UNITS_PER_ALTIVEC_WORD                     \
         : (TARGET_SPE ? UNITS_PER_SPE_WORD : (TARGET_PAIRED_FLOAT ? \
         UNITS_PER_PAIRED_WORD : UNITS_PER_WORD)))

diff --git a/gcc/config/sparc/sparc.h b/gcc/config/sparc/sparc.h
index 6e9e3ea54e40cd3a79ed265e340c4e6a5c80ce6e..ef60292cef30efd1d7e5fe7b9cff0f3655aeb99b 100644 (file)
--- a/gcc/config/sparc/sparc.h
+++ b/gcc/config/sparc/sparc.h
@@ -606,7 +606,7 @@ extern struct sparc_cpu_select sparc_select[];
 #define MIN_UNITS_PER_WORD     4
 #endif
 
-#define UNITS_PER_SIMD_WORD    (TARGET_VIS ? 8 : UNITS_PER_WORD)
+#define UNITS_PER_SIMD_WORD(MODE) (TARGET_VIS ? 8 : UNITS_PER_WORD)
 
 /* Now define the sizes of the C data types.  */
 

diff --git a/gcc/defaults.h b/gcc/defaults.h
index cc41b6e66128ab2e84a79acf0dd6e66e907e31ef..ff5b5c01cf33136f3abee802d169e5a1e23e8b20 100644 (file)
--- a/gcc/defaults.h
+++ b/gcc/defaults.h
@@ -739,7 +739,7 @@ along with GCC; see the file COPYING3.  If not see
 /* By default, only attempt to parallelize bitwise operations, and
    possibly adds/subtracts using bit-twiddling.  */
 #ifndef UNITS_PER_SIMD_WORD
-#define UNITS_PER_SIMD_WORD UNITS_PER_WORD
+#define UNITS_PER_SIMD_WORD(MODE) UNITS_PER_WORD
 #endif
 
 /* Determine whether __cxa_atexit, rather than atexit, is used to

diff --git a/gcc/doc/tm.texi b/gcc/doc/tm.texi
index 91448a71a42f595516b3818e3b023809d4eb1725..12a2740173bcfece661a692a2ca8d8377c214bf5 100644 (file)
--- a/gcc/doc/tm.texi
+++ b/gcc/doc/tm.texi
@@ -990,11 +990,11 @@ Minimum number of units in a word.  If this is undefined, the default is
 smallest value that @code{UNITS_PER_WORD} can have at run-time.
 @end defmac
 
-@defmac UNITS_PER_SIMD_WORD
-Number of units in the vectors that the vectorizer can produce.
-The default is equal to @code{UNITS_PER_WORD}, because the vectorizer
-can do some transformations even in absence of specialized @acronym{SIMD}
-hardware.
+@defmac UNITS_PER_SIMD_WORD (@var{mode})
+Number of units in the vectors that the vectorizer can produce for
+scalar mode @var{mode}.  The default is equal to @code{UNITS_PER_WORD},
+because the vectorizer can do some transformations even in absence of
+specialized @acronym{SIMD} hardware.
 @end defmac
 
 @defmac POINTER_SIZE

diff --git a/gcc/tree-vect-analyze.c b/gcc/tree-vect-analyze.c
index 66d83a5c32808d9becf32507b3bf1bde46d6ab80..18d7bb8bab108ff431e0b833d728fd0e567aeda2 100644 (file)
--- a/gcc/tree-vect-analyze.c
+++ b/gcc/tree-vect-analyze.c
@@ -1370,6 +1370,7 @@ vect_compute_data_ref_alignment (struct data_reference *dr)
   misalign = DR_INIT (dr);
   aligned_to = DR_ALIGNED_TO (dr);
   base_addr = DR_BASE_ADDRESS (dr);
+  vectype = STMT_VINFO_VECTYPE (stmt_info);
 
   /* In case the dataref is in an inner-loop of the loop that is being
      vectorized (LOOP), we use the base and misalignment information
@@ -1382,7 +1383,7 @@ vect_compute_data_ref_alignment (struct data_reference *dr)
       tree step = DR_STEP (dr);
       HOST_WIDE_INT dr_step = TREE_INT_CST_LOW (step);
     
-      if (dr_step % UNITS_PER_SIMD_WORD == 0)
+      if (dr_step % GET_MODE_SIZE (TYPE_MODE (vectype)) == 0)
         {
           if (vect_print_dump_info (REPORT_ALIGNMENT))
             fprintf (vect_dump, "inner step divides the vector-size.");
@@ -1399,7 +1400,6 @@ vect_compute_data_ref_alignment (struct data_reference *dr)
     }
 
   base = build_fold_indirect_ref (base_addr);
-  vectype = STMT_VINFO_VECTYPE (stmt_info);
   alignment = ssize_int (TYPE_ALIGN (vectype)/BITS_PER_UNIT);
 
   if ((aligned_to && tree_int_cst_compare (aligned_to, alignment) < 0)
@@ -1541,8 +1541,9 @@ vect_update_misalignment_for_peel (struct data_reference *dr,
       && known_alignment_for_access_p (dr_peel))
     {
       int misal = DR_MISALIGNMENT (dr);
+      tree vectype = STMT_VINFO_VECTYPE (stmt_info);
       misal += npeel * dr_size;
-      misal %= UNITS_PER_SIMD_WORD;
+      misal %= GET_MODE_SIZE (TYPE_MODE (vectype));
       SET_DR_MISALIGNMENT (dr, misal);
       return;
     }
@@ -1622,7 +1623,7 @@ vector_alignment_reachable_p (struct data_reference *dr)
       if (!known_alignment_for_access_p (dr))
        return false;
 
-      elem_size = UNITS_PER_SIMD_WORD / nelements;
+      elem_size = GET_MODE_SIZE (TYPE_MODE (vectype)) / nelements;
       mis_in_elements = DR_MISALIGNMENT (dr) / elem_size;
 
       if ((nelements - mis_in_elements) % DR_GROUP_SIZE (stmt_info))

diff --git a/gcc/tree-vect-transform.c b/gcc/tree-vect-transform.c
index 1f6a13b7bccf271798a2e81eb3bfa478874f83c5..72e87ef1e411750fc2af02d39bc70334e15bfbb9 100644 (file)
--- a/gcc/tree-vect-transform.c
+++ b/gcc/tree-vect-transform.c
@@ -5780,7 +5780,8 @@ vectorizable_load (tree stmt, block_stmt_iterator *bsi, tree *vec_stmt,
      nested within an outer-loop that is being vectorized.  */
 
   if (nested_in_vect_loop_p (loop, stmt)
-      && (TREE_INT_CST_LOW (DR_STEP (dr)) % UNITS_PER_SIMD_WORD != 0))
+      && (TREE_INT_CST_LOW (DR_STEP (dr))
+         % GET_MODE_SIZE (TYPE_MODE (vectype)) != 0))
     {
       gcc_assert (alignment_support_scheme != dr_explicit_realign_optimized);
       compute_in_loop = true;

diff --git a/gcc/tree-vectorizer.c b/gcc/tree-vectorizer.c
index d374a0640d2398a0db0ff2b72ebc8623a5a2f4a3..c513dda7652624f241c91e040f09b4094ba9349f 100644 (file)
--- a/gcc/tree-vectorizer.c
+++ b/gcc/tree-vectorizer.c
@@ -1806,12 +1806,12 @@ get_vectype_for_scalar_type (tree scalar_type)
   int nunits;
   tree vectype;
 
-  if (nbytes == 0 || nbytes >= UNITS_PER_SIMD_WORD)
+  if (nbytes == 0 || nbytes >= UNITS_PER_SIMD_WORD (inner_mode))
     return NULL_TREE;
 
-  /* FORNOW: Only a single vector size per target (UNITS_PER_SIMD_WORD)
+  /* FORNOW: Only a single vector size per mode (UNITS_PER_SIMD_WORD)
      is expected.  */
-  nunits = UNITS_PER_SIMD_WORD / nbytes;
+  nunits = UNITS_PER_SIMD_WORD (inner_mode) / nbytes;
 
   vectype = build_vector_type (scalar_type, nunits);
   if (vect_print_dump_info (REPORT_DETAILS))
@@ -1937,11 +1937,13 @@ vect_supportable_dr_alignment (struct data_reference *dr)
          && (!targetm.vectorize.builtin_mask_for_load
              || targetm.vectorize.builtin_mask_for_load ()))
        {
-           if (nested_in_vect_loop
-               && TREE_INT_CST_LOW (DR_STEP (dr)) != UNITS_PER_SIMD_WORD)
-             return dr_explicit_realign;
-           else
-             return dr_explicit_realign_optimized;
+         tree vectype = STMT_VINFO_VECTYPE (stmt_info);
+         if (nested_in_vect_loop
+             && (TREE_INT_CST_LOW (DR_STEP (dr))
+                 != GET_MODE_SIZE (TYPE_MODE (vectype))))
+           return dr_explicit_realign;
+         else
+           return dr_explicit_realign_optimized;
        }
 
       if (optab_handler (movmisalign_optab, mode)->insn_code !=