Merge pull request #25 from awxkee/dev

SSE/AVX refactoring, improvements
awxkee · Dec 13, 2024 · 746d2df · 746d2df
2 parents c995ed0 + 1b12f00
commit 746d2df
Show file tree

Hide file tree

Showing 48 changed files with 2,648 additions and 1,873 deletions.
diff --git a/.github/workflows/build_push.yml b/.github/workflows/build_push.yml
@@ -44,3 +44,17 @@ jobs:
       - run: cargo fuzz run yuv16_to_rgb16 -- -max_total_time=15
       - run: cargo fuzz run y16_to_rgb16 -- -max_total_time=15
       - run: cargo fuzz run yuv_to_yuyu2 -- -max_total_time=15
+
+  fuzz_encoding:
+    name: Fuzzing encoders
+    strategy:
+      matrix:
+        os: [ ubuntu-latest, macos-latest ]
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@nightly
+      - run: cargo install cargo-fuzz
+      - run: cargo fuzz run rgb_to_yuv -- -max_total_time=15
+      - run: cargo fuzz run rgb_to_y -- -max_total_time=15
+      - run: cargo fuzz run rgb16_to_yuv16 -- -max_total_time=15
diff --git a/README.md b/README.md
@@ -75,19 +75,19 @@ cargo bench --bench yuv8 --manifest-path ./app/Cargo.toml
 
 Tests performed on the image 5763x3842
 
-### Encoding
+### Encoding 8-bit
 
 |                        | time(NEON) | Time(AVX) |
 |------------------------|:----------:|:---------:|
 | utils RGB->YUV 4:2:0   |   3.16ms   |  3.53ms   |
 | libyuv RGB->YUV 4:2:0  |   3.58ms   |  33.87ms  |
 | utils RGBA->YUV 4:2:0  |   4.04ms   |  5.47ms   |
 | libyuv RGBA->YUV 4:2:0 |   4.87ms   |  23.48ms  |
-| utils RGBA->YUV 4:2:2  |   4.37ms   |  7.08ms   |
+| utils RGBA->YUV 4:2:2  |   4.34ms   |  7.08ms   |
 | libyuv RGBA->YUV 4:2:2 |   5.90ms   |  35.23ms  |
 | utils RGBA->YUV 4:4:4  |   4.49ms   |  7.97ms   |
 
-### Decoding
+### Decoding 8-bit
 
 |                        | time(NEON) | Time(AVX) |
 |------------------------|:----------:|:---------:|
@@ -102,6 +102,40 @@ Tests performed on the image 5763x3842
 | utils YUV 4:4:4->RGBA  |   4.79ms   |  7.20ms   |
 | libyuv YUV 4:4:4->RGBA |   4.82ms   |  7.30ms   |
 
+YUV 16 bit-depth conversion
+
+```bash
+cargo bench --bench yuv16 --manifest-path ./app/Cargo.toml
+```
+
+### Encoding 10-bit
+
+10-bit encoding is not implemented in `libyuv`
+
+|                            | time(NEON) | Time(AVX) |
+|----------------------------|:----------:|:---------:|
+| utils RGB10->YUV10 4:2:0   |   4.98ms   |   8.71    |
+| libyuv RGB10->YUV10 4:2:0  |     x      |     x     |
+| utils RGBA10->YUV10 4:2:0  |   6.03ms   |   9.79    |
+| libyuv RGBA10->YUV10 4:2:0 |     x      |     x     |
+| utils RGBA10->YUV10 4:2:2  |   5.99ms   |   13.54   |
+| libyuv RGBA10->YUV10 4:2:2 |     x      |     x     |
+| utils RGBA10->YUV10 4:4:4  |   4.84ms   |   16.88   |
+
+### Decoding 10-bit
+
+|                            | time(NEON) | Time(AVX) |
+|----------------------------|:----------:|:---------:|
+| utils YUV10 4:2:0->RGB10   |   5.64ms   |   12.27   |
+| libyuv YUV10 4:2:0->RGB10  |     -      |     -     |
+| utils YUV10 4:2:0->RGBA10  |   6.26ms   |   14.79   |
+| utils YUV10 4:2:0->RGBA8   |   7.05ms   |   42.44   |
+| libyuv YUV10 4:2:0->RGBA8  |  12.79ms   |   63.02   |
+| utils YUV10 4:2:2->RGBA10  |   6.31ms   |   15.33   |
+| utils YUV10 4:2:2->RGBA8   |   7.33ms   |   13.55   |
+| libyuv YUV10 4:2:2->RGBA10 |  12.62ms   |   58.98   |
+| utils YUV10 4:4:4->RGBA10  |   6.39ms   |   16.39   |
+
 This project is licensed under either of
 
 - BSD-3-Clause License (see [LICENSE](LICENSE.md))