config.gcc (i[34567]86-*-*): Add nmmintrin.h to extra_headers.

2007-05-31  H.J. Lu  <hongjiu.lu@intel.com>

	* config.gcc (i[34567]86-*-*): Add nmmintrin.h to
	extra_headers.
	(x86_64-*-*): Likewise.

	* config/i386/i386.c (OPTION_MASK_ISA_MMX_UNSET): New.
	(OPTION_MASK_ISA_3DNOW_UNSET): Likewise.
	(OPTION_MASK_ISA_SSE_UNSET): Likewise.
	(OPTION_MASK_ISA_SSE2_UNSET): Likewise.
	(OPTION_MASK_ISA_SSE3_UNSET): Likewise.
	(OPTION_MASK_ISA_SSSE3_UNSET): Likewise.
	(OPTION_MASK_ISA_SSE4_1_UNSET): Likewise.
	(OPTION_MASK_ISA_SSE4_2_UNSET): Likewise.
	(OPTION_MASK_ISA_SSE4): Likewise.
	(OPTION_MASK_ISA_SSE4_UNSET): Likewise.
	(OPTION_MASK_ISA_SSE4A_UNSET): Likewise.
	(ix86_handle_option): Use OPTION_MASK_ISA_*_UNSET.  Handle
	SSE4.2.
	(override_options): Support SSE4.2.
	(ix86_build_const_vector): Support SImode and DImode.
	(ix86_build_signbit_mask): Likewise.
	(ix86_expand_int_vcond): Support V2DImode.
	(IX86_BUILTIN_CRC32QI): New for SSE4.2.
	(IX86_BUILTIN_CRC32HI): Likewise.
	(IX86_BUILTIN_CRC32SI): Likewise.
	(IX86_BUILTIN_CRC32DI): Likewise.
	(IX86_BUILTIN_PCMPGTQ): Likewise.
	(bdesc_crc32): Likewise.
	(bdesc_sse_3arg): Likewise.
	(ix86_expand_crc32): Likewise.
	(ix86_init_mmx_sse_builtins): Support SSE4.2.
	(ix86_expand_builtin): Likewise.

	* config/i386/i386.h (TARGET_CPU_CPP_BUILTINS): Define
	__SSE4_2__ for -msse4.2.

	* config/i386/i386.md (UNSPEC_CRC32): New for SSE4.2.
	(CRC32MODE): Likewise.
	(crc32modesuffix): Likewise.
	(crc32modeconstraint): Likewise.
	(sse4_2_crc32<mode>): Likewise.
	(sse4_2_crc32di): Likewise.

	* config/i386/i386.opt (msse4.2): New for SSE4.2.
	(msse4): Likewise.

	* config/i386/nmmintrin.h: New. The dummy SSE4.2 intrinsic header
	file.

	* config/i386/smmintrin.h: Add SSE4.2 intrinsics.

	* config/i386/sse.md (sse4_2_gtv2di3): New pattern for
	SSE4.2.
	(vcond<mode>): Use SSEMODEI instead of SSEMODE124.
	(vcondu<mode>): Likewise.

	* doc/extend.texi: Document SSE4.2 built-in functions.

	* doc/invoke.texi: Document -msse4.2/-msse4.

From-SVN: r125236

2 files changed, 53 insertions, 1 deletions

diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index e1104dc..4217eaa 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -7502,6 +7502,54 @@ Generates the @code{pextrd} machine instruction.
 Generates the @code{pextrq} machine instruction in 64bit mode.
 @end table
 
+The following built-in functions are available when @option{-msse4.2} is
+used.  All of them generate the machine instruction that is part of the
+name.
+
+@smallexample
+v16qi __builtin_ia32_pcmpestrm128 (v16qi, int, v16qi, int, const int)
+int __builtin_ia32_pcmpestri128 (v16qi, int, v16qi, int, const int)
+int __builtin_ia32_pcmpestria128 (v16qi, int, v16qi, int, const int)
+int __builtin_ia32_pcmpestric128 (v16qi, int, v16qi, int, const int)
+int __builtin_ia32_pcmpestrio128 (v16qi, int, v16qi, int, const int)
+int __builtin_ia32_pcmpestris128 (v16qi, int, v16qi, int, const int)
+int __builtin_ia32_pcmpestriz128 (v16qi, int, v16qi, int, const int)
+v16qi __builtin_ia32_pcmpistrm128 (v16qi, v16qi, const int)
+int __builtin_ia32_pcmpistri128 (v16qi, v16qi, const int)
+int __builtin_ia32_pcmpistria128 (v16qi, v16qi, const int)
+int __builtin_ia32_pcmpistric128 (v16qi, v16qi, const int)
+int __builtin_ia32_pcmpistrio128 (v16qi, v16qi, const int)
+int __builtin_ia32_pcmpistris128 (v16qi, v16qi, const int)
+int __builtin_ia32_pcmpistriz128 (v16qi, v16qi, const int)
+__v2di __builtin_ia32_pcmpgtq (__v2di, __v2di)
+@end smallexample
+
+The following built-in functions are available when @option{-msse4.2} is
+used.
+
+@table @code
+unsigned int __builtin_ia32_crc32qi (unsigned int, unsigned char)
+Generates the @code{crc32b} machine instruction.
+unsigned int __builtin_ia32_crc32hi (unsigned int, unsigned short)
+Generates the @code{crc32w} machine instruction.
+unsigned int __builtin_ia32_crc32si (unsigned int, unsigned int)
+Generates the @code{crc32l} machine instruction.
+unsigned long long __builtin_ia32_crc32di (unsigned int, unsigned long long)
+@end table
+
+The following built-in functions are changed to generate new SSE4.2
+instructions when @option{-msse4.2} is used.
+
+@table @code
+int __builtin_popcount (unsigned int)
+Generates the @code{popcntl} machine instruction.
+int __builtin_popcountl (unsigned long)
+Generates the @code{popcntl} or @code{popcntq} machine instruction,
+depending on the size of @code{unsigned long}.
+int __builtin_popcountll (unsigned long long)
+Generates the @code{popcntq} machine instruction.
+@end table
+
 The following built-in functions are available when @option{-msse4a} is used.
 
 @smallexample
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index f93aeb1..4aedf30 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -548,7 +548,7 @@ Objective-C and Objective-C++ Dialects}.
 -mno-fp-ret-in-387  -msoft-float @gol
 -mno-wide-multiply  -mrtd  -malign-double @gol
 -mpreferred-stack-boundary=@var{num} -mcx16 -msahf @gol
--mmmx  -msse  -msse2 -msse3 -mssse3 -msse4.1 @gol
+-mmmx  -msse  -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4 @gol
 -msse4a -m3dnow -mpopcnt -mabm @gol
 -mthreads  -mno-align-stringops  -minline-all-stringops @gol
 -mpush-args  -maccumulate-outgoing-args  -m128bit-long-double @gol
@@ -10273,6 +10273,10 @@ preferred alignment to @option{-mpreferred-stack-boundary=2}.
 @itemx -mno-ssse3
 @item -msse4.1
 @itemx -mno-sse4.1
+@item -msse4.2
+@itemx -mno-sse4.2
+@item -msse4
+@itemx -mno-sse4
 @item -msse4a
 @item -mno-sse4a
 @item -m3dnow