From 6785121aef5dbcb13a9e8a7d0e5b9fcbf344ccfd Mon Sep 17 00:00:00 2001
From: ark <adrian@forn.dk>
Date: Sat, 23 May 2026 12:39:35 +0200
Subject: [PATCH 1/2] perf: AVX2 gather for PixmapRef::gather

---
 src/pipeline/mod.rs | 38 +++++++++++++++++++++++++++-----------
 1 file changed, 27 insertions(+), 11 deletions(-)

diff --git a/src/pipeline/mod.rs b/src/pipeline/mod.rs
index c4c0148..0c3b320 100644
--- a/src/pipeline/mod.rs
+++ b/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],
+                ]
+            }
+        }
     }
 }
 

From d66820e7b586046dc8ab009134720764ad20c38b Mon Sep 17 00:00:00 2001
From: ark <adrian@forn.dk>
Date: Tue, 26 May 2026 21:04:09 +0200
Subject: [PATCH 2/2] refactor: move AVX2 gather intrinsic into wide module

---
 src/pipeline/mod.rs | 30 +++---------------------------
 src/wide/u32x8_t.rs | 28 ++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+), 27 deletions(-)

diff --git a/src/pipeline/mod.rs b/src/pipeline/mod.rs
index 0c3b320..443c45a 100644
--- a/src/pipeline/mod.rs
+++ b/src/pipeline/mod.rs
@@ -155,33 +155,9 @@ impl PixmapRef<'_> {
     #[inline(always)]
     pub(crate) fn gather(&self, index: u32x8) -> [PremultipliedColorU8; highp::STAGE_WIDTH] {
         let pixels = self.pixels();
-        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],
-                ]
-            }
-        }
+        // safety: callers clamp indices to [0, w*h) via gather_ix.
+        let gathered = unsafe { u32x8::gather_u32(pixels.as_ptr() as *const u32, index) };
+        bytemuck::cast(gathered)
     }
 }
 
diff --git a/src/wide/u32x8_t.rs b/src/wide/u32x8_t.rs
index 8b69a0e..4ae0f90 100644
--- a/src/wide/u32x8_t.rs
+++ b/src/wide/u32x8_t.rs
@@ -81,6 +81,34 @@ impl u32x8 {
             }
         }
     }
+
+    /// Gathers 8 u32s from `base[index[i]]`.
+    ///
+    /// # Safety
+    /// Each lane in `index` must be a valid offset (in u32 units) into the
+    /// buffer at `base`. avx2 `vpgatherdd` faults on oob; the scalar fallback
+    /// indexes a raw slice and would UB on oob too.
+    #[inline(always)]
+    pub unsafe fn gather_u32(base: *const u32, index: Self) -> Self {
+        cfg_if::cfg_if! {
+            if #[cfg(all(feature = "simd", target_feature = "avx2"))] {
+                let vindex: __m256i = cast(index);
+                Self(_mm256_i32gather_epi32::<4>(base as *const i32, vindex))
+            } else {
+                let ix: [u32; 8] = bytemuck::cast(index);
+                bytemuck::cast([
+                    *base.add(ix[0] as usize),
+                    *base.add(ix[1] as usize),
+                    *base.add(ix[2] as usize),
+                    *base.add(ix[3] as usize),
+                    *base.add(ix[4] as usize),
+                    *base.add(ix[5] as usize),
+                    *base.add(ix[6] as usize),
+                    *base.add(ix[7] as usize),
+                ])
+            }
+        }
+    }
 }
 
 impl core::ops::Not for u32x8 {