[FFmpeg-devel] [PATCH] Boost FPS and performance: Optimize vertical loop for cache-friendly access [libavcodec/jpeg2000dwt.c:dwt_decode97_float]

[Chitra Dey Sarkar]

Original Implementation:
---------------------------------
In the original implementation, the "VER_SD" section processes image data stored in *data using strided memory access in a vertical fashion This leads to inefficient memory access patterns and cache thrashing due to non-sequential data access across multiple inner loops.

Proposed Refactor:
---------------------------------
The proposed refactor replaces this  by allocating a cache-friendly 2D array buffer. This change eliminates strided memory access across the three inner loops, significantly improving cache locality and reducing cache thrashing.

Additionally, the data is transposed outside the lp loop, which allows for efficient per-line access and write-back to the l buffer, further optimizing performance.

Performance improvements
-------------------------------------------------------
This change results in a substantial performance improvement  Sharing the FPS data benchmarked on our end for the file 'Tears of Steel' using HandBrake

Device / CPU Model                                    Official FPS           Optimized FPS   % Improvement
Surface Laptop 11 (10-core X1P64100, L2: 36MB)                  3.18           6.15                      +93%
Surface Laptop 11(10-core X1P64100, L2: 36MB)     5.16           7.31                      +41%
Surface Laptop 11 (10-core X1P64100, L2: 36MB)                  5.57           9.21                      +65%
AMD Ryzen + NVIDIA RTX 4060 Laptop (12C/24T)                9.97             11.22                   +12%
Mac Mini Apple M4         Chip                           9.00          12.00                   +30%

-------------------------------------------------------------------------------------------------------
---
 libavcodec/jpeg2000dwt.c | 72 +++++++++++++++++++++++++++++++---------
 1 file changed, 57 insertions(+), 15 deletions(-)

diff --git a/libavcodec/jpeg2000dwt.c b/libavcodec/jpeg2000dwt.c index 9ee8122658..45d7897893 100644
--- a/libavcodec/jpeg2000dwt.c
+++ b/libavcodec/jpeg2000dwt.c
@@ -409,6 +409,15 @@ static void dwt_decode97_float(DWTContext *s, float *t)
     /* position at index O of line range [0-5,w+5] cf. extend function */
     line += 5;

+    /* Find the largest lv and lv to allocate a 2D Array*/
+    int max_dim = 0;
+    for (lev = 0; lev < s->ndeclevels; lev++) {
+        if (s->linelen[lev][0]  > max_dim) max_dim = s->linelen[lev][0];
+        if (s->linelen[lev][1] > max_dim) max_dim = s->linelen[lev][1];
+    }
+    float *array2DBlock = av_malloc(max_dim * max_dim * sizeof(float));
+    int useFallback = !array2DBlock;
+
     for (lev = 0; lev < s->ndeclevels; lev++) {
         int lh = s->linelen[lev][0],
             lv = s->linelen[lev][1],
@@ -431,23 +440,56 @@ static void dwt_decode97_float(DWTContext *s, float *t)
             for (i = 0; i < lh; i++)
                 data[w * lp + i] = l[i];
         }
-
-        // VER_SD
-        l = line + mv;
-        for (lp = 0; lp < lh; lp++) {
-            int i, j = 0;
-            // copy with interleaving
-            for (i = mv; i < lv; i += 2, j++)
-                l[i] = data[w * j + lp];
-            for (i = 1 - mv; i < lv; i += 2, j++)
-                l[i] = data[w * j + lp];
-
-            sr_1d97_float(line, mv, mv + lv);
-
-            for (i = 0; i < lv; i++)
-                data[w * i + lp] = l[i];
+
+        if (useFallback) {
+            // VER_SD
+            l = line + mv;
+            for (lp = 0; lp < lh; lp++) {
+                int i, j = 0;
+                // copy with interleaving
+                for (i = mv; i < lv; i += 2, j++)
+                    l[i] = data[w * j + lp];
+                for (i = 1 - mv; i < lv; i += 2, j++)
+                    l[i] = data[w * j + lp];
+
+                sr_1d97_float(line, mv, mv + lv);
+
+                for (i = 0; i < lv; i++)
+                    data[w * i + lp] = l[i];
+            }
+                  }
+        else {
+            /*
+             * This array alleviates cache thrashing caused by vertical strided access across 'data'.
+             * By transposing the data outside the 'lp' loop, the inner loops gain sequential access,
+             * leading to substantial performance improvements.
+            */
+            for (int lp = 0; lp < lv; lp++)
+                for (int j = 0; j < lh; j++)
+                    array2DBlock[j * lv + lp] = data[w * lp + j];
+
+                l = line + mv;
+                for (lp = 0; lp < lh; lp++) {
+                    int i, j = 0;
+                    for (i = mv; i < lv; i += 2, j++)
+                        l[i] = array2DBlock[lp * lv + j];
+                    for (i = 1 - mv; i < lv; i += 2, j++)
+                        l[i] = array2DBlock[lp * lv + j];
+
+                    sr_1d97_float(line, mv, mv + lv);
+
+                    for (i = 0; i < lv; i++)
+                        array2DBlock[lp * lv + i] = l[i];
+                }
+
+            for (int lp = 0; lp < lv; lp++)
+                for (int j = 0; j < lh; j++)
+                    data[w * lp + j] = array2DBlock[j * lv + lp];
         }
     }
+
+    if (!useFallback)
+        av_free(array2DBlock);
 }

 static void sr_1d97_int(int32_t *p, int i0, int i1)
--
2.49.0.vfs.0.3