ShuriZma
/
project64
mirror of https://github.com/project64/project64.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

line break consistency fix: 3dmathSIMD.asm.cpp (btw inline asm SUCKS)

This commit is contained in:
unknown 2015-03-11 17:12:49 -04:00
parent 8ae5b052e7
commit 24d86ab329
1 changed files with 58 additions and 58 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

116
Source/Glide64/3dmathSIMD.asm.cpp
View File

@ -42,18 +42,18 @@ segment .text
extern "C" void __declspec(naked) DetectSIMD(int func, int * iedx, int * iecx) extern "C" void __declspec(naked) DetectSIMD(int func, int * iedx, int * iecx)
{ {
_asm { _asm {
push ebp push ebp
mov ebp,esp mov ebp,esp
mov eax,[func] mov eax,[func]
cpuid cpuid
mov eax,[iedx] mov eax,[iedx]
mov [eax],edx mov [eax],edx
mov eax,[iecx] mov eax,[iecx]
mov [eax],ecx mov [eax],ecx
leave leave
ret ret
} }
} }
/**************************************************************** /****************************************************************
; ;
@ -65,8 +65,8 @@ extern "C" void __declspec(naked) TransformVectorSSE(float *src, float *dst, flo
{ {
__asm __asm
{ {
push ebp push ebp
mov ebp,esp mov ebp,esp
mov ecx,[src] mov ecx,[src]
mov eax,[dst] mov eax,[dst]
@ -91,17 +91,17 @@ extern "C" void __declspec(naked) TransformVectorSSE(float *src, float *dst, flo
addps xmm0,xmm2 ; mat[0][2]*src[0]+mat[1][2]*src[1]+mat[2][2]*src[2] mat[0][1]*src[0]+mat[1][1]*src[1]+mat[2][1]*src[2] 0 mat[0][0]*src[0]+mat[1][0]*src[1]+mat[2][0]*src[2] addps xmm0,xmm2 ; mat[0][2]*src[0]+mat[1][2]*src[1]+mat[2][2]*src[2] mat[0][1]*src[0]+mat[1][1]*src[1]+mat[2][1]*src[2] 0 mat[0][0]*src[0]+mat[1][0]*src[1]+mat[2][0]*src[2]
movss [eax],xmm0 ; mat[0][0]*src[0]+mat[1][0]*src[1]+mat[2][0]*src[2] movss [eax],xmm0 ; mat[0][0]*src[0]+mat[1][0]*src[1]+mat[2][0]*src[2]
movhps [eax+4],xmm0 ; mat[0][2]*src[0]+mat[1][2]*src[1]+mat[2][2]*src[2] mat[0][1]*src[0]+mat[1][1]*src[1]+mat[2][1]*src[2] movhps [eax+4],xmm0 ; mat[0][2]*src[0]+mat[1][2]*src[1]+mat[2][2]*src[2] mat[0][1]*src[0]+mat[1][1]*src[1]+mat[2][1]*src[2]
leave leave
ret ret
} }
} }
extern "C" void __declspec(naked) MulMatricesSSE(float m1[4][4],float m2[4][4],float r[4][4]) extern "C" void __declspec(naked) MulMatricesSSE(float m1[4][4],float m2[4][4],float r[4][4])
{ {
__asm __asm
{ {
push ebp push ebp
mov ebp,esp mov ebp,esp
mov eax,[r] mov eax,[r]
mov ecx,[m1] mov ecx,[m1]
@ -204,17 +204,17 @@ extern "C" void __declspec(naked) MulMatricesSSE(float m1[4][4],float m2[4][4],f
addps xmm4,xmm7 addps xmm4,xmm7
movaps [eax+48],xmm4 movaps [eax+48],xmm4
leave leave
ret ret
} }
} }
extern "C" void __declspec(naked) NormalizeVectorSSE (float *v) extern "C" void __declspec(naked) NormalizeVectorSSE (float *v)
{ {
_asm _asm
{ {
push ebp push ebp
mov ebp,esp mov ebp,esp
mov edx, [v] mov edx, [v]
movaps xmm0, [edx] ; x y z 0 movaps xmm0, [edx] ; x y z 0
@ -229,10 +229,10 @@ extern "C" void __declspec(naked) NormalizeVectorSSE (float *v)
rsqrtps xmm0, xmm0 ; 1.0/sqrt(x*x+z*z+y*y) rsqrtps xmm0, xmm0 ; 1.0/sqrt(x*x+z*z+y*y)
mulps xmm2, xmm0 ; x/sqrt(x*x+z*z+y*y) y/sqrt(x*x+z*z+y*y) z/sqrt(x*x+z*z+y*y) 0 mulps xmm2, xmm0 ; x/sqrt(x*x+z*z+y*y) y/sqrt(x*x+z*z+y*y) z/sqrt(x*x+z*z+y*y) 0
movaps [edx], xmm2 movaps [edx], xmm2
leave leave
ret ret
} }
} }
/***************************************************************** /*****************************************************************
; ;
@ -243,8 +243,8 @@ extern "C" void __declspec(naked) NormalizeVectorSSE (float *v)
float __declspec(naked) DotProductSSE3(register float *v1, register float *v2) float __declspec(naked) DotProductSSE3(register float *v1, register float *v2)
{ {
_asm { _asm {
push ebp push ebp
mov ebp,esp mov ebp,esp
mov eax,[v1] mov eax,[v1]
mov edx,[v2] mov edx,[v2]
@ -253,10 +253,10 @@ float __declspec(naked) DotProductSSE3(register float *v1, register float *v2)
haddps xmm0, xmm0 haddps xmm0, xmm0
haddps xmm0, xmm0 haddps xmm0, xmm0
; movss eax, xmm0 ; movss eax, xmm0
leave leave
ret ret
} }
} }
/**************************************************************** /****************************************************************
; ;
@ -267,8 +267,8 @@ float __declspec(naked) DotProductSSE3(register float *v1, register float *v2)
extern "C" void __declspec(naked) TransformVector3DNOW(float *src, float *dst, float mat[4][4]) extern "C" void __declspec(naked) TransformVector3DNOW(float *src, float *dst, float mat[4][4])
{ {
_asm { _asm {
push ebp push ebp
mov ebp,esp mov ebp,esp
femms femms
mov ecx,[src] mov ecx,[src]
@ -296,16 +296,16 @@ extern "C" void __declspec(naked) TransformVector3DNOW(float *src, float *dst, f
movq [eax],mm0 ; mat[0][1]*src[0]+mat[1][1]*src[1]+mat[2][1]*src[2] mat[0][0]*src[0]+mat[1][0]*src[1]+mat[2][0]*src[2] movq [eax],mm0 ; mat[0][1]*src[0]+mat[1][1]*src[1]+mat[2][1]*src[2] mat[0][0]*src[0]+mat[1][0]*src[1]+mat[2][0]*src[2]
movd [eax+8],mm3 ; mat[0][2]*src[0]+mat[1][2]*src[1]+mat[2][2]*src[2] movd [eax+8],mm3 ; mat[0][2]*src[0]+mat[1][2]*src[1]+mat[2][2]*src[2]
femms femms
leave leave
ret ret
} }
} }
extern "C" void __declspec(naked) InverseTransformVector3DNOW(float *src, float *dst, float mat[4][4]) extern "C" void __declspec(naked) InverseTransformVector3DNOW(float *src, float *dst, float mat[4][4])
{ {
_asm { _asm {
push ebp push ebp
mov ebp,esp mov ebp,esp
femms femms
mov ecx,[src] mov ecx,[src]
@ -333,16 +333,16 @@ extern "C" void __declspec(naked) InverseTransformVector3DNOW(float *src, float
movq [eax],mm0 ; mat[1][0]*src[0]+mat[1][1]*src[1]+mat[1][2]*src[2] mat[0][0]*src[0]+mat[0][1]*src[1]+mat[0][2]*src[2] movq [eax],mm0 ; mat[1][0]*src[0]+mat[1][1]*src[1]+mat[1][2]*src[2] mat[0][0]*src[0]+mat[0][1]*src[1]+mat[0][2]*src[2]
movd [eax+8],mm2 ; mat[2][0]*src[0]+mat[2][1]*src[1]+mat[2][2]*src[2] movd [eax+8],mm2 ; mat[2][0]*src[0]+mat[2][1]*src[1]+mat[2][2]*src[2]
femms femms
leave leave
ret ret
} }
} }
extern "C" void __declspec(naked) MulMatrices3DNOW(float m1[4][4],float m2[4][4],float r[4][4]) extern "C" void __declspec(naked) MulMatrices3DNOW(float m1[4][4],float m2[4][4],float r[4][4])
{ {
_asm { _asm {
push ebp push ebp
mov ebp,esp mov ebp,esp
femms femms
mov ecx,[m1] mov ecx,[m1]
@ -465,16 +465,16 @@ extern "C" void __declspec(naked) MulMatrices3DNOW(float m1[4][4],float m2[4][4
movq [eax+48],mm7 movq [eax+48],mm7
movq [eax+56],mm3 movq [eax+56],mm3
femms femms
leave leave
ret ret
} }
} }
extern "C" float __declspec(naked) DotProduct3DNOW(register float *v1, register float *v2) extern "C" float __declspec(naked) DotProduct3DNOW(register float *v1, register float *v2)
{ {
_asm { _asm {
push ebp push ebp
mov ebp,esp mov ebp,esp
femms femms
mov edx,[v1] mov edx,[v1]
@ -489,15 +489,15 @@ extern "C" float __declspec(naked) DotProduct3DNOW(register float *v1, register
pfadd mm0,mm1 pfadd mm0,mm1
movd eax,mm0 movd eax,mm0
femms femms
leave leave
ret ret
} }
} }
extern "C" void __declspec(naked) NormalizeVector3DNOW(float *v) extern "C" void __declspec(naked) NormalizeVector3DNOW(float *v)
{ {
_asm { _asm {
push ebp push ebp
mov ebp,esp mov ebp,esp
femms femms
mov edx,[v] mov edx,[v]
@ -521,7 +521,7 @@ extern "C" void __declspec(naked) NormalizeVector3DNOW(float *v)
movq [edx],mm1 movq [edx],mm1
movq [edx+8],mm2 movq [edx+8],mm2
femms femms
leave leave
ret ret
} }
} }