⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 saxpy.s

📁 Optimized GotoBLAS libraries
💻 S
📖 第 1 页 / 共 2 页
字号:
	br.ret.sptk.many b0	;;	.align 32.L30:	{ .mmi	cmp.eq	p9, p0  =   r0, J	cmp.eq	p7 ,p0  = 0, I	mov	ar.ec = 4	}	{ .mmi	cmp.lt	p12, p0 = 33, XA	adds	I = -1, I	}	;;	{ .mmi	cmp.gt	p14, p0 =  15, XA	cmp.lt	p15, p0 =  60, XA	(p12) cmp.gt.unc p13, p0 = 53, XA	}	{ .bbb	(p13) br.cond.dpnt .L40	(p14) br.cond.dpnt .L40	(p15) br.cond.dpnt .L40	}	;;	{ .mmi	(p10) STFD [YYY] = f32	adds	PRE1 = (PREFETCHSIZE +  6) * SIZE, X	mov	ar.lc = I	}	{ .mib	adds	PRE2 = (PREFETCHSIZE +  0) * SIZE, Y	tbit.z	p0, p12 = N, 3	(p7) br.cond.dpnt  .L35	}	;;	.align 32.L32:	{ .mmf	(p19) STFD	[Y1] = f6,   1 * SIZE	(p19) STFD	[Y2] = f7,   1 * SIZE	(p18) FMA	f6  = ALPHA, f34, f82	}	{ .mmf	(p16) LDFPD	f32,  f35  = [X], 2 * SIZE	(p16) LDFD	f80 = [Y], 1 * SIZE	(p18) FMA	f7  = ALPHA, f46, f94	}	;;	{ .mmf	(p19) STFD	[Y1] = f10,  1 * SIZE	(p19) STFD	[Y2] = f11,  1 * SIZE	(p18) FMA	f10 = ALPHA, f37, f85	}	{ .mmf	(p16) LDFPD	f38,  f41  = [X], 2 * SIZE	(p16) LDFPD	f83,  f86  = [Y], 2 * SIZE	(p18) FMA	f11 = ALPHA, f49, f97	}	;;	{ .mmf	(p19) STFD	[Y1] = f12,  1 * SIZE	(p19) STFD	[Y2] = f13,  1 * SIZE	(p18) FMA	f12 = ALPHA, f40, f88	}	{ .mmf	(p16) LDFPD	f44,  f47  = [X], 2 * SIZE	(p16) LDFPD	f89,  f92  = [Y], 2 * SIZE	(p18) FMA	f13 = ALPHA, f52, f100	}	;;	{ .mmf	(p19) STFD	[Y1] = f14,  5 * SIZE	(p19) STFD	[Y2] = f15,  5 * SIZE	(p18) FMA	f14 = ALPHA, f43, f91	}	{ .mmf	(p16) LDFPD	f50,  f53  = [X], 2 * SIZE	(p16) LDFPD	f95,  f98  = [Y], 2 * SIZE	(p18) FMA	f15 = ALPHA, f55, f103	}	;;	{ .mmf	(p18) STFD	[Y1] = f6,   1 * SIZE	(p18) STFD	[Y2] = f7,   1 * SIZE	(p18) FMA	f6  = ALPHA, f58, f106	}	{ .mmf	(p16) LDFPD	f56,  f59  = [X], 2 * SIZE	(p16) LDFPD	f101, f104 = [Y], 2 * SIZE	(p18) FMA	f7  = ALPHA, f70, f118	}	;;	{ .mmf	(p18) STFD	[Y1] = f10,  1 * SIZE	(p18) STFD	[Y2] = f11,  1 * SIZE	(p18) FMA	f10 = ALPHA, f61, f109	}	{ .mmf	(p16) LDFPD	f62,  f65  = [X], 2 * SIZE	(p16) LDFPD	f107, f110 = [Y], 2 * SIZE	(p18) FMA	f11 = ALPHA, f73, f121	}	;;	{ .mmf	(p18) STFD	[Y1] = f12,  1 * SIZE	(p18) STFD	[Y2] = f13,  1 * SIZE	(p18) FMA	f12 = ALPHA, f64, f112	}	{ .mmf	(p16) LDFPD	f68,  f71  = [X], 2 * SIZE	(p16) LDFPD	f113, f116 = [Y], 2 * SIZE	(p18) FMA	f13 = ALPHA, f76, f124	}	;;	{ .mmf	(p18) STFD	[Y1] = f14,  5 * SIZE	(p18) STFD	[Y2] = f15,  5 * SIZE	(p18) FMA	f14 = ALPHA, f67, f115	}	{ .mmf	(p16) LDFPD	f74,  f77  = [X], 2 * SIZE	(p16) LDFPD	f119, f122 = [Y], 2 * SIZE	(p18) FMA	f15 = ALPHA, f79, f127	}	;;	{ .mmi	(p16) lfetch.nt1	[PRE1], 16 * SIZE	(p16) lfetch.excl.nt1	[PRE2], 16 * SIZE	nop.i 0	}	{ .mmb	(p16) LDFD	f125  = [Y], 1 * SIZE	nop.m 0	br.ctop.sptk.few .L32	}	;;	.align 32.L35:	{ .mmi	(p12) LDFPD	f32,  f33  = [X], 2 * SIZE	(p12) LDFD	f34 = [Y], 1 * SIZE;	mov	pr = PR, -65474	}	;;	{ .mmi	(p12) LDFPD	f36,  f37  = [X], 2 * SIZE	(p12) LDFPD	f35,  f38  = [Y], 2 * SIZE	mov	ar.lc  = ARLC	}	;;	{ .mmb	(p12) LDFPD	f40,  f41  = [X], 2 * SIZE	(p12) LDFPD	f39,  f42  = [Y], 2 * SIZE	(p9) br.ret.sptk.many b0	}	;;	{ .mmi	(p12) LDFPD	f44,  f45  = [X], 2 * SIZE	(p12) LDFPD	f43,  f46  = [Y], 2 * SIZE	tbit.z	p0, p13 = N, 2	}	;;	{ .mmi	(p13) LDFPD	f48,  f49  = [X], 2 * SIZE	(p12) LDFD	f47 = [Y], 1 * SIZE	tbit.z	p0, p14 = N, 1	}	;;	{ .mmi	(p13) LDFPD	f52,  f53  = [X], 2 * SIZE	(p13) LDFD	f50 = [Y], 1 * SIZE	tbit.z	p0, p15 = N, 0	}	;;	{ .mmi	(p14) LDFPD	f56,  f57  = [X], 2 * SIZE	(p13) LDFPD	f51,  f54  = [Y], 2 * SIZE	mov   YY = Y1;	}	;;	(p15) LDFD	f60 = [X]	(p13) LDFD	f55 = [Y], 1 * SIZE	;;	(p14) LDFD	f58 = [Y], 1 * SIZE	(p12) FMA	f6  = ALPHA, f32, f34	(p12) FMA	f7  = ALPHA, f40, f42	;;	(p14) LDFD	f59 = [Y], 1 * SIZE	(p12) shladd YY = INCY, 3, YY	(p12) FMA	f10 = ALPHA, f33, f35	(p12) FMA	f11 = ALPHA, f41, f43	;;	(p15) LDFD	f61  = [Y]	(p13) shladd YY = INCY, 2, YY	(p12) FMA	f12 = ALPHA, f36, f38	(p12) FMA	f13 = ALPHA, f44, f46	;;	(p12) STFD	[Y1] = f6,   1 * SIZE	(p12) FMA	f14 = ALPHA, f37, f39	(p12) STFD	[Y2] = f7,   1 * SIZE	(p12) FMA	f15 = ALPHA, f45, f47	;;	(p12) STFD	[Y1] = f10,  1 * SIZE	(p13) FMA	f6  = ALPHA, f48, f50	(p12) STFD	[Y2] = f11,  1 * SIZE	(p14) FMA	f7  = ALPHA, f56, f58	;;	(p12) STFD	[Y1] = f12,  1 * SIZE	(p13) FMA	f10 = ALPHA, f49, f51	(p12) STFD	[Y2] = f13,  1 * SIZE	(p14) FMA	f11 = ALPHA, f57, f59	;;	(p12) STFD	[Y1] = f14,  5 * SIZE	(p13) FMA	f12 = ALPHA, f52, f54	(p12) STFD	[Y2] = f15,  5 * SIZE	(p15) FMA	f13 = ALPHA, f60, f61	;;	(p13) STFD	[Y1] = f6,   1 * SIZE	(p14) STFD	[YY] = f7,   1 * SIZE	(p13) FMA	f14 = ALPHA, f53, f55	;;	(p13) STFD	[Y1] = f10,  1 * SIZE	(p14) STFD	[YY] = f11,  1 * SIZE	;;	(p13) STFD	[Y1] = f12,  1 * SIZE	(p15) STFD	[YY] = f13	;;	(p13) STFD	[Y1] = f14	br.ret.sptk.many b0	;;	.align 32.L40:	{ .mmi	(p10) STFD [YYY] = f32	adds	PRE1 = (PREFETCHSIZE + 38) * SIZE, X	mov	ar.lc = I	}	{ .mib	adds	PRE2 = (PREFETCHSIZE + 14) * SIZE, Y	tbit.z	p0, p12 = N, 3	(p7) br.cond.dpnt  .L45	}	;;	.align 32.L42:	{ .mmf	(p19) STFD	[Y1] = f6,   1 * SIZE	(p19) STFD	[Y2] = f7,   1 * SIZE	(p18) FMA	f6  = ALPHA, f34, f82	}	{ .mmf	(p16) lfetch.nt1	[PRE1], 16 * SIZE	(p17) LDFPD	f102, f105 = [Y], 2 * SIZE	(p18) FMA	f7  = ALPHA, f46, f94	}	;;	{ .mmf	(p19) STFD	[Y1] = f10,  1 * SIZE	(p19) STFD	[Y2] = f11,  1 * SIZE	(p18) FMA	f10 = ALPHA, f37, f85	}	{ .mmf	(p17) LDFPD	f33,  f36  = [X], 2 * SIZE	(p17) LDFPD	f108, f111 = [Y], 2 * SIZE	(p18) FMA	f11 = ALPHA, f49, f97	}	;;	{ .mmf	(p19) STFD	[Y1] = f12,  1 * SIZE	(p19) STFD	[Y2] = f13,  1 * SIZE	(p18) FMA	f12 = ALPHA, f40, f88	}	{ .mmf	(p17) LDFPD	f39,  f42  = [X], 2 * SIZE	(p17) LDFPD	f114, f117 = [Y], 2 * SIZE	(p18) FMA	f13 = ALPHA, f52, f100	}	;;	{ .mmf	(p19) STFD	[Y1] = f14,  5 * SIZE	(p19) STFD	[Y2] = f15,  5 * SIZE	(p18) FMA	f14 = ALPHA, f43, f91	}	{ .mmf	(p17) LDFPD	f45,  f48  = [X], 2 * SIZE	(p17) LDFPD	f120, f123 = [Y], 2 * SIZE	(p18) FMA	f15 = ALPHA, f55, f103	}	;;	{ .mmf	(p18) STFD	[Y1] = f6,   1 * SIZE	(p18) STFD	[Y2] = f7,   1 * SIZE	(p18) FMA	f6  = ALPHA, f58, f106	}	{ .mmf	(p17) LDFPD	f51,  f54  = [X], 2 * SIZE	(p17) LDFD	f126  = [Y], 1 * SIZE	(p18) FMA	f7  = ALPHA, f70, f118	}	;;	{ .mmf	(p18) STFD	[Y1] = f10,  1 * SIZE	(p18) STFD	[Y2] = f11,  1 * SIZE	(p18) FMA	f10 = ALPHA, f61, f109	}	{ .mmf	(p17) LDFPD	f57,  f60  = [X], 2 * SIZE	(p16) LDFD	f80 = [Y], 1 * SIZE	(p18) FMA	f11 = ALPHA, f73, f121	}	;;	{ .mmf	(p18) STFD	[Y1] = f12,  1 * SIZE	(p18) STFD	[Y2] = f13,  1 * SIZE	(p18) FMA	f12 = ALPHA, f64, f112	}	{ .mmf	(p17) LDFPD	f63,  f66  = [X], 2 * SIZE	(p16) LDFPD	f83,  f86  = [Y], 2 * SIZE	(p18) FMA	f13 = ALPHA, f76, f124	}	;;	{ .mmf	(p18) STFD	[Y1] = f14,  5 * SIZE	(p18) STFD	[Y2] = f15,  5 * SIZE	(p18) FMA	f14 = ALPHA, f67, f115	}	{ .mmf	(p17) LDFPD	f69,  f72  = [X], 2 * SIZE	(p16) LDFPD	f89,  f92  = [Y], 2 * SIZE	(p18) FMA	f15 = ALPHA, f79, f127	}	;;#if 0	(p16) lfetch.excl.nt1	[PRE2], 16 * SIZE#endif	{ .mmb	(p17) LDFPD	f75,  f78  = [X], 2 * SIZE	(p16) LDFPD	f95,  f98  = [Y], 2 * SIZE	br.ctop.sptk.few .L42	}	;;	{ .mmf	(p19) STFD	[Y1] = f6,   1 * SIZE	(p19) STFD	[Y2] = f7,   1 * SIZE	}	;;	{ .mmf	(p19) STFD	[Y1] = f10,  1 * SIZE	(p19) STFD	[Y2] = f11,  1 * SIZE	}	;;	{ .mmf	(p19) STFD	[Y1] = f12,  1 * SIZE	(p19) STFD	[Y2] = f13,  1 * SIZE	}	;;	{ .mmf	(p19) STFD	[Y1] = f14,  5 * SIZE	(p19) STFD	[Y2] = f15,  5 * SIZE	}	;;	.align 32.L45:	{ .mmi	(p12) LDFPD	f32,  f33  = [X], 2 * SIZE	(p12) LDFD	f34 = [Y], 1 * SIZE;	mov	pr = PR, -65474	}	;;	{ .mmi	(p12) LDFPD	f36,  f37  = [X], 2 * SIZE	(p12) LDFPD	f35,  f38  = [Y], 2 * SIZE	mov	ar.lc  = ARLC	}	;;	{ .mmb	(p12) LDFPD	f40,  f41  = [X], 2 * SIZE	(p12) LDFPD	f39,  f42  = [Y], 2 * SIZE	(p9) br.ret.sptk.many b0	}	;;	{ .mmi	(p12) LDFPD	f44,  f45  = [X], 2 * SIZE	(p12) LDFPD	f43,  f46  = [Y], 2 * SIZE	tbit.z	p0, p13 = N, 2	}	;;	{ .mmi	(p13) LDFPD	f48,  f49  = [X], 2 * SIZE	(p12) LDFD	f47 = [Y], 1 * SIZE	tbit.z	p0, p14 = N, 1	}	;;	{ .mmi	(p13) LDFPD	f52,  f53  = [X], 2 * SIZE	(p13) LDFD	f50 = [Y], 1 * SIZE	tbit.z	p0, p15 = N, 0	}	;;	{ .mmi	(p14) LDFPD	f56,  f57  = [X], 2 * SIZE	(p13) LDFPD	f51,  f54  = [Y], 2 * SIZE	mov   YY = Y1;	}	;;	(p15) LDFD	f60 = [X]	(p13) LDFD	f55 = [Y], 1 * SIZE	;;	(p14) LDFD	f58 = [Y], 1 * SIZE	(p12) FMA	f6  = ALPHA, f32, f34	(p12) FMA	f7  = ALPHA, f40, f42	;;	(p14) LDFD	f59 = [Y], 1 * SIZE	(p12) shladd YY = INCY, 3, YY	(p12) FMA	f10 = ALPHA, f33, f35	(p12) FMA	f11 = ALPHA, f41, f43	;;	(p15) LDFD	f61  = [Y]	(p13) shladd YY = INCY, 2, YY	(p12) FMA	f12 = ALPHA, f36, f38	(p12) FMA	f13 = ALPHA, f44, f46	;;	(p12) STFD	[Y1] = f6,   1 * SIZE	(p12) FMA	f14 = ALPHA, f37, f39	(p12) STFD	[Y2] = f7,   1 * SIZE	(p12) FMA	f15 = ALPHA, f45, f47	;;	(p12) STFD	[Y1] = f10,  1 * SIZE	(p13) FMA	f6  = ALPHA, f48, f50	(p12) STFD	[Y2] = f11,  1 * SIZE	(p14) FMA	f7  = ALPHA, f56, f58	;;	(p12) STFD	[Y1] = f12,  1 * SIZE	(p13) FMA	f10 = ALPHA, f49, f51	(p12) STFD	[Y2] = f13,  1 * SIZE	(p14) FMA	f11 = ALPHA, f57, f59	;;	(p12) STFD	[Y1] = f14,  5 * SIZE	(p13) FMA	f12 = ALPHA, f52, f54	(p12) STFD	[Y2] = f15,  5 * SIZE	(p15) FMA	f13 = ALPHA, f60, f61	;;	(p13) STFD	[Y1] = f6,   1 * SIZE	(p14) STFD	[YY] = f7,   1 * SIZE	(p13) FMA	f14 = ALPHA, f53, f55	;;	(p13) STFD	[Y1] = f10,  1 * SIZE	(p14) STFD	[YY] = f11,  1 * SIZE	;;	(p13) STFD	[Y1] = f12,  1 * SIZE	(p15) STFD	[YY] = f13	;;	(p13) STFD	[Y1] = f14	br.ret.sptk.many b0	;;	.align 32.L100:	{ .mii	and	J =  15, N	shr	I =  N, 4	mov	ar.ec = 3	}	;;	{ .mmi	cmp.eq	p9, p0  =   r0, J	cmp.eq	p7 ,p0  = 0, I	adds	I = -1, I	}	;;	{ .mmi	(p10) STFD [YYY] = f32	adds	PRE1 = PREFETCHSIZE * SIZE, X	mov	ar.lc = I	}	{ .mib	adds	PRE2 = PREFETCHSIZE * SIZE, Y	tbit.z	p0, p12 = N, 3	(p7) br.cond.dpnt  .L115	}	;;	.align 32.L112:	{ .mmi	(p18) STFD	[Y1] = f6	(p16) lfetch.nt1	[PRE1], INCX16	(p18) add Y1 = INCY, Y1	}	{.mmf	(p16) LDFD	f32  = [X], INCX	(p16) LDFD	f80  = [Y], INCY	(p18) FMA	f6  = ALPHA, f58, f106	}	;;	{ .mmi 	(p18) STFD	[Y1] = f7	(p16) lfetch.excl.nt1	[PRE2], INCY16	(p18) add Y1 = INCY, Y1	}	{ .mmf	(p16) LDFD	f35  = [X], INCX	(p16) LDFD	f83  = [Y], INCY	(p18) FMA	f7  = ALPHA, f61, f109	}	;;	{ .mmi	(p18) STFD	[Y1] = f10	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f38  = [X], INCX	(p16) LDFD	f86  = [Y], INCY	(p18) FMA	f10 = ALPHA, f64, f112	}	;;	{ .mmi	(p18) STFD	[Y1] = f11	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f41  = [X], INCX	(p16) LDFD	f89  = [Y], INCY	(p18) FMA	f11 = ALPHA, f67, f115	}	;;	{ .mmi	(p18) STFD	[Y1] = f12	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f44  = [X], INCX	(p16) LDFD	f92  = [Y], INCY	(p18) FMA	f12 = ALPHA, f70, f118	}	;;	{ .mmi	(p18) STFD	[Y1] = f13	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f47  = [X], INCX	(p16) LDFD	f95  = [Y], INCY	(p18) FMA	f13 = ALPHA, f73, f121	}	;;	{ .mmi	(p18) STFD	[Y1] = f14	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f50  = [X], INCX	(p16) LDFD	f98  = [Y], INCY	(p18) FMA	f14 = ALPHA, f76, f124	}	;;	{ .mmi	(p18) STFD	[Y1] = f15	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f53  = [X], INCX	(p16) LDFD	f101 = [Y], INCY	(p18) FMA	f15 = ALPHA, f79, f127	}	;;	{ .mmi	(p18) STFD	[Y1] = f6	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f56  = [X], INCX	(p16) LDFD	f104 = [Y], INCY	(p17) FMA	f6  = ALPHA, f33, f81	}	;;	{ .mmi 	(p18) STFD	[Y1] = f7	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f59  = [X], INCX	(p16) LDFD	f107 = [Y], INCY	(p17) FMA	f7  = ALPHA, f36, f84	}	;;	{ .mmi	(p18) STFD	[Y1] = f10	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f62  = [X], INCX	(p16) LDFD	f110 = [Y], INCY	(p17) FMA	f10 = ALPHA, f39, f87	}	;;	{ .mmi	(p18) STFD	[Y1] = f11	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f65  = [X], INCX	(p16) LDFD	f113 = [Y], INCY	(p17) FMA	f11 = ALPHA, f42, f90	}	;;	{ .mmi	(p18) STFD	[Y1] = f12	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f68  = [X], INCX	(p16) LDFD	f116 = [Y], INCY	(p17) FMA	f12 = ALPHA, f45, f93	}	;;	{ .mmi	(p18) STFD	[Y1] = f13	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f71  = [X], INCX	(p16) LDFD	f119 = [Y], INCY	(p17) FMA	f13 = ALPHA, f48, f96	}		;;	{ .mmi	(p18) STFD	[Y1] = f14	(p18) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p16) LDFD	f74  = [X], INCX	(p16) LDFD	f122 = [Y], INCY	(p17) FMA	f14 = ALPHA, f51, f99	}	;;	{ .mmf	(p18) STFD	[Y1] = f15	(p18) add Y1 = INCY, Y1	(p17) FMA	f15 = ALPHA, f54, f102	}	{ .mmb	(p16) LDFD	f77  = [X], INCX	(p16) LDFD	f125 = [Y], INCY	br.ctop.sptk.few .L112	}	;;	.align 32.L115:	(p12) LDFD f32 = [X], INCX	(p12) LDFD f34 = [Y], INCY	mov	pr = PR, -65474	;;	(p12) LDFD f33 = [X], INCX	(p12) LDFD f35 = [Y], INCY	mov	ar.lc  = ARLC	;;	(p12) LDFD f36 = [X], INCX	(p12) LDFD f38 = [Y], INCY	(p9) br.ret.sptk.many b0	;;	(p12) LDFD f37 = [X], INCX	(p12) LDFD f39 = [Y], INCY	tbit.z	p0, p13 = N, 2	;;	(p12) LDFD f40 = [X], INCX	(p12) LDFD f42 = [Y], INCY	tbit.z	p0, p14 = N, 1	;;	(p12) LDFD f41 = [X], INCX	(p12) LDFD f43 = [Y], INCY	tbit.z	p0, p15 = N, 0	;;	{ .mmf	(p12) LDFD f44 = [X], INCX	(p12) LDFD f46 = [Y], INCY	(p12) FMA	f6  = ALPHA, f32, f34	}	;;	{ .mmf	(p12) LDFD f45 = [X], INCX	(p12) LDFD f47 = [Y], INCY	(p12) FMA	f7  = ALPHA, f33, f35	}	;;	{ .mmf	(p13) LDFD f48 = [X], INCX	(p13) LDFD f50 = [Y], INCY	(p12) FMA	f10 = ALPHA, f36, f38	}	;;	{ .mmf	(p13) LDFD f49 = [X], INCX	(p13) LDFD f51 = [Y], INCY	(p12) FMA	f11 = ALPHA, f37, f39	}	;;	{ .mmi	(p12) STFD	[Y1] = f6	(p12) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p13) LDFD f52 = [X], INCX	(p13) LDFD f54 = [Y], INCY	(p12) FMA	f12 = ALPHA, f40, f42	}	;;	{ .mmi	(p12) STFD	[Y1] = f7	(p12) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p13) LDFD f53 = [X], INCX	(p13) LDFD f55 = [Y], INCY	(p12) FMA	f13 = ALPHA, f41, f43	}	;;	{ .mmi	(p12) STFD	[Y1] = f10	(p12) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p14) LDFD f56 = [X], INCX	(p14) LDFD f58 = [Y], INCY	(p12) FMA	f14 = ALPHA, f44, f46	}	;;	{ .mmi	(p12) STFD	[Y1] = f11	(p12) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p14) LDFD f57 = [X], INCX	(p14) LDFD f59 = [Y], INCY	(p12) FMA	f15 = ALPHA, f45, f47	}	;;	{ .mmi	(p12) STFD	[Y1] = f12	(p12) add Y1 = INCY, Y1	nop.i 0	}	{ .mmf	(p15) LDFD f60 = [X]	(p15) LDFD f61 = [Y]	(p13) FMA	f6  = ALPHA, f48, f50	}	;;	{ .mmf	(p12) STFD	[Y1] = f13	(p12) add Y1 = INCY, Y1	(p13) FMA	f7  = ALPHA, f49, f51	}	;;	{ .mmf	(p12) STFD	[Y1] = f14	(p12) add Y1 = INCY, Y1	(p13) FMA	f10 = ALPHA, f52, f54	}	;;	{ .mmf	(p12) STFD	[Y1] = f15	(p12) add Y1 = INCY, Y1	(p13) FMA	f11 = ALPHA, f53, f55	}	;;	{ .mmf	(p13) STFD	[Y1] = f6	(p13) add Y1 = INCY, Y1	(p14) FMA	f12 = ALPHA, f56, f58	}	;;	{ .mmf	(p13) STFD	[Y1] = f7	(p13) add Y1 = INCY, Y1	(p14) FMA	f13 = ALPHA, f57, f59	}	;;	{ .mmf	(p13) STFD	[Y1] = f10	(p13) add Y1 = INCY, Y1	(p15) FMA	f14 = ALPHA, f60, f61	}	;;	(p13) STFD	[Y1] = f11	(p13) add Y1 = INCY, Y1	;;	(p14) STFD	[Y1] = f12	(p14) add Y1 = INCY, Y1	;;	(p14) STFD	[Y1] = f13	(p14) add Y1 = INCY, Y1	;;	(p15) STFD	[Y1] = f14	br.ret.sptk.many b0	;;	EPILOGUE

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -