nb_kernel234_ia32_sse2.intel_syntax.s

来自「最著名最快的分子模拟软件」· S 代码 · 共 2,167 行 · 第 1/5 页

S
2,167
字号
	mulpd   xmm5, xmm6	;# luB*(3-rsqB*luB*luB) 	mulpd   xmm1, [esp + nb234_half] ;# rinv 	mulpd   xmm5, [esp + nb234_half] ;# rinv 	movapd [esp + nb234_rinvMH1], xmm1	movapd [esp + nb234_rinvH2M], xmm5	;# start with OO interaction 	movapd xmm0, [esp + nb234_rinvOO] 	movapd xmm4, [esp + nb234_rsqOO]			mulpd xmm4, xmm0	;# xmm4=r 	mulpd xmm4, [esp + nb234_tsc]		cvttpd2pi mm6, xmm4	;# mm6 = lu idx 	cvtpi2pd xmm5, mm6	subpd xmm4, xmm5	movapd xmm1, xmm4	;# xmm1=eps 	movapd xmm2, xmm1		mulpd  xmm2, xmm2	;# xmm2=eps2 	pslld mm6, 3		;# idx *= 8 		movd mm0, eax		movd mm1, ebx	mov  esi, [ebp + nb234_VFtab]	movd eax, mm6	psrlq mm6, 32	movd ebx, mm6	;# dispersion 	movlpd xmm4, [esi + eax*8]	;# Y1 		movlpd xmm3, [esi + ebx*8]	;# Y2 	movhpd xmm4, [esi + eax*8 + 8]	;# Y1 F1 		movhpd xmm3, [esi + ebx*8 + 8]	;# Y2 F2 	movapd xmm5, xmm4	unpcklpd xmm4, xmm3	;# Y1 Y2 	unpckhpd xmm5, xmm3	;# F1 F2 	movlpd xmm6, [esi + eax*8 + 16]	;# G1	movlpd xmm3, [esi + ebx*8 + 16]	;# G2	movhpd xmm6, [esi + eax*8 + 24]	;# G1 H1 		movhpd xmm3, [esi + ebx*8 + 24]	;# G2 H2 	movapd xmm7, xmm6	unpcklpd xmm6, xmm3	;# G1 G2 	unpckhpd xmm7, xmm3	;# H1 H2 	;# dispersion table ready, in xmm4-xmm7 		mulpd  xmm6, xmm1	;# xmm6=Geps 	mulpd  xmm7, xmm2	;# xmm7=Heps2 	addpd  xmm5, xmm6	addpd  xmm5, xmm7	;# xmm5=Fp 		mulpd  xmm7, [esp + nb234_two]	;# two*Heps2 	addpd  xmm7, xmm6	addpd  xmm7, xmm5 ;# xmm7=FF 	mulpd  xmm5, xmm1 ;# xmm5=eps*Fp 	addpd  xmm5, xmm4 ;# xmm5=VV 	movapd xmm4, [esp + nb234_c6]	mulpd  xmm7, xmm4	 ;# fijD 	mulpd  xmm5, xmm4	 ;# Vvdw6 	;# put scalar force on stack Update Vvdwtot directly 	addpd  xmm5, [esp + nb234_Vvdwtot]	xorpd  xmm3, xmm3	mulpd  xmm7, [esp + nb234_tsc]	subpd  xmm3, xmm7	movapd [esp + nb234_fstmp], xmm3	movapd [esp + nb234_Vvdwtot], xmm5	;# repulsion 	movlpd xmm4, [esi + eax*8 + 32]	;# Y1 		movlpd xmm3, [esi + ebx*8 + 32]	;# Y2 	movhpd xmm4, [esi + eax*8 + 40]	;# Y1 F1 		movhpd xmm3, [esi + ebx*8 + 40]	;# Y2 F2 	movapd xmm5, xmm4	unpcklpd xmm4, xmm3	;# Y1 Y2 	unpckhpd xmm5, xmm3	;# F1 F2 	movlpd xmm6, [esi + eax*8 + 48]	;# G1	movlpd xmm3, [esi + ebx*8 + 48]	;# G2	movhpd xmm6, [esi + eax*8 + 56]	;# G1 H1 		movhpd xmm3, [esi + ebx*8 + 56]	;# G2 H2 	movapd xmm7, xmm6	unpcklpd xmm6, xmm3	;# G1 G2 	unpckhpd xmm7, xmm3	;# H1 H2 		;# table ready, in xmm4-xmm7 		mulpd  xmm6, xmm1	;# xmm6=Geps 	mulpd  xmm7, xmm2	;# xmm7=Heps2 	addpd  xmm5, xmm6	addpd  xmm5, xmm7	;# xmm5=Fp 		mulpd  xmm7, [esp + nb234_two]	;# two*Heps2 	addpd  xmm7, xmm6	addpd  xmm7, xmm5 ;# xmm7=FF 	mulpd  xmm5, xmm1 ;# xmm5=eps*Fp 	addpd  xmm5, xmm4 ;# xmm5=VV 		movapd xmm4, [esp + nb234_c12]	mulpd  xmm7, xmm4 	mulpd  xmm5, xmm4  		addpd  xmm5, [esp + nb234_Vvdwtot]	movapd xmm3, [esp + nb234_fstmp]	mulpd  xmm7, [esp + nb234_tsc]	subpd  xmm3, xmm7	movapd [esp + nb234_Vvdwtot], xmm5	mulpd  xmm0, xmm3	movapd xmm1, xmm0	movapd xmm2, xmm0		movd eax, mm0		movd ebx, mm1	xorpd xmm3, xmm3	movapd xmm4, xmm3	movapd xmm5, xmm3	mulpd xmm0, [esp + nb234_dxOO]	mulpd xmm1, [esp + nb234_dyOO]	mulpd xmm2, [esp + nb234_dzOO]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb234_fixO]	addpd xmm1, [esp + nb234_fiyO]	addpd xmm2, [esp + nb234_fizO]	movapd [esp + nb234_fjxO], xmm3	movapd [esp + nb234_fjyO], xmm4	movapd [esp + nb234_fjzO], xmm5	movapd [esp + nb234_fixO], xmm0	movapd [esp + nb234_fiyO], xmm1	movapd [esp + nb234_fizO], xmm2	;# H1-H1 interaction 	movapd xmm0, [esp + nb234_rinvH1H1]	movapd xmm7, xmm0	;# xmm7=rinv 	movapd xmm5, [esp + nb234_krf]	mulpd  xmm0, xmm0	;# xmm0=rinvsq 	mulpd  xmm5, [esp + nb234_rsqH1H1] ;# xmm5=krsq 	movapd xmm6, xmm5	addpd  xmm6, xmm7	;# xmm6=rinv+ krsq 	subpd  xmm6, [esp + nb234_crf]	mulpd  xmm6, [esp + nb234_qqHH] ;# xmm6=voul=qq*(rinv+ krsq-crf) 	mulpd  xmm5, [esp + nb234_two]	subpd  xmm7, xmm5	;# xmm7=rinv-2*krsq 	mulpd  xmm7, [esp + nb234_qqHH] ;# xmm7 = coul part of fscal 		addpd  xmm6, [esp + nb234_vctot] ;# local vctot summation variable 	mulpd  xmm0, xmm7	movapd [esp + nb234_vctot], xmm6	movapd xmm1, xmm0	movapd xmm2, xmm0	xorpd xmm3, xmm3	movapd xmm4, xmm3	movapd xmm5, xmm3	mulpd xmm0, [esp + nb234_dxH1H1]	mulpd xmm1, [esp + nb234_dyH1H1]	mulpd xmm2, [esp + nb234_dzH1H1]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb234_fixH1]	addpd xmm1, [esp + nb234_fiyH1]	addpd xmm2, [esp + nb234_fizH1]	movapd [esp + nb234_fjxH1], xmm3	movapd [esp + nb234_fjyH1], xmm4	movapd [esp + nb234_fjzH1], xmm5	movapd [esp + nb234_fixH1], xmm0	movapd [esp + nb234_fiyH1], xmm1	movapd [esp + nb234_fizH1], xmm2	;# H1-H2 interaction  	movapd xmm0, [esp + nb234_rinvH1H2]	movapd xmm7, xmm0	;# xmm7=rinv 	movapd xmm5, [esp + nb234_krf]	mulpd  xmm0, xmm0	;# xmm0=rinvsq 	mulpd  xmm5, [esp + nb234_rsqH1H2] ;# xmm5=krsq 	movapd xmm6, xmm5	addpd  xmm6, xmm7	;# xmm6=rinv+ krsq 	subpd  xmm6, [esp + nb234_crf]	mulpd  xmm6, [esp + nb234_qqHH] ;# xmm6=voul=qq*(rinv+ krsq-crf) 	mulpd  xmm5, [esp + nb234_two]	subpd  xmm7, xmm5	;# xmm7=rinv-2*krsq 	mulpd  xmm7, [esp + nb234_qqHH] ;# xmm7 = coul part of fscal 		addpd  xmm6, [esp + nb234_vctot] ;# local vctot summation variable 	mulpd  xmm0, xmm7	movapd [esp + nb234_vctot], xmm6		movapd xmm1, xmm0	movapd xmm2, xmm0	xorpd xmm3, xmm3	movapd xmm4, xmm3	movapd xmm5, xmm3	mulpd xmm0, [esp + nb234_dxH1H2]	mulpd xmm1, [esp + nb234_dyH1H2]	mulpd xmm2, [esp + nb234_dzH1H2]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb234_fixH1]	addpd xmm1, [esp + nb234_fiyH1]	addpd xmm2, [esp + nb234_fizH1]	movapd [esp + nb234_fjxH2], xmm3	movapd [esp + nb234_fjyH2], xmm4	movapd [esp + nb234_fjzH2], xmm5	movapd [esp + nb234_fixH1], xmm0	movapd [esp + nb234_fiyH1], xmm1	movapd [esp + nb234_fizH1], xmm2	;# H1-M interaction 	movapd xmm0, [esp + nb234_rinvH1M]	movapd xmm7, xmm0	;# xmm7=rinv 	movapd xmm5, [esp + nb234_krf]	mulpd  xmm0, xmm0	;# xmm0=rinvsq 	mulpd  xmm5, [esp + nb234_rsqH1M] ;# xmm5=krsq 	movapd xmm6, xmm5	addpd  xmm6, xmm7	;# xmm6=rinv+ krsq 	subpd  xmm6, [esp + nb234_crf]	mulpd  xmm6, [esp + nb234_qqMH] ;# xmm6=voul=qq*(rinv+ krsq-crf) 	mulpd  xmm5, [esp + nb234_two]	subpd  xmm7, xmm5	;# xmm7=rinv-2*krsq 	mulpd  xmm7, [esp + nb234_qqMH] ;# xmm7 = coul part of fscal 		addpd  xmm6, [esp + nb234_vctot] ;# local vctot summation variable 	mulpd  xmm0, xmm7	movapd [esp + nb234_vctot], xmm6	movapd xmm1, xmm0	movapd xmm2, xmm0		xorpd xmm3, xmm3	movapd xmm4, xmm3	movapd xmm5, xmm3	mulpd xmm0, [esp + nb234_dxH1M]	mulpd xmm1, [esp + nb234_dyH1M]	mulpd xmm2, [esp + nb234_dzH1M]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb234_fixH1]	addpd xmm1, [esp + nb234_fiyH1]	addpd xmm2, [esp + nb234_fizH1]	movapd [esp + nb234_fjxM], xmm3	movapd [esp + nb234_fjyM], xmm4	movapd [esp + nb234_fjzM], xmm5	movapd [esp + nb234_fixH1], xmm0	movapd [esp + nb234_fiyH1], xmm1	movapd [esp + nb234_fizH1], xmm2	;# H2-H1 interaction 	movapd xmm0, [esp + nb234_rinvH2H1]	movapd xmm7, xmm0	;# xmm7=rinv 	movapd xmm5, [esp + nb234_krf]	mulpd  xmm0, xmm0	;# xmm0=rinvsq 	mulpd  xmm5, [esp + nb234_rsqH2H1] ;# xmm5=krsq 	movapd xmm6, xmm5	addpd  xmm6, xmm7	;# xmm6=rinv+ krsq 	subpd  xmm6, [esp + nb234_crf]	mulpd  xmm6, [esp + nb234_qqHH] ;# xmm6=voul=qq*(rinv+ krsq-crf) 	mulpd  xmm5, [esp + nb234_two]	subpd  xmm7, xmm5	;# xmm7=rinv-2*krsq 	mulpd  xmm7, [esp + nb234_qqHH] ;# xmm7 = coul part of fscal 		addpd  xmm6, [esp + nb234_vctot] ;# local vctot summation variable 	mulpd  xmm0, xmm7	movapd [esp + nb234_vctot], xmm6		movapd xmm1, xmm0	movapd xmm2, xmm0		movapd xmm3, [esp + nb234_fjxH1]	movapd xmm4, [esp + nb234_fjyH1]	movapd xmm5, [esp + nb234_fjzH1]	mulpd xmm0, [esp + nb234_dxH2H1]	mulpd xmm1, [esp + nb234_dyH2H1]	mulpd xmm2, [esp + nb234_dzH2H1]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb234_fixH2]	addpd xmm1, [esp + nb234_fiyH2]	addpd xmm2, [esp + nb234_fizH2]	movapd [esp + nb234_fjxH1], xmm3	movapd [esp + nb234_fjyH1], xmm4	movapd [esp + nb234_fjzH1], xmm5	movapd [esp + nb234_fixH2], xmm0	movapd [esp + nb234_fiyH2], xmm1	movapd [esp + nb234_fizH2], xmm2	;# H2-H2 interaction 	movapd xmm0, [esp + nb234_rinvH2H2]	movapd xmm7, xmm0	;# xmm7=rinv 	movapd xmm5, [esp + nb234_krf]	mulpd  xmm0, xmm0	;# xmm0=rinvsq 	mulpd  xmm5, [esp + nb234_rsqH2H2] ;# xmm5=krsq 	movapd xmm6, xmm5	addpd  xmm6, xmm7	;# xmm6=rinv+ krsq 	subpd  xmm6, [esp + nb234_crf]	mulpd  xmm6, [esp + nb234_qqHH] ;# xmm6=voul=qq*(rinv+ krsq-crf) 	mulpd  xmm5, [esp + nb234_two]	subpd  xmm7, xmm5	;# xmm7=rinv-2*krsq 	mulpd  xmm7, [esp + nb234_qqHH] ;# xmm7 = coul part of fscal 		addpd  xmm6, [esp + nb234_vctot] ;# local vctot summation variable 	mulpd  xmm0, xmm7	movapd [esp + nb234_vctot], xmm6		movapd xmm1, xmm0	movapd xmm2, xmm0		movapd xmm3, [esp + nb234_fjxH2]	movapd xmm4, [esp + nb234_fjyH2]	movapd xmm5, [esp + nb234_fjzH2]	mulpd xmm0, [esp + nb234_dxH2H2]	mulpd xmm1, [esp + nb234_dyH2H2]	mulpd xmm2, [esp + nb234_dzH2H2]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb234_fixH2]	addpd xmm1, [esp + nb234_fiyH2]	addpd xmm2, [esp + nb234_fizH2]	movapd [esp + nb234_fjxH2], xmm3	movapd [esp + nb234_fjyH2], xmm4	movapd [esp + nb234_fjzH2], xmm5	movapd [esp + nb234_fixH2], xmm0	movapd [esp + nb234_fiyH2], xmm1	movapd [esp + nb234_fizH2], xmm2	;# H2-M interaction 	movapd xmm0, [esp + nb234_rinvH2M]	movapd xmm7, xmm0	;# xmm7=rinv 	movapd xmm5, [esp + nb234_krf]	mulpd  xmm0, xmm0	;# xmm0=rinvsq 	mulpd  xmm5, [esp + nb234_rsqH2M] ;# xmm5=krsq 	movapd xmm6, xmm5	addpd  xmm6, xmm7	;# xmm6=rinv+ krsq 	subpd  xmm6, [esp + nb234_crf]	mulpd  xmm6, [esp + nb234_qqMH] ;# xmm6=voul=qq*(rinv+ krsq-crf) 	mulpd  xmm5, [esp + nb234_two]	subpd  xmm7, xmm5	;# xmm7=rinv-2*krsq 	mulpd  xmm7, [esp + nb234_qqMH] ;# xmm7 = coul part of fscal 		addpd  xmm6, [esp + nb234_vctot] ;# local vctot summation variable 	mulpd  xmm0, xmm7	movapd [esp + nb234_vctot], xmm6		movapd xmm1, xmm0	movapd xmm2, xmm0	movapd xmm3, [esp + nb234_fjxM]	movapd xmm4, [esp + nb234_fjyM]	movapd xmm5, [esp + nb234_fjzM]	mulpd xmm0, [esp + nb234_dxH2M]	mulpd xmm1, [esp + nb234_dyH2M]	mulpd xmm2, [esp + nb234_dzH2M]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb234_fixH2]	addpd xmm1, [esp + nb234_fiyH2]	addpd xmm2, [esp + nb234_fizH2]	movapd [esp + nb234_fjxM], xmm3	movapd [esp + nb234_fjyM], xmm4	movapd [esp + nb234_fjzM], xmm5	movapd [esp + nb234_fixH2], xmm0	movapd [esp + nb234_fiyH2], xmm1	movapd [esp + nb234_fizH2], xmm2	;# M-H1 interaction 	movapd xmm0, [esp + nb234_rinvMH1]	movapd xmm7, xmm0	;# xmm7=rinv 	movapd xmm5, [esp + nb234_krf]	mulpd  xmm0, xmm0	;# xmm0=rinvsq 	mulpd  xmm5, [esp + nb234_rsqMH1] ;# xmm5=krsq 	movapd xmm6, xmm5	addpd  xmm6, xmm7	;# xmm6=rinv+ krsq 	subpd  xmm6, [esp + nb234_crf]	mulpd  xmm6, [esp + nb234_qqMH] ;# xmm6=voul=qq*(rinv+ krsq-crf) 	mulpd  xmm5, [esp + nb234_two]	subpd  xmm7, xmm5	;# xmm7=rinv-2*krsq 	mulpd  xmm7, [esp + nb234_qqMH] ;# xmm7 = coul part of fscal 		addpd  xmm6, [esp + nb234_vctot] ;# local vctot summation variable 	mulpd  xmm0, xmm7	movapd [esp + nb234_vctot], xmm6		movapd xmm1, xmm0	movapd xmm2, xmm0	movapd xmm3, [esp + nb234_fjxH1]	movapd xmm4, [esp + nb234_fjyH1]	movapd xmm5, [esp + nb234_fjzH1]	mulpd xmm0, [esp + nb234_dxMH1]	mulpd xmm1, [esp + nb234_dyMH1]	mulpd xmm2, [esp + nb234_dzMH1]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb234_fixM]	addpd xmm1, [esp + nb234_fiyM]	addpd xmm2, [esp + nb234_fizM]	movapd [esp + nb234_fjxH1], xmm3	movapd [esp + nb234_fjyH1], xmm4	movapd [esp + nb234_fjzH1], xmm5	movapd [esp + nb234_fixM], xmm0	movapd [esp + nb234_fiyM], xmm1	movapd [esp + nb234_fizM], xmm2	;# M-H2 interaction 	movapd xmm0, [esp + nb234_rinvMH2]	movapd xmm7, xmm0	;# xmm7=rinv 	movapd xmm5, [esp + nb234_krf]	mulpd  xmm0, xmm0	;# xmm0=rinvsq 	mulpd  xmm5, [esp + nb234_rsqMH2] ;# xmm5=krsq 	movapd xmm6, xmm5	addpd  xmm6, xmm7	;# xmm6=rinv+ krsq 	subpd  xmm6, [esp + nb234_crf]	mulpd  xmm6, [esp + nb234_qqMH] ;# xmm6=voul=qq*(rinv+ krsq-crf) 	mulpd  xmm5, [esp + nb234_two]

⌨️ 快捷键说明

复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?