Re: [PATCH][PING] Vectorize conversions directly

[Dmitry Plotnikov <dplotnikov@ispras.ru>]

[-- Attachment #1: Type: text/plain, Size: 1487 bytes --]

Here is the patch with iterators for instructions and neon_type 
attributes.  Also fast-math-pr35982.c is changed according to Ira's 
comment.  I will look at integration with patterns for neon intrinsics 
later.

2011-12-22  Dmitry Plotnikov <dplotnikov@ispras.ru>

gcc/
     * tree-cfg.c (verify_gimple_assign_unary): Allow vector conversions.
     * optabs.c (supportable_convert_operation): New function.
     * optabs.h (supportable_convert_operation): New prototype.
     * tree-vect-stmts.c (vectorizable_conversion): Change condition
       and behavior for NONE modifier case.
     * tree.h (VECTOR_INTEGER_TYPE_P): New macro.

gcc/config/arm/
     * neon.md (float<mode><V_CVTTOF>2): New.
       (floatuns<mode><V_CVTTOF>2): New.
       (fix_trunc<mode><V_CVTTOI>2): New.
       (fix_truncuns<mode><V_CVTTOI>2): New.
     * iterators.md (V_CVTTOF): New iterator.
       (V_CVTTOI): New iterator.

gcc/testsuite/
     * gcc.target/arm/vect-vcvt.c: New test.
     * gcc.target/arm/vect-vcvtq.c: New test.

gcc/testsuite/gcc.dg/vect/
     * fast-math-pr35982.c: Added vect_strided2 alternative in final
       check.

gcc/testsuite/lib/
     * target-supports.exp (check_effective_target_vect_intfloat_cvt):
       True for ARM NEON.
       (check_effective_target_vect_uintfloat_cvt): Likewise.
       (check_effective_target_vect_intfloat_cvt): Likewise.
       (check_effective_target_vect_floatuint_cvt): Likewise.
       (check_effective_target_vect_floatint_cvt): Likewise.

[-- Attachment #2: vect-conv1.patch --]
[-- Type: text/x-patch, Size: 15568 bytes --]

diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
index 85dd641..de4340c 100644
--- a/gcc/config/arm/iterators.md
+++ b/gcc/config/arm/iterators.md
@@ -197,6 +197,10 @@
 (define_mode_attr V_CVTTO [(V2SI "V2SF") (V2SF "V2SI")
                (V4SI "V4SF") (V4SF "V4SI")])
 
+(define_mode_attr V_CVTTOF [(V2SI "v2sf") (V4SI "v4sf")])
+
+(define_mode_attr V_CVTTOI [(V2SF "v2si") (V4SF "v4si")])
+
 ;; Define element mode for each vector mode.
 (define_mode_attr V_elem [(V8QI "QI") (V16QI "QI")
               (V4HI "HI") (V8HI "HI")
diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index ea09da2..dc715ed 100644
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -2932,11 +2932,55 @@
   DONE;
 })
 
+(define_insn "float<mode><V_CVTTOF>2"
+  [(set (match_operand:<V_CVTTO> 0 "s_register_operand" "=w")
+       (float:<V_CVTTO> (match_operand:VCVTI 1 "s_register_operand" "w")))]
+  "TARGET_NEON && !flag_rounding_math"
+  "vcvt.f32.s32\t%<V_reg>0, %<V_reg>1"
+  [(set (attr "neon_type")
+     (if_then_else (match_test "<Is_d_reg>")
+                   (const_string "neon_fp_vadd_ddd_vabs_dd")
+                   (const_string "neon_fp_vadd_qqq_vabs_qq")))]
+)
+
+(define_insn "floatuns<mode><V_CVTTOF>2"
+  [(set (match_operand:<V_CVTTO> 0 "s_register_operand" "=w")
+       (unsigned_float:<V_CVTTO> (match_operand:VCVTI 1 "s_register_operand" "w")))] 
+  "TARGET_NEON && !flag_rounding_math"
+  "vcvt.f32.u32\t%<V_reg>0, %<V_reg>1"
+  [(set (attr "neon_type")
+     (if_then_else (match_test "<Is_d_reg>")
+                   (const_string "neon_fp_vadd_ddd_vabs_dd")
+                   (const_string "neon_fp_vadd_qqq_vabs_qq")))]
+)
+
+(define_insn "fix_trunc<mode><V_CVTTOI>2"
+  [(set (match_operand:<V_CVTTO> 0 "s_register_operand" "=w")
+        (fix:<V_CVTTO> (match_operand:VCVTF 1 "s_register_operand" "w")))]
+  "TARGET_NEON"
+  "vcvt.s32.f32\t%<V_reg>0, %<V_reg>1"
+  [(set (attr "neon_type")
+     (if_then_else (match_test "<Is_d_reg>")
+                   (const_string "neon_fp_vadd_ddd_vabs_dd")
+                   (const_string "neon_fp_vadd_qqq_vabs_qq")))]
+)
+
+(define_insn "fixuns_trunc<mode><V_CVTTOI>2"
+  [(set (match_operand:<V_CVTTO> 0 "s_register_operand" "=w")
+        (unsigned_fix:<V_CVTTO> (match_operand:VCVTF 1 "s_register_operand" "w")))]
+  "TARGET_NEON"
+  "vcvt.u32.f32\t%<V_reg>0, %<V_reg>1"
+  [(set (attr "neon_type")
+     (if_then_else (match_test "<Is_d_reg>")
+                   (const_string "neon_fp_vadd_ddd_vabs_dd")
+                   (const_string "neon_fp_vadd_qqq_vabs_qq")))]
+)
+
 (define_insn "neon_vcvt<mode>"
   [(set (match_operand:<V_CVTTO> 0 "s_register_operand" "=w")
	(unspec:<V_CVTTO> [(match_operand:VCVTF 1 "s_register_operand" "w")
diff --git a/gcc/optabs.c b/gcc/optabs.c
index a373d7a..e504284 100644
--- a/gcc/optabs.c
+++ b/gcc/optabs.c
@@ -4792,6 +4792,60 @@ can_float_p (enum machine_mode fltmode, enum machine_mode fixmode,
   tab = unsignedp ? ufloat_optab : sfloat_optab;
   return convert_optab_handler (tab, fltmode, fixmode);
 }
+
+/* Function supportable_convert_operation
+
+   Check whether an operation represented by the code CODE is a
+   convert operation that is supported by the target platform in
+   vector form (i.e., when operating on arguments of type VECTYPE_IN
+   producing a result of type VECTYPE_OUT).
+   
+   Convert operations we currently support directly are FIX_TRUNC and FLOAT.
+   This function checks if these operations are supported
+   by the target platform either directly (via vector tree-codes), or via
+   target builtins.
+   
+   Output:
+   - CODE1 is code of vector operation to be used when
+   vectorizing the operation, if available.
+   - DECL is decl of target builtin functions to be used
+   when vectorizing the operation, if available.  In this case,
+   CODE1 is CALL_EXPR.  */
+
+bool
+supportable_convert_operation (enum tree_code code,
+                                    tree vectype_out, tree vectype_in,
+                                    tree *decl, enum tree_code *code1)
+{
+  enum machine_mode m1,m2;
+  int truncp;
+
+  m1 = TYPE_MODE (vectype_out);
+  m2 = TYPE_MODE (vectype_in);
+
+  /* First check if we can done conversion directly.  */
+  if ((code == FIX_TRUNC_EXPR 
+       && can_fix_p (m1,m2,TYPE_UNSIGNED (vectype_out), &truncp) 
+          != CODE_FOR_nothing)
+      || (code == FLOAT_EXPR
+          && can_float_p (m1,m2,TYPE_UNSIGNED (vectype_in))
+	     != CODE_FOR_nothing))
+    {
+      *code1 = code;
+      return true;
+    }
+
+  /* Now check for builtin.  */
+  if (targetm.vectorize.builtin_conversion
+      && targetm.vectorize.builtin_conversion (code, vectype_out, vectype_in))
+    {
+      *code1 = CALL_EXPR;
+      *decl = targetm.vectorize.builtin_conversion (code, vectype_out, vectype_in);
+      return true;
+    }
+  return false;
+}
+
 \f
 /* Generate code to convert FROM to floating point
    and store in TO.  FROM must be fixed point and not VOIDmode.
diff --git a/gcc/optabs.h b/gcc/optabs.h
index 926d21f..4747ab6 100644
--- a/gcc/optabs.h
+++ b/gcc/optabs.h
@@ -873,6 +873,12 @@ extern void expand_float (rtx, rtx, int);
 /* Return the insn_code for a FLOAT_EXPR.  */
 enum insn_code can_float_p (enum machine_mode, enum machine_mode, int);
 
+/* Check whether an operation represented by the code CODE is a
+   convert operation that is supported by the target platform in
+   vector form */
+bool supportable_convert_operation (enum tree_code, tree, tree, tree *, 
+                                    enum tree_code *);
+
 /* Generate code for a FIX_EXPR.  */
 extern void expand_fix (rtx, rtx, int);
 
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index 77f8a00..d6c9180 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -1806,7 +1806,9 @@ proc check_effective_target_vect_intfloat_cvt { } {
         if { [istarget i?86-*-*]
               || ([istarget powerpc*-*-*]
                    && ![istarget powerpc-*-linux*paired*])
-              || [istarget x86_64-*-*] } {
+              || [istarget x86_64-*-*] 
+              || ([istarget arm*-*-*]
+                  && [check_effective_target_arm_neon_ok])} {
            set et_vect_intfloat_cvt_saved 1
         }
     }
@@ -1842,7 +1844,9 @@ proc check_effective_target_vect_uintfloat_cvt { } {
         if { [istarget i?86-*-*]
 	      || ([istarget powerpc*-*-*]
 		  && ![istarget powerpc-*-linux*paired*])
-	      || [istarget x86_64-*-*] } {
+	      || [istarget x86_64-*-*] 
+              || ([istarget arm*-*-*]
+                  && [check_effective_target_arm_neon_ok])} {
            set et_vect_uintfloat_cvt_saved 1
         }
     }
@@ -1865,7 +1869,9 @@ proc check_effective_target_vect_floatint_cvt { } {
         if { [istarget i?86-*-*]
               || ([istarget powerpc*-*-*]
                    && ![istarget powerpc-*-linux*paired*])
-              || [istarget x86_64-*-*] } {
+              || [istarget x86_64-*-*]
+              || ([istarget arm*-*-*]
+                  && [check_effective_target_arm_neon_ok])} {
            set et_vect_floatint_cvt_saved 1
         }
     }
@@ -1885,7 +1891,9 @@ proc check_effective_target_vect_floatuint_cvt { } {
     } else {
         set et_vect_floatuint_cvt_saved 0
         if { ([istarget powerpc*-*-*]
-	      && ![istarget powerpc-*-linux*paired*]) } {
+	      && ![istarget powerpc-*-linux*paired*]) 
+             || ([istarget arm*-*-*]
+                 && [check_effective_target_arm_neon_ok])} {
            set et_vect_floatuint_cvt_saved 1
         }
     }
diff --git a/gcc/tree-cfg.c b/gcc/tree-cfg.c
index bcf71b9..1f3f10a 100644
--- a/gcc/tree-cfg.c
+++ b/gcc/tree-cfg.c
@@ -3342,7 +3342,9 @@ verify_gimple_assign_unary (gimple stmt)
 
     case FLOAT_EXPR:
       {
-	if (!INTEGRAL_TYPE_P (rhs1_type) || !SCALAR_FLOAT_TYPE_P (lhs_type))
+	if ((!INTEGRAL_TYPE_P (rhs1_type) || !SCALAR_FLOAT_TYPE_P (lhs_type))
+	    && (!VECTOR_INTEGER_TYPE_P (rhs1_type)
+	        || !VECTOR_FLOAT_TYPE_P(lhs_type)))
 	  {
 	    error ("invalid types in conversion to floating point");
 	    debug_generic_expr (lhs_type);
@@ -3355,7 +3357,9 @@ verify_gimple_assign_unary (gimple stmt)
 
     case FIX_TRUNC_EXPR:
       {
-	if (!INTEGRAL_TYPE_P (lhs_type) || !SCALAR_FLOAT_TYPE_P (rhs1_type))
+        if ((!INTEGRAL_TYPE_P (lhs_type) || !SCALAR_FLOAT_TYPE_P (rhs1_type))
+            && (!VECTOR_INTEGER_TYPE_P (lhs_type)
+                || !VECTOR_FLOAT_TYPE_P(rhs1_type)))
 	  {
 	    error ("invalid types in conversion to integer");
 	    debug_generic_expr (lhs_type);
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index d986ff8..2dbae9a 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -1821,7 +1821,6 @@ vect_gen_widened_results_half (enum tree_code code,
   return new_stmt;
 }
 
-
 /* Check if STMT performs a conversion operation, that can be vectorized.
    If VEC_STMT is also passed, vectorize the STMT: create a vectorized
    stmt to replace it, put it in VEC_STMT, and insert it at BSI.
@@ -1850,7 +1849,6 @@ vectorizable_conversion (gimple stmt, gimple_stmt_iterator *gsi,
   tree vectype_out, vectype_in;
   int ncopies, j;
   tree rhs_type;
-  tree builtin_decl;
   enum { NARROW, NONE, WIDEN } modifier;
   int i;
   VEC(tree,heap) *vec_oprnds0 = NULL;
@@ -1939,7 +1937,7 @@ vectorizable_conversion (gimple stmt, gimple_stmt_iterator *gsi,
 
   /* Supportable by target?  */
   if ((modifier == NONE
-       && !targetm.vectorize.builtin_conversion (code, vectype_out, vectype_in))
+       && !supportable_convert_operation (code, vectype_out, vectype_in, &decl1, &code1))
       || (modifier == WIDEN
 	  && !supportable_widening_operation (code, stmt,
 					      vectype_out, vectype_in,
@@ -1989,19 +1987,28 @@ vectorizable_conversion (gimple stmt, gimple_stmt_iterator *gsi,
 	  else
 	    vect_get_vec_defs_for_stmt_copy (dt, &vec_oprnds0, NULL);
 
-	  builtin_decl =
-	    targetm.vectorize.builtin_conversion (code,
-						  vectype_out, vectype_in);
 	  FOR_EACH_VEC_ELT (tree, vec_oprnds0, i, vop0)
-	    {
-	      /* Arguments are ready. create the new vector stmt.  */
-	      new_stmt = gimple_build_call (builtin_decl, 1, vop0);
-	      new_temp = make_ssa_name (vec_dest, new_stmt);
-	      gimple_call_set_lhs (new_stmt, new_temp);
-	      vect_finish_stmt_generation (stmt, new_stmt, gsi);
-	      if (slp_node)
-		VEC_quick_push (gimple, SLP_TREE_VEC_STMTS (slp_node), new_stmt);
-	    }
+          {
+            /* Arguments are ready, create the new vector stmt.  */
+            if (code1 == CALL_EXPR)
+              {
+                new_stmt = gimple_build_call (decl1, 1, vop0);
+                new_temp = make_ssa_name (vec_dest, new_stmt);
+                gimple_call_set_lhs (new_stmt, new_temp);
+              }
+            else
+              {
+                gcc_assert (TREE_CODE_LENGTH (code) == unary_op);
+                new_stmt = gimple_build_assign_with_ops (code, vec_dest, vop0,
+                                                        NULL);
+                new_temp = make_ssa_name (vec_dest, new_stmt);
+                gimple_assign_set_lhs (new_stmt, new_temp);
+              }
+
+            vect_finish_stmt_generation (stmt, new_stmt, gsi);
+            if (slp_node)
+              VEC_quick_push (gimple, SLP_TREE_VEC_STMTS (slp_node), new_stmt);
+          }
 
 	  if (j == 0)
 	    STMT_VINFO_VEC_STMT (stmt_info) = *vec_stmt = new_stmt;
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index f22add6..d1d1835 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -818,6 +818,9 @@ extern bool vect_transform_stmt (gimple, gimple_stmt_iterator *,
                                  bool *, slp_tree, slp_instance);
 extern void vect_remove_stores (gimple);
 extern bool vect_analyze_stmt (gimple, bool *, slp_tree);
+extern bool supportable_convert_operation (enum tree_code, tree, tree,
+                                          tree *, enum tree_code *);
+
 extern bool vectorizable_condition (gimple, gimple_stmt_iterator *, gimple *,
                                     tree, int);
 extern void vect_get_load_cost (struct data_reference *, int, bool,
diff --git a/gcc/tree.h b/gcc/tree.h
index 18fdd07..537e54b 100644
--- a/gcc/tree.h
+++ b/gcc/tree.h
@@ -1120,6 +1120,13 @@ extern void omp_clause_range_check_failed (const_tree, const char *, int,
   (TREE_CODE (TYPE) == COMPLEX_TYPE	\
    && TREE_CODE (TREE_TYPE (TYPE)) == REAL_TYPE)
 
+/* Nonzero if TYPE represents a vector integer type.  */
+                
+#define VECTOR_INTEGER_TYPE_P(TYPE)                   \
+             (TREE_CODE (TYPE) == VECTOR_TYPE      \
+                 && TREE_CODE (TREE_TYPE (TYPE)) == INTEGER_TYPE)
+
+
 /* Nonzero if TYPE represents a vector floating-point type.  */
 
 #define VECTOR_FLOAT_TYPE_P(TYPE)	\
diff --git a/gcc/testsuite/gcc.dg/vect/fast-math-pr35982.c b/gcc/testsuite/gcc.dg/vect/fast-math-pr35982.c
index d839406..0d4c43a 100644
--- a/gcc/testsuite/gcc.dg/vect/fast-math-pr35982.c
+++ b/gcc/testsuite/gcc.dg/vect/fast-math-pr35982.c
@@ -20,7 +20,7 @@ float method2_int16 (struct mem *mem)
   return avg;
 }
 
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_extract_even_odd  } } } */
-/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 1 "vect" { xfail vect_extract_even_odd  } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_extract_even_odd || vect_strided2 } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 1 "vect" { xfail vect_extract_even_odd || vect_strided2 } } } */
 /* { dg-final { cleanup-tree-dump "vect" } } */
 
diff --git a/gcc/testsuite/gcc.target/arm/neon/vect-vcvt.c b/gcc/testsuite/gcc.target/arm/neon/vect-vcvt.c
new file mode 100644
index 0000000..f33206c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/neon/vect-vcvt.c
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -mvectorize-with-neon-double" } */
+/* { dg-add-options arm_neon } */
+
+#define N 32
+
+int ib[N] = {0,3,6,9,12,15,18,21,24,27,30,33,36,39,42,45,0,3,6,9,12,15,18,21,24,27,30,33,36,39,42,45};
+float fa[N];
+int ia[N];
+
+int convert()
+{
+  int i;
+
+  /* int -> float */
+  for (i = 0; i < N; i++)
+    fa[i] = (float) ib[i];
+
+  /* float -> int */
+  for (i = 0; i < N; i++)
+    ia[i] = (int) fa[i];
+
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
diff --git a/gcc/testsuite/gcc.target/arm/neon/vect-vcvtq.c b/gcc/testsuite/gcc.target/arm/neon/vect-vcvtq.c
new file mode 100644
index 0000000..3412cf2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/neon/vect-vcvtq.c
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details" } */
+/* { dg-add-options arm_neon } */
+
+#define N 32
+
+int ib[N] = {0,3,6,9,12,15,18,21,24,27,30,33,36,39,42,45,0,3,6,9,12,15,18,21,24,27,30,33,36,39,42,45};
+float fa[N];
+int ia[N];
+
+int convert()
+{
+  int i;
+
+  /* int -> float */
+  for (i = 0; i < N; i++)
+    fa[i] = (float) ib[i];
+
+  /* float -> int */
+  for (i = 0; i < N; i++)
+    ia[i] = (int) fa[i];
+
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */