Support for SIMD operations for RGG1555

Description

Up to 3x the performance for RGG1555 with SIMD operations. The current implementation is hardcoded for 16 bytes at a time (128 bits). Still requires some testing and validation for AVX2 and AVX512.

Fixes #45 (closed)

src/ppu.rs

@@ -12,7 +12,7 @@ use std::{
 use crate::{
     gb::{GameBoyConfig, GameBoyMode},
     mmu::BusComponent,
-    util::SharedThread,
+    util::{copy_fast, SharedThread},
     warnln,
 };
 
@@ -2091,6 +2091,9 @@ impl Ppu {
         (r << 11) | (g << 5) | b
     }
 
+    /// Converts an array of RGB888 pixels to RGB565 format using a scalar implementation.
+    ///
+    /// This method should provide the same results as the SIMD implementation.
     pub fn rgb888_to_rgb1555_scalar(rgb888_pixels: &[u8], rgb1555_pixels: &mut [u8]) {
         for index in 0..rgb888_pixels.len() / RGB_SIZE {
             let (r, g, b) = (
@@ -2099,12 +2102,16 @@ impl Ppu {
                 rgb888_pixels[index * RGB_SIZE + 2],
             );
             let rgb1555 = Self::rgb888_to_rgb1555(r, g, b);
-            rgb1555_pixels[index * RGB1555_SIZE] = rgb1555[0];
-            rgb1555_pixels[index * RGB1555_SIZE + 1] = rgb1555[1];
+            copy_fast(
+                &rgb1555,
+                &mut rgb1555_pixels[index * RGB1555_SIZE..index * RGB1555_SIZE + 1],
+                RGB565_SIZE,
+            )
         }
     }
 
     /// Converts an array of RGB888 pixels to RGB1555 format using SIMD.
+    ///
     /// This method is only available when the `simd` feature is enabled.
     ///
     /// Note: The length of `rgb888_pixels` must be a multiple of 3, and
@@ -2215,8 +2222,11 @@ impl Ppu {
             );
             let rgb1555 = Self::rgb888_to_rgb1555(r, g, b);
             let output_offset = offset_rgb1555 + i * RGB565_SIZE;
-            rgb1555_pixels[output_offset] = rgb1555[0];
-            rgb1555_pixels[output_offset + 1] = rgb1555[1];
+            copy_fast(
+                &rgb1555,
+                &mut rgb1555_pixels[output_offset..output_offset + 1],
+                RGB565_SIZE,
+            );
         }
     }
 }