Allow mmintrin headers to work with function specific target opts.

Allow mmintrin headers to work with function specific target opts.  Please
see discussion here:
http://gcc.gnu.org/ml/gcc-patches/2013-04/msg00740.html

	* config/i386/i386.c (ix86_pragma_target_parse):  Restore target
	when current target options does not apply.
	* config/i386/i386-protos.h (ix86_reset_previous_fndecl): New function.
	* config/i386/i386.c (ix86_reset_previous_fndecl): Ditto.
	* config/i386/bmiintrin.h: Pass appropriate target attributes to header.
	* config/i386/mmintrin.h: Ditto.
	* config/i386/nmmintrin.h: Ditto.
	* config/i386/avx2intrin.h: Ditto.
	* config/i386/fxsrintrin.h: Ditto.
	* config/i386/tbmintrin.h: Ditto.
	* config/i386/xsaveintrin.h: Ditto.
	* config/i386/f16cintrin.h: Ditto.
	* config/i386/xtestintrin.h: Ditto.
	* config/i386/xsaveoptintrin.h: Ditto.
	* config/i386/bmi2intrin.h: Ditto.
	* config/i386/lzcntintrin.h: Ditto.
	* config/i386/smmintrin.h: Ditto.
	* config/i386/wmmintrin.h: Ditto.
	* config/i386/x86intrin.h: Remove all header include guards.
	* config/i386/prfchwintrin.h: Ditto.
	* config/i386/pmmintrin.h: Ditto.
	* config/i386/tmmintrin.h: Ditto.
	* config/i386/xmmintrin.h: Ditto.
	* config/i386/popcntintrin.h: Ditto.
	* config/i386/rdseedintrin.h: Ditto.
	* config/i386/ammintrin.h: Ditto.
	* config/i386/emmintrin.h: Ditto.
	* config/i386/immintrin.h: Remove all header include guards.
	* config/i386/fma4intrin.h: Ditto.
	* config/i386/lwpintrin.h: Ditto.
	* config/i386/xopintrin.h: Ditto.
	* config/i386/ia32intrin.h: Ditto.
	* config/i386/avxintrin.h: Ditto.
	* config/i386/rtmintrin.h: Ditto.
	* config/i386/fmaintrin.h: Ditto.
	* config/i386/mm3dnow.h: Ditto.

	* testsuite/gcc.target/i386/intrinsics_1.c: New test.
	* testsuite/gcc.target/i386/intrinsics_2.c: Ditto.
	* testsuite/gcc.target/i386/intrinsics_3.c: Ditto.
	* testsuite/gcc.target/i386/intrinsics_4.c: Ditto.
	* testsuite/gcc.target/i386/intrinsics_5.c: Ditto.
	* testsuite/gcc.target/i386/intrinsics_6.c: Ditto.
	* testsuite/gcc.target/i386/avx-1.c: Provide macros for builtins
	needing immediate arguments in f16cintrin.h and rtmintrin.h.

From-SVN: r200349

gcc/ChangeLog

@@ -1,3 +1,42 @@
+2013-06-23  Sriraman Tallam  <tmsriram@google.com>
+
+	* config/i386/i386.c (ix86_pragma_target_parse):  Restore target
+	when current target options does not apply.
+	* config/i386/i386-protos.h (ix86_reset_previous_fndecl): New function.
+	* config/i386/i386.c (ix86_reset_previous_fndecl): Ditto.
+	* config/i386/bmiintrin.h: Pass appropriate target attributes to header.
+	* config/i386/mmintrin.h: Ditto.
+	* config/i386/nmmintrin.h: Ditto.
+	* config/i386/avx2intrin.h: Ditto.
+	* config/i386/fxsrintrin.h: Ditto.
+	* config/i386/tbmintrin.h: Ditto.
+	* config/i386/xsaveintrin.h: Ditto.
+	* config/i386/f16cintrin.h: Ditto.
+	* config/i386/xtestintrin.h: Ditto.
+	* config/i386/xsaveoptintrin.h: Ditto.
+	* config/i386/bmi2intrin.h: Ditto.
+	* config/i386/lzcntintrin.h: Ditto.
+	* config/i386/smmintrin.h: Ditto.
+	* config/i386/wmmintrin.h: Ditto.
+	* config/i386/x86intrin.h: Remove all header include guards.
+	* config/i386/prfchwintrin.h: Ditto.
+	* config/i386/pmmintrin.h: Ditto.
+	* config/i386/tmmintrin.h: Ditto.
+	* config/i386/xmmintrin.h: Ditto.
+	* config/i386/popcntintrin.h: Ditto.
+	* config/i386/rdseedintrin.h: Ditto.
+	* config/i386/ammintrin.h: Ditto.
+	* config/i386/emmintrin.h: Ditto.
+	* config/i386/immintrin.h: Remove all header include guards.
+	* config/i386/fma4intrin.h: Ditto.
+	* config/i386/lwpintrin.h: Ditto.
+	* config/i386/xopintrin.h: Ditto.
+	* config/i386/ia32intrin.h: Ditto.
+	* config/i386/avxintrin.h: Ditto.
+	* config/i386/rtmintrin.h: Ditto.
+	* config/i386/fmaintrin.h: Ditto.
+	* config/i386/mm3dnow.h: Ditto.
+
 2013-06-22  Sriraman Tallam  <tmsriram@google.com>
 
 	* common/config/i386/i386-common.c: Handle LZCNT.

gcc/config/i386/ammintrin.h

@@ -27,13 +27,15 @@
 #ifndef _AMMINTRIN_H_INCLUDED
 #define _AMMINTRIN_H_INCLUDED
 
-#ifndef __SSE4A__
-# error "SSE4A instruction set not enabled"
-#else
-
 /* We need definitions from the SSE3, SSE2 and SSE header files*/
 #include <pmmintrin.h>
 
+#ifndef __SSE4A__
+#pragma GCC push_options
+#pragma GCC target("sse4a")
+#define __DISABLE_SSE4A__
+#endif /* __SSE4A__ */
+
 extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_stream_sd (double * __P, __m128d __Y)
 {
@@ -83,6 +85,9 @@ _mm_inserti_si64(__m128i __X, __m128i __Y, unsigned const int __I, unsigned cons
 				      (unsigned int)(I), (unsigned int)(L)))
 #endif
 
-#endif /* __SSE4A__ */
+#ifdef __DISABLE_SSE4A__
+#undef __DISABLE_SSE4A__
+#pragma GCC pop_options
+#endif /* __DISABLE_SSE4A__ */
 
 #endif /* _AMMINTRIN_H_INCLUDED */

gcc/config/i386/avx2intrin.h

@@ -25,6 +25,15 @@
 # error "Never use <avx2intrin.h> directly; include <immintrin.h> instead."
 #endif
 
+#ifndef _AVX2INTRIN_H_INCLUDED
+#define _AVX2INTRIN_H_INCLUDED
+
+#ifndef __AVX2__
+#pragma GCC push_options
+#pragma GCC target("avx2")
+#define __DISABLE_AVX2__
+#endif /* __AVX2__ */
+
 /* Sum absolute 8-bit integer difference of adjacent groups of 4
    byte integers in the first 2 operands.  Starting offsets within
    operands are determined by the 3rd mask operand.  */
@@ -1871,3 +1880,10 @@ _mm256_mask_i64gather_epi32 (__m128i src, int const *base,
 					   (__v4si)(__m128i)MASK,  \
 					   (int)SCALE)
 #endif  /* __OPTIMIZE__ */
+
+#ifdef __DISABLE_AVX2__
+#undef __DISABLE_AVX2__
+#pragma GCC pop_options
+#endif /* __DISABLE_AVX2__ */
+
+#endif /* _AVX2INTRIN_H_INCLUDED */

gcc/config/i386/avxintrin.h

@@ -28,6 +28,15 @@
 # error "Never use <avxintrin.h> directly; include <immintrin.h> instead."
 #endif
 
+#ifndef _AVXINTRIN_H_INCLUDED
+#define _AVXINTRIN_H_INCLUDED
+
+#ifndef __AVX__
+#pragma GCC push_options
+#pragma GCC target("avx")
+#define __DISABLE_AVX__
+#endif /* __AVX__ */
+
 /* Internal data types for implementing the intrinsics.  */
 typedef double __v4df __attribute__ ((__vector_size__ (32)));
 typedef float __v8sf __attribute__ ((__vector_size__ (32)));
@@ -1424,3 +1433,10 @@ _mm256_castsi128_si256 (__m128i __A)
 {
   return (__m256i) __builtin_ia32_si256_si ((__v4si)__A);
 }
+
+#ifdef __DISABLE_AVX__
+#undef __DISABLE_AVX__
+#pragma GCC pop_options
+#endif /* __DISABLE_AVX__ */
+
+#endif /* _AVXINTRIN_H_INCLUDED */

gcc/config/i386/bmi2intrin.h

@@ -25,13 +25,15 @@
 # error "Never use <bmi2intrin.h> directly; include <x86intrin.h> instead."
 #endif
 
-#ifndef __BMI2__
-# error "BMI2 instruction set not enabled"
-#endif /* __BMI2__ */
-
 #ifndef _BMI2INTRIN_H_INCLUDED
 #define _BMI2INTRIN_H_INCLUDED
 
+#ifndef __BMI2__
+#pragma GCC push_options
+#pragma GCC target("bmi2")
+#define __DISABLE_BMI2__
+#endif /* __BMI2__ */
+
 extern __inline unsigned int
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _bzhi_u32 (unsigned int __X, unsigned int __Y)
@@ -99,4 +101,9 @@ _mulx_u32 (unsigned int __X, unsigned int __Y, unsigned int *__P)
 
 #endif /* !__x86_64__  */
 
+#ifdef __DISABLE_BMI2__
+#undef __DISABLE_BMI2__
+#pragma GCC pop_options
+#endif /* __DISABLE_BMI2__ */
+
 #endif /* _BMI2INTRIN_H_INCLUDED */

gcc/config/i386/bmiintrin.h

@@ -25,13 +25,15 @@
 # error "Never use <bmiintrin.h> directly; include <x86intrin.h> instead."
 #endif
 
-#ifndef __BMI__
-# error "BMI instruction set not enabled"
-#endif /* __BMI__ */
-
 #ifndef _BMIINTRIN_H_INCLUDED
 #define _BMIINTRIN_H_INCLUDED
 
+#ifndef __BMI__
+#pragma GCC push_options
+#pragma GCC target("bmi")
+#define __DISABLE_BMI__
+#endif /* __BMI__ */
+
 extern __inline unsigned short __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 __tzcnt_u16 (unsigned short __X)
 {
@@ -116,4 +118,9 @@ __tzcnt_u64 (unsigned long long __X)
 
 #endif /* __x86_64__  */
 
+#ifdef __DISABLE_BMI__
+#undef __DISABLE_BMI__
+#pragma GCC pop_options
+#endif /* __DISABLE_BMI__ */
+
 #endif /* _BMIINTRIN_H_INCLUDED */

gcc/config/i386/emmintrin.h

@@ -27,13 +27,15 @@
 #ifndef _EMMINTRIN_H_INCLUDED
 #define _EMMINTRIN_H_INCLUDED
 
-#ifndef __SSE2__
-# error "SSE2 instruction set not enabled"
-#else
-
 /* We need definitions from the SSE header files*/
 #include <xmmintrin.h>
 
+#ifndef __SSE2__
+#pragma GCC push_options
+#pragma GCC target("sse2")
+#define __DISABLE_SSE2__
+#endif /* __SSE2__ */
+
 /* SSE2 */
 typedef double __v2df __attribute__ ((__vector_size__ (16)));
 typedef long long __v2di __attribute__ ((__vector_size__ (16)));
@@ -1515,6 +1517,9 @@ _mm_castsi128_pd(__m128i __A)
   return (__m128d) __A;
 }
 
-#endif /* __SSE2__  */
+#ifdef __DISABLE_SSE2__
+#undef __DISABLE_SSE2__
+#pragma GCC pop_options
+#endif /* __DISABLE_SSE2__ */
 
 #endif /* _EMMINTRIN_H_INCLUDED */

gcc/config/i386/f16cintrin.h

@@ -25,13 +25,15 @@
 # error "Never use <f16intrin.h> directly; include <x86intrin.h> or <immintrin.h> instead."
 #endif
 
-#ifndef __F16C__
-# error "F16C instruction set not enabled"
-#else
-
 #ifndef _F16CINTRIN_H_INCLUDED
 #define _F16CINTRIN_H_INCLUDED
 
+#ifndef __F16C__
+#pragma GCC push_options
+#pragma GCC target("f16c")
+#define __DISABLE_F16C__
+#endif /* __F16C__ */
+
 extern __inline float __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _cvtsh_ss (unsigned short __S)
 {
@@ -88,5 +90,9 @@ _mm256_cvtps_ph (__m256 __A, const int __I)
   ((__m128i) __builtin_ia32_vcvtps2ph256 ((__v8sf)(__m256) A, (int) (I)))
 #endif /* __OPTIMIZE */
 
+#ifdef __DISABLE_F16C__
+#undef __DISABLE_F16C__
+#pragma GCC pop_options
+#endif /* __DISABLE_F16C__ */
+
 #endif /* _F16CINTRIN_H_INCLUDED */
-#endif /* __F16C__ */

gcc/config/i386/fma4intrin.h

@@ -28,13 +28,15 @@
 #ifndef _FMA4INTRIN_H_INCLUDED
 #define _FMA4INTRIN_H_INCLUDED
 
-#ifndef __FMA4__
-# error "FMA4 instruction set not enabled"
-#else
-
 /* We need definitions from the SSE4A, SSE3, SSE2 and SSE header files.  */
 #include <ammintrin.h>
 
+#ifndef __FMA4__
+#pragma GCC push_options
+#pragma GCC target("fma4")
+#define __DISABLE_FMA4__
+#endif /* __FMA4__ */
+
 /* 128b Floating point multiply/add type instructions.  */
 extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_macc_ps (__m128 __A, __m128 __B, __m128 __C)
@@ -231,6 +233,9 @@ _mm256_msubadd_pd (__m256d __A, __m256d __B, __m256d __C)
   return (__m256d) __builtin_ia32_vfmaddsubpd256 ((__v4df)__A, (__v4df)__B, -(__v4df)__C);
 }
 
-#endif
+#ifdef __DISABLE_FMA4__
+#undef __DISABLE_FMA4__
+#pragma GCC pop_options
+#endif /* __DISABLE_FMA4__ */
 
 #endif

gcc/config/i386/fmaintrin.h

@@ -29,8 +29,10 @@
 #define _FMAINTRIN_H_INCLUDED
 
 #ifndef __FMA__
-# error "FMA instruction set not enabled"
-#else
+#pragma GCC push_options
+#pragma GCC target("fma")
+#define __DISABLE_FMA__
+#endif /* __FMA__ */
 
 extern __inline __m128d
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
@@ -292,6 +294,9 @@ _mm256_fmsubadd_ps (__m256 __A, __m256 __B, __m256 __C)
                                                 -(__v8sf)__C);
 }
 
-#endif
+#ifdef __DISABLE_FMA__
+#undef __DISABLE_FMA__
+#pragma GCC pop_options
+#endif /* __DISABLE_FMA__ */
 
 #endif

gcc/config/i386/fxsrintrin.h

@@ -28,6 +28,12 @@
 #ifndef _FXSRINTRIN_H_INCLUDED
 #define _FXSRINTRIN_H_INCLUDED
 
+#ifndef __FXSR__
+#pragma GCC push_options
+#pragma GCC target("fxsr")
+#define __DISABLE_FXSR__
+#endif /* __FXSR__ */
+
 extern __inline void
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _fxsave (void *__P)
@@ -58,4 +64,10 @@ _fxrstor64 (void *__P)
 }
 #endif
 
+#ifdef __DISABLE_FXSR__
+#undef __DISABLE_FXSR__
+#pragma GCC pop_options
+#endif /* __DISABLE_FXSR__ */
+
+
 #endif /* _FXSRINTRIN_H_INCLUDED */

gcc/config/i386/i386-c.c

@@ -376,20 +376,23 @@ ix86_pragma_target_parse (tree args, tree pop_target)
 
   if (! args)
     {
-      cur_tree = ((pop_target)
-		  ? pop_target
-		  : target_option_default_node);
+      cur_tree = (pop_target ? pop_target : target_option_default_node);
       cl_target_option_restore (&global_options,
 				TREE_TARGET_OPTION (cur_tree));
     }
   else
     {
       cur_tree = ix86_valid_target_attribute_tree (args);
-      if (!cur_tree)
-	return false;
+      if (!cur_tree || cur_tree == error_mark_node)
+       {
+         cl_target_option_restore (&global_options,
+                                   TREE_TARGET_OPTION (prev_tree));
+         return false;
+       }
     }
 
   target_option_current_node = cur_tree;
+  ix86_reset_previous_fndecl ();
 
   /* Figure out the previous/current isa, arch, tune and the differences.  */
   prev_opt  = TREE_TARGET_OPTION (prev_tree);

gcc/config/i386/i386-protos.h

@@ -40,6 +40,8 @@ extern void ix86_output_addr_diff_elt (FILE *, int, int);
 extern enum calling_abi ix86_cfun_abi (void);
 extern enum calling_abi ix86_function_type_abi (const_tree);
 
+extern void ix86_reset_previous_fndecl (void);
+
 #ifdef RTX_CODE
 extern int standard_80387_constant_p (rtx);
 extern const char *standard_80387_constant_opcode (rtx);

gcc/config/i386/i386.c

@@ -4649,6 +4649,13 @@ ix86_can_inline_p (tree caller, tree callee)
 /* Remember the last target of ix86_set_current_function.  */
 static GTY(()) tree ix86_previous_fndecl;
 
+/* Invalidate ix86_previous_fndecl cache.  */
+void
+ix86_reset_previous_fndecl (void)
+{
+  ix86_previous_fndecl = NULL_TREE;
+}
+
 /* Establish appropriate back-end context for processing the function
    FNDECL.  The argument might be NULL to indicate processing at top
    level, outside of any function scope.  */