[GPU] Simplify local X offsetting with resolution scaling

Switch between even and odd 16-byte element sequences along X by simply
flipping a bit rather than going to a different resolution-scaled group of
pixels, by increasing the size of the group within the constraints imposed
by tiling.

src/xenia/gpu/d3d12/d3d12_texture_cache.cc

@@ -1906,13 +1906,8 @@ bool D3D12TextureCache::LoadTextureDataFromResidentMemoryImpl(Texture& texture,
     }
     const texture_util::TextureGuestLayout::Level& level_guest_layout =
         is_base ? guest_layout.base : guest_layout.mips[level];
-    uint32_t level_guest_pitch = level_guest_layout.row_pitch_bytes;
-    if (texture_key.tiled) {
-      // Shaders expect pitch in blocks for tiled textures.
-      level_guest_pitch /= bytes_per_block;
-      assert_zero(level_guest_pitch & (xenos::kTextureTileWidthHeight - 1));
-    }
-    load_constants.guest_pitch_aligned = level_guest_pitch;
+    load_constants.guest_pitch_aligned =
+        level_guest_layout.row_pitch_bytes / bytes_per_block;
     load_constants.guest_z_stride_block_rows_aligned =
         level_guest_layout.z_slice_stride_block_rows;
     assert_true(dimension != xenos::DataDimension::k3D ||

src/xenia/gpu/shaders/bytecode/d3d12_5_1/resolve_fast_32bpp_1x2xmsaa_cs.h

@@ -178,7 +178,7 @@ if_nz r0.z
   bfi r5.xyzw, l(16, 16, 16, 16), l(16, 16, 16, 16), r5.xyzw, r1.xyzw
 endif 
 store_uav_typed U0[0].xyzw, r0.xxxx, r5.xyzw
-iadd r0.x, r0.x, l(2)
+xor r0.x, r0.x, l(2)
 if_nz r0.y
   ishl r1.xyzw, r6.xyzw, l(8, 8, 8, 8)
   and r1.xyzw, r1.xyzw, l(0xff00ff00, 0xff00ff00, 0xff00ff00, 0xff00ff00)
@@ -197,10 +197,10 @@ ret
 
 const BYTE resolve_fast_32bpp_1x2xmsaa_cs[] =
 {
-     68,  88,  66,  67, 188,  44, 
-     61, 210, 116,  48, 173, 251, 
-      2, 141, 146, 110, 153,  13, 
-     14, 111,   1,   0,   0,   0, 
+     68,  88,  66,  67,  76,  81, 
+      6, 210, 127,  11, 121,  14, 
+     72,   0,  88, 214, 164, 189, 
+     19, 242,   1,   0,   0,   0, 
      96,  22,   0,   0,   5,   0, 
       0,   0,  52,   0,   0,   0, 
     208,   2,   0,   0, 224,   2, 
@@ -1060,7 +1060,7 @@ const BYTE resolve_fast_32bpp_1x2xmsaa_cs[] =
       0,   0,   0,   0,   6,   0, 
      16,   0,   0,   0,   0,   0, 
      70,  14,  16,   0,   5,   0, 
-      0,   0,  30,   0,   0,   7, 
+      0,   0,  87,   0,   0,   7, 
      18,   0,  16,   0,   0,   0, 
       0,   0,  10,   0,  16,   0, 
       0,   0,   0,   0,   1,  64, 
@@ -1130,8 +1130,8 @@ const BYTE resolve_fast_32bpp_1x2xmsaa_cs[] =
     146,   0,   0,   0,   9,   0, 
       0,   0,   0,   0,   0,   0, 
       1,   0,   0,   0,   0,   0, 
-      0,   0,  37,   0,   0,   0, 
-     30,   0,   0,   0,   7,   0, 
+      0,   0,  36,   0,   0,   0, 
+     31,   0,   0,   0,   7,   0, 
       0,   0,  11,   0,   0,   0, 
       0,   0,   0,   0,   0,   0, 
       0,   0,   0,   0,   0,   0, 

src/xenia/gpu/shaders/bytecode/d3d12_5_1/resolve_fast_32bpp_4xmsaa_cs.h

@@ -191,7 +191,7 @@ if_nz r0.z
   bfi r5.xyzw, l(16, 16, 16, 16), l(16, 16, 16, 16), r5.xyzw, r1.xyzw
 endif 
 store_uav_typed U0[0].xyzw, r0.xxxx, r5.xyzw
-iadd r0.x, r0.x, l(2)
+xor r0.x, r0.x, l(2)
 if_nz r0.y
   ishl r1.xyzw, r6.xyzw, l(8, 8, 8, 8)
   and r1.xyzw, r1.xyzw, l(0xff00ff00, 0xff00ff00, 0xff00ff00, 0xff00ff00)
@@ -210,10 +210,10 @@ ret
 
 const BYTE resolve_fast_32bpp_4xmsaa_cs[] =
 {
-     68,  88,  66,  67,  43,   2, 
-    242, 123,  12,   3, 198,  28, 
-    199,  75, 190,  87, 252, 165, 
-     36, 150,   1,   0,   0,   0, 
+     68,  88,  66,  67, 105, 223, 
+    164,  73, 249,  32, 219, 132, 
+    168, 214, 106, 172, 186,  75, 
+    112, 213,   1,   0,   0,   0, 
     184,  23,   0,   0,   5,   0, 
       0,   0,  52,   0,   0,   0, 
     208,   2,   0,   0, 224,   2, 
@@ -1130,7 +1130,7 @@ const BYTE resolve_fast_32bpp_4xmsaa_cs[] =
       0,   0,   0,   0,   0,   0, 
       6,   0,  16,   0,   0,   0, 
       0,   0,  70,  14,  16,   0, 
-      5,   0,   0,   0,  30,   0, 
+      5,   0,   0,   0,  87,   0, 
       0,   7,  18,   0,  16,   0, 
       0,   0,   0,   0,  10,   0, 
      16,   0,   0,   0,   0,   0, 
@@ -1200,8 +1200,8 @@ const BYTE resolve_fast_32bpp_4xmsaa_cs[] =
       0,   0, 159,   0,   0,   0, 
       9,   0,   0,   0,   0,   0, 
       0,   0,   1,   0,   0,   0, 
-      0,   0,   0,   0,  40,   0, 
-      0,   0,  28,   0,   0,   0, 
+      0,   0,   0,   0,  39,   0, 
+      0,   0,  29,   0,   0,   0, 
       9,   0,   0,   0,  12,   0, 
       0,   0,   0,   0,   0,   0, 
       0,   0,   0,   0,   0,   0,