⭐ 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:
	{ .mfi	nop	__LINE__	FMA_A	f101 = f77, f68, f101	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f98  = f76, f66, f98	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f102 = f76, f70, f102	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f99  = f77, f66, f99	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f103 = f77, f70, f103	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f96  = f77, f65, f96	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f100 = f77, f69, f100	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f97  = f76, f65, f97	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f101 = f76, f69, f101	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f98  = f77, f67, f98	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f102 = f77, f71, f102	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f99  = f76, f67, f99	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f103 = f76, f71, f103	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f112 = f78, f64, f112	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f116 = f78, f68, f116	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f113 = f79, f64, f113	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f117 = f79, f68, f117	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f114 = f78, f66, f114	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f118 = f78, f70, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f115 = f79, f66, f115	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f119 = f79, f70, f119	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f112 = f79, f65, f112	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f116 = f79, f69, f116	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f113 = f78, f65, f113	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f117 = f78, f69, f117	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f114 = f79, f67, f114	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f118 = f79, f71, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f115 = f78, f67, f115	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f119 = f78, f71, f119	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f32  = f90, f80	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f36  = f90, f84	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f33  = f91, f80	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f37  = f91, f84	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f34  = f90, f82	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f38  = f90, f86	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f35  = f91, f82	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f39  = f91, f86	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f80  = f91, f81,  f32	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f84  = f91, f85,  f36	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f81  = f90, f81,  f33	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f85  = f90, f85,  f37	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f82  = f91, f83,  f34	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f86  = f91, f87,  f38	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f83  = f90, f83,  f35	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f87  = f90, f87,  f39	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f80,  SIZE	FNMA	f96  = f92, f80, f96	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f84,  SIZE	FNMA	f100 = f92, f84, f100	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f81,  SIZE	FMA_A	f97  = f93, f80, f97	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f85,  SIZE	FMA_A	f101 = f93, f84, f101	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f82,  SIZE	FNMA	f98  = f92, f82, f98	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f86,  SIZE	FNMA	f102 = f92, f86, f102	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f83,  5 * SIZE	FMA_A	f99  = f93, f82, f99	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f87,  5 * SIZE	FMA_A	f103 = f93, f86, f103	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f80, SIZE	FMA_B	f96  = f93, f81, f96	nop	__LINE__	}	{ .mfi	STFD	[C6 ] = f84, SIZE	FMA_B	f100 = f93, f85, f100	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f81, SIZE	FNMA	f97  = f92, f81, f97	nop	__LINE__	}	{ .mfi	STFD	[C6 ] = f85, SIZE	FNMA	f101 = f92, f85, f101	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f82, SIZE	FMA_B	f98  = f93, f83, f98	nop	__LINE__	}	{ .mfi	STFD	[C6 ] = f86, SIZE	FMA_B	f102 = f93, f87, f102	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f83, 5 * SIZE	FNMA	f99  = f92, f83, f99	nop	__LINE__	}	{ .mfi	STFD	[C6 ] = f87, 5 * SIZE	FNMA	f103 = f92, f87, f103	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f112 = f94, f80, f112	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f116 = f94, f84, f116	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f113 = f95, f80, f113	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f117 = f95, f84, f117	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f114 = f94, f82, f114	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f118 = f94, f86, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f115 = f95, f82, f115	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f119 = f95, f86, f119	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f112 = f95, f81, f112	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f116 = f95, f85, f116	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f113 = f94, f81, f113	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f117 = f94, f85, f117	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f114 = f95, f83, f114	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f118 = f95, f87, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f115 = f94, f83, f115	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f119 = f94, f87, f119	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f32  = f108, f96	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f36  = f108, f100	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f33  = f109, f96	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f37  = f109, f100	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f34  = f108, f98	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f38  = f108, f102	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f35  = f109, f98	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f39  = f109, f102	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f96  = f109, f97,  f32	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f100 = f109, f101, f36	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f97  = f108, f97,  f33	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f101 = f108, f101, f37	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f98  = f109, f99,  f34	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f102 = f109, f103, f38	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f99  = f108, f99,  f35	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f103 = f108, f103, f39	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f96,  SIZE	FNMA	f112 = f110, f96, f112	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f100, SIZE	FNMA	f116 = f110, f100, f116	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f97,  SIZE	FMA_A	f113 = f111, f96, f113	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f101, SIZE	FMA_A	f117 = f111, f100, f117	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f98,  SIZE	FNMA	f114 = f110, f98, f114	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f102, SIZE	FNMA	f118 = f110, f102, f118	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f99,  5 * SIZE	FMA_A	f115 = f111, f98, f115	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f103, 5 * SIZE	FMA_A	f119 = f111, f102, f119	nop	__LINE__	}	;;	{ .mfi	STFD	[C3 ] = f96, SIZE	FMA_B	f112 = f111, f97, f112	nop	__LINE__	}	{ .mfi	STFD	[C7 ] = f100, SIZE	FMA_B	f116 = f111, f101, f116	nop	__LINE__	}	;;	{ .mfi	STFD	[C3 ] = f97, SIZE	FNMA	f113 = f110, f97, f113	nop	__LINE__	}	{ .mfi	STFD	[C7 ] = f101, SIZE	FNMA	f117 = f110, f101, f117	nop	__LINE__	}	;;	{ .mfi	STFD	[C3 ] = f98, SIZE	FMA_B	f114 = f111, f99, f114	nop	__LINE__	}	{ .mfi	STFD	[C7 ] = f102, SIZE	FMA_B	f118 = f111, f103, f118	nop	__LINE__	}	;;	{ .mfi	STFD	[C3 ] = f99, 5 * SIZE	FNMA	f115 = f110, f99, f115	nop	__LINE__	}	{ .mfi	STFD	[C7 ] = f103, 5 * SIZE	FNMA	f119 = f110, f103, f119	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f32  = f126, f112	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f36  = f126, f116	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f33  = f127, f112	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f37  = f127, f116	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f34  = f126, f114	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f38  = f126, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f35  = f127, f114	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f39  = f127, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f112 = f127, f113, f32	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f116 = f127, f117, f36	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f113 = f126, f113, f33	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f117 = f126, f117, f37	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f114 = f127, f115, f34	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f118 = f127, f119, f38	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f115 = f126, f115, f35	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f119 = f126, f119, f39	nop	__LINE__	}	;;	{ .mmi	STFD	[AOFFSET]  = f112, SIZE	STFD	[AOFFSET2] = f116, SIZE	sub	r2 = K, KK	}	;;	{ .mmi	STFD	[AOFFSET]  = f113, SIZE	STFD	[AOFFSET2] = f117, SIZE	mov	L = KK	}	;;	{ .mmi	STFD	[AOFFSET]  = f114, SIZE	STFD	[AOFFSET2] = f118, SIZE	shladd	r2 = r2, ZBASE_SHIFT, r0	}	;;	{ .mmi	STFD	[AOFFSET]  = f115, -27 * SIZE	STFD	[AOFFSET2] = f119	nop	__LINE__	}	;;	{ .mfi	STFD	[C4 ] = f112, SIZE	mov	f64 = f0	shladd	BOFFSET = r2, 2, BOFFSET	}	{ .mfi	STFD	[C8 ] = f116, SIZE	mov	f65 = f0	shladd	AOFFSET = r2, 2, AOFFSET	}	;;	{ .mfi	STFD	[C4 ] = f113, SIZE	mov	f80 = f0	cmp.ne	p6, p0 = 1, I	}	{ .mfi	STFD	[C8 ] = f117, SIZE	mov	f81 = f0	nop	__LINE__	}	;;	{ .mfi	STFD	[C4 ] = f114, SIZE	mov	f96 = f0	adds	I = -1, I	}	{ .mfi	STFD	[C8 ] = f118, SIZE	mov	f97 = f0	nop	__LINE__	}	;;	{ .mfi	STFD	[C4 ] = f115, 5 * SIZE	mov	f112 = f0	nop	__LINE__	}	{ .mfb	STFD	[C8 ] = f119, 5 * SIZE	mov	f113 = f0	(p6)	br.cond.dptk .L011	}#endif#ifdef RT	{ .mfi	LDFPD	f76, f77 = [BOFFSET]	FMPY	f32  = f72, f112	adds	BOFFSET = - 2 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FMPY	f36  = f72, f116	nop	__LINE__	}	;;	{ .mfi	LDFPD	f78, f79 = [BOFFSET]	FMPY	f33  = f73, f112	adds	BOFFSET = - 4 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FMPY	f37  = f73, f116	nop	__LINE__	}	;;	{ .mfi	LDFPD	f88, f89 = [BOFFSET]	FMPY	f34  = f72, f114	adds	BOFFSET = - 2 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FMPY	f38  = f72, f118	nop	__LINE__	}	;;	{ .mfi	LDFPD	f90, f91 = [BOFFSET]	FMPY	f35  = f73, f114	adds	BOFFSET = - 2 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FMPY	f39  = f73, f118	nop	__LINE__	}	;;	{ .mfi	LDFPD	f92, f93 = [BOFFSET]	FMA_C	f112 = f73, f113, f32	adds	BOFFSET = - 6 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FMA_C	f116 = f73, f117, f36	nop	__LINE__	}	;;	{ .mfi	LDFPD	f104, f105 = [BOFFSET]	FMA_D	f113 = f72, f113, f33	adds	BOFFSET = - 2 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FMA_D	f117 = f72, f117, f37	nop	__LINE__	}	;;	{ .mfi	LDFPD	f106, f107 = [BOFFSET]	FMA_C	f114 = f73, f115, f34	adds	BOFFSET = - 8 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FMA_C	f118 = f73, f119, f38	nop	__LINE__	}	;;	{ .mfi	LDFPD	f120, f121 = [BOFFSET]	FMA_D	f115 = f72, f115, f35	adds	AOFFSET2 = 28 * SIZE, AOFFSET	}	{ .mfi	nop	__LINE__	FMA_D	f119 = f72, f119, f39	adds	AOFFSET  = 24 * SIZE, AOFFSET	}	;;	{ .mfi	STFD	[AOFFSET]  = f112, SIZE	FNMA	f96  = f74, f112, f96	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f116, SIZE	FNMA	f100 = f74, f116, f100	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f113, SIZE	FMA_A	f97  = f75, f112, f97	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f117, SIZE	FMA_A	f101 = f75, f116, f101	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f114, SIZE	FNMA	f98  = f74, f114, f98	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f118, SIZE	FNMA	f102 = f74, f118, f102	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f115, -11 * SIZE	FMA_A	f99  = f75, f114, f99	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f119, -11 * SIZE	FMA_A	f103 = f75, f118, f103	nop	__LINE__	}	;;	{ .mfi	STFD	[C4 ] = f112, SIZE	FMA_B	f96  = f75, f113, f96	nop	__LINE__	}	{ .mfi	STFD	[C8 ] = f116, SIZE	FMA_B	f100 = f75, f117, f100	nop	__LINE__	}	;;	{ .mfi	STFD	[C4 ] = f113, SIZE	FNMA	f97  = f74, f113, f97	nop	__LINE__	}	{ .mfi	STFD	[C8 ] = f117, SIZE	FNMA	f101 = f74, f117, f101	nop	__LINE__	}	;;	{ .mfi	STFD	[C4 ] = f114, SIZE	FMA_B	f98  = f75, f115, f98	nop	__LINE__	}	{ .mfi	STFD	[C8 ] = f118, SIZE	FMA_B	f102 = f75, f119, f102	nop	__LINE__	}	;;	{ .mfi	STFD	[C4 ] =

⌨️ 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 + -