bicarusandGitHub
8b2f38307b
## 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.
146 lines
4.4 KiB
C
146 lines
4.4 KiB
C
/*
|
|
* jdcolext.c
|
|
*
|
|
* This file was part of the Independent JPEG Group's software:
|
|
* Copyright (C) 1991-1997, Thomas G. Lane.
|
|
* libjpeg-turbo Modifications:
|
|
* Copyright (C) 2009, 2011, 2015, 2022-2023, D. R. Commander.
|
|
* For conditions of distribution and use, see the accompanying README.ijg
|
|
* file.
|
|
*
|
|
* This file contains output colorspace conversion routines.
|
|
*/
|
|
|
|
|
|
/* This file is included by jdcolor.c */
|
|
|
|
|
|
/*
|
|
* Convert some rows of samples to the output colorspace.
|
|
*
|
|
* Note that we change from noninterleaved, one-plane-per-component format
|
|
* to interleaved-pixel format. The output buffer is therefore three times
|
|
* as wide as the input buffer.
|
|
* A starting row offset is provided only for the input buffer. The caller
|
|
* can easily adjust the passed output_buf value to accommodate any row
|
|
* offset required on that side.
|
|
*/
|
|
|
|
INLINE
|
|
LOCAL(void)
|
|
ycc_rgb_convert_internal(j_decompress_ptr cinfo, _JSAMPIMAGE input_buf,
|
|
JDIMENSION input_row, _JSAMPARRAY output_buf,
|
|
int num_rows)
|
|
{
|
|
#if BITS_IN_JSAMPLE != 16
|
|
my_cconvert_ptr cconvert = (my_cconvert_ptr)cinfo->cconvert;
|
|
register int y, cb, cr;
|
|
register _JSAMPROW outptr;
|
|
register _JSAMPROW inptr0, inptr1, inptr2;
|
|
register JDIMENSION col;
|
|
JDIMENSION num_cols = cinfo->output_width;
|
|
/* copy these pointers into registers if possible */
|
|
register _JSAMPLE *range_limit = (_JSAMPLE *)cinfo->sample_range_limit;
|
|
register int *Crrtab = cconvert->Cr_r_tab;
|
|
register int *Cbbtab = cconvert->Cb_b_tab;
|
|
register JLONG *Crgtab = cconvert->Cr_g_tab;
|
|
register JLONG *Cbgtab = cconvert->Cb_g_tab;
|
|
SHIFT_TEMPS
|
|
|
|
while (--num_rows >= 0) {
|
|
inptr0 = input_buf[0][input_row];
|
|
inptr1 = input_buf[1][input_row];
|
|
inptr2 = input_buf[2][input_row];
|
|
input_row++;
|
|
outptr = *output_buf++;
|
|
for (col = 0; col < num_cols; col++) {
|
|
y = inptr0[col];
|
|
cb = inptr1[col];
|
|
cr = inptr2[col];
|
|
/* Range-limiting is essential due to noise introduced by DCT losses. */
|
|
outptr[RGB_RED] = range_limit[y + Crrtab[cr]];
|
|
outptr[RGB_GREEN] = range_limit[y +
|
|
((int)RIGHT_SHIFT(Cbgtab[cb] + Crgtab[cr],
|
|
SCALEBITS))];
|
|
outptr[RGB_BLUE] = range_limit[y + Cbbtab[cb]];
|
|
/* Set unused byte to _MAXJSAMPLE so it can be interpreted as an */
|
|
/* opaque alpha channel value */
|
|
#ifdef RGB_ALPHA
|
|
outptr[RGB_ALPHA] = _MAXJSAMPLE;
|
|
#endif
|
|
outptr += RGB_PIXELSIZE;
|
|
}
|
|
}
|
|
#else
|
|
ERREXIT(cinfo, JERR_CONVERSION_NOTIMPL);
|
|
#endif
|
|
}
|
|
|
|
|
|
/*
|
|
* Convert grayscale to RGB: just duplicate the graylevel three times.
|
|
* This is provided to support applications that don't want to cope
|
|
* with grayscale as a separate case.
|
|
*/
|
|
|
|
INLINE
|
|
LOCAL(void)
|
|
gray_rgb_convert_internal(j_decompress_ptr cinfo, _JSAMPIMAGE input_buf,
|
|
JDIMENSION input_row, _JSAMPARRAY output_buf,
|
|
int num_rows)
|
|
{
|
|
register _JSAMPROW inptr, outptr;
|
|
register JDIMENSION col;
|
|
JDIMENSION num_cols = cinfo->output_width;
|
|
|
|
while (--num_rows >= 0) {
|
|
inptr = input_buf[0][input_row++];
|
|
outptr = *output_buf++;
|
|
for (col = 0; col < num_cols; col++) {
|
|
outptr[RGB_RED] = outptr[RGB_GREEN] = outptr[RGB_BLUE] = inptr[col];
|
|
/* Set unused byte to _MAXJSAMPLE so it can be interpreted as an */
|
|
/* opaque alpha channel value */
|
|
#ifdef RGB_ALPHA
|
|
outptr[RGB_ALPHA] = _MAXJSAMPLE;
|
|
#endif
|
|
outptr += RGB_PIXELSIZE;
|
|
}
|
|
}
|
|
}
|
|
|
|
|
|
/*
|
|
* Convert RGB to extended RGB: just swap the order of source pixels
|
|
*/
|
|
|
|
INLINE
|
|
LOCAL(void)
|
|
rgb_rgb_convert_internal(j_decompress_ptr cinfo, _JSAMPIMAGE input_buf,
|
|
JDIMENSION input_row, _JSAMPARRAY output_buf,
|
|
int num_rows)
|
|
{
|
|
register _JSAMPROW inptr0, inptr1, inptr2;
|
|
register _JSAMPROW outptr;
|
|
register JDIMENSION col;
|
|
JDIMENSION num_cols = cinfo->output_width;
|
|
|
|
while (--num_rows >= 0) {
|
|
inptr0 = input_buf[0][input_row];
|
|
inptr1 = input_buf[1][input_row];
|
|
inptr2 = input_buf[2][input_row];
|
|
input_row++;
|
|
outptr = *output_buf++;
|
|
for (col = 0; col < num_cols; col++) {
|
|
outptr[RGB_RED] = inptr0[col];
|
|
outptr[RGB_GREEN] = inptr1[col];
|
|
outptr[RGB_BLUE] = inptr2[col];
|
|
/* Set unused byte to _MAXJSAMPLE so it can be interpreted as an */
|
|
/* opaque alpha channel value */
|
|
#ifdef RGB_ALPHA
|
|
outptr[RGB_ALPHA] = _MAXJSAMPLE;
|
|
#endif
|
|
outptr += RGB_PIXELSIZE;
|
|
}
|
|
}
|
|
}
|