mirror of
https://github.com/spice2x/spice2x.github.io.git
synced 2026-10-06 10:08:13 -07:00
bicarus
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.
110 lines
3.1 KiB
NASM
110 lines
3.1 KiB
NASM
;
|
|
; jcgray.asm - grayscale colorspace conversion (AVX2)
|
|
;
|
|
; Copyright (C) 2011, 2016, 2024, D. R. Commander.
|
|
; Copyright (C) 2015, Intel Corporation.
|
|
;
|
|
; Based on the x86 SIMD extension for IJG JPEG library
|
|
; Copyright (C) 1999-2006, MIYASAKA Masaru.
|
|
; For conditions of distribution and use, see copyright notice in jsimdext.inc
|
|
;
|
|
; This file should be assembled with NASM (Netwide Assembler) or Yasm.
|
|
|
|
%include "jsimdext.inc"
|
|
|
|
; --------------------------------------------------------------------------
|
|
|
|
%define SCALEBITS 16
|
|
|
|
F_0_114 equ 7471 ; FIX(0.11400)
|
|
F_0_250 equ 16384 ; FIX(0.25000)
|
|
F_0_299 equ 19595 ; FIX(0.29900)
|
|
F_0_587 equ 38470 ; FIX(0.58700)
|
|
F_0_337 equ (F_0_587 - F_0_250) ; FIX(0.58700) - FIX(0.25000)
|
|
|
|
; --------------------------------------------------------------------------
|
|
SECTION SEG_CONST
|
|
|
|
ALIGNZ 32
|
|
GLOBAL_DATA(jconst_rgb_gray_convert_avx2)
|
|
|
|
EXTN(jconst_rgb_gray_convert_avx2):
|
|
|
|
PW_F0299_F0337 times 8 dw F_0_299, F_0_337
|
|
PW_F0114_F0250 times 8 dw F_0_114, F_0_250
|
|
PD_ONEHALF times 8 dd (1 << (SCALEBITS - 1))
|
|
|
|
ALIGNZ 32
|
|
|
|
; --------------------------------------------------------------------------
|
|
SECTION SEG_TEXT
|
|
BITS 32
|
|
|
|
%include "jcgryext-avx2.asm"
|
|
|
|
%undef RGB_RED
|
|
%undef RGB_GREEN
|
|
%undef RGB_BLUE
|
|
%undef RGB_PIXELSIZE
|
|
%define RGB_RED EXT_RGB_RED
|
|
%define RGB_GREEN EXT_RGB_GREEN
|
|
%define RGB_BLUE EXT_RGB_BLUE
|
|
%define RGB_PIXELSIZE EXT_RGB_PIXELSIZE
|
|
%define jsimd_rgb_gray_convert_avx2 jsimd_extrgb_gray_convert_avx2
|
|
%include "jcgryext-avx2.asm"
|
|
|
|
%undef RGB_RED
|
|
%undef RGB_GREEN
|
|
%undef RGB_BLUE
|
|
%undef RGB_PIXELSIZE
|
|
%define RGB_RED EXT_RGBX_RED
|
|
%define RGB_GREEN EXT_RGBX_GREEN
|
|
%define RGB_BLUE EXT_RGBX_BLUE
|
|
%define RGB_PIXELSIZE EXT_RGBX_PIXELSIZE
|
|
%define jsimd_rgb_gray_convert_avx2 jsimd_extrgbx_gray_convert_avx2
|
|
%include "jcgryext-avx2.asm"
|
|
|
|
%undef RGB_RED
|
|
%undef RGB_GREEN
|
|
%undef RGB_BLUE
|
|
%undef RGB_PIXELSIZE
|
|
%define RGB_RED EXT_BGR_RED
|
|
%define RGB_GREEN EXT_BGR_GREEN
|
|
%define RGB_BLUE EXT_BGR_BLUE
|
|
%define RGB_PIXELSIZE EXT_BGR_PIXELSIZE
|
|
%define jsimd_rgb_gray_convert_avx2 jsimd_extbgr_gray_convert_avx2
|
|
%include "jcgryext-avx2.asm"
|
|
|
|
%undef RGB_RED
|
|
%undef RGB_GREEN
|
|
%undef RGB_BLUE
|
|
%undef RGB_PIXELSIZE
|
|
%define RGB_RED EXT_BGRX_RED
|
|
%define RGB_GREEN EXT_BGRX_GREEN
|
|
%define RGB_BLUE EXT_BGRX_BLUE
|
|
%define RGB_PIXELSIZE EXT_BGRX_PIXELSIZE
|
|
%define jsimd_rgb_gray_convert_avx2 jsimd_extbgrx_gray_convert_avx2
|
|
%include "jcgryext-avx2.asm"
|
|
|
|
%undef RGB_RED
|
|
%undef RGB_GREEN
|
|
%undef RGB_BLUE
|
|
%undef RGB_PIXELSIZE
|
|
%define RGB_RED EXT_XBGR_RED
|
|
%define RGB_GREEN EXT_XBGR_GREEN
|
|
%define RGB_BLUE EXT_XBGR_BLUE
|
|
%define RGB_PIXELSIZE EXT_XBGR_PIXELSIZE
|
|
%define jsimd_rgb_gray_convert_avx2 jsimd_extxbgr_gray_convert_avx2
|
|
%include "jcgryext-avx2.asm"
|
|
|
|
%undef RGB_RED
|
|
%undef RGB_GREEN
|
|
%undef RGB_BLUE
|
|
%undef RGB_PIXELSIZE
|
|
%define RGB_RED EXT_XRGB_RED
|
|
%define RGB_GREEN EXT_XRGB_GREEN
|
|
%define RGB_BLUE EXT_XRGB_BLUE
|
|
%define RGB_PIXELSIZE EXT_XRGB_PIXELSIZE
|
|
%define jsimd_rgb_gray_convert_avx2 jsimd_extxrgb_gray_convert_avx2
|
|
%include "jcgryext-avx2.asm"
|