⭐ 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

📄 trsm_kernel_ln.s

📁 Optimized GotoBLAS libraries
💻 S
📖 第 1 页 / 共 5 页
字号:
	 }	 ;;	 { .mfi	 (p3) LDFPD	f58, f59 = [BOFFSET],  2 * SIZE	 FMA	f65   = f33, f48, f65	// A2 * B1	 (p5) adds	C13 = 2 * SIZE, C5	 }	 { .mfi	 nop	__LINE__	 FMA	f73   = f33, f49, f73	// A2 * B2	 (p5) adds	C14 = 2 * SIZE, C6	 }	 ;;	 { .mfi	 (p3) LDFPD	f60, f61 = [BOFFSET], 2 * SIZE	 FMA	f81   = f33, f50, f81	// A2 * B3	 (p5) adds	C15 = 2 * SIZE, C7	 }	 { .mfi	 nop	__LINE__	 FMA	f89   = f33, f51, f89	// A2 * B4	 (p5) adds	C16 = 2 * SIZE, C8	 }	 ;;	 { .mfb	 (p3) LDFPD	f62, f63 = [BOFFSET], 2 * SIZE	 FMA	f97   = f33, f52, f97	// A2 * B5	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f105  = f33, f53, f105	// A2 * B6	 nop	__LINE__	 }	 ;;	 { .mfb	 (p3) LDFPD	f42, f43 = [AOFFSET], 2 * SIZE	 FMA	f113  = f33, f54, f113	// A2 * B7	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f121  = f33, f55, f121	// A2 * B8	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 FMA	f66   = f34, f48, f66	// A3 * B1	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f74   = f34, f49, f74	// A3 * B2	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 FMA	f82   = f34, f50, f82	// A3 * B3	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f90   = f34, f51, f90	// A3 * B4	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 FMA	f98   = f34, f52, f98	// A3 * B5	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f106  = f34, f53, f106	// A3 * B6	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f114  = f34, f54, f114	// A3 * B7	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f122  = f34, f55, f122	// A3 * B8	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f67   = f35, f48, f67	// A4 * B1	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f75   = f35, f49, f75	// A4 * B2	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f83   = f35, f50, f83	// A4 * B3	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f91   = f35, f51, f91	// A4 * B4	 nop	__LINE__	 }	 { .mfb	 (p4) LDFPD	f32, f33 = [AOFFSET],   2 * SIZE	 FMA	f99   = f35, f52, f99	// A4 * B5	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f107  = f35, f53, f107	// A4 * B6	 nop	__LINE__	 }	 { .mfb	 (p4) LDFPD	f48, f49 = [BOFFSET],   2 * SIZE	 FMA	f115  = f35, f54, f115	// A4 * B7	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 FMA	f123  = f35, f55, f123	// A4 * B8	 nop	__LINE__	 }	 ;;	 { .mfb	 (p4) LDFPD	f50, f51 = [BOFFSET],  2 * SIZE	 (p3) FMA	f64   = f40, f56, f64	// A1 * B1	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f72   = f40, f57, f72	// A1 * B2	 nop	__LINE__	 }	 ;;	 { .mfb	 (p4) LDFPD	f52, f53 = [BOFFSET], 2 * SIZE	 (p3) FMA	f80   = f40, f58, f80	// A1 * B3	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f88   = f40, f59, f88	// A1 * B4	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 (p3) FMA	f96   = f40, f60, f96	// A1 * B5	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f104  = f40, f61, f104	// A1 * B6	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 (p3) FMA	f112  = f40, f62, f112	// A1 * B7	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f120  = f40, f63, f120	// A1 * B8	 nop	__LINE__	 }	 ;;	 { .mfb	 (p4) LDFPD	f54, f55 = [BOFFSET], 2 * SIZE	 (p3) FMA	f65   = f41, f56, f65	// A2 * B1	 nop	__LINE__	 }	 { .mfb	 (p3) FMA	f73   = f41, f57, f73	// A2 * B2	 nop	__LINE__	 }	 { .mfb	 (p4) LDFPD	f34, f35 = [AOFFSET], 2 * SIZE	 (p3) FMA	f81   = f41, f58, f81	// A2 * B3	 nop	__LINE__	 }	 { .mfb	 (p3) FMA	f89   = f41, f59, f89	// A2 * B4	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 (p3) FMA	f97   = f41, f60, f97	// A2 * B5	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f105  = f41, f61, f105	// A2 * B6	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 (p3) FMA	f113  = f41, f62, f113	// A2 * B7	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f121  = f41, f63, f121	// A2 * B8	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 (p3) FMA	f66   = f42, f56, f66	// A3 * B1	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f74   = f42, f57, f74	// A3 * B2	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 (p3) FMA	f82   = f42, f58, f82	// A3 * B3	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f90   = f42, f59, f90	// A3 * B4	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 (p3) FMA	f98   = f42, f60, f98	// A3 * B5	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f106  = f42, f61, f106	// A3 * B6	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 (p3) FMA	f114  = f42, f62, f114	// A3 * B7	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f122  = f42, f63, f122	// A3 * B8	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 (p3) FMA	f67   = f43, f56, f67	// A4 * B1	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f75   = f43, f57, f75	// A4 * B2	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 (p3) FMA	f83   = f43, f58, f83	// A4 * B3	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f91   = f43, f59, f91	// A4 * B4	 nop	__LINE__	 }	 ;;	 { .mfb	 nop	__LINE__	 (p3) FMA	f99   = f43, f60, f99	// A4 * B5	 nop	__LINE__	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f107  = f43, f61, f107	// A4 * B6	 nop	__LINE__	 }	 ;;	 { .mfi	 nop	__LINE__	 (p3) FMA	f115  = f43, f62, f115	// A4 * B7	 adds	L = -1, L	 }	 { .mfb	 nop	__LINE__	 (p3) FMA	f123  = f43, f63, f123	// A4 * B8	 br.cloop.sptk.few .L022	 }	 ;; .L028: #if defined(LN) || defined(RT) #ifdef LN	 adds	r2 = -4, KK #else	 adds	r2 = -8, KK #endif	 ;;	 shladd	r2 = r2, BASE_SHIFT, r0	 ;;	 shladd	AOFFSET = r2, 2, AORIG	 shladd	BOFFSET = r2, 3, B	 ;;	 #endif	 adds	AOFFSET2 = 4 * SIZE, AOFFSET	 adds	BOFFSET2 = 4 * SIZE, BOFFSET	 ;; #if defined(LN) || defined(LT)	 LDFPD	f32, f33 = [BOFFSET], 2 * SIZE	 ;;	 LDFPD	f34, f35 = [BOFFSET], 2 * SIZE	 ;;	 LDFPD	f36, f37 = [BOFFSET], 2 * SIZE	 ;;	 LDFPD	f38, f39 = [BOFFSET], 2 * SIZE	 ;;	 LDFPD	f40, f41 = [BOFFSET], 2 * SIZE	 ;;	 LDFPD	f42, f43 = [BOFFSET], 2 * SIZE	 ;;	 LDFPD	f44, f45 = [BOFFSET], 2 * SIZE	 ;;	 LDFPD	f46, f47 = [BOFFSET], 2 * SIZE	 ;;	 { .mfi	 LDFPD	f48, f49 = [BOFFSET], 2 * SIZE	 FSUB	f64  = f32, f64	 nop	__LINE__	 }	 { .mfi	 nop	__LINE__	 FSUB	f72  = f33, f72	 nop	__LINE__	 }	 ;;	 { .mfi	 LDFPD	f50, f51 = [BOFFSET], 2 * SIZE	 FSUB	f80  = f34, f80	 nop	__LINE__	 }	 { .mfi	 nop	__LINE__	 FSUB	f88  = f35, f88	 nop	__LINE__	 }	 ;;	 { .mfi	 LDFPD	f52, f53 = [BOFFSET], 2 * SIZE	 FSUB	f96  = f36, f96	 nop	__LINE__	 }	 { .mfi	 nop	__LINE__	 FSUB	f104 = f37, f104	 nop	__LINE__	 }	 ;;	 { .mfi	 LDFPD	f54, f55 = [BOFFSET], 2 * SIZE	 FSUB	f112 = f38, f112	 nop	__LINE__	 }	 { .mfi	 nop	__LINE__	 FSUB	f120 = f39, f120	 nop	__LINE__	 }	 ;;	 { .mfi	 LDFPD	f56, f57 = [BOFFSET], 2 * SIZE	 FSUB	f65  = f40, f65	 nop	__LINE__	 }	 { .mfi	 nop	__LINE__	 FSUB	f73  = f41, f73	 nop	__LINE__	 }	 ;;	 { .mfi	 LDFPD	f58, f59 = [BOFFSET], 2 * SIZE	 FSUB	f81  = f42, f81	 nop	__LINE__	 }	 { .mfi	 nop	__LINE__	 FSUB	f89  = f43, f89	 nop	__LINE__	 }	 ;;	 { .mfi	 LDFPD	f60, f61 = [BOFFSET], 2 * SIZE	 FSUB	f97  = f44, f97	 nop	__LINE__	 }	 { .mfi	 nop	__LINE__	 FSUB	f105 = f45, f105	 nop	__LINE__	 }	 ;;	 { .mfi	 LDFPD	f62, f63 = [BOFFSET]	 FSUB	f113 = f46, f113	 adds	BOFFSET = -30 * SIZE, BOFFSET	 }	 { .mfi	 nop	__LINE__	 FSUB	f121 = f47, f121	 nop	__LINE__	 }	 ;;	 FSUB	f66  = f48, f66	 FSUB	f74  = f49, f74	 FSUB	f82  = f50, f82	 FSUB	f90  = f51, f90	 FSUB	f98  = f52, f98	 FSUB	f106 = f53, f106	 FSUB	f114 = f54, f114	 FSUB	f122 = f55, f122	 ;;	 FSUB	f67  = f56, f67	 FSUB	f75  = f57, f75	 FSUB	f83  = f58, f83	 FSUB	f91  = f59, f91	 FSUB	f99  = f60, f99	 FSUB	f107 = f61, f107	 FSUB	f115 = f62, f115	 FSUB	f123 = f63, f123	 ;; #else	 LDFPD	f32, f33 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f34, f35 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f36, f37 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f38, f39 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f40, f41 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f42, f43 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f44, f45 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f46, f47 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f48, f49 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f50, f51 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f52, f53 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f54, f55 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f56, f57 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f58, f59 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f60, f61 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f62, f63 = [AOFFSET]	 adds	AOFFSET = -30 * SIZE, AOFFSET	 ;;	 FSUB	f64  = f32, f64	 FSUB	f65  = f33, f65	 FSUB	f66  = f34, f66	 FSUB	f67  = f35, f67	 FSUB	f72  = f36, f72	 FSUB	f73  = f37, f73	 FSUB	f74  = f38, f74	 FSUB	f75  = f39, f75	 FSUB	f80  = f40, f80	 FSUB	f81  = f41, f81	 FSUB	f82  = f42, f82	 FSUB	f83  = f43, f83	 FSUB	f88  = f44, f88	 FSUB	f89  = f45, f89	 FSUB	f90  = f46, f90	 FSUB	f91  = f47, f91	 ;;	 FSUB	f96  = f48, f96	 FSUB	f97  = f49, f97	 FSUB	f98  = f50, f98	 FSUB	f99  = f51, f99	 ;;	 FSUB	f104 = f52, f104	 FSUB	f105 = f53, f105	 FSUB	f106 = f54, f106	 FSUB	f107 = f55, f107	 ;;	 FSUB	f112 = f56, f112	 FSUB	f113 = f57, f113	 FSUB	f114 = f58, f114	 FSUB	f115 = f59, f115	 ;;	 FSUB	f120 = f60, f120	 FSUB	f121 = f61, f121	 FSUB	f122 = f62, f122	 FSUB	f123 = f63, f123	 ;; #endif #ifdef LN	 adds	AOFFSET = 14 * SIZE, AOFFSET	 ;;	 LDFPD	f33, f32 = [AOFFSET]	 adds	AOFFSET = - 2 * SIZE, AOFFSET	 ;;	 LDFPD	f35, f34 = [AOFFSET]	 adds	AOFFSET = - 2 * SIZE, AOFFSET	 ;;	 LDFD	f36 = [AOFFSET], - 2 * SIZE	 ;;	 LDFPD	f38, f37 = [AOFFSET]	 adds	AOFFSET = - 4 * SIZE, AOFFSET	 ;;	 LDFPD	f40, f39 = [AOFFSET]	 adds	AOFFSET = - 4 * SIZE, AOFFSET	 ;;	 LDFD	f41 = [AOFFSET]	 ;;	 FMPY	f67  = f67,  f32	 FMPY	f99  = f99,  f32	 FMPY	f75  = f75,  f32	 FMPY	f107 = f107, f32	 FMPY	f83  = f83,  f32	 FMPY	f115 = f115, f32	 FMPY	f91  = f91,  f32	 FMPY	f123 = f123, f32	 ;;	 FNMA	f66  = f67,  f33, f66	 FNMA	f98  = f99,  f33, f98	 FNMA	f74  = f75,  f33, f74	 FNMA	f106 = f107, f33, f106	 FNMA	f82  = f83,  f33, f82	 FNMA	f114 = f115, f33, f114	 FNMA	f90  = f91,  f33, f90	 FNMA	f122 = f123, f33, f122	 ;;	 FNMA	f65  = f67,  f34, f65	 FNMA	f97  = f99,  f34, f97	 FNMA	f73  = f75,  f34, f73	 FNMA	f105 = f107, f34, f105	 FNMA	f81  = f83,  f34, f81	 FNMA	f113 = f115, f34, f113	 FNMA	f89  = f91,  f34, f89	 FNMA	f121 = f123, f34, f121	 ;;	 FNMA	f64  = f67,  f35, f64	 FNMA	f96  = f99,  f35, f96	 FNMA	f72  = f75,  f35, f72	 FNMA	f104 = f107, f35, f104	 FNMA	f80  = f83,  f35, f80	 FNMA	f112 = f115, f35, f112	 FNMA	f88  = f91,  f35, f88	 FNMA	f120 = f123, f35, f120	 ;;	 FMPY	f66  = f66,  f36	 FMPY	f98  = f98,  f36	 FMPY	f74  = f74,  f36	 FMPY	f106 = f106, f36	 FMPY	f82  = f82,  f36	 FMPY	f114 = f114, f36	 FMPY	f90  = f90,  f36	 FMPY	f122 = f122, f36	 ;;	 FNMA	f65  = f66,  f37, f65	 FNMA	f97  = f98,  f37, f97	 FNMA	f73  = f74,  f37, f73	 FNMA	f105 = f106, f37, f105	 FNMA	f81  = f82,  f37, f81	 FNMA	f113 = f114, f37, f113	 FNMA	f89  = f90,  f37, f89	 FNMA	f121 = f122, f37, f121	 ;;	 FNMA	f64  = f66,  f38, f64	 FNMA	f96  = f98,  f38, f96	 FNMA	f72  = f74,  f38, f72	 FNMA	f104 = f106, f38, f104	 FNMA	f80  = f82,  f38, f80	 FNMA	f112 = f114, f38, f112	 FNMA	f88  = f90,  f38, f88	 FNMA	f120 = f122, f38, f120	 ;;	 adds	BOFFSET  = 24 * SIZE, BOFFSET	 adds	BOFFSET2 = 24 * SIZE, BOFFSET2	 ;;	 { .mfi	 STFD	[BOFFSET]  = f67, SIZE	 FMPY	f65  = f65,  f39	 }	 { .mfi	 STFD	[BOFFSET2] = f99, SIZE	 FMPY	f97  = f97,  f39	 }	 ;;	 { .mfi	 STFD	[BOFFSET]  = f75, SIZE	 FMPY	f73  = f73,  f39	 }	 { .mfi	 STFD	[BOFFSET2] = f107, SIZE	 FMPY	f105 = f105, f39	 }	 ;;	 { .mfi	 STFD	[BOFFSET]  = f83, SIZE	 FMPY	f81  = f81,  f39	 }	 { .mfi	 STFD	[BOFFSET2] = f115, SIZE	 FMPY	f113 = f113, f39	 }	 ;;	 { .mfi	 STFD	[BOFFSET]  = f91,  - 11 * SIZE	 FMPY	f89  = f89,  f39	 }	 { .mfi	 STFD	[BOFFSET2] = f123, - 11 * SIZE	 FMPY	f121 = f121, f39	 }	 ;;	 { .mfi	 STFD	[BOFFSET]  = f66, SIZE	 FNMA	f64  = f65,  f40, f64	 }	 { .mfi	 STFD	[BOFFSET2] = f98, SIZE	 FNMA	f96  = f97,  f40, f96	 }	 ;;	 { .mfi	 STFD	[BOFFSET]  = f74, SIZE	 FNMA	f72  = f73,  f40, f72	 }	 { .mfi	 STFD	[BOFFSET2] = f106, SIZE	 FNMA	f104 = f105, f40, f104	 }	 ;;	 { .mfi	 STFD	[BOFFSET]  = f82, SIZE	 FNMA	f80  = f81,  f40, f80	 }	 { .mfi	 STFD	[BOFFSET2] = f114, SIZE	 FNMA	f112 = f113, f40, f112	 }	 ;;	 { .mfi	 STFD	[BOFFSET]  = f90,  -11 * SIZE	 FNMA	f88  = f89,  f40, f88	 }	 { .mfi	 STFD	[BOFFSET2] = f122, -11 * SIZE	 FNMA	f120 = f121, f40, f120	 }	 ;;	 { .mfi	 STFD	[BOFFSET]  = f65, SIZE	 FMPY	f64  = f64,  f41	 }	 { .mfi	 STFD	[BOFFSET2] = f97, SIZE	 FMPY	f96  = f96,  f41	 }	 ;;	 { .mfi	 STFD	[BOFFSET]  = f73, SIZE	 FMPY	f72  = f72,  f41	 }	 { .mfi	 STFD	[BOFFSET2] = f105, SIZE	 FMPY	f104 = f104, f41	 }	 ;;	 { .mfi	 STFD	[BOFFSET]  = f81, SIZE	 FMPY	f80  = f80,  f41	 }	 { .mfi	 STFD	[BOFFSET2] = f113, SIZE	 FMPY	f112 = f112, f41	 }	 ;;	 { .mfi	 STFD	[BOFFSET]  = f89,  - 11 * SIZE	 FMPY	f88  = f88,  f41	 }	 { .mfi	 STFD	[BOFFSET2] = f121, - 11 * SIZE	 FMPY	f120 = f120, f41	 }	 ;;	 { .mmi	 STFD	[BOFFSET]  = f64, SIZE	 STFD	[BOFFSET2] = f96, SIZE	 adds	C1 = -4 * SIZE, C1	 }	 ;;	 { .mmi	 STFD	[BOFFSET]  = f72, SIZE	 STFD	[BOFFSET2] = f104, SIZE	 adds	C2 = -4 * SIZE, C2	 }	 ;;	 { .mmi	 STFD	[BOFFSET]  = f80, SIZE	 STFD	[BOFFSET2] = f112, SIZE	 nop	__LINE__	 }	 ;;	 { .mmi	 STFD	[BOFFSET]  = f88,  - 3 * SIZE	 STFD	[BOFFSET2] = f120, - 3 * SIZE	 }	 ;; #endif #ifdef LT	 LDFPD	f32, f33 = [AOFFSET], 2 * SIZE	 ;;	 LDFPD	f34, f35 = [AOFFSET]	 adds	AOFFSET = 3 * SIZE, AOFFSET	 ;;	 LDFD	f36 = [AOFFSET], 1 * SIZE	 ;;

⌨️ 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 + -