neon.md (float<mode><V_cvtto>2): New.

2011-12-23  Dmitry Plotnikov  <dplotnikov@ispras.ru>

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

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

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

	* 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_floatuint_cvt): Likewise.
	(check_effective_target_vect_floatint_cvt): Likewise.

From-SVN: r182657

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 508ce45..462a8d3 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2011-12-23  Dmitry Plotnikov  <dplotnikov@ispras.ru>
+
+       * config/arm/neon.md (float<mode><V_cvtto>2): New.
+       (floatuns<mode><V_cvtto>2): New.
+       (fix_trunc<mode><V_cvtto>2): New.
+       (fix_truncuns<mode><V_cvtto>2): New.
+       * config/arm/iterators.md (V_cvtto): New iterator.
+
 2011-12-23  Richard Guenther  <rguenther@suse.de>
 
        PR rtl-optimization/50396

diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
index 08874ff..1567264 100644 (file)
--- 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")])
 
+;; As above but in lower case.
+(define_mode_attr V_cvtto [(V2SI "v2sf") (V2SF "v2si")
+                           (V4SI "v4sf") (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 94e0a5f..d7caa37 100644 (file)
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -2932,6 +2932,50 @@
   DONE;
 })
 
+(define_insn "float<mode><V_cvtto>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_cvtto>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_cvtto>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_cvtto>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/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 86ff93e..fd1683c 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,17 @@
+2011-12-23  Dmitry Plotnikov  <dplotnikov@ispras.ru>
+
+       * gcc.target/arm/vect-vcvt.c: New test.
+       * gcc.target/arm/vect-vcvtq.c: New test.
+       
+       * gcc.dg/vect/fast-math-pr35982.c: Added vect_strided2 alternative
+       in final check.
+       
+       * 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_floatuint_cvt): Likewise.
+       (check_effective_target_vect_floatint_cvt): Likewise.
+
 2011-12-23  Richard Guenther  <rguenther@suse.de>
 
        PR rtl-optimization/50396

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 (file)
--- 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 (file)
index 0000000..f31d9bf
--- /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 (file)
index 0000000..f3f01c6
--- /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" } } */

diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index 1a54043..ebf69db 100644 (file)
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -1829,7 +1829,9 @@ 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
         }
     }
@@ -1865,7 +1867,9 @@ 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
         }
     }
@@ -1888,7 +1892,9 @@ 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
         }
     }
@@ -1908,7 +1914,9 @@ 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
         }
     }