memcpy.s

Glibc 2.3.2源代码(解压后有100多M)

313:	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)	STORE_JUMP(o0, f48, 434f) membar #Sync
	VISLOOP_PAD
320:	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)	LOOP_CHUNK1(o1, o0, g6, 321f)
	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)	LOOP_CHUNK2(o1, o0, g6, 322f)
	FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)	LOOP_CHUNK3(o1, o0, g6, 323f)
	b,pt		%xcc, 320b+4; faligndata %f4, %f6, %f48
321:	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)	STORE_JUMP(o0, f48, 404f) membar #Sync
322:	FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)	STORE_JUMP(o0, f48, 420f) membar #Sync
323:	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)	STORE_JUMP(o0, f48, 436f) membar #Sync
	VISLOOP_PAD
330:	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)	LOOP_CHUNK1(o1, o0, g6, 331f)
	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)	LOOP_CHUNK2(o1, o0, g6, 332f)
	FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)	LOOP_CHUNK3(o1, o0, g6, 333f)
	b,pt		%xcc, 330b+4; faligndata %f6, %f8, %f48
331:	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)	STORE_JUMP(o0, f48, 406f) membar #Sync
332:	FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)	STORE_JUMP(o0, f48, 422f) membar #Sync
333:	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)	STORE_JUMP(o0, f48, 438f) membar #Sync
	VISLOOP_PAD
340:	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)	LOOP_CHUNK1(o1, o0, g6, 341f)
	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)	LOOP_CHUNK2(o1, o0, g6, 342f)
	FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)	LOOP_CHUNK3(o1, o0, g6, 343f)
	b,pt		%xcc, 340b+4; faligndata %f8, %f10, %f48
341:	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)	STORE_JUMP(o0, f48, 408f) membar #Sync
342:	FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)	STORE_JUMP(o0, f48, 424f) membar #Sync
343:	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)	STORE_JUMP(o0, f48, 440f) membar #Sync
	VISLOOP_PAD
350:	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)	LOOP_CHUNK1(o1, o0, g6, 351f)
	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)	LOOP_CHUNK2(o1, o0, g6, 352f)
	FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)	LOOP_CHUNK3(o1, o0, g6, 353f)
	b,pt		%xcc, 350b+4; faligndata %f10, %f12, %f48
351:	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)	STORE_JUMP(o0, f48, 410f) membar #Sync
352:	FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)	STORE_JUMP(o0, f48, 426f) membar #Sync
353:	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)	STORE_JUMP(o0, f48, 442f) membar #Sync
	VISLOOP_PAD
360:	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)	LOOP_CHUNK1(o1, o0, g6, 361f)
	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)	LOOP_CHUNK2(o1, o0, g6, 362f)
	FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)	LOOP_CHUNK3(o1, o0, g6, 363f)
	b,pt		%xcc, 360b+4; faligndata %f12, %f14, %f48
361:	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)	STORE_JUMP(o0, f48, 412f) membar #Sync
362:	FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)	STORE_JUMP(o0, f48, 428f) membar #Sync
363:	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)	STORE_JUMP(o0, f48, 444f) membar #Sync
	VISLOOP_PAD
370:	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)	LOOP_CHUNK1(o1, o0, g6, 371f)
	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)	LOOP_CHUNK2(o1, o0, g6, 372f)
	FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)	LOOP_CHUNK3(o1, o0, g6, 373f)
	b,pt		%xcc, 370b+4; faligndata %f14, %f16, %f48
371:	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)	STORE_JUMP(o0, f48, 414f) membar #Sync
372:	FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)	STORE_JUMP(o0, f48, 430f) membar #Sync
373:	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)	STORE_SYNC(o0, f48) membar #Sync
	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)	STORE_JUMP(o0, f48, 446f) membar #Sync
	VISLOOP_PAD
400:	FINISH_VISCHUNK(o0, f0,  f2,  g3)
402:	FINISH_VISCHUNK(o0, f2,  f4,  g3)
404:	FINISH_VISCHUNK(o0, f4,  f6,  g3)
406:	FINISH_VISCHUNK(o0, f6,  f8,  g3)
408:	FINISH_VISCHUNK(o0, f8,  f10, g3)
410:	FINISH_VISCHUNK(o0, f10, f12, g3)
412:	FINISH_VISCHUNK(o0, f12, f14, g3)
414:	UNEVEN_VISCHUNK(o0, f14, f0,  g3)
416:	FINISH_VISCHUNK(o0, f16, f18, g3)
418:	FINISH_VISCHUNK(o0, f18, f20, g3)
420:	FINISH_VISCHUNK(o0, f20, f22, g3)
422:	FINISH_VISCHUNK(o0, f22, f24, g3)
424:	FINISH_VISCHUNK(o0, f24, f26, g3)
426:	FINISH_VISCHUNK(o0, f26, f28, g3)
428:	FINISH_VISCHUNK(o0, f28, f30, g3)
430:	UNEVEN_VISCHUNK(o0, f30, f0,  g3)
432:	FINISH_VISCHUNK(o0, f32, f34, g3)
434:	FINISH_VISCHUNK(o0, f34, f36, g3)
436:	FINISH_VISCHUNK(o0, f36, f38, g3)
438:	FINISH_VISCHUNK(o0, f38, f40, g3)
440:	FINISH_VISCHUNK(o0, f40, f42, g3)
442:	FINISH_VISCHUNK(o0, f42, f44, g3)
444:	FINISH_VISCHUNK(o0, f44, f46, g3)
446:	UNEVEN_VISCHUNK(o0, f46, f0,  g3)
204:	ldd		[%o1], %f2			/* Load		Group		*/
	add		%o1, 8, %o1			/* IEU0				*/
	subcc		%g3, 8, %g3			/* IEU1				*/
	faligndata	%f0, %f2, %f8			/* GRU		Group		*/
	std		%f8, [%o0]			/* Store			*/
	bl,pn		%xcc, 205f			/* CTI				*/
	 add		%o0, 8, %o0			/* IEU0		Group		*/
	ldd		[%o1], %f0			/* Load		Group		*/
	add		%o1, 8, %o1			/* IEU0				*/
	subcc		%g3, 8, %g3			/* IEU1				*/
	faligndata	%f2, %f0, %f8			/* GRU		Group		*/
	std		%f8, [%o0]			/* Store			*/
	bge,pt		%xcc, 204b			/* CTI				*/
	 add		%o0, 8, %o0			/* IEU0		Group		*/
205:	brz,pt		%o2, 207f			/* CTI		Group		*/
	 mov		%g1, %o1			/* IEU0				*/
206:	ldub		[%o1], %g5			/* LOAD				*/
	add		%o1, 1, %o1			/* IEU0				*/
	add		%o0, 1, %o0			/* IEU1				*/
	subcc		%o2, 1, %o2			/* IEU1				*/
	bne,pt		%xcc, 206b			/* CTI				*/
	 stb		%g5, [%o0 - 1]			/* Store	Group		*/
207:	membar		#StoreLoad | #StoreStore	/* LSU		Group		*/
	wr		%g0, FPRS_FEF, %fprs
	retl
	 mov		%g4, %o0

208:	andcc		%o2, 1, %g0			/* IEU1		Group		*/
	be,pt		%icc, 2f+4			/* CTI				*/
1:	 ldub		[%o1], %g5			/* LOAD		Group		*/
	add		%o1, 1, %o1			/* IEU0				*/
	add		%o0, 1, %o0			/* IEU1				*/
	subcc		%o2, 1, %o2			/* IEU1		Group		*/
	be,pn		%xcc, 209f			/* CTI				*/
	 stb		%g5, [%o0 - 1]			/* Store			*/
2:	ldub		[%o1], %g5			/* LOAD		Group		*/
	add		%o0, 2, %o0			/* IEU0				*/
	ldub		[%o1 + 1], %o5			/* LOAD		Group		*/
	add		%o1, 2, %o1			/* IEU0				*/
	subcc		%o2, 2, %o2			/* IEU1		Group		*/
	stb		%g5, [%o0 - 2]			/* Store			*/
	bne,pt		%xcc, 2b			/* CTI				*/
	 stb		%o5, [%o0 - 1]			/* Store			*/
209:	retl
	 mov		%g4, %o0

#ifdef USE_BPR

	/* void *__align_cpy_4(void *dest, void *src, size_t n)
	 * SPARC v9 SYSV ABI
	 * Like memcpy, but results are undefined if (!n || ((dest | src | n) & 3))
	 */

	.align		32
ENTRY(__align_cpy_4)
	mov		%o0, %g4			/* IEU0		Group		*/
	cmp		%o2, 15				/* IEU1				*/
	bleu,pn		%xcc, 208b			/* CTI				*/
	 cmp		%o2, (64 * 6)			/* IEU1		Group		*/
	bgeu,pn		%xcc, 200b			/* CTI				*/
	 andcc		%o0, 7, %g2			/* IEU1		Group		*/
	ba,pt		%xcc, 216f			/* CTI				*/
	 andcc		%o1, 4, %g0			/* IEU1		Group		*/
END(__align_cpy_4)

	/* void *__align_cpy_8(void *dest, void *src, size_t n)
	 * SPARC v9 SYSV ABI
	 * Like memcpy, but results are undefined if (!n || ((dest | src | n) & 7))
	 */

	.align		32
ENTRY(__align_cpy_8)
	mov		%o0, %g4			/* IEU0		Group		*/
	cmp		%o2, 15				/* IEU1				*/
	bleu,pn		%xcc, 208b			/* CTI				*/
	 cmp		%o2, (64 * 6)			/* IEU1		Group		*/
	bgeu,pn		%xcc, 201b			/* CTI				*/
	 andcc		%o0, 0x38, %g5			/* IEU1		Group		*/
	andcc		%o2, -128, %g6			/* IEU1		Group		*/
	bne,a,pt	%xcc, 82f + 4			/* CTI				*/
	 ldx		[%o1], %g1			/* Load				*/
	ba,pt		%xcc, 41f			/* CTI		Group		*/
	 andcc		%o2, 0x70, %g6			/* IEU1				*/
END(__align_cpy_8)

	/* void *__align_cpy_16(void *dest, void *src, size_t n)
	 * SPARC v9 SYSV ABI
	 * Like memcpy, but results are undefined if (!n || ((dest | src | n) & 15))
	 */

	.align		32
ENTRY(__align_cpy_16)
	mov		%o0, %g4			/* IEU0		Group		*/
	cmp		%o2, (64 * 6)			/* IEU1				*/
	bgeu,pn		%xcc, 201b			/* CTI				*/
	 andcc		%o0, 0x38, %g5			/* IEU1		Group		*/
	andcc		%o2, -128, %g6			/* IEU1		Group		*/
	bne,a,pt	%xcc, 82f + 4			/* CTI				*/
	 ldx		[%o1], %g1			/* Load				*/
	ba,pt		%xcc, 41f			/* CTI		Group		*/
	 andcc		%o2, 0x70, %g6			/* IEU1				*/
END(__align_cpy_16)

#endif

	.align		32
ENTRY(memcpy)
210:
#ifndef USE_BPR
	srl		%o2, 0, %o2			/* IEU1		Group		*/
#endif	
	brz,pn		%o2, 209b			/* CTI		Group		*/
	 mov		%o0, %g4			/* IEU0				*/
218:	cmp		%o2, 15				/* IEU1		Group		*/
	bleu,pn		%xcc, 208b			/* CTI				*/
	 cmp		%o2, (64 * 6)			/* IEU1		Group		*/
	bgeu,pn		%xcc, 200b			/* CTI				*/
	 andcc		%o0, 7, %g2			/* IEU1		Group		*/
	sub		%o0, %o1, %g5			/* IEU0				*/
	andcc		%g5, 3, %o5			/* IEU1		Group		*/
	bne,pn		%xcc, 212f			/* CTI				*/
	 andcc		%o1, 3, %g0			/* IEU1		Group		*/
	be,a,pt		%xcc, 216f			/* CTI				*/
	 andcc		%o1, 4, %g0			/* IEU1		Group		*/
	andcc		%o1, 1, %g0			/* IEU1		Group		*/
	be,pn		%xcc, 4f			/* CTI				*/
	 andcc		%o1, 2, %g0			/* IEU1		Group		*/
	ldub		[%o1], %g2			/* Load		Group		*/
	add		%o1, 1, %o1			/* IEU0				*/
	add		%o0, 1, %o0			/* IEU1				*/
	sub		%o2, 1, %o2			/* IEU0		Group		*/
	bne,pn		%xcc, 5f			/* CTI		Group		*/
	 stb		%g2, [%o0 - 1]			/* Store			*/
4:	lduh		[%o1], %g2			/* Load		Group		*/
	add		%o1, 2, %o1			/* IEU0				*/
	add		%o0, 2, %o0			/* IEU1				*/
	sub		%o2, 2, %o2			/* IEU0				*/
	sth		%g2, [%o0 - 2]			/* Store	Group + bubble	*/
5:	andcc		%o1, 4, %g0			/* IEU1				*/
216:	be,a,pn		%xcc, 2f			/* CTI				*/
	 andcc		%o2, -128, %g6			/* IEU1		Group		*/
	lduw		[%o1], %g5			/* Load		Group		*/
	add		%o1, 4, %o1			/* IEU0				*/
	add		%o0, 4, %o0			/* IEU1				*/
	sub		%o2, 4, %o2			/* IEU0		Group		*/
	stw		%g5, [%o0 - 4]			/* Store			*/
	andcc		%o2, -128, %g6			/* IEU1		Group		*/
2:	be,pn		%xcc, 215f			/* CTI				*/
	 andcc		%o0, 4, %g0			/* IEU1		Group		*/
	be,pn		%xcc, 82f + 4			/* CTI		Group		*/
5:	MOVE_BIGCHUNK(o1, o0, 0x00, g1, g3, g5, o5)
	MOVE_BIGCHUNK(o1, o0, 0x20, g1, g3, g5, o5)
	MOVE_BIGCHUNK(o1, o0, 0x40, g1, g3, g5, o5)
	MOVE_BIGCHUNK(o1, o0, 0x60, g1, g3, g5, o5)
35:	subcc		%g6, 128, %g6			/* IEU1		Group		*/
	add		%o1, 128, %o1			/* IEU0				*/
	bne,pt		%xcc, 5b			/* CTI				*/
	 add		%o0, 128, %o0			/* IEU0		Group		*/
215:	andcc		%o2, 0x70, %g6			/* IEU1		Group		*/
41:	be,pn		%xcc, 80f			/* CTI				*/
	 andcc		%o2, 8, %g0			/* IEU1		Group		*/
							/* Clk1 8-(			*/
							/* Clk2 8-(			*/
							/* Clk3 8-(			*/
							/* Clk4 8-(			*/
79:	rd		%pc, %o5			/* PDU		Group		*/
	sll		%g6, 1, %g5			/* IEU0		Group		*/
	add		%o1, %g6, %o1			/* IEU1				*/
	sub		%o5, %g5, %o5			/* IEU0  	Group		*/
	jmpl		%o5 + %lo(80f - 79b), %g0	/* CTI		Group brk forced*/
	 add		%o0, %g6, %o0			/* IEU0		Group		*/
36:	MOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g5, o5)
	MOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g5, o5)
	MOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g5, o5)
	MOVE_LASTCHUNK(o1, o0, 0x30, g2, g3, g5, o5)
	MOVE_LASTCHUNK(o1, o0, 0x20, g2, g3, g5, o5)
	MOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g5, o5)
	MOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g5, o5)
80:	be,pt		%xcc, 81f			/* CTI				*/
	 andcc		%o2, 4, %g0			/* IEU1				*/
	ldx		[%o1], %g2			/* Load		Group		*/
	add		%o0, 8, %o0			/* IEU0				*/
	stw		%g2, [%o0 - 0x4]		/* Store	Group		*/
	add		%o1, 8, %o1			/* IEU1				*/
	srlx		%g2, 32, %g2			/* IEU0		Group		*/
	stw		%g2, [%o0 - 0x8]		/* Store			*/
81:	be,pt		%xcc, 1f			/* CTI				*/
	 andcc		%o2, 2, %g0			/* IEU1		Group		*/
	lduw		[%o1], %g2			/* Load		Group		*/
	add		%o1, 4, %o1			/* IEU0				*/
	stw		%g2, [%o0]			/* Store	Group		*/
	add		%o0, 4, %o0			/* IEU0				*/
1:	be,pt		%xcc, 1f			/* CTI				*/
	 andcc		%o2, 1, %g0			/* IEU1		Group		*/
	lduh		[%o1], %g2			/* Load		Group		*/
	add		%o1, 2, %o1			/* IEU0				*/
	sth		%g2, [%o0]			/* Store	Group		*/
	add		%o0, 2, %o0			/* IEU0				*/
1:	be,pt		%xcc, 211f			/* CTI				*/
	 nop						/* IEU1				*/
	ldub		[%o1], %g2			/* Load		Group		*/
	stb		%g2, [%o0]			/* Store	Group + bubble	*/
211:	retl
	 mov		%g4, %o0

82:	MOVE_BIGALIGNCHUNK(o1, o0, 0x00, g1, g3, g5, o5)
	MOVE_BIGALIGNCHUNK(o1, o0, 0x40, g1, g3, g5, o5)
37:	subcc		%g6, 128, %g6			/* IEU1		Group		*/
	add		%o1, 128, %o1			/* IEU0				*/
	bne,pt		%xcc, 82b			/* CTI				*/
	 add		%o0, 128, %o0			/* IEU0		Group		*/
	andcc		%o2, 0x70, %g6			/* IEU1				*/
	be,pn		%xcc, 84f			/* CTI				*/
	 andcc		%o2, 8, %g0			/* IEU1		Group		*/