⭐ 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_B	f68  = f77, f65, f68	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f100 = f77, f97, f100	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f69  = f76, f65, f69	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f101 = f76, f97, f101	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f84  = f77, f81, f84	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f116 = f77, f113, f116	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f85  = f76, f81, f85	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f117 = f76, f113, f117	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f70  = f78, f64, f70	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f102 = f78, f96, f102	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f71  = f79, f64, f71	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f103 = f79, f96, f103	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f86  = f78, f80, f86	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f118 = f78, f112, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f87  = f79, f80, f87	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f119 = f79, f112, f119	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f70  = f79, f65, f70	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f102 = f79, f97, f102	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f71  = f78, f65, f71	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f103 = f78, f97, f103	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f86  = f79, f81, f86	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f118 = f79, f113, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f87  = f78, f81, f87	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f119 = f78, f113, f119	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f32  = f90, f66	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f36  = f90, f98	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f33  = f91, f66	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f37  = f91, f98	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f34  = f90, f82	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f38  = f90, f114	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f35  = f91, f82	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f39  = f91, f114	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f66  = f91, f67,  f32	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f98  = f91, f99,  f36	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f67  = f90, f67,  f33	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f99  = f90, f99,  f37	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f82  = f91, f83,  f34	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f114 = f91, f115, f38	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f83  = f90, f83,  f35	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f115 = f90, f115, f39	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f66,  SIZE	FNMA	f68  = f92, f66, f68	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f98,  SIZE	FNMA	f100 = f92, f98, f100	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f67,  SIZE	FMA_A	f69  = f93, f66, f69	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f99,  SIZE	FMA_A	f101 = f93, f98, f101	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f82,  SIZE	FNMA	f84  = f92, f82, f84	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f114, SIZE	FNMA	f116 = f92, f114, f116	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f83,  5 * SIZE	FMA_A	f85  = f93, f82, f85	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f115, 5 * SIZE	FMA_A	f117 = f93, f114, f117	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f66, SIZE	FMA_B	f68  = f93, f67, f68	nop	__LINE__	}	{ .mfi	STFD	[C3 ] = f98, SIZE	FMA_B	f100 = f93, f99, f100	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f67, SIZE	FNMA	f69  = f92, f67, f69	nop	__LINE__	}	{ .mfi	STFD	[C3 ] = f99, SIZE	FNMA	f101 = f92, f99, f101	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f82, SIZE	FMA_B	f84  = f93, f83, f84	nop	__LINE__	}	{ .mfi	STFD	[C4 ] = f114, SIZE	FMA_B	f116 = f93, f115, f116	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f83, SIZE	FNMA	f85  = f92, f83, f85	nop	__LINE__	}	{ .mfi	STFD	[C4 ] = f115, SIZE	FNMA	f117 = f92, f115, f117	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f70  = f94, f66, f70	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f102 = f94, f98, f102	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f71  = f95, f66, f71	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f103 = f95, f98, f103	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f86  = f94, f82, f86	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f118 = f94, f114, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f87  = f95, f82, f87	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_A	f119 = f95, f114, f119	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f70  = f95, f67, f70	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f102 = f95, f99, f102	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f71  = f94, f67, f71	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f103 = f94, f99, f103	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_B	f86  = f95, f83, f86	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_B	f118 = f95, f115, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f87  = f94, f83, f87	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f119 = f94, f115, f119	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f32  = f108, f68	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f36  = f108, f100	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f33  = f109, f68	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f37  = f109, f100	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f34  = f108, f84	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f38  = f108, f116	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f35  = f109, f84	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f39  = f109, f116	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f68  = f109, f69,  f32	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f100 = f109, f101, f36	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f69  = f108, f69,  f33	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f101 = f108, f101, f37	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f84  = f109, f85,  f34	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f116 = f109, f117, f38	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f85  = f108, f85,  f35	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f117 = f108, f117, f39	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f68,  SIZE	FNMA	f70  = f110, f68, f70	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f100, SIZE	FNMA	f102 = f110, f100, f102	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f69,  SIZE	FMA_A	f71  = f111, f68, f71	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f101, SIZE	FMA_A	f103 = f111, f100, f103	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f84,  SIZE	FNMA	f86  = f110, f84, f86	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f116, SIZE	FNMA	f118 = f110, f116, f118	nop	__LINE__	}	;;	{ .mfi	STFD	[BOFFSET]  = f85,  5 * SIZE	FMA_A	f87  = f111, f84, f87	nop	__LINE__	}	{ .mfi	STFD	[BOFFSET2] = f117, 5 * SIZE	FMA_A	f119 = f111, f116, f119	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f68, SIZE	FMA_B	f70  = f111, f69, f70	nop	__LINE__	}	{ .mfi	STFD	[C3 ] = f100, SIZE	FMA_B	f102 = f111, f101, f102	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f69, SIZE	FNMA	f71  = f110, f69, f71	nop	__LINE__	}	{ .mfi	STFD	[C3 ] = f101, SIZE	FNMA	f103 = f110, f101, f103	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f84, SIZE	FMA_B	f86  = f111, f85, f86	nop	__LINE__	}	{ .mfi	STFD	[C4 ] = f116, SIZE	FMA_B	f118 = f111, f117, f118	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f85, SIZE	FNMA	f87  = f110, f85, f87	nop	__LINE__	}	{ .mfi	STFD	[C4 ] = f117, SIZE	FNMA	f119 = f110, f117, f119	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f32  = f126, f70	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f36  = f126, f102	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f33  = f127, f70	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f37  = f127, f102	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f34  = f126, f86	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f38  = f126, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMPY	f35  = f127, f86	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f39  = f127, f118	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f70  = f127, f71,  f32	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f102 = f127, f103, f36	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f71  = f126, f71,  f33	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f103 = f126, f103, f37	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_C	f86  = f127, f87,  f34	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_C	f118 = f127, f119, f38	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_D	f87  = f126, f87,  f35	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f119 = f126, f119, f39	nop	__LINE__	}	;;	{ .mmi	STFD	[BOFFSET]  = f70,  SIZE	STFD	[BOFFSET2] = f102, SIZE	nop	__LINE__	}	;;	{ .mmi	STFD	[BOFFSET]  = f71,  SIZE	STFD	[BOFFSET2] = f103, SIZE	sub	r2 = K, KK	}	;;	{ .mmi	STFD	[BOFFSET]  = f86,  SIZE	STFD	[BOFFSET2] = f118, SIZE	adds	KK =  4, KK	}	;;	{ .mmi	STFD	[BOFFSET]  = f87,  -27 * SIZE	STFD	[BOFFSET2] = f119	shladd	r2 = r2, ZBASE_SHIFT, r0	}	;;	{ .mfi	STFD	[C1 ] = f70, SIZE	mov	f64 = f0	shladd	AOFFSET = r2, 2, AOFFSET	}	{ .mfi	STFD	[C3 ] = f102, SIZE	mov	f65 = f0	shladd	BOFFSET = r2, 2, BOFFSET	}	;;	{ .mfi	STFD	[C1 ] = f71, SIZE	mov	f80 = f0	mov	L = KK	}	{ .mfi	STFD	[C3 ] = f103, SIZE	mov	f81 = f0	nop	__LINE__	}	;;	{ .mfi	STFD	[C2 ] = f86, SIZE	mov	f96 = f0	cmp.ne	p6, p0 = 1, I	}	{ .mfi	STFD	[C4 ] = f118, SIZE	mov	f97 = f0	nop	__LINE__	}	;;	{ .mfi		STFD	[C2 ] = f87, SIZE	mov	f112 = f0	adds	I = -1, I	}	{ .mfb	STFD	[C4 ] = f119, SIZE	mov	f113 = f0	(p6)	br.cond.dptk .L011	}	;;#endif#ifdef RN	{ .mfi	LDFPD	f76, f77 = [BOFFSET], 2 * SIZE	FMPY	f32  = f72, f64	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f36  = f72, f68	nop	__LINE__	}	;;	{ .mfi	LDFPD	f78, f79 = [BOFFSET]	FMPY	f33  = f73, f64	adds	BOFFSET = 4 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FMPY	f37  = f73, f68	nop	__LINE__	}	;;	{ .mfi	LDFPD	f90, f91 = [BOFFSET], 2 * SIZE	FMPY	f34  = f72, f66	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f38  = f72, f70	nop	__LINE__	}	;;	{ .mfi	LDFPD	f92, f93 = [BOFFSET], 2 * SIZE	FMPY	f35  = f73, f66	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMPY	f39  = f73, f70	nop	__LINE__	}	;;	{ .mfi	LDFPD	f94, f95 = [BOFFSET]	FMA_C	f64  = f73, f65, f32	adds	BOFFSET = 6 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FMA_C	f68  = f73, f69, f36	nop	__LINE__	}	;;	{ .mfi	LDFPD	f108, f109 = [BOFFSET], 2 * SIZE	FMA_D	f65  = f72, f65, f33	nop	__LINE__	}	{ .mfi	nop	__LINE__	FMA_D	f69  = f72, f69, f37	nop	__LINE__	}	;;	{ .mfi	LDFPD	f110, f111 = [BOFFSET]	FMA_C	f66  = f73, f67, f34	adds	BOFFSET = 8 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FMA_C	f70  = f73, f71, f38	nop	__LINE__	}	;;	{ .mfi	LDFPD	f126, f127 = [BOFFSET]	FMA_D	f67  = f72, f67, f35	adds	BOFFSET = - 30 * SIZE, BOFFSET	}	{ .mfi	nop	__LINE__	FMA_D	f71  = f72, f71, f39	adds	AOFFSET2 = 4 * SIZE, AOFFSET	}	;;	{ .mfi	STFD	[AOFFSET]  = f64,  SIZE	FNMA	f80  = f74, f64, f80	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f68,  SIZE	FNMA	f84  = f74, f68, f84	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f65,  SIZE	FMA_A	f81  = f75, f64, f81	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f69,  SIZE	FMA_A	f85  = f75, f68, f85	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f66,  SIZE	FNMA	f82  = f74, f66, f82	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f70,  SIZE	FNMA	f86  = f74, f70, f86	nop	__LINE__	}	;;	{ .mfi	STFD	[AOFFSET]  = f67,  5 * SIZE	FMA_A	f83  = f75, f66, f83	nop	__LINE__	}	{ .mfi	STFD	[AOFFSET2] = f71,  5 * SIZE	FMA_A	f87  = f75, f70, f87	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f64, SIZE	FMA_B	f80  = f75, f65, f80	nop	__LINE__	}	{ .mfi	STFD	[C5 ] = f68, SIZE	FMA_B	f84  = f75, f69, f84	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f65, SIZE	FNMA	f81  = f74, f65, f81	nop	__LINE__	}	{ .mfi	STFD	[C5 ] = f69, SIZE	FNMA	f85  = f74, f69, f85	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f66, SIZE	FMA_B	f82  = f75, f67, f82	nop	__LINE__	}	{ .mfi	STFD	[C5 ] = f70, SIZE	FMA_B	f86  = f75, f71, f86	nop	__LINE__	}	;;	{ .mfi	STFD	[C1 ] = f67, 5 * SIZE	FNMA	f83  = f74, f67, f83	nop	__LINE__	}	{ .mfi	STFD	[C5 ] = f71, 5 * SIZE	FNMA	f87  = f74, f71, f87	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FNMA	f96  = f76, f64, f96	nop	__LINE__	}	{ .mfi	nop	__LINE__	FNMA	f100 = f76, f68, f100	nop	__LINE__	}	;;	{ .mfi	nop	__LINE__	FMA_A	f97  = f77, f64, f97	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 + -