/*	mmx.h	MultiMedia eXtensions GCC interface library for IA32.	To use this library, simply include this header file	and compile with GCC.  You MUST have inlining enabled	in order for mmx_ok() to work; this can be done by	simply using -O on the GCC command line.	Compiling with -DMMX_TRACE will cause detailed trace	output to be sent to stderr for each mmx operation.	This adds lots of code, and obviously slows execution to	a crawl, but can be very useful for debugging.	THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY	EXPRESS OR IMPLIED WARRANTIES, INCLUDING, WITHOUT	LIMITATION, THE IMPLIED WARRANTIES OF MERCHANTABILITY	AND FITNESS FOR ANY PARTICULAR PURPOSE.	1997-98 by H. Dietz and R. Fisher History:	97-98*	R.Fisher	Early versions	980501	R.Fisher	Original Release	980611*	H.Dietz		Rewrite, correctly implementing inlines, and		R.Fisher	 including direct register accesses.	980616	R.Fisher	Release of 980611 as 980616.	980714	R.Fisher	Minor corrections to Makefile, etc.	980715	R.Fisher	mmx_ok() now prevents optimizer from using				 clobbered values.				mmx_ok() now checks if cpuid instruction is				 available before trying to use it.	980726*	R.Fisher	mm_support() searches for AMD 3DNow, Cyrix				 Extended MMX, and standard MMX.  It returns a				 value which is positive if any of these are				 supported, and can be masked with constants to				 see which.  mmx_ok() is now a call to this	980726*	R.Fisher	Added i2r support for shift functions	980919	R.Fisher	Fixed AMD extended feature recognition bug.	980921	R.Fisher	Added definition/check for _MMX_H.				Added "float s[2]" to mmx_t for use with				  3DNow and EMMX.  So same mmx_t can be used.	981013	R.Fisher	Fixed cpuid function 1 bug (looked at wrong reg)				Fixed psllq_i2r error in mmxtest.c	* Unreleased (internal or interim) versions Notes:	It appears that the latest gas has the pand problem fixed, therefore	  I'll undefine BROKEN_PAND by default.	String compares may be quicker than the multiple test/jumps in vendor	  test sequence in mmx_ok(), but I'm not concerned with that right now. Acknowledgments:	Jussi Laako for pointing out the errors ultimately found to be	  connected to the failure to notify the optimizer of clobbered values.	Roger Hardiman for reminding us that CPUID isn't everywhere, and that	  someone may actually try to use this on a machine without CPUID.	  Also for suggesting code for checking this.	Robert Dale for pointing out the AMD recognition bug.	Jimmy Mayfield and Carl Witty for pointing out the Intel recognition	  bug.	Carl Witty for pointing out the psllq_i2r test bug.*/#ifndef _MMX_H#define _MMX_H/*	Warning:  at this writing, the version of GAS packaged	with most Linux distributions does not handle the	parallel AND operation mnemonic correctly.  If the	symbol BROKEN_PAND is defined, a slower alternative	coding will be used.  If execution of mmxtest results	in an illegal instruction fault, define this symbol.*/#undef	BROKEN_PAND/*	The type of an value that fits in an MMX register	(note that long long constant values MUST be suffixed	 by LL and unsigned long long values by ULL, lest	 they be truncated by the compiler)*/typedef	union {	long long		q;	/* Quadword (64-bit) value */	unsigned long long	uq;	/* Unsigned Quadword */	int			d[2];	/* 2 Doubleword (32-bit) values */	unsigned int		ud[2];	/* 2 Unsigned Doubleword */	short			w[4];	/* 4 Word (16-bit) values */	unsigned short		uw[4];	/* 4 Unsigned Word */	char			b[8];	/* 8 Byte (8-bit) values */	unsigned char		ub[8];	/* 8 Unsigned Byte */	float			s[2];	/* Single-precision (32-bit) value */} mmx_t;/*	Function to test if multimedia instructions are supported...*/inline extern intmm_support(void){	/* Returns 1 if MMX instructions are supported,	   3 if Cyrix MMX and Extended MMX instructions are supported	   5 if AMD MMX and 3DNow! instructions are supported	   0 if hardware does not support any of these	*/	register int rval = 0;	__asm__ __volatile__ (		/* See if CPUID instruction is supported ... */		/* ... Get copies of EFLAGS into eax and ecx */		"pushf\n\t"		"popl %%eax\n\t"		"movl %%eax, %%ecx\n\t"		/* ... Toggle the ID bit in one copy and store */		/*     to the EFLAGS reg */		"xorl $0x200000, %%eax\n\t"		"push %%eax\n\t"		"popf\n\t"		/* ... Get the (hopefully modified) EFLAGS */		"pushf\n\t"		"popl %%eax\n\t"		/* ... Compare and test result */		"xorl %%eax, %%ecx\n\t"		"testl $0x200000, %%ecx\n\t"		"jz NotSupported1\n\t"		/* Nothing supported */		/* Get standard CPUID information, and		       go to a specific vendor section */		"movl $0, %%eax\n\t"		"cpuid\n\t"		/* Check for Intel */		"cmpl $0x756e6547, %%ebx\n\t"		"jne TryAMD\n\t"		"cmpl $0x49656e69, %%edx\n\t"		"jne TryAMD\n\t"		"cmpl $0x6c65746e, %%ecx\n"		"jne TryAMD\n\t"		"jmp Intel\n\t"		/* Check for AMD */		"\nTryAMD:\n\t"		"cmpl $0x68747541, %%ebx\n\t"		"jne TryCyrix\n\t"		"cmpl $0x69746e65, %%edx\n\t"		"jne TryCyrix\n\t"		"cmpl $0x444d4163, %%ecx\n"		"jne TryCyrix\n\t"		"jmp AMD\n\t"		/* Check for Cyrix */		"\nTryCyrix:\n\t"		"cmpl $0x69727943, %%ebx\n\t"		"jne NotSupported2\n\t"		"cmpl $0x736e4978, %%edx\n\t"		"jne NotSupported3\n\t"		"cmpl $0x64616574, %%ecx\n\t"		"jne NotSupported4\n\t"		/* Drop through to Cyrix... */		/* Cyrix Section */		/* See if extended CPUID is supported */		"movl $0x80000000, %%eax\n\t"		"cpuid\n\t"		"cmpl $0x80000000, %%eax\n\t"		"jl MMXtest\n\t"	/* Try standard CPUID instead */		/* Extended CPUID supported, so get extended features */		"movl $0x80000001, %%eax\n\t"		"cpuid\n\t"		"testl $0x00800000, %%eax\n\t"	/* Test for MMX */		"jz NotSupported5\n\t"		/* MMX not supported */		"testl $0x01000000, %%eax\n\t"	/* Test for Ext'd MMX */		"jnz EMMXSupported\n\t"		"movl $1, %0:\n\n\t"		/* MMX Supported */		"jmp Return\n\n"		"EMMXSupported:\n\t"		"movl $3, %0:\n\n\t"		/* EMMX and MMX Supported */		"jmp Return\n\t"		/* AMD Section */		"AMD:\n\t"		/* See if extended CPUID is supported */		"movl $0x80000000, %%eax\n\t"		"cpuid\n\t"		"cmpl $0x80000000, %%eax\n\t"		"jl MMXtest\n\t"	/* Try standard CPUID instead */		/* Extended CPUID supported, so get extended features */		"movl $0x80000001, %%eax\n\t"		"cpuid\n\t"		"testl $0x00800000, %%edx\n\t"	/* Test for MMX */		"jz NotSupported6\n\t"		/* MMX not supported */		"testl $0x80000000, %%edx\n\t"	/* Test for 3DNow! */		"jnz ThreeDNowSupported\n\t"		"movl $1, %0:\n\n\t"		/* MMX Supported */		"jmp Return\n\n"		"ThreeDNowSupported:\n\t"		"movl $5, %0:\n\n\t"		/* 3DNow! and MMX Supported */		"jmp Return\n\t"		/* Intel Section */		"Intel:\n\t"		/* Check for MMX */		"MMXtest:\n\t"		"movl $1, %%eax\n\t"		"cpuid\n\t"		"testl $0x00800000, %%edx\n\t"	/* Test for MMX */		"jz NotSupported7\n\t"		/* MMX Not supported */		"movl $1, %0:\n\n\t"		/* MMX Supported */		"jmp Return\n\t"		/* Nothing supported */		"\nNotSupported1:\n\t"		"#movl $101, %0:\n\n\t"		"\nNotSupported2:\n\t"		"#movl $102, %0:\n\n\t"		"\nNotSupported3:\n\t"		"#movl $103, %0:\n\n\t"		"\nNotSupported4:\n\t"		"#movl $104, %0:\n\n\t"		"\nNotSupported5:\n\t"		"#movl $105, %0:\n\n\t"		"\nNotSupported6:\n\t"		"#movl $106, %0:\n\n\t"		"\nNotSupported7:\n\t"		"#movl $107, %0:\n\n\t"		"movl $0, %0:\n\n\t"		"Return:\n\t"		: "=a" (rval)		: /* no input */		: "eax", "ebx", "ecx", "edx"	);	/* Return */	return(rval);}/*	Function to test if mmx instructions are supported...*/inline extern intmmx_ok(void){	/* Returns 1 if MMX instructions are supported, 0 otherwise */	return ( mm_support() & 0x1 );}/*	Helper functions for the instruction macros that follow...	(note that memory-to-register, m2r, instructions are nearly	 as efficient as register-to-register, r2r, instructions;	 however, memory-to-memory instructions are really simulated	 as a convenience, and are only 1/3 as efficient)*/#ifdef	MMX_TRACE/*	Include the stuff for printing a trace to stderr...*/#include <stdio.h>#define	mmx_i2r(op, imm, reg) \	{ \		mmx_t mmx_trace; \		mmx_trace = (imm); \		fprintf(stderr, #op "_i2r(" #imm "=0x%016llx, ", mmx_trace.q); \		__asm__ __volatile__ ("movq %%" #reg ", %0" \				      : "=X" (mmx_trace) \				      : /* nothing */ ); \		fprintf(stderr, #reg "=0x%016llx) => ", mmx_trace.q); \		__asm__ __volatile__ (#op " %0, %%" #reg \				      : /* nothing */ \				      : "X" (imm)); \		__asm__ __volatile__ ("movq %%" #reg ", %0" \				      : "=X" (mmx_trace) \				      : /* nothing */ ); \		fprintf(stderr, #reg "=0x%016llx\n", mmx_trace.q); \	}#define	mmx_m2r(op, mem, reg) \	{ \		mmx_t mmx_trace; \		mmx_trace = (mem); \		fprintf(stderr, #op "_m2r(" #mem "=0x%016llx, ", mmx_trace.q); \		__asm__ __volatile__ ("movq %%" #reg ", %0" \				      : "=X" (mmx_trace) \				      : /* nothing */ ); \		fprintf(stderr, #reg "=0x%016llx) => ", mmx_trace.q); \		__asm__ __volatile__ (#op " %0, %%" #reg \				      : /* nothing */ \				      : "X" (mem)); \		__asm__ __volatile__ ("movq %%" #reg ", %0" \				      : "=X" (mmx_trace) \				      : /* nothing */ ); \		fprintf(stderr, #reg "=0x%016llx\n", mmx_trace.q); \	}#define	mmx_r2m(op, reg, mem) \	{ \		mmx_t mmx_trace; \		__asm__ __volatile__ ("movq %%" #reg ", %0" \				      : "=X" (mmx_trace) \				      : /* nothing */ ); \		fprintf(stderr, #op "_r2m(" #reg "=0x%016llx, ", mmx_trace.q); \		mmx_trace = (mem); \		fprintf(stderr, #mem "=0x%016llx) => ", mmx_trace.q); \		__asm__ __volatile__ (#op " %%" #reg ", %0" \				      : "=X" (mem) \				      : /* nothing */ ); \		mmx_trace = (mem); \		fprintf(stderr, #mem "=0x%016llx\n", mmx_trace.q); \	}#define	mmx_r2r(op, regs, regd) \	{ \		mmx_t mmx_trace; \		__asm__ __volatile__ ("movq %%" #regs ", %0" \				      : "=X" (mmx_trace) \				      : /* nothing */ ); \		fprintf(stderr, #op "_r2r(" #regs "=0x%016llx, ", mmx_trace.q); \		__asm__ __volatile__ ("movq %%" #regd ", %0" \				      : "=X" (mmx_trace) \				      : /* nothing */ ); \		fprintf(stderr, #regd "=0x%016llx) => ", mmx_trace.q); \		__asm__ __volatile__ (#op " %" #regs ", %" #regd); \		__asm__ __volatile__ ("movq %%" #regd ", %0" \				      : "=X" (mmx_trace) \				      : /* nothing */ ); \		fprintf(stderr, #regd "=0x%016llx\n", mmx_trace.q); \	}#define	mmx_m2m(op, mems, memd) \	{ \		mmx_t mmx_trace; \		mmx_trace = (mems); \		fprintf(stderr, #op "_m2m(" #mems "=0x%016llx, ", mmx_trace.q); \		mmx_trace = (memd); \		fprintf(stderr, #memd "=0x%016llx) => ", mmx_trace.q); \		__asm__ __volatile__ ("movq %0, %%mm0\n\t" \				      #op " %1, %%mm0\n\t" \				      "movq %%mm0, %0" \				      : "=X" (memd) \				      : "X" (mems)); \		mmx_trace = (memd); \		fprintf(stderr, #memd "=0x%016llx\n", mmx_trace.q); \	}#else/*	These macros are a lot simpler without the tracing...