⭐ 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

📄 ztrsm_kernel_ln.s

📁 Optimized GotoBLAS libraries
💻 S
📖 第 1 页 / 共 5 页
字号:
	}	;;/* 14 */	{ .mfb	FMA	f83   = f35, f50, f83	// A4 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_A	f82   = f35, f51, f82	// A4 * B4	nop	__LINE__	}	;;/* 15 */	{ .mfb	FMA	f99   = f35, f52, f99	// A4 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_A	f98  = f35, f53, f98	// A4 * B6	nop	__LINE__	}	;;/* 16 */	{ .mfb	FMA	f115  = f35, f54, f115	// A4 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_A	f114  = f35, f55, f114	// A4 * B8	nop	__LINE__	}	;;/* 17 */	{ .mfb	nop	__LINE__	FMA	f68   = f36, f48, f68	// A5 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_B	f69   = f36, f49, f69	// A5 * B2	nop	__LINE__	}	;;/* 18 */	{ .mfb	nop	__LINE__	FMA	f84   = f36, f50, f84	// A5 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_B	f85   = f36, f51, f85	// A5 * B4	nop	__LINE__	}	;;/* 19 */	{ .mfb	nop	__LINE__	FMA	f100  = f36, f52, f100	// A5 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_B	f101  = f36, f53, f101	// A5 * B6	nop	__LINE__	}	;;/* 20 */	{ .mfb	nop	__LINE__	FMA	f116  = f36, f54, f116	// A5 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_B	f117  = f36, f55, f117	// A5 * B8	nop	__LINE__	}	;;/* 21 */	{ .mfb	nop	__LINE__	FMA	f69   = f37, f48, f69	// A6 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_A	f68   = f37, f49, f68	// A6 * B2	nop	__LINE__	}	;;/* 22 */	{ .mfb	nop	__LINE__	FMA	f85   = f37, f50, f85	// A6 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_A	f84   = f37, f51, f84	// A6 * B4	nop	__LINE__	}	;;/* 23 */	{ .mfb	nop	__LINE__	FMA	f101  = f37, f52, f101	// A6 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_A	f100  = f37, f53, f100	// A6 * B6	nop	__LINE__	}	;;/* 24 */	{ .mfb	nop	__LINE__	FMA	f117  = f37, f54, f117	// A6 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_A	f116  = f37, f55, f116	// A6 * B8	nop	__LINE__	}	;;/* 25 */	{ .mfb	nop	__LINE__	FMA	f70   = f38, f48, f70	// A7 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_B	f71   = f38, f49, f71	// A7 * B2	nop	__LINE__	}	;;/* 26 */	{ .mfb	nop	__LINE__	FMA	f86   = f38, f50, f86	// A7 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_B	f87   = f38, f51, f87	// A7 * B4	nop	__LINE__	}	;;/* 27 */	{ .mfb	nop	__LINE__	FMA	f102  = f38, f52, f102	// A7 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_B	f103  = f38, f53, f103	// A7 * B6	nop	__LINE__	}	;;/* 28 */	{ .mfb	nop	__LINE__	FMA	f118  = f38, f54, f118	// A7 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_B	f119  = f38, f55, f119	// A7 * B8	nop	__LINE__	}	;;/* 29 */	{ .mfb	nop	__LINE__	FMA	f71   = f39, f48, f71	// A8 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_A	f70   = f39, f49, f70	// A8 * B2	nop	__LINE__	}	;;/* 30 */	{ .mfb	(p4) LDFPD	f32, f33 = [AOFFSET],   2 * SIZE	FMA	f87   = f39, f50, f87	// A8 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_A	f86   = f39, f51, f86	// A8 * B4	nop	__LINE__	}	;;/* 31 */	{ .mfb	(p4) LDFPD	f48, f49 = [BOFFSET],   2 * SIZE	FMA	f103  = f39, f52, f103	// A8 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_A	f102  = f39, f53, f102	// A8 * B6	nop	__LINE__	}	;;/* 32 */	{ .mfb	nop	__LINE__	FMA	f119  = f39, f54, f119	// A8 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	FMA_A	f118  = f39, f55, f118	// A8 * B8	nop	__LINE__	}	;;/* 33 */	{ .mfb	nop	__LINE__	(p3) FMA	f64   = f40, f56, f64	// A1 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f65   = f40, f57, f65	// A1 * B2	nop	__LINE__	}	;;/* 34 */	{ .mfb	(p4) LDFPD	f50, f51 = [BOFFSET],  2 * SIZE	(p3) FMA	f80   = f40, f58, f80	// A1 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f81   = f40, f59, f81	// A1 * B4	nop	__LINE__	}	;;/* 35 */	{ .mfb	(p4) LDFPD	f52, f53 = [BOFFSET], 2 * SIZE	(p3) FMA	f96   = f40, f60, f96	// A1 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f97  = f40, f61, f97	// A1 * B6	nop	__LINE__	}	;;/* 36 */	{ .mfb	(p4) LDFPD	f54, f55 = [BOFFSET], 2 * SIZE	(p3) FMA	f112  = f40, f62, f112	// A1 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f113  = f40, f63, f113	// A1 * B8	nop	__LINE__	}	;;/* 37 */	{ .mfb	(p4) LDFPD	f34, f35 = [AOFFSET], 2 * SIZE	(p3) FMA	f65   = f41, f56, f65	// A2 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f64   = f41, f57, f64	// A2 * B2	nop	__LINE__	}	;;/* 38 */	{ .mfb	(p4) LDFPD	f36, f37 = [AOFFSET], 2 * SIZE	(p3) FMA	f81   = f41, f58, f81	// A2 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f80   = f41, f59, f80	// A2 * B4	nop	__LINE__	}	;;/* 39 */	{ .mfb	(p4) LDFPD	f38, f39 = [AOFFSET], 2 * SIZE	(p3) FMA	f97   = f41, f60, f97	// A2 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f96  = f41, f61, f96	// A2 * B6	nop	__LINE__	}	;;/* 40 */	{ .mfb	nop	__LINE__	(p3) FMA	f113  = f41, f62, f113	// A2 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f112  = f41, f63, f112	// A2 * B8	nop	__LINE__	}	;; /* 41 */	{ .mfb	nop	__LINE__	(p3) FMA	f66   = f42, f56, f66	// A3 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f67   = f42, f57, f67	// A3 * B2	nop	__LINE__	}	;;/* 42 */	{ .mfb	nop	__LINE__	(p3) FMA	f82   = f42, f58, f82	// A3 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f83   = f42, f59, f83	// A3 * B4	nop	__LINE__	}	;;/* 43 */	{ .mfb	nop	__LINE__	(p3) FMA	f98   = f42, f60, f98	// A3 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f99  = f42, f61, f99	// A3 * B6	nop	__LINE__	}	;;/* 44 */	{ .mfb	nop	__LINE__	(p3) FMA	f114  = f42, f62, f114	// A3 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f115  = f42, f63, f115	// A3 * B8	nop	__LINE__	}	;;/* 45 */	{ .mfb	nop	__LINE__	(p3) FMA	f67   = f43, f56, f67	// A4 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f66   = f43, f57, f66	// A4 * B2	nop	__LINE__	}	;;/* 46 */	{ .mfb	nop	__LINE__	(p3) FMA	f83   = f43, f58, f83	// A4 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f82   = f43, f59, f82	// A4 * B4	nop	__LINE__	}	;;/* 47 */	{ .mfb	nop	__LINE__	(p3) FMA	f99   = f43, f60, f99	// A4 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f98  = f43, f61, f98	// A4 * B6	nop	__LINE__	}	;;/* 48 */	{ .mfb	nop	__LINE__	(p3) FMA	f115  = f43, f62, f115	// A4 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f114  = f43, f63, f114	// A4 * B8	nop	__LINE__	}	;;/* 49 */	{ .mfb	nop	__LINE__	(p3) FMA	f68   = f44, f56, f68	// A5 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f69   = f44, f57, f69	// A5 * B2	nop	__LINE__	}	;;/* 50 */	{ .mfb	nop	__LINE__	(p3) FMA	f84   = f44, f58, f84	// A5 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f85   = f44, f59, f85	// A5 * B4	nop	__LINE__	}	;;/* 51 */	{ .mfb	nop	__LINE__	(p3) FMA	f100  = f44, f60, f100	// A5 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f101  = f44, f61, f101	// A5 * B6	nop	__LINE__	}	;;/* 52 */	{ .mfb	nop	__LINE__	(p3) FMA	f116  = f44, f62, f116	// A5 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f117  = f44, f63, f117	// A5 * B8	nop	__LINE__	}	;;/* 53 */	{ .mfb	nop	__LINE__	(p3) FMA	f69   = f45, f56, f69	// A6 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f68   = f45, f57, f68	// A6 * B2	nop	__LINE__	}	;;/* 54 */	{ .mfb	nop	__LINE__	(p3) FMA	f85   = f45, f58, f85	// A6 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f84   = f45, f59, f84	// A6 * B4	nop	__LINE__	}	;;/* 55 */	{ .mfb	nop	__LINE__ 	(p3) FMA	f101  = f45, f60, f101	// A6 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f100  = f45, f61, f100	// A6 * B6	nop	__LINE__	}	;;/* 56 */	{ .mfb	nop	__LINE__	(p3) FMA	f117  = f45, f62, f117	// A6 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f116  = f45, f63, f116	// A6 * B8	nop	__LINE__	}	;;/* 57 */	{ .mfb	nop	__LINE__	(p3) FMA	f70   = f46, f56, f70	// A7 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f71   = f46, f57, f71	// A7 * B2	nop	__LINE__	}	;;/* 58 */	{ .mfb	nop	__LINE__	(p3) FMA	f86   = f46, f58, f86	// A7 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f87   = f46, f59, f87	// A7 * B4	nop	__LINE__	}	;;/* 59 */	{ .mfb	nop	__LINE__	(p3) FMA	f102  = f46, f60, f102	// A7 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f103  = f46, f61, f103	// A7 * B6	nop	__LINE__	}	;;/* 60 */	{ .mfb	nop	__LINE__	(p3) FMA	f118  = f46, f62, f118	// A7 * B7	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_B	f119  = f46, f63, f119	// A7 * B8	nop	__LINE__	}	;;/* 61 */	{ .mfb	nop	__LINE__	(p3) FMA	f71   = f47, f56, f71	// A8 * B1	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f70   = f47, f57, f70	// A8 * B2	nop	__LINE__	}	;;/* 62 */	{ .mfb	nop	__LINE__	(p3) FMA	f87   = f47, f58, f87	// A8 * B3	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f86   = f47, f59, f86	// A8 * B4	nop	__LINE__	}	;;/* 63 */	{ .mfb	nop	__LINE__	(p3) FMA	f103  = f47, f60, f103	// A8 * B5	nop	__LINE__	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f102  = f47, f61, f102	// A8 * B6	nop	__LINE__	}	;;/* 64 */	{ .mfi	nop	__LINE__	(p3) FMA	f119  = f47, f62, f119	// A8 * B7	adds	L = -1, L	}	{ .mfb	nop	__LINE__	(p3) FMA_A	f118  = f47, f63, f118	// A8 * B8	br.cloop.sptk.few .L012	}	;;.L018:#if defined(LN) || defined(RT)#ifdef LN	adds	r2 = -4, KK#else	adds	r2 = -4, KK#endif	;;	shladd	r2 = r2, ZBASE_SHIFT, r0	;;	shladd	AOFFSET = r2, 2, AORIG	shladd	BOFFSET = r2, 2, B	;;	#endif#if defined(LN) || defined(LT)	LDFPD	f72, f73 = [BOFFSET], 2 * SIZE	;;	LDFPD	f74, f75 = [BOFFSET], 2 * SIZE	;;	LDFPD	f76, f77 = [BOFFSET], 2 * SIZE	;;	LDFPD	f78, f79 = [BOFFSET], 2 * SIZE	;;	LDFPD	f88, f89 = [BOFFSET], 2 * SIZE	;;	LDFPD	f90, f91 = [BOFFSET], 2 * SIZE	;;	LDFPD	f92, f93 = [BOFFSET], 2 * SIZE	;;	{ .mfi	LDFPD	f94, f95 = [BOFFSET], 2 * SIZE	FSUB	f64  = f72, f64	nop	__LINE__	}	{ .mfi	nop	__LINE__	FSUB_A	f65  = f73, f65	nop	__LINE__	}	;;	{ .mfi	LDFPD	f104, f105 = [BOFFSET], 2 * SIZE	FSUB	f80  = f74, f80	nop	__LINE__	}	{ .mfi	nop	__LINE__	FSUB_A	f81  = f75, f81	nop	__LINE__	}	;;	{ .mfi	LDFPD	f106, f107 = [BOFFSET], 2 * SIZE	FSUB	f96  = f76, f96	nop	__LINE__	}	{ .mfi	nop	__LINE__	FSUB_A	f97  = f77, f97	nop	__LINE__	}	;;	{ .mfi	LDFPD	f108, f109 = [BOFFSET], 2 * SIZE	FSUB	f112 = f78, f112	nop	__LINE__	}	{ .mfi	nop	__LINE__	FSUB_A	f113 = f79, f113	nop	__LINE__	}	;;	{ .mfi	LDFPD	f110, f111 = [BOFFSET], 2 * SIZE	FSUB	f66  = f88, f66	nop	__LINE__	}	{ .mfi	nop	__LINE__	FSUB_A	f67  = f89, f67	nop	__LINE__	}	;;	{ .mfi	LDFPD	f120, f121 = [BOFFSET], 2 * SIZE	FSUB	f82  = f90, f82	nop	__LINE__	}	{ .mfi	nop	__LINE__	FSUB_A	f83  = f91, f83	nop	__LINE__	}	;;	{ .mfi	LDFPD	f122, f123 = [BOFFSET], 2 * SIZE	FSUB	f98  = f92, f98	nop	__LINE__	}	{ .mfi	nop	__LINE__	FSUB_A	f99  = f93, f99	nop	__LINE__	}	;;	{ .mfi	LDFPD	f124, f125 = [BOFFSET], 2 * SIZE	FSUB	f114 = f94, f114	nop	__LINE__	}	{ .mfi	nop	__LINE__	FSUB_A	f115 = f95, f115	nop	__LINE__	}	;;	{ .mfi	LDFPD	f126, f127 = [BOFFSET]	FSUB	f68  = f104, f68	adds	BOFFSET = -30 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FSUB_A	f69  = f105, f69#ifdef LN	adds	AOFFSET = 30 * SIZE, AOFFSET#else	nop	__LINE__#endif	}	;;	{ .mfi	LDFPD	f72, f73 = [AOFFSET]	FSUB	f84  = f106, f84#ifdef LN	adds	AOFFSET = - 2 * SIZE, AOFFSET#else	adds	AOFFSET =   2 * SIZE, AOFFSET#endif	}	{ .mfi	nop	__LINE__	FSUB_A	f85  = f107, f85	nop	__LINE__	}	;;	{ .mfi	LDFPD	f74, f75 = [AOFFSET]	FSUB	f100 = f108, f100#ifdef LN	adds	AOFFSET = - 2 * SIZE, AOFFSET#else	adds	AOFFSET =   2 * SIZE, AOFFSET#endif	}	{ .mfi	nop	__LINE__	FSUB_A	f101 = f109, f101	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FSUB	f116 = f110, f116	nop	__LINE__	}	{ .mfi	nop	__LINE__	FSUB_A	f117 = f111, f117	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FSUB	f70  = f120, f70	nop	__LINE__	}	{ .mfi	nop	__LINE__	FSUB_A	f71  = f121, f71	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FSUB	f86  = f122, f86	nop	__LINE__	}	{ .mfi	nop	__LINE__	FSUB_A	f87  = f123, f87	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FSUB	f102 = f124, f102

⌨️ 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 + -