perf: AVX2 gather for PixmapRef::gather

src/pipeline/mod.rs

@@ -154,18 +154,34 @@ pub const STAGES_COUNT: usize = Stage::GammaCompressSrgb as usize + 1;
 impl PixmapRef<'_> {
     #[inline(always)]
     pub(crate) fn gather(&self, index: u32x8) -> [PremultipliedColorU8; highp::STAGE_WIDTH] {
-        let index: [u32; 8] = bytemuck::cast(index);
         let pixels = self.pixels();
-        [
-            pixels[index[0] as usize],
-            pixels[index[1] as usize],
-            pixels[index[2] as usize],
-            pixels[index[3] as usize],
-            pixels[index[4] as usize],
-            pixels[index[5] as usize],
-            pixels[index[6] as usize],
-            pixels[index[7] as usize],
-        ]
+        cfg_if::cfg_if! {
+            if #[cfg(all(feature = "simd", target_feature = "avx2"))] {
+                #[cfg(target_arch = "x86")]
+                use core::arch::x86::*;
+                #[cfg(target_arch = "x86_64")]
+                use core::arch::x86_64::*;
+
+                // gather faults on oob; callers clamp indices to [0, w*h) via gather_ix.
+                unsafe {
+                    let vindex: __m256i = bytemuck::cast(index);
+                    let gathered = _mm256_i32gather_epi32::<4>(pixels.as_ptr() as *const i32, vindex);
+                    bytemuck::cast(gathered)
+                }
+            } else {
+                let index: [u32; 8] = bytemuck::cast(index);
+                [
+                    pixels[index[0] as usize],
+                    pixels[index[1] as usize],
+                    pixels[index[2] as usize],
+                    pixels[index[3] as usize],
+                    pixels[index[4] as usize],
+                    pixels[index[5] as usize],
+                    pixels[index[6] as usize],
+                    pixels[index[7] as usize],
+                ]
+            }
+        }
     }
 }