nb_kernel334_ia32_sse2.intel_syntax.s

来自「最著名最快的分子模拟软件」· S 代码 · 共 2,176 行 · 第 1/5 页

S
2,176 行
字号
12345
	movapd xmm2, xmm1		mulpd  xmm2, xmm2	;# xmm2=eps2 		pslld mm6, 2		;# idx *= 4 	movd mm0, eax		movd mm1, ebx	mov  esi, [ebp + nb334_VFtab]	movd eax, mm6	psrlq mm6, 32	movd ebx, mm6		;# indices in eax/ebx 	lea   eax, [eax + eax*2]	;# idx*=3 (12 total now) 	lea   ebx, [ebx + ebx*2]	;# idx*=3 (12 total now) 	;# Dispersion 	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 	;# 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 + nb334_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 + nb334_c6]	mulpd  xmm7, xmm4	 ;# fijD 	mulpd  xmm5, xmm4	 ;# Vvdw6 	;# put scalar force on stack. Update Vvdwtot directly 	addpd  xmm5, [esp + nb334_Vvdwtot]	movapd [esp + nb334_fscal], xmm7	movapd [esp + nb334_Vvdwtot], xmm5	;# Repulsion 	movlpd xmm4, [esi + eax*8 + 64]	;# Y1	movlpd xmm3, [esi + ebx*8 + 64]	;# Y2	movhpd xmm4, [esi + eax*8 + 72]	;# Y1 F1 		movhpd xmm3, [esi + ebx*8 + 72]	;# Y2 F2 	movapd xmm5, xmm4	unpcklpd xmm4, xmm3	;# Y1 Y2 	unpckhpd xmm5, xmm3	;# F1 F2 	movlpd xmm6, [esi + eax*8 + 80]	;# G1	movlpd xmm3, [esi + ebx*8 + 80]	;# G2	movhpd xmm6, [esi + eax*8 + 88]	;# G1 H1 		movhpd xmm3, [esi + ebx*8 + 88]	;# G2 H2 	movapd xmm7, xmm6	unpcklpd xmm6, xmm3	;# G1 G2 	unpckhpd xmm7, xmm3	;# H1 H2 	;# Repulsion 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 + nb334_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 + nb334_c12]	mulpd  xmm7, xmm4 ;# fijR 	mulpd  xmm5, xmm4 ;# Vvdw12 	addpd  xmm7, [esp + nb334_fscal]	addpd  xmm5, [esp + nb334_Vvdwtot]	movapd [esp + nb334_Vvdwtot], xmm5	xorpd  xmm4, xmm4	mulpd xmm7, [esp + nb334_tsc]	mulpd xmm7, [esp + nb334_rinvOO]	subpd xmm4, xmm7	movapd xmm0, xmm4	movapd xmm1, xmm4	movapd xmm2, xmm4	xorpd xmm3, xmm3	movapd xmm4, xmm3	movapd xmm5, xmm3	mulpd xmm0, [esp + nb334_dxOO]	mulpd xmm1, [esp + nb334_dyOO]	mulpd xmm2, [esp + nb334_dzOO]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb334_fixO]	addpd xmm1, [esp + nb334_fiyO]	addpd xmm2, [esp + nb334_fizO]	movapd [esp + nb334_fjxO], xmm3	movapd [esp + nb334_fjyO], xmm4	movapd [esp + nb334_fjzO], xmm5	movapd [esp + nb334_fixO], xmm0	movapd [esp + nb334_fiyO], xmm1	movapd [esp + nb334_fizO], xmm2	;# H1-H1 interaction 	movapd xmm0, [esp + nb334_rinvH1H1]	movapd xmm1, xmm0	mulpd  xmm1, [esp + nb334_rsqH1H1] ;# xmm1=r 	mulpd  xmm1, [esp + nb334_tsc]	cvttpd2pi mm6, xmm1	;# mm6 = lu idx 	cvtpi2pd xmm6, mm6	subpd xmm1, xmm6	;# xmm1=eps 	movapd xmm2, xmm1		mulpd  xmm2, xmm2	;# xmm2=eps2 		pslld mm6, 2		;# idx *= 4 	mov  esi, [ebp + nb334_VFtab]	movd eax, mm6	psrlq mm6, 32	movd ebx, mm6		;# indices in eax/ebx 	lea   eax, [eax + eax*2]	;# idx*=3 (12 total now) 	lea   ebx, [ebx + ebx*2]	;# idx*=3 (12 total now) 	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 	;# coulomb 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 + nb334_two]	;# two*Heps2 	movapd xmm3, [esp + nb334_qqHH]	addpd  xmm7, xmm6	addpd  xmm7, xmm5 ;# xmm7=FF 	mulpd  xmm5, xmm1 ;# xmm5=eps*Fp 	addpd  xmm5, xmm4 ;# xmm5=VV 	mulpd  xmm5, xmm3 ;# vcoul=qq*VV  	mulpd  xmm3, xmm7 ;# fijC=FF*qq     	;# at this point mm5 contains vcoul and xmm3 fijC     	addpd  xmm5, [esp + nb334_vctot]    	movapd [esp + nb334_vctot], xmm5	xorpd  xmm1, xmm1	mulpd  xmm3,  [esp + nb334_tsc]	mulpd  xmm3, xmm0	subpd  xmm1, xmm3	movapd xmm0, xmm1	movapd xmm2, xmm1		xorpd xmm3, xmm3	movapd xmm4, xmm3	movapd xmm5, xmm3	mulpd xmm0, [esp + nb334_dxH1H1]	mulpd xmm1, [esp + nb334_dyH1H1]	mulpd xmm2, [esp + nb334_dzH1H1]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb334_fixH1]	addpd xmm1, [esp + nb334_fiyH1]	addpd xmm2, [esp + nb334_fizH1]	movapd [esp + nb334_fjxH1], xmm3	movapd [esp + nb334_fjyH1], xmm4	movapd [esp + nb334_fjzH1], xmm5	movapd [esp + nb334_fixH1], xmm0	movapd [esp + nb334_fiyH1], xmm1	movapd [esp + nb334_fizH1], xmm2	;# H1-H2 interaction  	movapd xmm0, [esp + nb334_rinvH1H2]	movapd xmm1, xmm0	mulpd  xmm1, [esp + nb334_rsqH1H2] ;# xmm1=r 	mulpd  xmm1, [esp + nb334_tsc]		cvttpd2pi mm6, xmm1	;# mm6 = lu idx 	cvtpi2pd xmm6, mm6	subpd xmm1, xmm6	;# xmm1=eps 	movapd xmm2, xmm1		mulpd  xmm2, xmm2	;# xmm2=eps2 		pslld mm6, 2		;# idx *= 4 	mov  esi, [ebp + nb334_VFtab]	movd eax, mm6	psrlq mm6, 32	movd ebx, mm6		;# indices in eax/ebx 	lea   eax, [eax + eax*2]	;# idx*=3 (12 total now) 	lea   ebx, [ebx + ebx*2]	;# idx*=3 (12 total now) 	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 	;# coulomb 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 + nb334_two]	;# two*Heps2 	movapd xmm3, [esp + nb334_qqHH]	addpd  xmm7, xmm6	addpd  xmm7, xmm5 ;# xmm7=FF 	mulpd  xmm5, xmm1 ;# xmm5=eps*Fp 	addpd  xmm5, xmm4 ;# xmm5=VV 	mulpd  xmm5, xmm3 ;# vcoul=qq*VV  	mulpd  xmm3, xmm7 ;# fijC=FF*qq     	;# at this point mm5 contains vcoul and xmm3 fijC     	addpd  xmm5, [esp + nb334_vctot]    	movapd [esp + nb334_vctot], xmm5	xorpd  xmm1, xmm1	mulpd  xmm3,  [esp + nb334_tsc]	mulpd  xmm3, xmm0	subpd  xmm1, xmm3	movapd xmm0, xmm1	movapd xmm2, xmm1		xorpd xmm3, xmm3	movapd xmm4, xmm3	movapd xmm5, xmm3	mulpd xmm0, [esp + nb334_dxH1H2]	mulpd xmm1, [esp + nb334_dyH1H2]	mulpd xmm2, [esp + nb334_dzH1H2]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb334_fixH1]	addpd xmm1, [esp + nb334_fiyH1]	addpd xmm2, [esp + nb334_fizH1]	movapd [esp + nb334_fjxH2], xmm3	movapd [esp + nb334_fjyH2], xmm4	movapd [esp + nb334_fjzH2], xmm5	movapd [esp + nb334_fixH1], xmm0	movapd [esp + nb334_fiyH1], xmm1	movapd [esp + nb334_fizH1], xmm2	;# H1-M interaction 	movapd xmm0, [esp + nb334_rinvH1M]	movapd xmm1, xmm0	mulpd  xmm1, [esp + nb334_rsqH1M] ;# xmm1=r 	mulpd  xmm1, [esp + nb334_tsc]		cvttpd2pi mm6, xmm1	;# mm6 = lu idx 	cvtpi2pd xmm6, mm6	subpd xmm1, xmm6	;# xmm1=eps 	movapd xmm2, xmm1		mulpd  xmm2, xmm2	;# xmm2=eps2 		pslld mm6, 2		;# idx *= 4 	mov  esi, [ebp + nb334_VFtab]	movd eax, mm6	psrlq mm6, 32	movd ebx, mm6		;# indices in eax/ebx 	lea   eax, [eax + eax*2]	;# idx*=3 (12 total now) 	lea   ebx, [ebx + ebx*2]	;# idx*=3 (12 total now) 	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 	;# coulomb 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 + nb334_two]	;# two*Heps2 	movapd xmm3, [esp + nb334_qqMH]	addpd  xmm7, xmm6	addpd  xmm7, xmm5 ;# xmm7=FF 	mulpd  xmm5, xmm1 ;# xmm5=eps*Fp 	addpd  xmm5, xmm4 ;# xmm5=VV 	mulpd  xmm5, xmm3 ;# vcoul=qq*VV  	mulpd  xmm3, xmm7 ;# fijC=FF*qq     	;# at this point mm5 contains vcoul and xmm3 fijC     	addpd  xmm5, [esp + nb334_vctot]    	movapd [esp + nb334_vctot], xmm5	xorpd  xmm1, xmm1	mulpd  xmm3,  [esp + nb334_tsc]	mulpd  xmm3, xmm0	subpd  xmm1, xmm3	movapd xmm0, xmm1	movapd xmm2, xmm1		xorpd xmm3, xmm3	movapd xmm4, xmm3	movapd xmm5, xmm3	mulpd xmm0, [esp + nb334_dxH1M]	mulpd xmm1, [esp + nb334_dyH1M]	mulpd xmm2, [esp + nb334_dzH1M]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb334_fixH1]	addpd xmm1, [esp + nb334_fiyH1]	addpd xmm2, [esp + nb334_fizH1]	movapd [esp + nb334_fjxM], xmm3	movapd [esp + nb334_fjyM], xmm4	movapd [esp + nb334_fjzM], xmm5	movapd [esp + nb334_fixH1], xmm0	movapd [esp + nb334_fiyH1], xmm1	movapd [esp + nb334_fizH1], xmm2	;# H2-H1 interaction 	movapd xmm0, [esp + nb334_rinvH2H1]	movapd xmm1, xmm0	mulpd  xmm1, [esp + nb334_rsqH2H1] ;# xmm1=r 	mulpd  xmm1, [esp + nb334_tsc]		cvttpd2pi mm6, xmm1	;# mm6 = lu idx 	cvtpi2pd xmm6, mm6	subpd xmm1, xmm6	;# xmm1=eps 	movapd xmm2, xmm1		mulpd  xmm2, xmm2	;# xmm2=eps2 		pslld mm6, 2		;# idx *= 4 	mov  esi, [ebp + nb334_VFtab]	movd eax, mm6	psrlq mm6, 32	movd ebx, mm6		;# indices in eax/ebx 	lea   eax, [eax + eax*2]	;# idx*=3 (12 total now) 	lea   ebx, [ebx + ebx*2]	;# idx*=3 (12 total now) 	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 	;# coulomb 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 + nb334_two]	;# two*Heps2 	movapd xmm3, [esp + nb334_qqHH]	addpd  xmm7, xmm6	addpd  xmm7, xmm5 ;# xmm7=FF 	mulpd  xmm5, xmm1 ;# xmm5=eps*Fp 	addpd  xmm5, xmm4 ;# xmm5=VV 	mulpd  xmm5, xmm3 ;# vcoul=qq*VV  	mulpd  xmm3, xmm7 ;# fijC=FF*qq     	;# at this point mm5 contains vcoul and xmm3 fijC     	addpd  xmm5, [esp + nb334_vctot]    	movapd [esp + nb334_vctot], xmm5	xorpd  xmm1, xmm1	mulpd  xmm3,  [esp + nb334_tsc]	mulpd  xmm3, xmm0	subpd  xmm1, xmm3	movapd xmm0, xmm1	movapd xmm2, xmm1		movapd xmm3, [esp + nb334_fjxH1]	movapd xmm4, [esp + nb334_fjyH1]	movapd xmm5, [esp + nb334_fjzH1]	mulpd xmm0, [esp + nb334_dxH2H1]	mulpd xmm1, [esp + nb334_dyH2H1]	mulpd xmm2, [esp + nb334_dzH2H1]	subpd xmm3, xmm0	subpd xmm4, xmm1	subpd xmm5, xmm2	addpd xmm0, [esp + nb334_fixH2]	addpd xmm1, [esp + nb334_fiyH2]	addpd xmm2, [esp + nb334_fizH2]	movapd [esp + nb334_fjxH1], xmm3	movapd [esp + nb334_fjyH1], xmm4	movapd [esp + nb334_fjzH1], xmm5	movapd [esp + nb334_fixH2], xmm0	movapd [esp + nb334_fiyH2], xmm1	movapd [esp + nb334_fizH2], xmm2	;# H2-H2 interaction
12345

nb_kernel334_ia32_sse2.intel_syntax.s - 源码说明

本页面展示了「最著名最快的分子模拟软件」中的 nb_kernel334_ia32_sse2.intel_syntax.s 源码文件，采用 S 编程语言编写，共 2,176 行代码。您可以在线阅读完整代码内容，也可以返回资源详情页下载完整源码包进行本地学习和开发。

虫虫开发者社区收录了大量与分子模拟相关的技术资源，包括源代码、技术文档、电路图等，是电子工程师和嵌入式开发者的专业学习平台。

⌨️ 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?