graphics: rewrite screenshot and api capture image processing (#870)

## Link to GitHub Issue or related Pull Request, if one exists #0 ## Description of change Significantly speeds up API screen capture and D3D9 screenshots saving. Two reasons for doing this: 1. We now have a 4K game (GITADORA) and existing capture code was taking multiple seconds. 2. Renewed user interest on streaming as we have a couple more companion apps in active development. **API screen capture (streaming), 1280x720:** 14.3ms -> 6.3ms per frame. Back buffer copies go to pooled `D3DPOOL_SYSTEMMEM` surfaces via `GetRenderTargetData` instead of allocating a lockable render target every frame, and TooJpeg is replaced with libjpeg-turbo (encode 9.8ms -> 3.0ms). MSAA remains unsupported **Screenshots for GITADORA arena model, across 4 screens with one of them 4K**: 4068ms -> 124ms. `D3DXSaveSurfaceToFileA` is replaced with fpng (encode 4043ms -> 76ms) and the screens encode in parallel. Dropping D3DX also removes the `d3dx9_43.dll` ... `d3dx9_24.dll` probing loop, so screenshots no longer fail outright on machines with no D3DX9 runtime installed. Screenshot surfaces are read on the present thread, so no D3D call reaches another thread for screenshots. This fixes a hang in DDR X2 introduced earlier in the branch: its device has no internal locking, and reading the surface on a pool thread while the present thread sat inside `GetRenderTargetData` left the game's own render thread deadlocked. ## Testing - **GITADORA** (arena model, D3D9Ex, 4K main plus three subscreens, windowed) with `-screenshotsub`: three sets of four screenshots, images verified correct. Completion order differs between sets, so the screens really are encoding in parallel. - **LovePlus** (KLP, plain D3D9, 768x1360): covers the inline path used by games whose image processing must not leave the present thread. - **API screen capture** through a companion app: live video correct throughout. - **Print Screen** bound as the screenshot key: the clipboard copy succeeded on every shot. - Quitting the game after capturing leaves no `IDirect3DDevice9` reference count warning, so the pooled readback surfaces are released along with the device.
2026-08-18 00:22:45 -07:00
parent 3863d5a4ed
commit 8b2f38307b
209 changed files with 87027 additions and 1065 deletions
@@ -0,0 +1,148 @@
+/*
+ * jutils.c
+ *
+ * This file was part of the Independent JPEG Group's software:
+ * Copyright (C) 1991-1996, Thomas G. Lane.
+ * libjpeg-turbo Modifications:
+ * Copyright (C) 2022, D. R. Commander.
+ * For conditions of distribution and use, see the accompanying README.ijg
+ * file.
+ *
+ * This file contains tables and miscellaneous utility routines needed
+ * for both compression and decompression.
+ * Note we prefix all global names with "j" to minimize conflicts with
+ * a surrounding application.
+ */
+
+#define JPEG_INTERNALS
+#include "jinclude.h"
+#include "jpeglib.h"
+#include "jsamplecomp.h"
+
+
+#if BITS_IN_JSAMPLE == 8
+
+/*
+ * jpeg_zigzag_order[i] is the zigzag-order position of the i'th element
+ * of a DCT block read in natural order (left to right, top to bottom).
+ */
+
+#if 0                           /* This table is not actually needed in v6a */
+
+const int jpeg_zigzag_order[DCTSIZE2] = {
+   0,  1,  5,  6, 14, 15, 27, 28,
+   2,  4,  7, 13, 16, 26, 29, 42,
+   3,  8, 12, 17, 25, 30, 41, 43,
+   9, 11, 18, 24, 31, 40, 44, 53,
+  10, 19, 23, 32, 39, 45, 52, 54,
+  20, 22, 33, 38, 46, 51, 55, 60,
+  21, 34, 37, 47, 50, 56, 59, 61,
+  35, 36, 48, 49, 57, 58, 62, 63
+};
+
+#endif
+
+/*
+ * jpeg_natural_order[i] is the natural-order position of the i'th element
+ * of zigzag order.
+ *
+ * When reading corrupted data, the Huffman decoders could attempt
+ * to reference an entry beyond the end of this array (if the decoded
+ * zero run length reaches past the end of the block).  To prevent
+ * wild stores without adding an inner-loop test, we put some extra
+ * "63"s after the real entries.  This will cause the extra coefficient
+ * to be stored in location 63 of the block, not somewhere random.
+ * The worst case would be a run-length of 15, which means we need 16
+ * fake entries.
+ */
+
+const int jpeg_natural_order[DCTSIZE2 + 16] = {
+  0,  1,  8, 16,  9,  2,  3, 10,
+ 17, 24, 32, 25, 18, 11,  4,  5,
+ 12, 19, 26, 33, 40, 48, 41, 34,
+ 27, 20, 13,  6,  7, 14, 21, 28,
+ 35, 42, 49, 56, 57, 50, 43, 36,
+ 29, 22, 15, 23, 30, 37, 44, 51,
+ 58, 59, 52, 45, 38, 31, 39, 46,
+ 53, 60, 61, 54, 47, 55, 62, 63,
+ 63, 63, 63, 63, 63, 63, 63, 63, /* extra entries for safety in decoder */
+ 63, 63, 63, 63, 63, 63, 63, 63
+};
+
+
+/*
+ * Arithmetic utilities
+ */
+
+GLOBAL(long)
+jdiv_round_up(long a, long b)
+/* Compute a/b rounded up to next integer, ie, ceil(a/b) */
+/* Assumes a >= 0, b > 0 */
+{
+  return (a + b - 1L) / b;
+}
+
+
+GLOBAL(long)
+jround_up(long a, long b)
+/* Compute a rounded up to next multiple of b, ie, ceil(a/b)*b */
+/* Assumes a >= 0, b > 0 */
+{
+  a += b - 1L;
+  return a - (a % b);
+}
+
+#endif /* BITS_IN_JSAMPLE == 8 */
+
+
+#if BITS_IN_JSAMPLE != 16 || \
+    defined(C_LOSSLESS_SUPPORTED) || defined(D_LOSSLESS_SUPPORTED)
+
+GLOBAL(void)
+_jcopy_sample_rows(_JSAMPARRAY input_array, int source_row,
+                   _JSAMPARRAY output_array, int dest_row, int num_rows,
+                   JDIMENSION num_cols)
+/* Copy some rows of samples from one place to another.
+ * num_rows rows are copied from input_array[source_row++]
+ * to output_array[dest_row++]; these areas may overlap for duplication.
+ * The source and destination arrays must be at least as wide as num_cols.
+ */
+{
+  register _JSAMPROW inptr, outptr;
+  register size_t count = (size_t)(num_cols * sizeof(_JSAMPLE));
+  register int row;
+
+  input_array += source_row;
+  output_array += dest_row;
+
+  for (row = num_rows; row > 0; row--) {
+    inptr = *input_array++;
+    outptr = *output_array++;
+    memcpy(outptr, inptr, count);
+  }
+}
+
+#endif /* BITS_IN_JSAMPLE != 16 ||
+          defined(C_LOSSLESS_SUPPORTED) || defined(D_LOSSLESS_SUPPORTED) */
+
+
+#if BITS_IN_JSAMPLE == 8
+
+GLOBAL(void)
+jcopy_block_row(JBLOCKROW input_row, JBLOCKROW output_row,
+                JDIMENSION num_blocks)
+/* Copy a row of coefficient blocks from one place to another. */
+{
+  memcpy(output_row, input_row, num_blocks * (DCTSIZE2 * sizeof(JCOEF)));
+}
+
+
+GLOBAL(void)
+jzero_far(void *target, size_t bytestozero)
+/* Zero out a chunk of memory. */
+/* This might be sample-array data, block-array data, or alloc_large data. */
+{
+  memset(target, 0, bytestozero);
+}
+
+#endif /* BITS_IN_JSAMPLE == 8 */