⭐ 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_lt.s

📁 Optimized GotoBLAS libraries
💻 S
📖 第 1 页 / 共 5 页
字号:
	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f83  = f76, f87, f83	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f115 = f76, f119, f115	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f64  = f78, f70, f64	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f96  = f78, f102, f96	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f65  = f79, f70, f65	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f97  = f79, f102, f97	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f80  = f78, f86, f80	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f112 = f78, f118, f112	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f81  = f79, f86, f81	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f113 = f79, f118, f113	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f64  = f79, f71, f64	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f96  = f79, f103, f96	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f65  = f78, f71, f65	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f97  = f78, f103, f97	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f80  = f79, f87, f80	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f112 = f79, f119, f112	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f81  = f78, f87, f81	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f113 = f78, f119, f113	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f32  = f88, f68	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f36  = f88, f100	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f33  = f89, f68	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f37  = f89, f100	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f34  = f88, f84	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f38  = f88, f116	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f35  = f89, f84	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f39  = f89, f116	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f68  = f89, f69,  f32	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f100 = f89, f101, f36	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f69  = f88, f69,  f33	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f101 = f88, f101, f37	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f84  = f89, f85,  f34	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f116 = f89, f117, f38	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f85  = f88, f85,  f35	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f117 = f88, f117, f39	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f68,  SIZE	FNMA	f66  = f90, f68, f66	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f100, SIZE	FNMA	f98  = f90, f100, f98	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f69,  SIZE	FMA_A	f67  = f91, f68, f67	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f101, SIZE	FMA_A	f99  = f91, f100, f99	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f84,  SIZE	FNMA	f82  = f90, f84, f82	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f116, SIZE	FNMA	f114 = f90, f116, f114	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f85,  -11 * SIZE	FMA_A	f83  = f91, f84, f83	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f117, -11 * SIZE	FMA_A	f115 = f91, f116, f115	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f68, SIZE	FMA_B	f66  = f91, f69, f66	nop	__LINE__	}	{ .mfi	STFD	[C3 ] = f100, SIZE	FMA_B	f98  = f91, f101, f98	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f69, -3 * SIZE	FNMA	f67  = f90, f69, f67	nop	__LINE__	}	{ .mfi	STFD	[C3 ] = f101, -3 * SIZE	FNMA	f99  = f90, f101, f99	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f84, SIZE	FMA_B	f82  = f91, f85, f82	nop	__LINE__	}	{ .mfi	STFD	[C4 ] = f116, SIZE	FMA_B	f114 = f91, f117, f114	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f85, -3 * SIZE	FNMA	f83  = f90, f85, f83	nop	__LINE__	}	{ .mfi	STFD	[C4 ] = f117, -3 * SIZE	FNMA	f115 = f90, f117, f115	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f64  = f92, f68, f64	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f96  = f92, f100, f96	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f65  = f93, f68, f65	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f97  = f93, f100, f97	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f80  = f92, f84, f80	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f112 = f92, f116, f112	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f81  = f93, f84, f81	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f113 = f93, f116, f113	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f64  = f93, f69, f64	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f96  = f93, f101, f96	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f65  = f92, f69, f65	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f97  = f92, f101, f97	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f80  = f93, f85, f80	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f112 = f93, f117, f112	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f81  = f92, f85, f81	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f113 = f92, f117, f113	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f32  = f104, f66	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f36  = f104, f98	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f33  = f105, f66	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f37  = f105, f98	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f34  = f104, f82	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f38  = f104, f114	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f35  = f105, f82	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f39  = f105, f114	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f66  = f105, f67,  f32	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f98  = f105, f99,  f36	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f67  = f104, f67,  f33	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f99  = f104, f99,  f37	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f82  = f105, f83,  f34	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f114 = f105, f115, f38	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f83  = f104, f83,  f35	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f115 = f104, f115, f39	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f66,  SIZE	FNMA	f64  = f106, f66, f64	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f98,  SIZE	FNMA	f96  = f106, f98, f96	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f67,  SIZE	FMA_A	f65  = f107, f66, f65	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f99,  SIZE	FMA_A	f97  = f107, f98, f97	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f82,  SIZE	FNMA	f80  = f106, f82, f80	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f114, SIZE	FNMA	f112 = f106, f114, f112	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f83,  -11 * SIZE	FMA_A	f81  = f107, f82, f81	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f115, -11 * SIZE	FMA_A	f113 = f107, f114, f113	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f66, SIZE	FMA_B	f64  = f107, f67, f64	nop	__LINE__	}	{ .mfi	STFD	[C3 ] = f98, SIZE	FMA_B	f96  = f107, f99, f96	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f67, -3 * SIZE	FNMA	f65  = f106, f67, f65	nop	__LINE__	}	{ .mfi	STFD	[C3 ] = f99,  -3 * SIZE	FNMA	f97  = f106, f99, f97	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f82, SIZE	FMA_B	f80  = f107, f83, f80	nop	__LINE__	}	{ .mfi	STFD	[C4 ] = f114, SIZE	FMA_B	f112 = f107, f115, f112	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f83, -3 * SIZE	FNMA	f81  = f106, f83, f81	nop	__LINE__	}	{ .mfi	STFD	[C4 ] = f115, -3 * SIZE	FNMA	f113 = f106, f115, f113	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f32  = f120, f64	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f36  = f120, f96	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f33  = f121, f64	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f37  = f121, f96	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f34  = f120, f80	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f38  = f120, f112	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f35  = f121, f80	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f39  = f121, f112	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f64  = f121, f65,  f32	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f96  = f121, f97,  f36	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f65  = f120, f65,  f33	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f97  = f120, f97,  f37	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f80  = f121, f81,  f34	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f112 = f121, f113, f38	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f81  = f120, f81,  f35	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f113 = f120, f113, f39	nop	__LINE__	}	;;	{ .mmi	STFD	[BOFFSET]  = f64,  SIZE	STFD	[BOFFSET2] = f96,  SIZE	nop	__LINE__	}	;;	{ .mmi	STFD	[BOFFSET]  = f65,  SIZE	STFD	[BOFFSET2] = f97,  SIZE	nop	__LINE__	}	;;	{ .mmi	STFD	[BOFFSET]  = f80,  SIZE	STFD	[BOFFSET2] = f112, SIZE	nop	__LINE__	}	;;	{ .mmi	STFD	[BOFFSET]  = f81,  -3 * SIZE	STFD	[BOFFSET2] = f113, -3 * SIZE	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f64, SIZE	mov	f64 = f0	nop	__LINE__	}	{ .mfi	STFD	[C3 ] = f96, SIZE	mov	f96 = f0	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f65, -1 * SIZE	mov	f65 = f0	adds	KK = -4, KK	}	{ .mfi	STFD	[C3 ] = f97, -1 * SIZE	mov	f97 = f0	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f80, SIZE	mov	f80 = f0	cmp.ne	p6, p0 = 1, I	}	{ .mfi	STFD	[C4 ] = f112, SIZE	mov	f112 = f0	sub	L = K, KK	}	;;	{ .mfi	STFD	[C2 ] = f81, -1 * SIZE	mov	f81 = f0	adds	I = -1, I	}	{ .mfb	STFD	[C4 ] = f113, -1 * SIZE	mov	f113 = f0	(p6)	br.cond.dptk .L011	}	;;#endif#ifdef LT	{ .mfi	LDFPD	f76, f77 = [AOFFSET], 2 * SIZE	FMPY	f32  = f72, f64	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f36  = f72, f96	nop	__LINE__	}	;;	{ .mfi	LDFPD	f78, f79 = [AOFFSET]	FMPY	f33  = f73, f64	adds	AOFFSET = 4 * SIZE, AOFFSET	}	{ .mfi	nop	__LINE__	FMPY	f37  = f73, f96	nop	__LINE__	}	;;	{ .mfi	LDFPD	f90, f91 = [AOFFSET], 2 * SIZE	FMPY	f34  = f72, f80	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f38  = f72, f112	nop	__LINE__	}	;;	{ .mfi	LDFPD	f92, f93 = [AOFFSET], 2 * SIZE	FMPY	f35  = f73, f80	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f39  = f73, f112	nop	__LINE__	}	;;	{ .mfi	LDFPD	f94, f95 = [AOFFSET]	FMA_C	f64  = f73, f65,  f32	adds	AOFFSET = 6 * SIZE, AOFFSET	}	{ .mfi	nop	__LINE__	FMA_C	f96  = f73, f97,  f36	nop	__LINE__	}	;;	{ .mfi	LDFPD	f108, f109 = [AOFFSET], 2 * SIZE	FMA_D	f65  = f72, f65,  f33	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f97  = f72, f97,  f37	nop	__LINE__	}	;;	{ .mfi	LDFPD	f110, f111 = [AOFFSET]	FMA_C	f80  = f73, f81,  f34	adds	AOFFSET = 8 * SIZE, AOFFSET	}	{ .mfi	nop	__LINE__	FMA_C	f112 = f73, f113, f38	nop	__LINE__	}	;;	{ .mfi	LDFPD	f126, f127 = [AOFFSET]	FMA_D	f81  = f72, f81,  f35	adds	AOFFSET = - 30 * SIZE, AOFFSET	}	{ .mfi	nop	__LINE__	FMA_D	f113 = f72, f113, f39	adds	BOFFSET2 = 4 * SIZE, BOFFSET	}	;;	{ .mfi	STFD	[BOFFSET]  = f64,  SIZE	FNMA	f66  = f74, f64, f66	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f96,  SIZE	FNMA	f98  = f74, f96, f98	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f65,  SIZE	FMA_A	f67  = f75, f64, f67	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f97,  SIZE	FMA_A	f99  = f75, f96, f99	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f80,  SIZE	FNMA	f82  = f74, f80, f82	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f112, SIZE	FNMA	f114 = f74, f112, f114	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f81,  5 * SIZE	FMA_A	f83  = f75, f80, f83	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f113, 5 * SIZE	FMA_A	f115 = f75, f112, f115	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f64, SIZE	FMA_B	f66  = f75, f65, f66	nop	__LINE__	}	{ .mfi	STFD	[C3 ] = f96, SIZE	FMA_B	f98  = f75, f97, f98	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f65, SIZE	FNMA	f67  = f74, f65, f67	nop	__LINE__	}	{ .mfi	STFD	[C3 ] = f97, SIZE	FNMA	f99  = f74, f97, f99	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f80, SIZE	FMA_B	f82  = f75, f81, f82	nop	__LINE__	}	{ .mfi	STFD	[C4 ] = f112, SIZE	FMA_B	f114 = f75, f113, f114	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f81, SIZE	FNMA	f83  = f74, f81, f83	nop	__LINE__	}	{ .mfi	STFD	[C4 ] = f113, SIZE	FNMA	f115 = f74, f113, f115	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f68  = f76, f64, f68	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f100 = f76, f96, f100	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f69  = f77, f64, f69	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f101 = f77, f96, f101	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f84  = f76, f80, f84	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f116 = f76, f112, f116	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f85  = f77, f80, f85	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f117 = f77, f112, f117	nop	__LINE__

⌨️ 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 + -