[GPU/WGF] Use ByteAddressBuffer in precompiled shaders

Drivers and hardware may provide more optimal paths for untyped buffers
compared to typed.

Also, ByteAddressBuffer may be bound via a root descriptor in Direct3D 12,
greatly simplifying the binding logic.

ByteAddressBuffer also doesn't have the 128 * 2^20 element count limit that
typed and structured buffers have, and doesn't require the structure stride
to be specified at resource creation time in Direct3D 11.

src/xenia/gpu/shaders/resolve_full_128bpp.xesli

@@ -8,18 +8,17 @@
  */
 
 #include "endian.xesli"
-#define XE_RESOLVE_COPY_EDRAM_IS_UINT_VECTOR_BUFFER
+#define XE_RESOLVE_COPY_EDRAM_BYTE_BUFFER_ALIGNMENT 4
 #include "resolve.xesli"
 
-array_buffer_wo_declare_xe(uint4_xe, xe_resolve_dest, set=1, binding=0, u0,
-                           space0)
+byte_buffer_align16_wo_declare_xe(xe_resolve_dest, set=1, binding=0, u0, space0)
 #define LOCAL_SIZE_X_XE 8
 #define LOCAL_SIZE_Y_XE 8
 #define LOCAL_SIZE_Z_XE 1
 entry_bindings_begin_compute_xe
   XE_RESOLVE_PUSH_CONST_BINDING
   entry_binding_next_xe
-  array_buffer_wo_binding_xe(uint4_xe, xe_resolve_dest, buffer(1))
+  byte_buffer_wo_binding_xe(xe_resolve_dest, buffer(1))
   entry_binding_next_xe
   XE_RESOLVE_COPY_EDRAM_BINDING
 entry_bindings_end_inputs_begin_compute_xe
@@ -36,10 +35,9 @@ entry_inputs_end_code_begin_compute_xe
   }
   float4_xe pixel_0, pixel_1;
   XeResolveLoad2RGBAColors(
-      pass_uint_vector_buffer_xe(xe_resolve_edram)
-      pass_next_after_uint_vector_buffer_xe
+      pass_byte_buffer_xe(xe_resolve_edram) pass_next_after_byte_buffer_xe
       resolve_info,
-      XeResolveColorCopySourcePixelAddressIntsYHalfPixelOffsetFilling(
+      XeResolveColorCopySourcePixelAddressBytesYHalfPixelOffsetFilling(
           resolve_info,
           uint2_xe(max(pixel_index.x,
                        resolve_info.half_pixel_offset_fill_source.x),
@@ -56,14 +54,13 @@ entry_inputs_end_code_begin_compute_xe
     pixel_1 = pixel_0;
   }
   // Only 32_32_32_32_FLOAT color format is 128bpp.
-  uint dest_address =
-      XeResolveDestPixelAddress(resolve_info, pixel_index, 4u) >> 4u;
-  array_buffer_store_xe(
+  uint dest_address = XeResolveDestPixelAddress(resolve_info, pixel_index, 4u);
+  byte_buffer_align16_store16_xe(
       xe_resolve_dest, dest_address,
       XeEndianSwap128(float_bits_to_uint_xe(pixel_0),
                       resolve_info.dest_endian_128));
-  dest_address += XeResolveLocalXAddressXor(1u, 4u) >> 4u;
-  array_buffer_store_xe(
+  dest_address += XeResolveLocalXAddressXor(1u, 4u);
+  byte_buffer_align16_store16_xe(
       xe_resolve_dest, dest_address,
       XeEndianSwap128(float_bits_to_uint_xe(pixel_1),
                       resolve_info.dest_endian_128));