diff --git a/plugins/GSdx/res/glsl/tfx_fs.glsl b/plugins/GSdx/res/glsl/tfx_fs.glsl
index 3ecdb53c81..51eb214a69 100644
--- a/plugins/GSdx/res/glsl/tfx_fs.glsl
+++ b/plugins/GSdx/res/glsl/tfx_fs.glsl
@@ -45,13 +45,13 @@
 
 in SHADER
 {
-    vec4 t;
-    vec4 c;
-    flat vec4 fc;
+	vec4 t;
+	vec4 c;
+	flat vec4 fc;
 #if PS_SPRITE == 1
-    flat vec4 flat_T;
-    flat vec2 flat_P;
-    vec2 alpha;
+	flat vec4 flat_T;
+	flat vec2 flat_P;
+	vec2 alpha;
 #endif
 } PSin;
 
@@ -80,30 +80,26 @@ layout(binding = 3) uniform sampler2D RtSampler; // note 2 already use by the im
 #if PS_DATE > 0
 // FIXME how to declare memory access
 layout(r32i, binding = 2) coherent uniform iimage2D img_prim_min;
+layout(early_fragment_tests) in;
+// origin_upper_left
+layout(pixel_center_integer) in vec4 gl_FragCoord;
 #endif
 #else
 // use basic stencil
 #endif
 
-#ifndef DISABLE_GL42_image
-#if PS_DATE > 0
-// origin_upper_left
-layout(pixel_center_integer) in vec4 gl_FragCoord;
-//in int gl_PrimitiveID;
-#endif
-#endif
 
 layout(std140, binding = 21) uniform cb21
 {
-    vec3 FogColor;
-    float AREF;
-    vec4 WH;
-    vec2 MinF;
-    vec2 TA;
-    uvec4 MskFix;
-    vec4 HalfTexel;
-    vec4 MinMax;
-    vec4 TC_OffsetHack;
+	vec3 FogColor;
+	float AREF;
+	vec4 WH;
+	vec2 MinF;
+	vec2 TA;
+	uvec4 MskFix;
+	vec4 HalfTexel;
+	vec4 MinMax;
+	vec4 TC_OffsetHack;
 };
 
 #ifdef SUBROUTINE_GL40
@@ -121,242 +117,242 @@ layout(location = 1) subroutine uniform ColClipType colclip;
 
 vec4 sample_c(vec2 uv)
 {
-    // FIXME: check the issue on openGL
+	// FIXME: check the issue on openGL
 #if (ATI_SUCKS == 1) && (PS_POINT_SAMPLER == 1)
-    // Weird issue with ATI cards (happens on at least HD 4xxx and 5xxx),
-    // it looks like they add 127/128 of a texel to sampling coordinates
-    // occasionally causing point sampling to erroneously round up.
-    // I'm manually adjusting coordinates to the centre of texels here,
-    // though the centre is just paranoia, the top left corner works fine.
-    uv = (trunc(uv * WH.zw) + vec2(0.5, 0.5)) / WH.zw;
+	// Weird issue with ATI cards (happens on at least HD 4xxx and 5xxx),
+	// it looks like they add 127/128 of a texel to sampling coordinates
+	// occasionally causing point sampling to erroneously round up.
+	// I'm manually adjusting coordinates to the centre of texels here,
+	// though the centre is just paranoia, the top left corner works fine.
+	uv = (trunc(uv * WH.zw) + vec2(0.5, 0.5)) / WH.zw;
 #endif
 
-    return texture(TextureSampler, uv);
+	return texture(TextureSampler, uv);
 }
 
 vec4 sample_p(float u)
 {
-    //FIXME do we need a 1D sampler. Big impact on opengl to find 1 dim
-    // So for the moment cheat with 0.0f dunno if it work
-    return texture(PaletteSampler, vec2(u, 0.0f));
+	//FIXME do we need a 1D sampler. Big impact on opengl to find 1 dim
+	// So for the moment cheat with 0.0f dunno if it work
+	return texture(PaletteSampler, vec2(u, 0.0f));
 }
 
 vec4 wrapuv(vec4 uv)
 {
-    vec4 uv_out = uv;
+	vec4 uv_out = uv;
 
 #if PS_WMS == PS_WMT
 
 #if PS_WMS == 2
-    uv_out = clamp(uv, MinMax.xyxy, MinMax.zwzw);
+	uv_out = clamp(uv, MinMax.xyxy, MinMax.zwzw);
 #elif PS_WMS == 3
-    uv_out = vec4((ivec4(uv * WH.xyxy) & ivec4(MskFix.xyxy)) | ivec4(MskFix.zwzw)) / WH.xyxy;
+	uv_out = vec4((ivec4(uv * WH.xyxy) & ivec4(MskFix.xyxy)) | ivec4(MskFix.zwzw)) / WH.xyxy;
 #endif
 
 #else // PS_WMS != PS_WMT
 
 #if PS_WMS == 2
-    uv_out.xz = clamp(uv.xz, MinMax.xx, MinMax.zz);
+	uv_out.xz = clamp(uv.xz, MinMax.xx, MinMax.zz);
 
 #elif PS_WMS == 3
-    uv_out.xz = vec2((ivec2(uv.xz * WH.xx) & ivec2(MskFix.xx)) | ivec2(MskFix.zz)) / WH.xx;
+	uv_out.xz = vec2((ivec2(uv.xz * WH.xx) & ivec2(MskFix.xx)) | ivec2(MskFix.zz)) / WH.xx;
 
 #endif
 
 #if PS_WMT == 2
-    uv_out.yw = clamp(uv.yw, MinMax.yy, MinMax.ww);
+	uv_out.yw = clamp(uv.yw, MinMax.yy, MinMax.ww);
 
 #elif PS_WMT == 3
 
-    uv_out.yw = vec2((ivec2(uv.yw * WH.yy) & ivec2(MskFix.yy)) | ivec2(MskFix.ww)) / WH.yy;
+	uv_out.yw = vec2((ivec2(uv.yw * WH.yy) & ivec2(MskFix.yy)) | ivec2(MskFix.ww)) / WH.yy;
 #endif
 
 #endif
 
-    return uv_out;
+	return uv_out;
 }
 
 vec2 clampuv(vec2 uv)
 {
-    vec2 uv_out = uv;
+	vec2 uv_out = uv;
 
-#if (PS_WMS == 2) && (PS_WMT == 2) 
-    uv_out = clamp(uv, MinF, MinMax.zw);
+#if (PS_WMS == 2) && (PS_WMT == 2)
+	uv_out = clamp(uv, MinF, MinMax.zw);
 #elif PS_WMS == 2
-    uv_out.x = clamp(uv.x, MinF.x, MinMax.z);
+	uv_out.x = clamp(uv.x, MinF.x, MinMax.z);
 #elif PS_WMT == 2
-    uv_out.y = clamp(uv.y, MinF.y, MinMax.w);
+	uv_out.y = clamp(uv.y, MinF.y, MinMax.w);
 #endif
 
-    return uv_out;
+	return uv_out;
 }
 
 mat4 sample_4c(vec4 uv)
 {
-    mat4 c;
+	mat4 c;
 
-    c[0] = sample_c(uv.xy);
-    c[1] = sample_c(uv.zy);
-    c[2] = sample_c(uv.xw);
-    c[3] = sample_c(uv.zw);
+	c[0] = sample_c(uv.xy);
+	c[1] = sample_c(uv.zy);
+	c[2] = sample_c(uv.xw);
+	c[3] = sample_c(uv.zw);
 
-    return c;
+	return c;
 }
 
 vec4 sample_4a(vec4 uv)
 {
-    vec4 c;
+	vec4 c;
 
-    // Dx used the alpha channel.
-    // Opengl is only 8 bits on red channel.
-    c.x = sample_c(uv.xy).r;
-    c.y = sample_c(uv.zy).r;
-    c.z = sample_c(uv.xw).r;
-    c.w = sample_c(uv.zw).r;
+	// Dx used the alpha channel.
+	// Opengl is only 8 bits on red channel.
+	c.x = sample_c(uv.xy).r;
+	c.y = sample_c(uv.zy).r;
+	c.z = sample_c(uv.xw).r;
+	c.w = sample_c(uv.zw).r;
 
 	return c * 255.0/256.0 + 0.5/256.0;
 }
 
 mat4 sample_4p(vec4 u)
 {
-    mat4 c;
+	mat4 c;
 
-    c[0] = sample_p(u.x);
-    c[1] = sample_p(u.y);
-    c[2] = sample_p(u.z);
-    c[3] = sample_p(u.w);
+	c[0] = sample_p(u.x);
+	c[1] = sample_p(u.y);
+	c[2] = sample_p(u.z);
+	c[3] = sample_p(u.w);
 
-    return c;
+	return c;
 }
 
 vec4 sample_color(vec2 st, float q)
 {
 #if (PS_FST == 0)
-    st /= q;
+	st /= q;
 #endif
 
 #if (PS_TCOFFSETHACK == 1)
-    st += TC_OffsetHack.xy;
+	st += TC_OffsetHack.xy;
 #endif
 
-    vec4 t;
-    mat4 c;
-    vec2 dd;
+	vec4 t;
+	mat4 c;
+	vec2 dd;
 
 #if (PS_LTF == 0 && PS_FMT <= FMT_16 && PS_WMS < 3 && PS_WMT < 3)
-        c[0] = sample_c(clampuv(st));
+	c[0] = sample_c(clampuv(st));
 #ifdef TEX_COORD_DEBUG
-        c[0].rg = clampuv(st).xy;
+	c[0].rg = clampuv(st).xy;
 #endif
 
 #else
-        vec4 uv;
+	vec4 uv;
 
-        if(PS_LTF != 0)
-        {
-            uv = st.xyxy + HalfTexel;
-            dd = fract(uv.xy * WH.zw);
-        }
-        else
-        {
-            uv = st.xyxy;
-        }
+	if(PS_LTF != 0)
+	{
+		uv = st.xyxy + HalfTexel;
+		dd = fract(uv.xy * WH.zw);
+	}
+	else
+	{
+		uv = st.xyxy;
+	}
 
-        uv = wrapuv(uv);
+	uv = wrapuv(uv);
 
-        if((PS_FMT & FMT_PAL) != 0)
-        {
-            c = sample_4p(sample_4a(uv));
-        }
-        else
-        {
-            c = sample_4c(uv);
-        }
+	if((PS_FMT & FMT_PAL) != 0)
+	{
+		c = sample_4p(sample_4a(uv));
+	}
+	else
+	{
+		c = sample_4c(uv);
+	}
 #ifdef TEX_COORD_DEBUG
-        c[0].rg = uv.xy;
-        c[1].rg = uv.xy;
-        c[2].rg = uv.xy;
-        c[3].rg = uv.xy;
+	c[0].rg = uv.xy;
+	c[1].rg = uv.xy;
+	c[2].rg = uv.xy;
+	c[3].rg = uv.xy;
 #endif
 
 #endif
 
-    // PERF: see the impact of the exansion before/after the interpolation
-    for (int i = 0; i < 4; i++)
-    {
+	// PERF: see the impact of the exansion before/after the interpolation
+	for (int i = 0; i < 4; i++)
+	{
 #if ((PS_FMT & ~FMT_PAL) == FMT_24)
-        c[i].a = ( (PS_AEM == 0) || any(bvec3(c[i].rgb))  ) ? TA.x : 0.0f;
+		c[i].a = ( (PS_AEM == 0) || any(bvec3(c[i].rgb))  ) ? TA.x : 0.0f;
 #elif ((PS_FMT & ~FMT_PAL) == FMT_16)
-        c[i].a = c[i].a >= 0.5 ? TA.y : ( (PS_AEM == 0) || any(bvec3(c[i].rgb)) ) ? TA.x : 0.0f;
+		c[i].a = c[i].a >= 0.5 ? TA.y : ( (PS_AEM == 0) || any(bvec3(c[i].rgb)) ) ? TA.x : 0.0f;
 #endif
-    }
+	}
 
 #if(PS_LTF != 0)
-    t = mix(mix(c[0], c[1], dd.x), mix(c[2], c[3], dd.x), dd.y);
+	t = mix(mix(c[0], c[1], dd.x), mix(c[2], c[3], dd.x), dd.y);
 #else
-    t = c[0];
+	t = c[0];
 #endif
 
-    return t;
+	return t;
 }
 
 #ifndef SUBROUTINE_GL40
 vec4 tfx(vec4 t, vec4 c)
 {
-    vec4 c_out = c;
+	vec4 c_out = c;
 #if (PS_TFX == 0)
-    if(PS_TCC != 0) 
-        c_out = c * t * 255.0f / 128.0f;
-    else
-        c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f;
+	if(PS_TCC != 0)
+		c_out = c * t * 255.0f / 128.0f;
+	else
+		c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f;
 #elif (PS_TFX == 1)
-    if(PS_TCC != 0) 
-        c_out = t;
-    else
-        c_out.rgb = t.rgb;
+	if(PS_TCC != 0)
+		c_out = t;
+	else
+		c_out.rgb = t.rgb;
 #elif (PS_TFX == 2)
-    c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f + c.a;
+	c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f + c.a;
 
-    if(PS_TCC != 0) 
-        c_out.a += t.a;
+	if(PS_TCC != 0)
+		c_out.a += t.a;
 #elif (PS_TFX == 3)
-    c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f + c.a;
+	c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f + c.a;
 
-    if(PS_TCC != 0) 
-        c_out.a = t.a;
+	if(PS_TCC != 0)
+		c_out.a = t.a;
 #endif
 
-    return c_out;
+	return c_out;
 }
 #endif
 
 #ifndef SUBROUTINE_GL40
 void atst(vec4 c)
 {
-    float a = trunc(c.a * 255.0 + 0.01);
+	float a = trunc(c.a * 255.0 + 0.01);
 
 #if (PS_ATST == 0) // never
-    discard;
+	discard;
 #elif (PS_ATST == 1) // always
-    // nothing to do
+	// nothing to do
 #elif (PS_ATST == 2) && (PS_SPRITEHACK == 0) // l
-    if ((AREF - a - 0.5f) < 0.0f)
-        discard;
+	if ((AREF - a - 0.5f) < 0.0f)
+		discard;
 #elif (PS_ATST == 3 ) // le
-    if ((AREF - a + 0.5f) < 0.0f)
-        discard;
+	if ((AREF - a + 0.5f) < 0.0f)
+		discard;
 #elif (PS_ATST == 4) // e
-    if ((0.5f - abs(a - AREF)) < 0.0f)
-        discard;
+	if ((0.5f - abs(a - AREF)) < 0.0f)
+		discard;
 #elif (PS_ATST == 5) // ge
-    if ((a-AREF + 0.5f) < 0.0f)
-        discard;
+	if ((a-AREF + 0.5f) < 0.0f)
+		discard;
 #elif (PS_ATST == 6) // g
-    if ((a-AREF - 0.5f) < 0.0f)
-        discard;
+	if ((a-AREF - 0.5f) < 0.0f)
+		discard;
 #elif (PS_ATST == 7) // ne
-    if ((abs(a - AREF) - 0.5f) < 0.0f)
-        discard;
+	if ((abs(a - AREF) - 0.5f) < 0.0f)
+		discard;
 #endif
 }
 #endif
@@ -366,12 +362,12 @@ void atst(vec4 c)
 void colclip(inout vec4 c)
 {
 #if (PS_COLCLIP == 2)
-        c.rgb = 256.0f/255.0f - c.rgb;
+	c.rgb = 256.0f/255.0f - c.rgb;
 #elif (PS_COLCLIP > 0)
-        // FIXME !!!!
-        //c.rgb *= c.rgb < 128./255;
-        bvec3 factor = bvec3(128.0f/255.0f, 128.0f/255.0f, 128.0f/255.0f);
-        c.rgb *= vec3(factor);
+	// FIXME !!!!
+	//c.rgb *= c.rgb < 128./255;
+	bvec3 factor = bvec3(128.0f/255.0f, 128.0f/255.0f, 128.0f/255.0f);
+	c.rgb *= vec3(factor);
 #endif
 }
 #endif
@@ -379,59 +375,59 @@ void colclip(inout vec4 c)
 void fog(inout vec4 c, float f)
 {
 #if PS_FOG != 0
-    c.rgb = mix(FogColor, c.rgb, f);
+	c.rgb = mix(FogColor, c.rgb, f);
 #endif
 }
 
 vec4 ps_color()
 {
 #if PS_SPRITE == 1
-    // Reinterpolate manually the texture coordinate.
-    // trunc => native resolution. Maybe we can add an option to choose a value between
-    // trunc and current.
-    vec2 factor = vec2(trunc(PSin.alpha.x), floor(PSin.alpha.y));
-    //vec2 factor = trunc(PSin.alpha);
-    factor *= PSin.flat_P;
-    vec2 txy;
-    txy.x = mix(PSin.flat_T.x, PSin.flat_T.y, factor.x);
-    txy.y = mix(PSin.flat_T.z, PSin.flat_T.w, factor.y);
+	// Reinterpolate manually the texture coordinate.
+	// trunc => native resolution. Maybe we can add an option to choose a value between
+	// trunc and current.
+	vec2 factor = vec2(trunc(PSin.alpha.x), floor(PSin.alpha.y));
+	//vec2 factor = trunc(PSin.alpha);
+	factor *= PSin.flat_P;
+	vec2 txy;
+	txy.x = mix(PSin.flat_T.x, PSin.flat_T.y, factor.x);
+	txy.y = mix(PSin.flat_T.z, PSin.flat_T.w, factor.y);
 
 #else
-    vec2 txy = PSin_t.xy;
+	vec2 txy = PSin_t.xy;
 #endif
-    vec4 t = sample_color(txy, PSin_t.w);
+	vec4 t = sample_color(txy, PSin_t.w);
 
-    vec4 zero = vec4(0.0f, 0.0f, 0.0f, 0.0f);
-    vec4 one = vec4(1.0f, 1.0f, 1.0f, 1.0f);
+	vec4 zero = vec4(0.0f, 0.0f, 0.0f, 0.0f);
+	vec4 one = vec4(1.0f, 1.0f, 1.0f, 1.0f);
 #ifdef TEX_COORD_DEBUG
-    vec4 c = clamp(t, zero, one);
+	vec4 c = clamp(t, zero, one);
 #else
 #if PS_IIP == 1
-    vec4 c = clamp(tfx(t, PSin_c), zero, one);
+	vec4 c = clamp(tfx(t, PSin_c), zero, one);
 #else
-    vec4 c = clamp(tfx(t, PSin_fc), zero, one);
+	vec4 c = clamp(tfx(t, PSin_fc), zero, one);
 #endif
 #endif
 
-    atst(c);
+	atst(c);
 
-    fog(c, PSin_t.z);
+	fog(c, PSin_t.z);
 
 	colclip(c);
 
 #if (PS_CLR1 != 0) // needed for Cd * (As/Ad/F + 1) blending modes
-    c.rgb = vec3(1.0f, 1.0f, 1.0f); 
+	c.rgb = vec3(1.0f, 1.0f, 1.0f);
 #endif
 
-    return c;
+	return c;
 }
 
 #if pGL_ES
 void ps_main()
 {
-    vec4 c = ps_color();
-    c.a *= 2.0;
-    SV_Target0 = c;
+	vec4 c = ps_color();
+	c.a *= 2.0;
+	SV_Target0 = c;
 }
 #endif
 
@@ -439,30 +435,32 @@ void ps_main()
 void ps_main()
 {
 #if (PS_DATE & 3) == 1 && !defined(DISABLE_GL42_image)
-    // DATM == 0
-    // Pixel with alpha equal to 1 will failed
+	// DATM == 0
+	// Pixel with alpha equal to 1 will failed
 	float rt_a = texelFetch(RtSampler, ivec2(gl_FragCoord.xy), 0).a;
-	if ((127.5f / 255.0f) < rt_a) // < 0x80 pass (== 0x80 should not pass)
+	if ((127.5f / 255.0f) < rt_a) { // < 0x80 pass (== 0x80 should not pass)
 		discard;
+	}
 #elif (PS_DATE & 3) == 2 && !defined(DISABLE_GL42_image)
-    // DATM == 1
-    // Pixel with alpha equal to 0 will failed
+	// DATM == 1
+	// Pixel with alpha equal to 0 will failed
 	float rt_a = texelFetch(RtSampler, ivec2(gl_FragCoord.xy), 0).a;
-    if(rt_a < (127.5f / 255.0f)) // >= 0x80 pass
+	if(rt_a < (127.5f / 255.0f)) { // >= 0x80 pass
 		discard;
+	}
 #endif
 
 #if PS_DATE == 3 && !defined(DISABLE_GL42_image)
-    int stencil_ceil = imageLoad(img_prim_min, ivec2(gl_FragCoord.xy));
-    // Note gl_PrimitiveID == stencil_ceil will be the primitive that will update
-    // the bad alpha value so we must keep it.
+	int stencil_ceil = imageLoad(img_prim_min, ivec2(gl_FragCoord.xy));
+	// Note gl_PrimitiveID == stencil_ceil will be the primitive that will update
+	// the bad alpha value so we must keep it.
 
 	if (gl_PrimitiveID > stencil_ceil) {
 		discard;
 	}
 #endif
 
-    vec4 c = ps_color();
+	vec4 c = ps_color();
 #if (APITRACE_DEBUG & 1) == 1
 	c.r = 1.0f;
 #endif
@@ -476,39 +474,39 @@ void ps_main()
 	c.a = 0.5f;
 #endif
 
-    float alpha = c.a * 2.0;
+	float alpha = c.a * 2.0;
 
 #if (PS_AOUT != 0) // 16 bit output
-    float a = 128.0f / 255.0; // alpha output will be 0x80
+	float a = 128.0f / 255.0; // alpha output will be 0x80
 
-    c.a = (PS_FBA != 0) ? a : step(0.5, c.a) * a;
+	c.a = (PS_FBA != 0) ? a : step(0.5, c.a) * a;
 #elif (PS_FBA != 0)
-    if(c.a < 0.5) c.a += 0.5;
+	if(c.a < 0.5) c.a += 0.5;
 #endif
 
-    // Get first primitive that will write a failling alpha value
+	// Get first primitive that will write a failling alpha value
 #if PS_DATE == 1 && !defined(DISABLE_GL42_image)
-    // DATM == 0
-    // Pixel with alpha equal to 1 will failed
-    if (c.a > 127.5f / 255.0f) {
-        imageAtomicMin(img_prim_min, ivec2(gl_FragCoord.xy), gl_PrimitiveID);
-    }
+	// DATM == 0
+	// Pixel with alpha equal to 1 will failed (128-255)
+	if (c.a > 127.5f / 255.0f) {
+		imageAtomicMin(img_prim_min, ivec2(gl_FragCoord.xy), gl_PrimitiveID);
+	}
 #elif PS_DATE == 2 && !defined(DISABLE_GL42_image)
-    // DATM == 1
-    // Pixel with alpha equal to 0 will failed
-    if (c.a < 127.5f / 255.0f) {
-        imageAtomicMin(img_prim_min, ivec2(gl_FragCoord.xy), gl_PrimitiveID);
-    }
+	// DATM == 1
+	// Pixel with alpha equal to 0 will failed (0-127)
+	if (c.a < 127.5f / 255.0f) {
+		imageAtomicMin(img_prim_min, ivec2(gl_FragCoord.xy), gl_PrimitiveID);
+	}
 #endif
 
 
 #if (PS_DATE == 2 || PS_DATE == 1) && !defined(DISABLE_GL42_image)
-    // Don't write anything on the framebuffer
-    // Note: you can't use discard because it will also drop
-    // image operation
+	// Don't write anything on the framebuffer
+	// Note: you can't use discard because it will also drop
+	// image operation
 #else
-    SV_Target0 = c;
-    SV_Target1 = vec4(alpha, alpha, alpha, alpha);
+	SV_Target0 = c;
+	SV_Target1 = vec4(alpha, alpha, alpha, alpha);
 #endif
 
 }
diff --git a/plugins/GSdx/res/glsl_source.h b/plugins/GSdx/res/glsl_source.h
index 5ceec51bed..335fa60315 100644
--- a/plugins/GSdx/res/glsl_source.h
+++ b/plugins/GSdx/res/glsl_source.h
@@ -794,13 +794,13 @@ static const char* tfx_fs_all_glsl =
 	"\n"
 	"in SHADER\n"
 	"{\n"
-	"    vec4 t;\n"
-	"    vec4 c;\n"
-	"    flat vec4 fc;\n"
+	"	vec4 t;\n"
+	"	vec4 c;\n"
+	"	flat vec4 fc;\n"
 	"#if PS_SPRITE == 1\n"
-	"    flat vec4 flat_T;\n"
-	"    flat vec2 flat_P;\n"
-	"    vec2 alpha;\n"
+	"	flat vec4 flat_T;\n"
+	"	flat vec2 flat_P;\n"
+	"	vec2 alpha;\n"
 	"#endif\n"
 	"} PSin;\n"
 	"\n"
@@ -829,30 +829,26 @@ static const char* tfx_fs_all_glsl =
 	"#if PS_DATE > 0\n"
 	"// FIXME how to declare memory access\n"
 	"layout(r32i, binding = 2) coherent uniform iimage2D img_prim_min;\n"
+	"layout(early_fragment_tests) in;\n"
+	"// origin_upper_left\n"
+	"layout(pixel_center_integer) in vec4 gl_FragCoord;\n"
 	"#endif\n"
 	"#else\n"
 	"// use basic stencil\n"
 	"#endif\n"
 	"\n"
-	"#ifndef DISABLE_GL42_image\n"
-	"#if PS_DATE > 0\n"
-	"// origin_upper_left\n"
-	"layout(pixel_center_integer) in vec4 gl_FragCoord;\n"
-	"//in int gl_PrimitiveID;\n"
-	"#endif\n"
-	"#endif\n"
 	"\n"
 	"layout(std140, binding = 21) uniform cb21\n"
 	"{\n"
-	"    vec3 FogColor;\n"
-	"    float AREF;\n"
-	"    vec4 WH;\n"
-	"    vec2 MinF;\n"
-	"    vec2 TA;\n"
-	"    uvec4 MskFix;\n"
-	"    vec4 HalfTexel;\n"
-	"    vec4 MinMax;\n"
-	"    vec4 TC_OffsetHack;\n"
+	"	vec3 FogColor;\n"
+	"	float AREF;\n"
+	"	vec4 WH;\n"
+	"	vec2 MinF;\n"
+	"	vec2 TA;\n"
+	"	uvec4 MskFix;\n"
+	"	vec4 HalfTexel;\n"
+	"	vec4 MinMax;\n"
+	"	vec4 TC_OffsetHack;\n"
 	"};\n"
 	"\n"
 	"#ifdef SUBROUTINE_GL40\n"
@@ -870,242 +866,242 @@ static const char* tfx_fs_all_glsl =
 	"\n"
 	"vec4 sample_c(vec2 uv)\n"
 	"{\n"
-	"    // FIXME: check the issue on openGL\n"
+	"	// FIXME: check the issue on openGL\n"
 	"#if (ATI_SUCKS == 1) && (PS_POINT_SAMPLER == 1)\n"
-	"    // Weird issue with ATI cards (happens on at least HD 4xxx and 5xxx),\n"
-	"    // it looks like they add 127/128 of a texel to sampling coordinates\n"
-	"    // occasionally causing point sampling to erroneously round up.\n"
-	"    // I'm manually adjusting coordinates to the centre of texels here,\n"
-	"    // though the centre is just paranoia, the top left corner works fine.\n"
-	"    uv = (trunc(uv * WH.zw) + vec2(0.5, 0.5)) / WH.zw;\n"
+	"	// Weird issue with ATI cards (happens on at least HD 4xxx and 5xxx),\n"
+	"	// it looks like they add 127/128 of a texel to sampling coordinates\n"
+	"	// occasionally causing point sampling to erroneously round up.\n"
+	"	// I'm manually adjusting coordinates to the centre of texels here,\n"
+	"	// though the centre is just paranoia, the top left corner works fine.\n"
+	"	uv = (trunc(uv * WH.zw) + vec2(0.5, 0.5)) / WH.zw;\n"
 	"#endif\n"
 	"\n"
-	"    return texture(TextureSampler, uv);\n"
+	"	return texture(TextureSampler, uv);\n"
 	"}\n"
 	"\n"
 	"vec4 sample_p(float u)\n"
 	"{\n"
-	"    //FIXME do we need a 1D sampler. Big impact on opengl to find 1 dim\n"
-	"    // So for the moment cheat with 0.0f dunno if it work\n"
-	"    return texture(PaletteSampler, vec2(u, 0.0f));\n"
+	"	//FIXME do we need a 1D sampler. Big impact on opengl to find 1 dim\n"
+	"	// So for the moment cheat with 0.0f dunno if it work\n"
+	"	return texture(PaletteSampler, vec2(u, 0.0f));\n"
 	"}\n"
 	"\n"
 	"vec4 wrapuv(vec4 uv)\n"
 	"{\n"
-	"    vec4 uv_out = uv;\n"
+	"	vec4 uv_out = uv;\n"
 	"\n"
 	"#if PS_WMS == PS_WMT\n"
 	"\n"
 	"#if PS_WMS == 2\n"
-	"    uv_out = clamp(uv, MinMax.xyxy, MinMax.zwzw);\n"
+	"	uv_out = clamp(uv, MinMax.xyxy, MinMax.zwzw);\n"
 	"#elif PS_WMS == 3\n"
-	"    uv_out = vec4((ivec4(uv * WH.xyxy) & ivec4(MskFix.xyxy)) | ivec4(MskFix.zwzw)) / WH.xyxy;\n"
+	"	uv_out = vec4((ivec4(uv * WH.xyxy) & ivec4(MskFix.xyxy)) | ivec4(MskFix.zwzw)) / WH.xyxy;\n"
 	"#endif\n"
 	"\n"
 	"#else // PS_WMS != PS_WMT\n"
 	"\n"
 	"#if PS_WMS == 2\n"
-	"    uv_out.xz = clamp(uv.xz, MinMax.xx, MinMax.zz);\n"
+	"	uv_out.xz = clamp(uv.xz, MinMax.xx, MinMax.zz);\n"
 	"\n"
 	"#elif PS_WMS == 3\n"
-	"    uv_out.xz = vec2((ivec2(uv.xz * WH.xx) & ivec2(MskFix.xx)) | ivec2(MskFix.zz)) / WH.xx;\n"
+	"	uv_out.xz = vec2((ivec2(uv.xz * WH.xx) & ivec2(MskFix.xx)) | ivec2(MskFix.zz)) / WH.xx;\n"
 	"\n"
 	"#endif\n"
 	"\n"
 	"#if PS_WMT == 2\n"
-	"    uv_out.yw = clamp(uv.yw, MinMax.yy, MinMax.ww);\n"
+	"	uv_out.yw = clamp(uv.yw, MinMax.yy, MinMax.ww);\n"
 	"\n"
 	"#elif PS_WMT == 3\n"
 	"\n"
-	"    uv_out.yw = vec2((ivec2(uv.yw * WH.yy) & ivec2(MskFix.yy)) | ivec2(MskFix.ww)) / WH.yy;\n"
+	"	uv_out.yw = vec2((ivec2(uv.yw * WH.yy) & ivec2(MskFix.yy)) | ivec2(MskFix.ww)) / WH.yy;\n"
 	"#endif\n"
 	"\n"
 	"#endif\n"
 	"\n"
-	"    return uv_out;\n"
+	"	return uv_out;\n"
 	"}\n"
 	"\n"
 	"vec2 clampuv(vec2 uv)\n"
 	"{\n"
-	"    vec2 uv_out = uv;\n"
+	"	vec2 uv_out = uv;\n"
 	"\n"
-	"#if (PS_WMS == 2) && (PS_WMT == 2) \n"
-	"    uv_out = clamp(uv, MinF, MinMax.zw);\n"
+	"#if (PS_WMS == 2) && (PS_WMT == 2)\n"
+	"	uv_out = clamp(uv, MinF, MinMax.zw);\n"
 	"#elif PS_WMS == 2\n"
-	"    uv_out.x = clamp(uv.x, MinF.x, MinMax.z);\n"
+	"	uv_out.x = clamp(uv.x, MinF.x, MinMax.z);\n"
 	"#elif PS_WMT == 2\n"
-	"    uv_out.y = clamp(uv.y, MinF.y, MinMax.w);\n"
+	"	uv_out.y = clamp(uv.y, MinF.y, MinMax.w);\n"
 	"#endif\n"
 	"\n"
-	"    return uv_out;\n"
+	"	return uv_out;\n"
 	"}\n"
 	"\n"
 	"mat4 sample_4c(vec4 uv)\n"
 	"{\n"
-	"    mat4 c;\n"
+	"	mat4 c;\n"
 	"\n"
-	"    c[0] = sample_c(uv.xy);\n"
-	"    c[1] = sample_c(uv.zy);\n"
-	"    c[2] = sample_c(uv.xw);\n"
-	"    c[3] = sample_c(uv.zw);\n"
+	"	c[0] = sample_c(uv.xy);\n"
+	"	c[1] = sample_c(uv.zy);\n"
+	"	c[2] = sample_c(uv.xw);\n"
+	"	c[3] = sample_c(uv.zw);\n"
 	"\n"
-	"    return c;\n"
+	"	return c;\n"
 	"}\n"
 	"\n"
 	"vec4 sample_4a(vec4 uv)\n"
 	"{\n"
-	"    vec4 c;\n"
+	"	vec4 c;\n"
 	"\n"
-	"    // Dx used the alpha channel.\n"
-	"    // Opengl is only 8 bits on red channel.\n"
-	"    c.x = sample_c(uv.xy).r;\n"
-	"    c.y = sample_c(uv.zy).r;\n"
-	"    c.z = sample_c(uv.xw).r;\n"
-	"    c.w = sample_c(uv.zw).r;\n"
+	"	// Dx used the alpha channel.\n"
+	"	// Opengl is only 8 bits on red channel.\n"
+	"	c.x = sample_c(uv.xy).r;\n"
+	"	c.y = sample_c(uv.zy).r;\n"
+	"	c.z = sample_c(uv.xw).r;\n"
+	"	c.w = sample_c(uv.zw).r;\n"
 	"\n"
 	"	return c * 255.0/256.0 + 0.5/256.0;\n"
 	"}\n"
 	"\n"
 	"mat4 sample_4p(vec4 u)\n"
 	"{\n"
-	"    mat4 c;\n"
+	"	mat4 c;\n"
 	"\n"
-	"    c[0] = sample_p(u.x);\n"
-	"    c[1] = sample_p(u.y);\n"
-	"    c[2] = sample_p(u.z);\n"
-	"    c[3] = sample_p(u.w);\n"
+	"	c[0] = sample_p(u.x);\n"
+	"	c[1] = sample_p(u.y);\n"
+	"	c[2] = sample_p(u.z);\n"
+	"	c[3] = sample_p(u.w);\n"
 	"\n"
-	"    return c;\n"
+	"	return c;\n"
 	"}\n"
 	"\n"
 	"vec4 sample_color(vec2 st, float q)\n"
 	"{\n"
 	"#if (PS_FST == 0)\n"
-	"    st /= q;\n"
+	"	st /= q;\n"
 	"#endif\n"
 	"\n"
 	"#if (PS_TCOFFSETHACK == 1)\n"
-	"    st += TC_OffsetHack.xy;\n"
+	"	st += TC_OffsetHack.xy;\n"
 	"#endif\n"
 	"\n"
-	"    vec4 t;\n"
-	"    mat4 c;\n"
-	"    vec2 dd;\n"
+	"	vec4 t;\n"
+	"	mat4 c;\n"
+	"	vec2 dd;\n"
 	"\n"
 	"#if (PS_LTF == 0 && PS_FMT <= FMT_16 && PS_WMS < 3 && PS_WMT < 3)\n"
-	"        c[0] = sample_c(clampuv(st));\n"
+	"	c[0] = sample_c(clampuv(st));\n"
 	"#ifdef TEX_COORD_DEBUG\n"
-	"        c[0].rg = clampuv(st).xy;\n"
+	"	c[0].rg = clampuv(st).xy;\n"
 	"#endif\n"
 	"\n"
 	"#else\n"
-	"        vec4 uv;\n"
+	"	vec4 uv;\n"
 	"\n"
-	"        if(PS_LTF != 0)\n"
-	"        {\n"
-	"            uv = st.xyxy + HalfTexel;\n"
-	"            dd = fract(uv.xy * WH.zw);\n"
-	"        }\n"
-	"        else\n"
-	"        {\n"
-	"            uv = st.xyxy;\n"
-	"        }\n"
+	"	if(PS_LTF != 0)\n"
+	"	{\n"
+	"		uv = st.xyxy + HalfTexel;\n"
+	"		dd = fract(uv.xy * WH.zw);\n"
+	"	}\n"
+	"	else\n"
+	"	{\n"
+	"		uv = st.xyxy;\n"
+	"	}\n"
 	"\n"
-	"        uv = wrapuv(uv);\n"
+	"	uv = wrapuv(uv);\n"
 	"\n"
-	"        if((PS_FMT & FMT_PAL) != 0)\n"
-	"        {\n"
-	"            c = sample_4p(sample_4a(uv));\n"
-	"        }\n"
-	"        else\n"
-	"        {\n"
-	"            c = sample_4c(uv);\n"
-	"        }\n"
+	"	if((PS_FMT & FMT_PAL) != 0)\n"
+	"	{\n"
+	"		c = sample_4p(sample_4a(uv));\n"
+	"	}\n"
+	"	else\n"
+	"	{\n"
+	"		c = sample_4c(uv);\n"
+	"	}\n"
 	"#ifdef TEX_COORD_DEBUG\n"
-	"        c[0].rg = uv.xy;\n"
-	"        c[1].rg = uv.xy;\n"
-	"        c[2].rg = uv.xy;\n"
-	"        c[3].rg = uv.xy;\n"
+	"	c[0].rg = uv.xy;\n"
+	"	c[1].rg = uv.xy;\n"
+	"	c[2].rg = uv.xy;\n"
+	"	c[3].rg = uv.xy;\n"
 	"#endif\n"
 	"\n"
 	"#endif\n"
 	"\n"
-	"    // PERF: see the impact of the exansion before/after the interpolation\n"
-	"    for (int i = 0; i < 4; i++)\n"
-	"    {\n"
+	"	// PERF: see the impact of the exansion before/after the interpolation\n"
+	"	for (int i = 0; i < 4; i++)\n"
+	"	{\n"
 	"#if ((PS_FMT & ~FMT_PAL) == FMT_24)\n"
-	"        c[i].a = ( (PS_AEM == 0) || any(bvec3(c[i].rgb))  ) ? TA.x : 0.0f;\n"
+	"		c[i].a = ( (PS_AEM == 0) || any(bvec3(c[i].rgb))  ) ? TA.x : 0.0f;\n"
 	"#elif ((PS_FMT & ~FMT_PAL) == FMT_16)\n"
-	"        c[i].a = c[i].a >= 0.5 ? TA.y : ( (PS_AEM == 0) || any(bvec3(c[i].rgb)) ) ? TA.x : 0.0f;\n"
+	"		c[i].a = c[i].a >= 0.5 ? TA.y : ( (PS_AEM == 0) || any(bvec3(c[i].rgb)) ) ? TA.x : 0.0f;\n"
 	"#endif\n"
-	"    }\n"
+	"	}\n"
 	"\n"
 	"#if(PS_LTF != 0)\n"
-	"    t = mix(mix(c[0], c[1], dd.x), mix(c[2], c[3], dd.x), dd.y);\n"
+	"	t = mix(mix(c[0], c[1], dd.x), mix(c[2], c[3], dd.x), dd.y);\n"
 	"#else\n"
-	"    t = c[0];\n"
+	"	t = c[0];\n"
 	"#endif\n"
 	"\n"
-	"    return t;\n"
+	"	return t;\n"
 	"}\n"
 	"\n"
 	"#ifndef SUBROUTINE_GL40\n"
 	"vec4 tfx(vec4 t, vec4 c)\n"
 	"{\n"
-	"    vec4 c_out = c;\n"
+	"	vec4 c_out = c;\n"
 	"#if (PS_TFX == 0)\n"
-	"    if(PS_TCC != 0) \n"
-	"        c_out = c * t * 255.0f / 128.0f;\n"
-	"    else\n"
-	"        c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f;\n"
+	"	if(PS_TCC != 0)\n"
+	"		c_out = c * t * 255.0f / 128.0f;\n"
+	"	else\n"
+	"		c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f;\n"
 	"#elif (PS_TFX == 1)\n"
-	"    if(PS_TCC != 0) \n"
-	"        c_out = t;\n"
-	"    else\n"
-	"        c_out.rgb = t.rgb;\n"
+	"	if(PS_TCC != 0)\n"
+	"		c_out = t;\n"
+	"	else\n"
+	"		c_out.rgb = t.rgb;\n"
 	"#elif (PS_TFX == 2)\n"
-	"    c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f + c.a;\n"
+	"	c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f + c.a;\n"
 	"\n"
-	"    if(PS_TCC != 0) \n"
-	"        c_out.a += t.a;\n"
+	"	if(PS_TCC != 0)\n"
+	"		c_out.a += t.a;\n"
 	"#elif (PS_TFX == 3)\n"
-	"    c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f + c.a;\n"
+	"	c_out.rgb = c.rgb * t.rgb * 255.0f / 128.0f + c.a;\n"
 	"\n"
-	"    if(PS_TCC != 0) \n"
-	"        c_out.a = t.a;\n"
+	"	if(PS_TCC != 0)\n"
+	"		c_out.a = t.a;\n"
 	"#endif\n"
 	"\n"
-	"    return c_out;\n"
+	"	return c_out;\n"
 	"}\n"
 	"#endif\n"
 	"\n"
 	"#ifndef SUBROUTINE_GL40\n"
 	"void atst(vec4 c)\n"
 	"{\n"
-	"    float a = trunc(c.a * 255.0 + 0.01);\n"
+	"	float a = trunc(c.a * 255.0 + 0.01);\n"
 	"\n"
 	"#if (PS_ATST == 0) // never\n"
-	"    discard;\n"
+	"	discard;\n"
 	"#elif (PS_ATST == 1) // always\n"
-	"    // nothing to do\n"
+	"	// nothing to do\n"
 	"#elif (PS_ATST == 2) && (PS_SPRITEHACK == 0) // l\n"
-	"    if ((AREF - a - 0.5f) < 0.0f)\n"
-	"        discard;\n"
+	"	if ((AREF - a - 0.5f) < 0.0f)\n"
+	"		discard;\n"
 	"#elif (PS_ATST == 3 ) // le\n"
-	"    if ((AREF - a + 0.5f) < 0.0f)\n"
-	"        discard;\n"
+	"	if ((AREF - a + 0.5f) < 0.0f)\n"
+	"		discard;\n"
 	"#elif (PS_ATST == 4) // e\n"
-	"    if ((0.5f - abs(a - AREF)) < 0.0f)\n"
-	"        discard;\n"
+	"	if ((0.5f - abs(a - AREF)) < 0.0f)\n"
+	"		discard;\n"
 	"#elif (PS_ATST == 5) // ge\n"
-	"    if ((a-AREF + 0.5f) < 0.0f)\n"
-	"        discard;\n"
+	"	if ((a-AREF + 0.5f) < 0.0f)\n"
+	"		discard;\n"
 	"#elif (PS_ATST == 6) // g\n"
-	"    if ((a-AREF - 0.5f) < 0.0f)\n"
-	"        discard;\n"
+	"	if ((a-AREF - 0.5f) < 0.0f)\n"
+	"		discard;\n"
 	"#elif (PS_ATST == 7) // ne\n"
-	"    if ((abs(a - AREF) - 0.5f) < 0.0f)\n"
-	"        discard;\n"
+	"	if ((abs(a - AREF) - 0.5f) < 0.0f)\n"
+	"		discard;\n"
 	"#endif\n"
 	"}\n"
 	"#endif\n"
@@ -1115,12 +1111,12 @@ static const char* tfx_fs_all_glsl =
 	"void colclip(inout vec4 c)\n"
 	"{\n"
 	"#if (PS_COLCLIP == 2)\n"
-	"        c.rgb = 256.0f/255.0f - c.rgb;\n"
+	"	c.rgb = 256.0f/255.0f - c.rgb;\n"
 	"#elif (PS_COLCLIP > 0)\n"
-	"        // FIXME !!!!\n"
-	"        //c.rgb *= c.rgb < 128./255;\n"
-	"        bvec3 factor = bvec3(128.0f/255.0f, 128.0f/255.0f, 128.0f/255.0f);\n"
-	"        c.rgb *= vec3(factor);\n"
+	"	// FIXME !!!!\n"
+	"	//c.rgb *= c.rgb < 128./255;\n"
+	"	bvec3 factor = bvec3(128.0f/255.0f, 128.0f/255.0f, 128.0f/255.0f);\n"
+	"	c.rgb *= vec3(factor);\n"
 	"#endif\n"
 	"}\n"
 	"#endif\n"
@@ -1128,59 +1124,59 @@ static const char* tfx_fs_all_glsl =
 	"void fog(inout vec4 c, float f)\n"
 	"{\n"
 	"#if PS_FOG != 0\n"
-	"    c.rgb = mix(FogColor, c.rgb, f);\n"
+	"	c.rgb = mix(FogColor, c.rgb, f);\n"
 	"#endif\n"
 	"}\n"
 	"\n"
 	"vec4 ps_color()\n"
 	"{\n"
 	"#if PS_SPRITE == 1\n"
-	"    // Reinterpolate manually the texture coordinate.\n"
-	"    // trunc => native resolution. Maybe we can add an option to choose a value between\n"
-	"    // trunc and current.\n"
-	"    vec2 factor = vec2(trunc(PSin.alpha.x), floor(PSin.alpha.y));\n"
-	"    //vec2 factor = trunc(PSin.alpha);\n"
-	"    factor *= PSin.flat_P;\n"
-	"    vec2 txy;\n"
-	"    txy.x = mix(PSin.flat_T.x, PSin.flat_T.y, factor.x);\n"
-	"    txy.y = mix(PSin.flat_T.z, PSin.flat_T.w, factor.y);\n"
+	"	// Reinterpolate manually the texture coordinate.\n"
+	"	// trunc => native resolution. Maybe we can add an option to choose a value between\n"
+	"	// trunc and current.\n"
+	"	vec2 factor = vec2(trunc(PSin.alpha.x), floor(PSin.alpha.y));\n"
+	"	//vec2 factor = trunc(PSin.alpha);\n"
+	"	factor *= PSin.flat_P;\n"
+	"	vec2 txy;\n"
+	"	txy.x = mix(PSin.flat_T.x, PSin.flat_T.y, factor.x);\n"
+	"	txy.y = mix(PSin.flat_T.z, PSin.flat_T.w, factor.y);\n"
 	"\n"
 	"#else\n"
-	"    vec2 txy = PSin_t.xy;\n"
+	"	vec2 txy = PSin_t.xy;\n"
 	"#endif\n"
-	"    vec4 t = sample_color(txy, PSin_t.w);\n"
+	"	vec4 t = sample_color(txy, PSin_t.w);\n"
 	"\n"
-	"    vec4 zero = vec4(0.0f, 0.0f, 0.0f, 0.0f);\n"
-	"    vec4 one = vec4(1.0f, 1.0f, 1.0f, 1.0f);\n"
+	"	vec4 zero = vec4(0.0f, 0.0f, 0.0f, 0.0f);\n"
+	"	vec4 one = vec4(1.0f, 1.0f, 1.0f, 1.0f);\n"
 	"#ifdef TEX_COORD_DEBUG\n"
-	"    vec4 c = clamp(t, zero, one);\n"
+	"	vec4 c = clamp(t, zero, one);\n"
 	"#else\n"
 	"#if PS_IIP == 1\n"
-	"    vec4 c = clamp(tfx(t, PSin_c), zero, one);\n"
+	"	vec4 c = clamp(tfx(t, PSin_c), zero, one);\n"
 	"#else\n"
-	"    vec4 c = clamp(tfx(t, PSin_fc), zero, one);\n"
+	"	vec4 c = clamp(tfx(t, PSin_fc), zero, one);\n"
 	"#endif\n"
 	"#endif\n"
 	"\n"
-	"    atst(c);\n"
+	"	atst(c);\n"
 	"\n"
-	"    fog(c, PSin_t.z);\n"
+	"	fog(c, PSin_t.z);\n"
 	"\n"
 	"	colclip(c);\n"
 	"\n"
 	"#if (PS_CLR1 != 0) // needed for Cd * (As/Ad/F + 1) blending modes\n"
-	"    c.rgb = vec3(1.0f, 1.0f, 1.0f); \n"
+	"	c.rgb = vec3(1.0f, 1.0f, 1.0f);\n"
 	"#endif\n"
 	"\n"
-	"    return c;\n"
+	"	return c;\n"
 	"}\n"
 	"\n"
 	"#if pGL_ES\n"
 	"void ps_main()\n"
 	"{\n"
-	"    vec4 c = ps_color();\n"
-	"    c.a *= 2.0;\n"
-	"    SV_Target0 = c;\n"
+	"	vec4 c = ps_color();\n"
+	"	c.a *= 2.0;\n"
+	"	SV_Target0 = c;\n"
 	"}\n"
 	"#endif\n"
 	"\n"
@@ -1188,30 +1184,32 @@ static const char* tfx_fs_all_glsl =
 	"void ps_main()\n"
 	"{\n"
 	"#if (PS_DATE & 3) == 1 && !defined(DISABLE_GL42_image)\n"
-	"    // DATM == 0\n"
-	"    // Pixel with alpha equal to 1 will failed\n"
+	"	// DATM == 0\n"
+	"	// Pixel with alpha equal to 1 will failed\n"
 	"	float rt_a = texelFetch(RtSampler, ivec2(gl_FragCoord.xy), 0).a;\n"
-	"	if ((127.5f / 255.0f) < rt_a) // < 0x80 pass (== 0x80 should not pass)\n"
+	"	if ((127.5f / 255.0f) < rt_a) { // < 0x80 pass (== 0x80 should not pass)\n"
 	"		discard;\n"
+	"	}\n"
 	"#elif (PS_DATE & 3) == 2 && !defined(DISABLE_GL42_image)\n"
-	"    // DATM == 1\n"
-	"    // Pixel with alpha equal to 0 will failed\n"
+	"	// DATM == 1\n"
+	"	// Pixel with alpha equal to 0 will failed\n"
 	"	float rt_a = texelFetch(RtSampler, ivec2(gl_FragCoord.xy), 0).a;\n"
-	"    if(rt_a < (127.5f / 255.0f)) // >= 0x80 pass\n"
+	"	if(rt_a < (127.5f / 255.0f)) { // >= 0x80 pass\n"
 	"		discard;\n"
+	"	}\n"
 	"#endif\n"
 	"\n"
 	"#if PS_DATE == 3 && !defined(DISABLE_GL42_image)\n"
-	"    int stencil_ceil = imageLoad(img_prim_min, ivec2(gl_FragCoord.xy));\n"
-	"    // Note gl_PrimitiveID == stencil_ceil will be the primitive that will update\n"
-	"    // the bad alpha value so we must keep it.\n"
+	"	int stencil_ceil = imageLoad(img_prim_min, ivec2(gl_FragCoord.xy));\n"
+	"	// Note gl_PrimitiveID == stencil_ceil will be the primitive that will update\n"
+	"	// the bad alpha value so we must keep it.\n"
 	"\n"
 	"	if (gl_PrimitiveID > stencil_ceil) {\n"
 	"		discard;\n"
 	"	}\n"
 	"#endif\n"
 	"\n"
-	"    vec4 c = ps_color();\n"
+	"	vec4 c = ps_color();\n"
 	"#if (APITRACE_DEBUG & 1) == 1\n"
 	"	c.r = 1.0f;\n"
 	"#endif\n"
@@ -1225,39 +1223,39 @@ static const char* tfx_fs_all_glsl =
 	"	c.a = 0.5f;\n"
 	"#endif\n"
 	"\n"
-	"    float alpha = c.a * 2.0;\n"
+	"	float alpha = c.a * 2.0;\n"
 	"\n"
 	"#if (PS_AOUT != 0) // 16 bit output\n"
-	"    float a = 128.0f / 255.0; // alpha output will be 0x80\n"
+	"	float a = 128.0f / 255.0; // alpha output will be 0x80\n"
 	"\n"
-	"    c.a = (PS_FBA != 0) ? a : step(0.5, c.a) * a;\n"
+	"	c.a = (PS_FBA != 0) ? a : step(0.5, c.a) * a;\n"
 	"#elif (PS_FBA != 0)\n"
-	"    if(c.a < 0.5) c.a += 0.5;\n"
+	"	if(c.a < 0.5) c.a += 0.5;\n"
 	"#endif\n"
 	"\n"
-	"    // Get first primitive that will write a failling alpha value\n"
+	"	// Get first primitive that will write a failling alpha value\n"
 	"#if PS_DATE == 1 && !defined(DISABLE_GL42_image)\n"
-	"    // DATM == 0\n"
-	"    // Pixel with alpha equal to 1 will failed\n"
-	"    if (c.a > 127.5f / 255.0f) {\n"
-	"        imageAtomicMin(img_prim_min, ivec2(gl_FragCoord.xy), gl_PrimitiveID);\n"
-	"    }\n"
+	"	// DATM == 0\n"
+	"	// Pixel with alpha equal to 1 will failed (128-255)\n"
+	"	if (c.a > 127.5f / 255.0f) {\n"
+	"		imageAtomicMin(img_prim_min, ivec2(gl_FragCoord.xy), gl_PrimitiveID);\n"
+	"	}\n"
 	"#elif PS_DATE == 2 && !defined(DISABLE_GL42_image)\n"
-	"    // DATM == 1\n"
-	"    // Pixel with alpha equal to 0 will failed\n"
-	"    if (c.a < 127.5f / 255.0f) {\n"
-	"        imageAtomicMin(img_prim_min, ivec2(gl_FragCoord.xy), gl_PrimitiveID);\n"
-	"    }\n"
+	"	// DATM == 1\n"
+	"	// Pixel with alpha equal to 0 will failed (0-127)\n"
+	"	if (c.a < 127.5f / 255.0f) {\n"
+	"		imageAtomicMin(img_prim_min, ivec2(gl_FragCoord.xy), gl_PrimitiveID);\n"
+	"	}\n"
 	"#endif\n"
 	"\n"
 	"\n"
 	"#if (PS_DATE == 2 || PS_DATE == 1) && !defined(DISABLE_GL42_image)\n"
-	"    // Don't write anything on the framebuffer\n"
-	"    // Note: you can't use discard because it will also drop\n"
-	"    // image operation\n"
+	"	// Don't write anything on the framebuffer\n"
+	"	// Note: you can't use discard because it will also drop\n"
+	"	// image operation\n"
 	"#else\n"
-	"    SV_Target0 = c;\n"
-	"    SV_Target1 = vec4(alpha, alpha, alpha, alpha);\n"
+	"	SV_Target0 = c;\n"
+	"	SV_Target1 = vec4(alpha, alpha, alpha, alpha);\n"
 	"#endif\n"
 	"\n"
 	"}\n"