From 862c80382ccd9e81d0d586f6f65d9931797f3f6c Mon Sep 17 00:00:00 2001
From: Aarni Koskela <akx@iki.fi>
Date: Wed, 2 Sep 2026 13:19:59 +0300
Subject: [PATCH 1/2] Benchmarks: split PATHS to LOAD_PATHS/SAVE_PATHS;
 benchmark uncompressed DDS

---
 Tests/benchmarks.py | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/Tests/benchmarks.py b/Tests/benchmarks.py
index 11ed3cf743b..f00f2a895c6 100644
--- a/Tests/benchmarks.py
+++ b/Tests/benchmarks.py
@@ -45,9 +45,13 @@
 
 # For benchmarks that act on test fixture files, these are the paths loaded.
 IMAGES_PATH = pathlib.Path(__file__).parent / "images"
-PATHS = [
+SAVE_PATHS = [
     IMAGES_PATH / "flower2.jpg",
 ]
+LOAD_PATHS = [
+    *SAVE_PATHS,
+    IMAGES_PATH / "uncompressed_rgb.dds",
+]
 
 # These are derived from the other configuration, above.
 RGB_MODES = [mode for mode in MODES if mode.startswith("RGB")]
@@ -567,7 +571,7 @@ def test_draw_lines_blend(
 
 
 @pytest.mark.benchmark(group="load")
-@pytest.mark.parametrize("path", PATHS, ids=_format_path)
+@pytest.mark.parametrize("path", LOAD_PATHS, ids=_format_path)
 def test_load(bench: BenchmarkFixture, path: pathlib.Path) -> None:
     def run() -> None:
         with Image.open(path) as im:
@@ -577,7 +581,7 @@ def run() -> None:
 
 
 @pytest.mark.benchmark(group="save")
-@pytest.mark.parametrize("path", PATHS, ids=_format_path)
+@pytest.mark.parametrize("path", SAVE_PATHS, ids=_format_path)
 def test_save_jpeg(bench: BenchmarkFixture, path: pathlib.Path) -> None:
     with Image.open(path) as im:
         im.load()
@@ -853,7 +857,7 @@ def test_quantize_grayscale_to_palette(
     "source_type",
     [
         "synthetic",
-        *(pytest.param(image, id=f"{image.stem}") for image in PATHS),
+        *(pytest.param(image, id=f"{image.stem}") for image in LOAD_PATHS),
     ],
 )
 @pytest.mark.parametrize("palette_type", ["exact", "grayscale", "web"])

From 57f358fee152931838cf41bd170ba2491563d4a3 Mon Sep 17 00:00:00 2001
From: Aarni Koskela <akx@iki.fi>
Date: Wed, 2 Sep 2026 14:00:15 +0300
Subject: [PATCH 2/2] Speed up uncompressed DDS reading

---
 src/PIL/DdsImagePlugin.py | 43 +++++++++++++++++++++++++++------------
 1 file changed, 30 insertions(+), 13 deletions(-)

diff --git a/src/PIL/DdsImagePlugin.py b/src/PIL/DdsImagePlugin.py
index e09a2b867a1..e2e2effabbb 100644
--- a/src/PIL/DdsImagePlugin.py
+++ b/src/PIL/DdsImagePlugin.py
@@ -18,7 +18,6 @@
 
 from . import Image, ImageFile, ImagePalette
 from ._binary import i32le as i32
-from ._binary import o8
 from ._binary import o32le as o32
 
 TYPE_CHECKING = False
@@ -514,20 +513,38 @@ def decode(self, buffer: Image.DecoderInput) -> tuple[int, int]:
             mask_totals.append(mask >> offset)
 
         assert self.fd is not None
-        dest_length = self.state.xsize * self.state.ysize * len(masks)
-        while len(data) < dest_length:
-            bytes_read = self.fd.read(bytecount)
-            if len(bytes_read) < bytecount:
+        pixel_count = self.state.xsize * self.state.ysize
+
+        src = bytearray()
+        needed = pixel_count * bytecount
+        while len(src) < needed:
+            chunk = self.fd.read(min(needed - len(src), ImageFile.SAFEBLOCK))
+            if not chunk:
                 break
-            value = int.from_bytes(bytes_read, "little")
-            for i, mask in enumerate(masks):
-                masked_value = value & mask
+            src += chunk
+        pixel_count = min(pixel_count, len(src) // bytecount)
+        src_length = pixel_count * bytecount
+        del src[src_length:]
+
+        nmasks = len(masks)
+        data = bytearray(pixel_count * nmasks)
+        for i, (mask, offset, total) in enumerate(
+            zip(masks, mask_offsets, mask_totals)
+        ):
+            if not total:  # Nothing to do here
+                continue
+            if total == 0xFF and offset % 8 == 0:  # Whole byte, fast path
+                data[i::nmasks] = src[offset // 8 :: bytecount]
+                continue
+            values = (
+                int.from_bytes(src[p : p + bytecount], "little")
+                for p in range(0, src_length, bytecount)
+            )
+            data[i::nmasks] = bytes(
                 # Remove the zero padding, and scale it to 8 bits
-                data += o8(
-                    int(((masked_value >> mask_offsets[i]) / mask_totals[i]) * 255)
-                    if mask_totals[i]
-                    else 0
-                )
+                int((((value & mask) >> offset) / total) * 255)
+                for value in values
+            )
         self.set_as_raw(data)
         return -1, 0