Files
spice2x.github.io/src/spice2x/external/libjpeg-turbo/jcmainct.c
T
bicarus 8b2f38307b 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

174 lines
5.5 KiB
C

/*
* jcmainct.c
*
* This file was part of the Independent JPEG Group's software:
* Copyright (C) 1994-1996, Thomas G. Lane.
* Lossless JPEG Modifications:
* Copyright (C) 1999, Ken Murchison.
* libjpeg-turbo Modifications:
* Copyright (C) 2022, D. R. Commander.
* For conditions of distribution and use, see the accompanying README.ijg
* file.
*
* This file contains the main buffer controller for compression.
* The main buffer lies between the pre-processor and the JPEG
* compressor proper; it holds downsampled data in the JPEG colorspace.
*/
#define JPEG_INTERNALS
#include "jinclude.h"
#include "jpeglib.h"
#include "jsamplecomp.h"
#if BITS_IN_JSAMPLE != 16 || defined(C_LOSSLESS_SUPPORTED)
/* Private buffer controller object */
typedef struct {
struct jpeg_c_main_controller pub; /* public fields */
JDIMENSION cur_iMCU_row; /* number of current iMCU row */
JDIMENSION rowgroup_ctr; /* counts row groups received in iMCU row */
boolean suspended; /* remember if we suspended output */
J_BUF_MODE pass_mode; /* current operating mode */
/* If using just a strip buffer, this points to the entire set of buffers
* (we allocate one for each component). In the full-image case, this
* points to the currently accessible strips of the virtual arrays.
*/
_JSAMPARRAY buffer[MAX_COMPONENTS];
} my_main_controller;
typedef my_main_controller *my_main_ptr;
/* Forward declarations */
METHODDEF(void) process_data_simple_main(j_compress_ptr cinfo,
_JSAMPARRAY input_buf,
JDIMENSION *in_row_ctr,
JDIMENSION in_rows_avail);
/*
* Initialize for a processing pass.
*/
METHODDEF(void)
start_pass_main(j_compress_ptr cinfo, J_BUF_MODE pass_mode)
{
my_main_ptr main_ptr = (my_main_ptr)cinfo->main;
/* Do nothing in raw-data mode. */
if (cinfo->raw_data_in)
return;
if (pass_mode != JBUF_PASS_THRU)
ERREXIT(cinfo, JERR_BAD_BUFFER_MODE);
main_ptr->cur_iMCU_row = 0; /* initialize counters */
main_ptr->rowgroup_ctr = 0;
main_ptr->suspended = FALSE;
main_ptr->pass_mode = pass_mode; /* save mode for use by process_data */
main_ptr->pub._process_data = process_data_simple_main;
}
/*
* Process some data.
* This routine handles the simple pass-through mode,
* where we have only a strip buffer.
*/
METHODDEF(void)
process_data_simple_main(j_compress_ptr cinfo, _JSAMPARRAY input_buf,
JDIMENSION *in_row_ctr, JDIMENSION in_rows_avail)
{
my_main_ptr main_ptr = (my_main_ptr)cinfo->main;
JDIMENSION data_unit = cinfo->master->lossless ? 1 : DCTSIZE;
while (main_ptr->cur_iMCU_row < cinfo->total_iMCU_rows) {
/* Read input data if we haven't filled the main buffer yet */
if (main_ptr->rowgroup_ctr < data_unit)
(*cinfo->prep->_pre_process_data) (cinfo, input_buf, in_row_ctr,
in_rows_avail, main_ptr->buffer,
&main_ptr->rowgroup_ctr, data_unit);
/* If we don't have a full iMCU row buffered, return to application for
* more data. Note that preprocessor will always pad to fill the iMCU row
* at the bottom of the image.
*/
if (main_ptr->rowgroup_ctr != data_unit)
return;
/* Send the completed row to the compressor */
if (!(*cinfo->coef->_compress_data) (cinfo, main_ptr->buffer)) {
/* If compressor did not consume the whole row, then we must need to
* suspend processing and return to the application. In this situation
* we pretend we didn't yet consume the last input row; otherwise, if
* it happened to be the last row of the image, the application would
* think we were done.
*/
if (!main_ptr->suspended) {
(*in_row_ctr)--;
main_ptr->suspended = TRUE;
}
return;
}
/* We did finish the row. Undo our little suspension hack if a previous
* call suspended; then mark the main buffer empty.
*/
if (main_ptr->suspended) {
(*in_row_ctr)++;
main_ptr->suspended = FALSE;
}
main_ptr->rowgroup_ctr = 0;
main_ptr->cur_iMCU_row++;
}
}
/*
* Initialize main buffer controller.
*/
GLOBAL(void)
_jinit_c_main_controller(j_compress_ptr cinfo, boolean need_full_buffer)
{
my_main_ptr main_ptr;
int ci;
jpeg_component_info *compptr;
int data_unit = cinfo->master->lossless ? 1 : DCTSIZE;
if (cinfo->data_precision != BITS_IN_JSAMPLE)
ERREXIT1(cinfo, JERR_BAD_PRECISION, cinfo->data_precision);
main_ptr = (my_main_ptr)
(*cinfo->mem->alloc_small) ((j_common_ptr)cinfo, JPOOL_IMAGE,
sizeof(my_main_controller));
cinfo->main = (struct jpeg_c_main_controller *)main_ptr;
main_ptr->pub.start_pass = start_pass_main;
/* We don't need to create a buffer in raw-data mode. */
if (cinfo->raw_data_in)
return;
/* Create the buffer. It holds downsampled data, so each component
* may be of a different size.
*/
if (need_full_buffer) {
ERREXIT(cinfo, JERR_BAD_BUFFER_MODE);
} else {
/* Allocate a strip buffer for each component */
for (ci = 0, compptr = cinfo->comp_info; ci < cinfo->num_components;
ci++, compptr++) {
main_ptr->buffer[ci] = (_JSAMPARRAY)(*cinfo->mem->alloc_sarray)
((j_common_ptr)cinfo, JPOOL_IMAGE,
compptr->width_in_blocks * data_unit,
(JDIMENSION)(compptr->v_samp_factor * data_unit));
}
}
}
#endif /* BITS_IN_JSAMPLE != 16 || defined(C_LOSSLESS_SUPPORTED) */