//Pixel Shader for TEV stages
//3 TEV stages, 2 texgens, 2 IND stages
int idot(int3 x, int3 y)
{
	int3 tmp = x * y;
	return tmp.x + tmp.y + tmp.z;
}
int idot(int4 x, int4 y)
{
	int4 tmp = x * y;
	return tmp.x + tmp.y + tmp.z + tmp.w;
}

int  iround(float  x) { return int (round(x)); }
int2 iround(float2 x) { return int2(round(x)); }
int3 iround(float3 x) { return int3(round(x)); }
int4 iround(float4 x) { return int4(round(x)); }

SamplerState samp[8] : register(s0);

Texture2DArray Tex[8] : register(t0);

cbuffer PSBlock : register(b0) {
	int4 color[4];
	int4 k[4];
	int4 alphaRef;
	float4 texdim[8];
	int4 czbias[2];
	int4 cindscale[2];
	int4 cindmtx[6];
	int4 cfogcolor;
	int4 cfogi;
	float4 cfogf[2];
	float4 czslope;
	float2 cefbscale;
	uint  bpmem_genmode;
	uint  bpmem_alphaTest;
	uint  bpmem_fogParam3;
	uint  bpmem_fogRangeBase;
	uint  bpmem_dstalpha;
	uint  bpmem_ztex_op;
	bool  bpmem_late_ztest;
	bool  bpmem_rgba6_format;
	bool  bpmem_dither;
	bool  bpmem_bounding_box;
	uint4 bpmem_pack1[16];
	uint4 bpmem_pack2[8];
	int4  konstLookup[32];
};

#define bpmem_combiners(i) (bpmem_pack1[(i)].xy)
#define bpmem_tevind(i) (bpmem_pack1[(i)].z)
#define bpmem_iref(i) (bpmem_pack1[(i)].w)
#define bpmem_tevorder(i) (bpmem_pack2[(i)].x)
#define bpmem_tevksel(i) (bpmem_pack2[(i)].y)

struct VS_OUTPUT {
	 float4 pos : POSITION;
	 float4 colors_0 : COLOR0;
	 float4 colors_1 : COLOR1;
	 float3 tex0 : TEXCOORD0;
	 float3 tex1 : TEXCOORD1;
	 float4 clipPos : TEXCOORD2;
	 float clipDist0 : SV_ClipDistance0;
	 float clipDist1 : SV_ClipDistance1;
};
void main(
  out uint4 ocol0 : SV_Target,
  in float4 rawpos : SV_Position,
  in  float4 colors_0 : COLOR0,
  in  float4 colors_1 : COLOR1
,
  in  float3 tex0 : TEXCOORD0,
  in  float3 tex1 : TEXCOORD1,
  in  float4 clipPos : TEXCOORD2,
  in float clipDist0 : SV_ClipDistance0
,
  in float clipDist1 : SV_ClipDistance1
        ) {
	int4 c0 = color[1], c1 = color[2], c2 = color[3], prev = color[0];
	int4 rastemp = int4(0, 0, 0, 0), textemp = int4(0, 0, 0, 0), konsttemp = int4(0, 0, 0, 0);
	int3 comp16 = int3(1, 256, 0), comp24 = int3(1, 256, 256*256);
	int alphabump=0;
	int3 tevcoord=int3(0, 0, 0);
	int2 wrappedcoord=int2(0,0), tempcoord=int2(0,0);
	int4 tevin_a=int4(0,0,0,0),tevin_b=int4(0,0,0,0),tevin_c=int4(0,0,0,0),tevin_d=int4(0,0,0,0);

	float4 col0 = colors_0;
	float4 col1 = colors_1;
	int2 fixpoint_uv0 = int2((tex0.z == 0.0 ? tex0.xy : tex0.xy / tex0.z) * texdim[0].zw);
	int2 fixpoint_uv1 = int2((tex1.z == 0.0 ? tex1.xy : tex1.xy / tex1.z) * texdim[1].zw);
	tempcoord = fixpoint_uv1 >> cindscale[0].zw;
	int3 iindtex1 = iround(255.0 * Tex[2].Sample(samp[2], float3(float2(tempcoord).xy * texdim[2].xy, 0.0))).abg;

	// TEV stage 0
	// indirect op
	int2 indtevtrans0 = int2(0, 0);
	wrappedcoord.x = fixpoint_uv0.x;
	wrappedcoord.y = fixpoint_uv0.y;
	tevcoord.xy = wrappedcoord + indtevtrans0;
	tevcoord.xy = (tevcoord.xy << 8) >> 8;
	rastemp = iround(col0 * 255.0).rgba;
	textemp = int4(255, 255, 255, 255);
	tevin_a = int4(rastemp.rgb, 0)&int4(255, 255, 255, 255);
	tevin_b = int4(int3(0,0,0), 0)&int4(255, 255, 255, 255);
	tevin_c = int4(int3(0,0,0), 0)&int4(255, 255, 255, 255);
	tevin_d = int4(int3(0,0,0), rastemp.a);
	// color combine
	c2.rgb = clamp((((tevin_d.rgb)) + (((((tevin_a.rgb<<8) + (tevin_b.rgb-tevin_a.rgb)*(tevin_c.rgb+(tevin_c.rgb>>7)))) + 128)>>8)), int3(0,0,0), int3(255,255,255));
	// alpha combine
	prev.a = clamp((((tevin_d.a)) + (((((tevin_a.a<<8) + (tevin_b.a-tevin_a.a)*(tevin_c.a+(tevin_c.a>>7)))))>>8)), 0, 255);

	// TEV stage 1
	// indirect op
	int3 iindtevcrd1 = iindtex1 & 255;
	int2 indtevtrans1 = int2(idot(cindmtx[0].xyz, iindtevcrd1), idot(cindmtx[1].xyz, iindtevcrd1)) >> 3;
	if (cindmtx[0].w >= 0) indtevtrans1 >>= cindmtx[0].w;
	else indtevtrans1 <<= (-cindmtx[0].w);
	wrappedcoord.x = fixpoint_uv1.x;
	wrappedcoord.y = 0;
	tevcoord.xy += wrappedcoord + indtevtrans1;
	tevcoord.xy = (tevcoord.xy << 8) >> 8;
	textemp = iround(255.0 * Tex[0].Sample(samp[0], float3(float2(tevcoord.xy).xy * texdim[0].xy, 0.0))).rgba;
	tevin_a = int4(c2.rgb, 0)&int4(255, 255, 255, 255);
	tevin_b = int4(int3(0,0,0), 0)&int4(255, 255, 255, 255);
	tevin_c = int4(int3(0,0,0), 0)&int4(255, 255, 255, 255);
	tevin_d = int4(textemp.rgb, textemp.a);
	// color combine
	prev.rgb = clamp((((tevin_d.rgb)) + (((((tevin_a.rgb<<8) + (tevin_b.rgb-tevin_a.rgb)*(tevin_c.rgb+(tevin_c.rgb>>7)))) + 128)>>8)), int3(0,0,0), int3(255,255,255));
	// alpha combine
	prev.a = clamp((((tevin_d.a)) + (((((tevin_a.a<<8) + (tevin_b.a-tevin_a.a)*(tevin_c.a+(tevin_c.a>>7)))))>>8)), 0, 255);

	// TEV stage 2
	// indirect op
	int2 indtevtrans2 = int2(0, 0);
	wrappedcoord.x = fixpoint_uv0.x;
	wrappedcoord.y = fixpoint_uv0.y;
	tevcoord.xy = wrappedcoord + indtevtrans2;
	tevcoord.xy = (tevcoord.xy << 8) >> 8;
	textemp = int4(255, 255, 255, 255);
	tevin_a = int4(c0.rgb, prev.a)&int4(255, 255, 255, 255);
	tevin_b = int4(c2.rgb, 0)&int4(255, 255, 255, 255);
	tevin_c = int4(prev.rgb, 0)&int4(255, 255, 255, 255);
	tevin_d = int4(int3(0,0,0), 0);
	// color combine
	prev.rgb = clamp(   tevin_d.rgb + ((idot(tevin_a.rgb, comp16) >  idot(tevin_b.rgb, comp16)) ? tevin_c.rgb : int3(0,0,0)), int3(0,0,0), int3(255,255,255));
	// alpha combine
	prev.a = clamp((((tevin_d.a)) + (((((tevin_a.a<<8) + (tevin_b.a-tevin_a.a)*(tevin_c.a+(tevin_c.a>>7)))))>>8)), 0, 255);
	prev = prev & 255;
	if(!( (prev.a >  alphaRef.r) && (true))) {
		ocol0 = float4(0.0, 0.0, 0.0, 0.0);
		ocol1 = float4(0.0, 0.0, 0.0, 0.0);
		discard;
	}
	int zCoord = int((1.0 - rawpos.z) * 16777216.0);
	zCoord = clamp(zCoord, 0, 0xFFFFFF);
	ocol0 = uint4(prev);
}