Re: Ping: Make 128 bits the default vector size for NEON

2011-05-08 Thread Ira Rosen 
On 6 May 2011 13:29, Richard Earnshaw rearn...@arm.com wrote:

 On Thu, 2011-04-21 at 09:02 +0300, Ira Rosen wrote:
 http://gcc.gnu.org/ml/gcc-patches/2011-03/msg02172.html

 The last version:

 ChangeLog:

      * doc/invoke.texi (preferred-vector-size): Document.
      * params.h (PREFERRED_VECTOR_SIZE): Define.
      * config/arm/arm.c (arm_preferred_simd_mode): Use param
      PREFERRED_VECTOR_SIZE instead of
      TARGET_NEON_VECTORIZE_QUAD. Make 128 bits the default.
      (arm_autovectorize_vector_sizes): Likewise.
      * config/arm/arm.opt (NEON_VECTORIZE_QUAD): Add
      RejectNegative.
      * params.def (PARAM_PREFERRED_VECTOR_SIZE): Define.

 testsuite/ChangeLog:

      * lib/target-supports.exp (check_effective_target_vect_multiple_sizes):
      New procedure.
      (add_options_for_quad_vectors): Replace with ...
      (add_options_for_double_vectors): ... this.
      * gfortran.dg/vect/pr19049.f90: Expect more printings on targets that
      support multiple vector sizes since the vectorizer attempts to
      vectorize with both vector sizes.
      * gcc.dg/vect/slp-reduc-6.c, gcc.dg/vect/no-vfa-vect-79.c,
      gcc.dg/vect/no-vfa-vect-102a.c, gcc.dg/vect/vect-outer-1a.c,
      gcc.dg/vect/vect-outer-1b.c, gcc.dg/vect/vect-outer-2b.c,
      gcc.dg/vect/vect-outer-3a.c, gcc.dg/vect/no-vfa-vect-37.c,
      gcc.dg/vect/vect-outer-3b.c, gcc.dg/vect/no-vfa-vect-101.c,
      gcc.dg/vect/no-vfa-vect-102.c, gcc.dg/vect/vect-reduc-dot-s8b.c,
      gcc.dg/vect/vect-outer-1.c, gcc.dg/vect/vect-104.c: Likewise.
      * gcc.dg/vect/vect-16.c: Rename to...
      * gcc.dg/vect/no-fast-math-vect-16.c: ... this to ensure that it runs
      without -ffast-math.
      * gcc.dg/vect/vect-42.c: Run with 64 bit vectors if applicable.
      * gcc.dg/vect/vect-multitypes-6.c, gcc.dg/vect/vect-52.c,
      gcc.dg/vect/vect-54.c, gcc.dg/vect/vect-46.c, gcc.dg/vect/vect-48.c,
      gcc.dg/vect/vect-96.c, gcc.dg/vect/vect-multitypes-3.c,
      gcc.dg/vect/vect-40.c: Likewise.
      * gcc.dg/vect/vect-outer-5.c: Remove quad-vectors option as
      redundant.
      * gcc.dg/vect/vect-109.c, gcc.dg/vect/vect-peel-1.c,
      gcc.dg/vect/vect-peel-2.c, gcc.dg/vect/slp-25.c,
      gcc.dg/vect/vect-multitypes-1.c, gcc.dg/vect/slp-3.c,
      gcc.dg/vect/no-vfa-pr29145.c, gcc.dg/vect/vect-multitypes-4.c:
      Likewise.
      * gcc.dg/vect/vect.exp: Run no-fast-math-vect*.c tests with
      -fno-fast-math.

 Thanks,
 Ira

 +@item preferred-vector-size
 +Preferred vector size in bits for targets that support multiple vector sizes.
 +Invalid values are ignored.  The default is 128.
 +

 Shouldn't the preferred size be the largest size supported by the
 target?  Setting it to 128 might be OK today, but who knows what might
 happen in future?

How about ARM specific flag similar to -mprefer-avx128 (not tested)?

Thanks,
Ira

ChangeLog:

 * config/arm/arm.c (arm_preferred_simd_mode): Use
  flag_prefer_neon_double instead of
  TARGET_NEON_VECTORIZE_QUAD. Make 128 bits the default.
  (arm_autovectorize_vector_sizes): Likewise.
  * config/arm/arm.opt (NEON_VECTORIZE_QUAD): Add
  RejectNegative.
  (mprefer-neon-double): New flag.

(the testsuite part is unchanged).


Index: config/arm/arm.c
===
--- config/arm/arm.c(revision 173546)
+++ config/arm/arm.c(working copy)
@@ -22482,16 +22482,16 @@ arm_preferred_simd_mode (enum machine_mode mode)
 switch (mode)
   {
   case SFmode:
-   return TARGET_NEON_VECTORIZE_QUAD ? V4SFmode : V2SFmode;
-  case SImode:
-   return TARGET_NEON_VECTORIZE_QUAD ? V4SImode : V2SImode;
-  case HImode:
-   return TARGET_NEON_VECTORIZE_QUAD ? V8HImode : V4HImode;
-  case QImode:
-   return TARGET_NEON_VECTORIZE_QUAD ? V16QImode : V8QImode;
-  case DImode:
-   if (TARGET_NEON_VECTORIZE_QUAD)
- return V2DImode;
+return flag_prefer_neon_double ? V2SFmode : V4SFmode;
+   case SImode:
+return flag_prefer_neon_double ? V2SImode : V4SImode;
+   case HImode:
+return flag_prefer_neon_double ? V4HImode : V8HImode;
+   case QImode:
+return flag_prefer_neon_double ? V8QImode : V16QImode;
+   case DImode:
+if (!flag_prefer_neon_double)
+  return V2DImode;
break;

   default:;
@@ -23722,7 +23722,7 @@ arm_expand_sync (enum machine_mode mode,
 static unsigned int
 arm_autovectorize_vector_sizes (void)
 {
-  return TARGET_NEON_VECTORIZE_QUAD ? 16 | 8 : 0;
+  return (!flag_prefer_neon_double) ? 16 | 8 : 0;
 }

 static bool
Index: config/arm/arm.opt
===
--- config/arm/arm.opt  (revision 173546)
+++ config/arm/arm.opt  (working copy)
@@ -160,9 +160,13 @@ Target Report RejectNegative Mask(LITTLE_WORDS)
 Assume big endian bytes, little endian words

 mvectorize-with-neon-quad
-Target Report Mask(NEON_VECTORIZE_QUAD)
+Target Report

Re: Ping: Make 128 bits the default vector size for NEON

2011-05-08 Thread Gerald Pfeifer 
On Sun, 8 May 2011, Ira Rosen wrote:
 How about ARM specific flag similar to -mprefer-avx128 (not tested)?

If this goes in, please also update gcc-4.7/changes.html.

Thanks,
Gerald

Re: Ping: Make 128 bits the default vector size for NEON

2011-05-08 Thread Ira Rosen 
On 8 May 2011 15:02, Gerald Pfeifer ger...@pfeifer.com wrote:
 On Sun, 8 May 2011, Ira Rosen wrote:
 How about ARM specific flag similar to -mprefer-avx128 (not tested)?

 If this goes in, please also update gcc-4.7/changes.html.

Do you mean that the new flag should be documented?
This patch http://gcc.gnu.org/ml/gcc-patches/2011-04/msg00318.html
updates about the change of the default vector size.

Thanks,
Ira


 Thanks,
 Gerald

Re: Ping: Make 128 bits the default vector size for NEON

2011-05-08 Thread Gerald Pfeifer 
On Sun, 8 May 2011, Ira Rosen wrote:
 If this goes in, please also update gcc-4.7/changes.html.
 Do you mean that the new flag should be documented?

Yes, as we're adding new flags, it's (nearly?) always a good idea to
document them as part of the release notes.

 This patch http://gcc.gnu.org/ml/gcc-patches/2011-04/msg00318.html
 updates about the change of the default vector size.

That one I acked, right?

Gerald

Re: Ping: Make 128 bits the default vector size for NEON

2011-05-08 Thread Ira Rosen 


Gerald Pfeifer ger...@pfeifer.com wrote on 09/05/2011 01:53:35 AM:


 On Sun, 8 May 2011, Ira Rosen wrote:
  If this goes in, please also update gcc-4.7/changes.html.
  Do you mean that the new flag should be documented?

 Yes, as we're adding new flags, it's (nearly?) always a good idea to
 document them as part of the release notes.

OK.


  This patch http://gcc.gnu.org/ml/gcc-patches/2011-04/msg00318.html
  updates about the change of the default vector size.

 That one I acked, right?

Yes.

Thanks,
Ira


 Gerald

Re: Ping: Make 128 bits the default vector size for NEON

2011-05-06 Thread Richard Earnshaw 

On Thu, 2011-04-21 at 09:02 +0300, Ira Rosen wrote:
 http://gcc.gnu.org/ml/gcc-patches/2011-03/msg02172.html
 
 The last version:
 
 ChangeLog:
 
  * doc/invoke.texi (preferred-vector-size): Document.
  * params.h (PREFERRED_VECTOR_SIZE): Define.
  * config/arm/arm.c (arm_preferred_simd_mode): Use param
  PREFERRED_VECTOR_SIZE instead of
  TARGET_NEON_VECTORIZE_QUAD. Make 128 bits the default.
  (arm_autovectorize_vector_sizes): Likewise.
  * config/arm/arm.opt (NEON_VECTORIZE_QUAD): Add
  RejectNegative.
  * params.def (PARAM_PREFERRED_VECTOR_SIZE): Define.
 
 testsuite/ChangeLog:
 
  * lib/target-supports.exp (check_effective_target_vect_multiple_sizes):
  New procedure.
  (add_options_for_quad_vectors): Replace with ...
  (add_options_for_double_vectors): ... this.
  * gfortran.dg/vect/pr19049.f90: Expect more printings on targets that
  support multiple vector sizes since the vectorizer attempts to
  vectorize with both vector sizes.
  * gcc.dg/vect/slp-reduc-6.c, gcc.dg/vect/no-vfa-vect-79.c,
  gcc.dg/vect/no-vfa-vect-102a.c, gcc.dg/vect/vect-outer-1a.c,
  gcc.dg/vect/vect-outer-1b.c, gcc.dg/vect/vect-outer-2b.c,
  gcc.dg/vect/vect-outer-3a.c, gcc.dg/vect/no-vfa-vect-37.c,
  gcc.dg/vect/vect-outer-3b.c, gcc.dg/vect/no-vfa-vect-101.c,
  gcc.dg/vect/no-vfa-vect-102.c, gcc.dg/vect/vect-reduc-dot-s8b.c,
  gcc.dg/vect/vect-outer-1.c, gcc.dg/vect/vect-104.c: Likewise.
  * gcc.dg/vect/vect-16.c: Rename to...
  * gcc.dg/vect/no-fast-math-vect-16.c: ... this to ensure that it runs
  without -ffast-math.
  * gcc.dg/vect/vect-42.c: Run with 64 bit vectors if applicable.
  * gcc.dg/vect/vect-multitypes-6.c, gcc.dg/vect/vect-52.c,
  gcc.dg/vect/vect-54.c, gcc.dg/vect/vect-46.c, gcc.dg/vect/vect-48.c,
  gcc.dg/vect/vect-96.c, gcc.dg/vect/vect-multitypes-3.c,
  gcc.dg/vect/vect-40.c: Likewise.
  * gcc.dg/vect/vect-outer-5.c: Remove quad-vectors option as
  redundant.
  * gcc.dg/vect/vect-109.c, gcc.dg/vect/vect-peel-1.c,
  gcc.dg/vect/vect-peel-2.c, gcc.dg/vect/slp-25.c,
  gcc.dg/vect/vect-multitypes-1.c, gcc.dg/vect/slp-3.c,
  gcc.dg/vect/no-vfa-pr29145.c, gcc.dg/vect/vect-multitypes-4.c:
  Likewise.
  * gcc.dg/vect/vect.exp: Run no-fast-math-vect*.c tests with
  -fno-fast-math.
 
 Thanks,
 Ira

+@item preferred-vector-size
+Preferred vector size in bits for targets that support multiple vector sizes.
+Invalid values are ignored.  The default is 128.
+

Shouldn't the preferred size be the largest size supported by the
target?  Setting it to 128 might be OK today, but who knows what might
happen in future?  

R.

Ping: Make 128 bits the default vector size for NEON

2011-04-21 Thread Ira Rosen 
http://gcc.gnu.org/ml/gcc-patches/2011-03/msg02172.html

The last version:

ChangeLog:

 * doc/invoke.texi (preferred-vector-size): Document.
 * params.h (PREFERRED_VECTOR_SIZE): Define.
 * config/arm/arm.c (arm_preferred_simd_mode): Use param
 PREFERRED_VECTOR_SIZE instead of
 TARGET_NEON_VECTORIZE_QUAD. Make 128 bits the default.
 (arm_autovectorize_vector_sizes): Likewise.
 * config/arm/arm.opt (NEON_VECTORIZE_QUAD): Add
 RejectNegative.
 * params.def (PARAM_PREFERRED_VECTOR_SIZE): Define.

testsuite/ChangeLog:

 * lib/target-supports.exp (check_effective_target_vect_multiple_sizes):
 New procedure.
 (add_options_for_quad_vectors): Replace with ...
 (add_options_for_double_vectors): ... this.
 * gfortran.dg/vect/pr19049.f90: Expect more printings on targets that
 support multiple vector sizes since the vectorizer attempts to
 vectorize with both vector sizes.
 * gcc.dg/vect/slp-reduc-6.c, gcc.dg/vect/no-vfa-vect-79.c,
 gcc.dg/vect/no-vfa-vect-102a.c, gcc.dg/vect/vect-outer-1a.c,
 gcc.dg/vect/vect-outer-1b.c, gcc.dg/vect/vect-outer-2b.c,
 gcc.dg/vect/vect-outer-3a.c, gcc.dg/vect/no-vfa-vect-37.c,
 gcc.dg/vect/vect-outer-3b.c, gcc.dg/vect/no-vfa-vect-101.c,
 gcc.dg/vect/no-vfa-vect-102.c, gcc.dg/vect/vect-reduc-dot-s8b.c,
 gcc.dg/vect/vect-outer-1.c, gcc.dg/vect/vect-104.c: Likewise.
 * gcc.dg/vect/vect-16.c: Rename to...
 * gcc.dg/vect/no-fast-math-vect-16.c: ... this to ensure that it runs
 without -ffast-math.
 * gcc.dg/vect/vect-42.c: Run with 64 bit vectors if applicable.
 * gcc.dg/vect/vect-multitypes-6.c, gcc.dg/vect/vect-52.c,
 gcc.dg/vect/vect-54.c, gcc.dg/vect/vect-46.c, gcc.dg/vect/vect-48.c,
 gcc.dg/vect/vect-96.c, gcc.dg/vect/vect-multitypes-3.c,
 gcc.dg/vect/vect-40.c: Likewise.
 * gcc.dg/vect/vect-outer-5.c: Remove quad-vectors option as
 redundant.
 * gcc.dg/vect/vect-109.c, gcc.dg/vect/vect-peel-1.c,
 gcc.dg/vect/vect-peel-2.c, gcc.dg/vect/slp-25.c,
 gcc.dg/vect/vect-multitypes-1.c, gcc.dg/vect/slp-3.c,
 gcc.dg/vect/no-vfa-pr29145.c, gcc.dg/vect/vect-multitypes-4.c:
 Likewise.
 * gcc.dg/vect/vect.exp: Run no-fast-math-vect*.c tests with
 -fno-fast-math.

Thanks,
Ira
Index: doc/invoke.texi
===
--- doc/invoke.texi (revision 171723)
+++ doc/invoke.texi (working copy)
@@ -8874,6 +8874,10 @@ The maximum number of conditional stores paires th
 if either vectorization (@option{-ftree-vectorize}) or if-conversion
 (@option{-ftree-loop-if-convert}) is disabled.  The default is 2.
 
+@item preferred-vector-size
+Preferred vector size in bits for targets that support multiple vector sizes.
+Invalid values are ignored.  The default is 128.
+
 @end table
 @end table
 
Index: params.h
===
--- params.h(revision 171723)
+++ params.h(working copy)
@@ -204,6 +204,8 @@ extern void init_param_values (int *params);
   PARAM_VALUE (PARAM_PREFETCH_MIN_INSN_TO_MEM_RATIO)
 #define MIN_NONDEBUG_INSN_UID \
   PARAM_VALUE (PARAM_MIN_NONDEBUG_INSN_UID)
+#define PREFERRED_VECTOR_SIZE \
+  PARAM_VALUE (PARAM_PREFERRED_VECTOR_SIZE)
 #define MAX_STORES_TO_SINK \
   PARAM_VALUE (PARAM_MAX_STORES_TO_SINK)
 #endif /* ! GCC_PARAMS_H */
Index: testsuite/lib/target-supports.exp
===
--- testsuite/lib/target-supports.exp   (revision 171723)
+++ testsuite/lib/target-supports.exp   (working copy)
@@ -3203,6 +3203,24 @@ proc check_effective_target_vect_strided_wide { }
 return $et_vect_strided_wide_saved
 }
 
+# Return 1 if the target supports multiple vector sizes
+
+proc check_effective_target_vect_multiple_sizes { } {
+global et_vect_multiple_sizes
+
+if [info exists et_vect_multiple_sizes_saved] {
+verbose check_effective_target_vect_multiple_sizes: using cached 
result 2
+} else {
+set et_vect_multiple_sizes_saved 0
+if { ([istarget arm*-*-*]  [check_effective_target_arm_neon]) } {
+   set et_vect_multiple_sizes_saved 1
+}
+}
+
+verbose check_effective_target_vect_multiple_sizes: returning 
$et_vect_multiple_sizes_saved 2
+return $et_vect_multiple_sizes_saved
+}
+
 # Return 1 if the target supports section-anchors
 
 proc check_effective_target_section_anchors { } {
@@ -3585,9 +3603,9 @@ proc add_options_for_bind_pic_locally { flags } {
 
 # Add to FLAGS the flags needed to enable 128-bit vectors.
 
-proc add_options_for_quad_vectors { flags } {
+proc add_options_for_double_vectors { flags } {
 if [is-effective-target arm_neon_ok] {
-   return $flags -mvectorize-with-neon-quad
+   return $flags --param preferred-vector-size=64
 }
 
 return $flags
Index: testsuite/gfortran.dg/vect/pr19049.f90
===
---