[PATCH] arm: Fix iwmmxt shift and logical intrinsics (PR 35294).

[PATCH] arm: Fix iwmmxt shift and logical intrinsics (PR 35294).

[Matt Turner]

PR 36798 and 36966 are duplicates.

2012-02-24  Matt Turner  <mattst88@gmail.com>

	PR target/35294
	* config/arm/arm.c (arm_expand_builtin): Wire up missing
	intrinsics.
---
 gcc/config/arm/arm.c |   62 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 61 insertions(+), 1 deletions(-)

diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 7f0dc6b..f5935d6 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -20502,7 +20502,8 @@ arm_expand_binop_builtin (enum insn_code icode,
       || ! (*insn_data[icode].operand[0].predicate) (target, tmode))
     target = gen_reg_rtx (tmode);
 
-  gcc_assert (GET_MODE (op0) == mode0 && GET_MODE (op1) == mode1);
+  gcc_assert ((GET_MODE (op0) == mode0 || GET_MODE (op0) == VOIDmode)
+             && (GET_MODE (op1) == mode1 || GET_MODE (op1) == VOIDmode));
 
   if (! (*insn_data[icode].operand[1].predicate) (op0, mode0))
     op0 = copy_to_mode_reg (mode0, op0);
@@ -21181,6 +21182,65 @@ arm_expand_builtin (tree exp,
       emit_insn (pat);
       return target;
 
+    case ARM_BUILTIN_WSLLH:
+    case ARM_BUILTIN_WSLLHI:
+    case ARM_BUILTIN_WSLLW:
+    case ARM_BUILTIN_WSLLWI:
+    case ARM_BUILTIN_WSLLD:
+    case ARM_BUILTIN_WSLLDI:
+    case ARM_BUILTIN_WSRAH:
+    case ARM_BUILTIN_WSRAHI:
+    case ARM_BUILTIN_WSRAW:
+    case ARM_BUILTIN_WSRAWI:
+    case ARM_BUILTIN_WSRAD:
+    case ARM_BUILTIN_WSRADI:
+    case ARM_BUILTIN_WSRLH:
+    case ARM_BUILTIN_WSRLHI:
+    case ARM_BUILTIN_WSRLW:
+    case ARM_BUILTIN_WSRLWI:
+    case ARM_BUILTIN_WSRLD:
+    case ARM_BUILTIN_WSRLDI:
+    case ARM_BUILTIN_WRORH:
+    case ARM_BUILTIN_WRORHI:
+    case ARM_BUILTIN_WRORW:
+    case ARM_BUILTIN_WRORWI:
+    case ARM_BUILTIN_WRORD:
+    case ARM_BUILTIN_WRORDI:
+    case ARM_BUILTIN_WAND:
+    case ARM_BUILTIN_WANDN:
+    case ARM_BUILTIN_WOR:
+    case ARM_BUILTIN_WXOR:
+      icode = (fcode == ARM_BUILTIN_WSLLH ? CODE_FOR_ashlv4hi3_di
+	       : fcode == ARM_BUILTIN_WSLLHI ? CODE_FOR_ashlv4hi3_iwmmxt
+	       : fcode == ARM_BUILTIN_WSLLW  ? CODE_FOR_ashlv2si3_di
+	       : fcode == ARM_BUILTIN_WSLLWI ? CODE_FOR_ashlv2si3_iwmmxt
+	       : fcode == ARM_BUILTIN_WSLLD  ? CODE_FOR_ashldi3_di
+	       : fcode == ARM_BUILTIN_WSLLDI ? CODE_FOR_ashldi3_iwmmxt
+	       : fcode == ARM_BUILTIN_WSRAH  ? CODE_FOR_ashrv4hi3_di
+	       : fcode == ARM_BUILTIN_WSRAHI ? CODE_FOR_ashrv4hi3_iwmmxt
+	       : fcode == ARM_BUILTIN_WSRAW  ? CODE_FOR_ashrv2si3_di
+	       : fcode == ARM_BUILTIN_WSRAWI ? CODE_FOR_ashrv2si3_iwmmxt
+	       : fcode == ARM_BUILTIN_WSRAD  ? CODE_FOR_ashrdi3_di
+	       : fcode == ARM_BUILTIN_WSRADI ? CODE_FOR_ashrdi3_iwmmxt
+	       : fcode == ARM_BUILTIN_WSRLH  ? CODE_FOR_lshrv4hi3_di
+	       : fcode == ARM_BUILTIN_WSRLHI ? CODE_FOR_lshrv4hi3_iwmmxt
+	       : fcode == ARM_BUILTIN_WSRLW  ? CODE_FOR_lshrv2si3_di
+	       : fcode == ARM_BUILTIN_WSRLWI ? CODE_FOR_lshrv2si3_iwmmxt
+	       : fcode == ARM_BUILTIN_WSRLD  ? CODE_FOR_lshrdi3_di
+	       : fcode == ARM_BUILTIN_WSRLDI ? CODE_FOR_lshrdi3_iwmmxt
+	       : fcode == ARM_BUILTIN_WRORH  ? CODE_FOR_rorv4hi3_di
+	       : fcode == ARM_BUILTIN_WRORHI ? CODE_FOR_rorv4hi3
+	       : fcode == ARM_BUILTIN_WRORW  ? CODE_FOR_rorv2si3_di
+	       : fcode == ARM_BUILTIN_WRORWI ? CODE_FOR_rorv2si3
+	       : fcode == ARM_BUILTIN_WRORD  ? CODE_FOR_rordi3_di
+	       : fcode == ARM_BUILTIN_WRORDI ? CODE_FOR_rordi3
+	       : fcode == ARM_BUILTIN_WAND   ? CODE_FOR_iwmmxt_anddi3
+	       : fcode == ARM_BUILTIN_WANDN  ? CODE_FOR_iwmmxt_nanddi3
+	       : fcode == ARM_BUILTIN_WOR    ? CODE_FOR_iwmmxt_iordi3
+	       : fcode == ARM_BUILTIN_WXOR   ? CODE_FOR_iwmmxt_xordi3
+	       : CODE_FOR_rordi3);
+      return arm_expand_binop_builtin (icode, exp, target);
+
     case ARM_BUILTIN_WZERO:
       target = gen_reg_rtx (DImode);
       emit_insn (gen_iwmmxt_clrdi (target));
-- 
1.7.3.4

[PATCH] arm: add _mm_empty to mmintrin.h for source compatibility

[Matt Turner]

The x86/amd64 mmintrin.h provides the _mm_empty intrinsic for the 'emms'
MMX instruction. Although ARM does not need such an instruction, we
should provide an empty _mm_empty function nonetheless for source
compatibility.

2012-02-24  Matt Turner  <mattst88@gmail.com>

	* config/arm/mmintrin.h (_mm_empty): New.
---
 gcc/config/arm/mmintrin.h |    7 +++++++
 1 files changed, 7 insertions(+), 0 deletions(-)

diff --git a/gcc/config/arm/mmintrin.h b/gcc/config/arm/mmintrin.h
index 2cc500d..ea73bf1 100644
--- a/gcc/config/arm/mmintrin.h
+++ b/gcc/config/arm/mmintrin.h
@@ -32,6 +32,12 @@ typedef int __v2si __attribute__ ((vector_size (8)));
 typedef short __v4hi __attribute__ ((vector_size (8)));
 typedef char __v8qi __attribute__ ((vector_size (8)));
 
+/* Provided for source compatibility with MMX.  */
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_empty (void)
+{
+}
+
 /* "Convert" __m64 and __int64 into each other.  */
 static __inline __m64 
 _mm_cvtsi64_m64 (__int64 __i)
@@ -1248,6 +1254,7 @@ _m_from_int (int __a)
 #define _m_psadzbw _mm_sadz_pu8
 #define _m_psadzwd _mm_sadz_pu16
 #define _m_paligniq _mm_align_si64
+#define _m_empty _mm_empty
 #define _m_cvt_si2pi _mm_cvtsi64_m64
 #define _m_cvt_pi2si _mm_cvtm64_si64
 
-- 
1.7.3.4

Re: [PATCH] arm: add _mm_empty to mmintrin.h for source compatibility

[Ramana Radhakrishnan]

On Fri, Feb 24, 2012 at 10:53:35PM -0500, Matt Turner wrote:
> The x86/amd64 mmintrin.h provides the _mm_empty intrinsic for the 'emms'
> MMX instruction. Although ARM does not need such an instruction, we
> should provide an empty _mm_empty function nonetheless for source
> compatibility.

OK for 4.8 and after your copyright assignment has been 
sorted.

Ramana

> 
> 2012-02-24  Matt Turner  <mattst88@gmail.com>
> 
> 	* config/arm/mmintrin.h (_mm_empty): New.
> ---
>  gcc/config/arm/mmintrin.h |    7 +++++++
>  1 files changed, 7 insertions(+), 0 deletions(-)
> 
> diff --git a/gcc/config/arm/mmintrin.h b/gcc/config/arm/mmintrin.h
> index 2cc500d..ea73bf1 100644
> --- a/gcc/config/arm/mmintrin.h
> +++ b/gcc/config/arm/mmintrin.h
> @@ -32,6 +32,12 @@ typedef int __v2si __attribute__ ((vector_size (8)));
>  typedef short __v4hi __attribute__ ((vector_size (8)));
>  typedef char __v8qi __attribute__ ((vector_size (8)));
>  
> +/* Provided for source compatibility with MMX.  */
> +extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> +_mm_empty (void)
> +{
> +}
> +
>  /* "Convert" __m64 and __int64 into each other.  */
>  static __inline __m64 
>  _mm_cvtsi64_m64 (__int64 __i)
> @@ -1248,6 +1254,7 @@ _m_from_int (int __a)
>  #define _m_psadzbw _mm_sadz_pu8
>  #define _m_psadzwd _mm_sadz_pu16
>  #define _m_paligniq _mm_align_si64
> +#define _m_empty _mm_empty
>  #define _m_cvt_si2pi _mm_cvtsi64_m64
>  #define _m_cvt_pi2si _mm_cvtm64_si64
>  
> -- 
> 1.7.3.4
> 

Re: [PATCH] arm: add _mm_empty to mmintrin.h for source compatibility

[Matt Turner]

On Tue, Feb 28, 2012 at 7:13 PM, Ramana Radhakrishnan
<ramana.radhakrishnan@linaro.org> wrote:
> On Fri, Feb 24, 2012 at 10:53:35PM -0500, Matt Turner wrote:
>> The x86/amd64 mmintrin.h provides the _mm_empty intrinsic for the 'emms'
>> MMX instruction. Although ARM does not need such an instruction, we
>> should provide an empty _mm_empty function nonetheless for source
>> compatibility.
>
> OK for 4.8 and after your copyright assignment has been
> sorted.
>
> Ramana
>
>>
>> 2012-02-24  Matt Turner  <mattst88@gmail.com>
>>
>>       * config/arm/mmintrin.h (_mm_empty): New.
>> ---
>>  gcc/config/arm/mmintrin.h |    7 +++++++
>>  1 files changed, 7 insertions(+), 0 deletions(-)
>>
>> diff --git a/gcc/config/arm/mmintrin.h b/gcc/config/arm/mmintrin.h
>> index 2cc500d..ea73bf1 100644
>> --- a/gcc/config/arm/mmintrin.h
>> +++ b/gcc/config/arm/mmintrin.h
>> @@ -32,6 +32,12 @@ typedef int __v2si __attribute__ ((vector_size (8)));
>>  typedef short __v4hi __attribute__ ((vector_size (8)));
>>  typedef char __v8qi __attribute__ ((vector_size (8)));
>>
>> +/* Provided for source compatibility with MMX.  */
>> +extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
>> +_mm_empty (void)
>> +{
>> +}
>> +
>>  /* "Convert" __m64 and __int64 into each other.  */
>>  static __inline __m64
>>  _mm_cvtsi64_m64 (__int64 __i)
>> @@ -1248,6 +1254,7 @@ _m_from_int (int __a)
>>  #define _m_psadzbw _mm_sadz_pu8
>>  #define _m_psadzwd _mm_sadz_pu16
>>  #define _m_paligniq _mm_align_si64
>> +#define _m_empty _mm_empty
>>  #define _m_cvt_si2pi _mm_cvtsi64_m64
>>  #define _m_cvt_pi2si _mm_cvtm64_si64
>>
>> --
>> 1.7.3.4
>>

Copyright assignment is sorted. Please commit. :)

Re: [PATCH] arm: Fix iwmmxt shift and logical intrinsics (PR 35294).

[Matt Turner]

On Fri, Feb 24, 2012 at 10:53 PM, Matt Turner <mattst88@gmail.com> wrote:
> PR 36798 and 36966 are duplicates.
>
> 2012-02-24  Matt Turner  <mattst88@gmail.com>
>
>        PR target/35294
>        * config/arm/arm.c (arm_expand_builtin): Wire up missing
>        intrinsics.
> ---
>  gcc/config/arm/arm.c |   62 +++++++++++++++++++++++++++++++++++++++++++++++++-
>  1 files changed, 61 insertions(+), 1 deletions(-)

Drop this patch. Marvell has a five patch series that fixes this and
more. Maybe this patch would be suitable for the 4.6 and 4.7 branches,
since Marvell's adds some features?

Re: [PATCH] arm: add _mm_empty to mmintrin.h for source compatibility

[Ramana Radhakrishnan]

On 28 May 2012 22:56, Matt Turner <mattst88@gmail.com> wrote:
> On Tue, Feb 28, 2012 at 7:13 PM, Ramana Radhakrishnan
> <ramana.radhakrishnan@linaro.org> wrote:
>> On Fri, Feb 24, 2012 at 10:53:35PM -0500, Matt Turner wrote:
>>> The x86/amd64 mmintrin.h provides the _mm_empty intrinsic for the 'emms'
>>> MMX instruction. Although ARM does not need such an instruction, we
>>> should provide an empty _mm_empty function nonetheless for source
>>> compatibility.
>>
>> OK for 4.8 and after your copyright assignment has been
>> sorted.
>>
>> Ramana
>>
>>>
>>> 2012-02-24  Matt Turner  <mattst88@gmail.com>
>>>
>>>       * config/arm/mmintrin.h (_mm_empty): New.
>>> ---
>>>  gcc/config/arm/mmintrin.h |    7 +++++++
>>>  1 files changed, 7 insertions(+), 0 deletions(-)
>>>
>>> diff --git a/gcc/config/arm/mmintrin.h b/gcc/config/arm/mmintrin.h
>>> index 2cc500d..ea73bf1 100644
>>> --- a/gcc/config/arm/mmintrin.h
>>> +++ b/gcc/config/arm/mmintrin.h
>>> @@ -32,6 +32,12 @@ typedef int __v2si __attribute__ ((vector_size (8)));
>>>  typedef short __v4hi __attribute__ ((vector_size (8)));
>>>  typedef char __v8qi __attribute__ ((vector_size (8)));
>>>
>>> +/* Provided for source compatibility with MMX.  */
>>> +extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
>>> +_mm_empty (void)
>>> +{
>>> +}
>>> +
>>>  /* "Convert" __m64 and __int64 into each other.  */
>>>  static __inline __m64
>>>  _mm_cvtsi64_m64 (__int64 __i)
>>> @@ -1248,6 +1254,7 @@ _m_from_int (int __a)
>>>  #define _m_psadzbw _mm_sadz_pu8
>>>  #define _m_psadzwd _mm_sadz_pu16
>>>  #define _m_paligniq _mm_align_si64
>>> +#define _m_empty _mm_empty
>>>  #define _m_cvt_si2pi _mm_cvtsi64_m64
>>>  #define _m_cvt_pi2si _mm_cvtm64_si64
>>>
>>> --
>>> 1.7.3.4
>>>
>
> Copyright assignment is sorted. Please commit. :)

Done now. Only change was to put _m_empty in alphabetical order  and
this is what I committed.

Thanks,
Ramana

Index: gcc/config/arm/mmintrin.h
===================================================================
--- gcc/config/arm/mmintrin.h	(revision 188258)
+++ gcc/config/arm/mmintrin.h	(revision 188259)
@@ -32,6 +32,12 @@
 typedef short __v4hi __attribute__ ((vector_size (8)));
 typedef char __v8qi __attribute__ ((vector_size (8)));

+/* Provided for source compatibility with MMX.  */
+extern __inline void __attribute__((__gnu_inline__,
__always_inline__, __artificial__))
+_mm_empty (void)
+{
+}
+
 /* "Convert" __m64 and __int64 into each other.  */
 static __inline __m64
 _mm_cvtsi64_m64 (__int64 __i)
@@ -1115,6 +1121,7 @@
   return (__m64)__a;
 }

+#define _m_empty _mm_empty
 #define _m_packsswb _mm_packs_pi16
 #define _m_packssdw _mm_packs_pi32
 #define _m_packuswb _mm_packs_pu16

Re: [PATCH] arm: Fix iwmmxt shift and logical intrinsics (PR 35294).

[Ramana Radhakrishnan]

On 28 May 2012 22:57, Matt Turner <mattst88@gmail.com> wrote:
> On Fri, Feb 24, 2012 at 10:53 PM, Matt Turner <mattst88@gmail.com> wrote:
>> PR 36798 and 36966 are duplicates.
>>
>> 2012-02-24  Matt Turner  <mattst88@gmail.com>
>>
>>        PR target/35294
>>        * config/arm/arm.c (arm_expand_builtin): Wire up missing
>>        intrinsics.
>> ---
>>  gcc/config/arm/arm.c |   62 +++++++++++++++++++++++++++++++++++++++++++++++++-
>>  1 files changed, 61 insertions(+), 1 deletions(-)
>
> Drop this patch. Marvell has a five patch series that fixes this and
> more. Maybe this patch would be suitable for the 4.6 and 4.7 branches,
> since Marvell's adds some features?

So you want  to drop this patch for trunk in favour of the Marvell
patches and use this only for the 4.6 and 4.7 branches ? Instead,
could the bug fix be teased out of the appropriate Marvell patch and
that submitted as a separate patch which can then be applied to trunk
and the release branches. ?

regards,
Ramana