GPU: Implemented bits 3 and 1 from the display transfer flags.

Bit 3 is used to specify a raw copy, where no processing is done to the data, seems to behave exactly as a DMA.
Bit 1 is used to specify whether to convert from a tiled format to a linear format or viceversa.

src/video_core/utils.h

@@ -35,4 +35,54 @@ struct TGAHeader {
  */
 void DumpTGA(std::string filename, short width, short height, u8* raw_data);
 
+/**
+ * Interleave the lower 3 bits of each coordinate to get the intra-block offsets, which are
+ * arranged in a Z-order curve. More details on the bit manipulation at:
+ * https://fgiesen.wordpress.com/2009/12/13/decoding-morton-codes/
+ */
+static inline u32 MortonInterleave(u32 x, u32 y) {
+    u32 i = (x & 7) | ((y & 7) << 8); // ---- -210
+    i = (i ^ (i << 2)) & 0x1313;      // ---2 --10
+    i = (i ^ (i << 1)) & 0x1515;      // ---2 -1-0
+    i = (i | (i >> 7)) & 0x3F;
+    return i;
+}
+
+/**
+ * Calculates the offset of the position of the pixel in Morton order
+ */
+static inline u32 GetMortonOffset(u32 x, u32 y, u32 bytes_per_pixel) {
+    // Images are split into 8x8 tiles. Each tile is composed of four 4x4 subtiles each
+    // of which is composed of four 2x2 subtiles each of which is composed of four texels.
+    // Each structure is embedded into the next-bigger one in a diagonal pattern, e.g.
+    // texels are laid out in a 2x2 subtile like this:
+    // 2 3
+    // 0 1
+    //
+    // The full 8x8 tile has the texels arranged like this:
+    //
+    // 42 43 46 47 58 59 62 63
+    // 40 41 44 45 56 57 60 61
+    // 34 35 38 39 50 51 54 55
+    // 32 33 36 37 48 49 52 53
+    // 10 11 14 15 26 27 30 31
+    // 08 09 12 13 24 25 28 29
+    // 02 03 06 07 18 19 22 23
+    // 00 01 04 05 16 17 20 21
+    //
+    // This pattern is what's called Z-order curve, or Morton order.
+
+    const unsigned int block_width = 8;
+    const unsigned int block_height = 8;
+
+    const unsigned int coarse_x = x & ~7;
+    const unsigned int coarse_y = y & ~7;
+
+    u32 i = VideoCore::MortonInterleave(x, y);
+
+    const unsigned int offset = coarse_x * block_height;
+
+    return (i + offset) * bytes_per_pixel;
+}
+
 } // namespace