mirror of
https://github.com/RetroPortingToolKit/psxrecomp
synced 2026-10-26 10:19:47 -04:00
Matthew Stanley
8d58b494b2
Measured Tomba village = 93% textured prims, so draw batching must target the textured path (per-prim uv-limits/texpage/clut/depth move to vertex attributes so consecutive textured prims coalesce into one draw). Flat batching alone would touch only 7% of prims. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
108 lines
5.0 KiB
C
108 lines
5.0 KiB
C
#ifndef PSX_GPU_GL_RENDERER_H
|
|
#define PSX_GPU_GL_RENDERER_H
|
|
|
|
/* GL backend context + present entry points, called from main.cpp's window
|
|
* setup and present path when [video] renderer = "opengl". The backend's
|
|
* rasterization vtable is obtained separately via gl_backend_get()
|
|
* (gpu_render.h). SDL_Window is forward-declared (SDL typedefs it from this
|
|
* same struct tag) so this header needs no SDL include. */
|
|
|
|
#include <stdint.h>
|
|
|
|
struct SDL_Window;
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
/* Create the GL context on a window made with SDL_WINDOW_OPENGL.
|
|
* Returns 1 on success, 0 to fall back to the SDL_Renderer present path. */
|
|
int gl_renderer_init_context(struct SDL_Window *win);
|
|
|
|
/* Present an ARGB8888 image (BGRA byte order) as a letterboxed quad + swap.
|
|
* Used for 24-bit (FMV) frames and the PSX_GL_FORCE_CPU_PRESENT diagnostic.
|
|
* force_4_3 = pillarbox at native 4:3 even on a wide display aspect (FMVs
|
|
* are authored 4:3 and get no GTE squash to compensate the stretch). */
|
|
void gl_renderer_present(const uint32_t *pixels, int src_w, int src_h, int linear,
|
|
int force_4_3);
|
|
|
|
/* Clear to black + swap (display-disabled frame). */
|
|
void gl_renderer_present_blank(void);
|
|
|
|
/* Sync the authoritative FBO down to CPU VRAM if the GPU side is ahead (else
|
|
* a no-op). The 24-bit (FMV) present path, screenshots, and the debug server
|
|
* call this before reading CPU VRAM. */
|
|
void gl_renderer_sync_cpu(void);
|
|
|
|
/* THE present path for 15-bit frames: blit the display region straight from
|
|
* the authoritative VRAM FBO into a letterboxed rect (no readback).
|
|
* Deterministic — used for every 15-bit frame. linear = filter on scale.
|
|
* force_4_3 pins to native 4:3 (15-bit MDEC FMV frames on a wide aspect). */
|
|
void gl_renderer_present_vram(int disp_x, int disp_y, int w, int h, int linear,
|
|
int force_4_3);
|
|
|
|
/* GPU-direct native-wide present: blit the displayed buffer's wide FBO (key =
|
|
* disp_x) straight to the window, no CPU readback. Returns 0 if no wide surface
|
|
* exists for disp_x (caller falls back to the CPU readout path). */
|
|
int gl_renderer_present_wide_fbo(int disp_x, int disp_y, int disp_h, int linear);
|
|
|
|
/* Display aspect for the present letterbox (default 4:3). A wide aspect
|
|
* stretches the 4:3 frame; pair with gte_set_display_aspect (cpu_state.h)
|
|
* for the widescreen field-of-view hack. */
|
|
void gl_renderer_set_display_aspect(int num, int den);
|
|
|
|
void gl_renderer_shutdown(void);
|
|
|
|
/* Diagnostics (debug server): read GPU-side VRAM without touching the CPU
|
|
* array; report coherency flags + dirty rects. fbo_peek returns 0 when the
|
|
* GL pipeline is inactive. */
|
|
int gl_renderer_fbo_peek(int x, int y, int w, int h, uint16_t *out);
|
|
void gl_renderer_diag(int *gpu_dirty, int pending[5], int pack[5]);
|
|
|
|
/* Always-on coherency event ring (debug server "gl_coh_ring"): every upload
|
|
* flush, fill, copy, draw bbox, pack, full readback, present, and probe
|
|
* perturbation, with rect + frame. An op that flushes internally records its
|
|
* own event AFTER the FLUSH it caused (the event after a FLUSH = trigger). */
|
|
enum {
|
|
GL_COH_FLUSH = 1, /* CPU->FBO upload flush (pending box) */
|
|
GL_COH_FILL = 2, /* GP0(02) fill rect */
|
|
GL_COH_COPY_SRC = 3, /* GP0(80) copy, source rect */
|
|
GL_COH_COPY = 4, /* GP0(80) copy, dest rect */
|
|
GL_COH_DRAW = 5, /* drawn prim bbox (clipped to draw area) */
|
|
GL_COH_PACK = 6, /* hr FBO -> raw mirror pack (dirty box) */
|
|
GL_COH_ENSURE = 7, /* full FBO -> CPU VRAM readback */
|
|
GL_COH_PRESENT = 8, /* 15-bit present blit (display rect) */
|
|
GL_COH_UPLOAD = 9, /* bulk CPU->VRAM transfer_in dest rect */
|
|
GL_COH_PEEK = 10, /* gl_fbo_peek probe (perturbs: flushes) */
|
|
GL_COH_DIFF = 11, /* gl_vram_diff probe (perturbs: flushes) */
|
|
};
|
|
|
|
typedef struct {
|
|
uint32_t frame;
|
|
uint8_t kind;
|
|
int16_t x0, y0, x1, y1; /* native VRAM coords, inclusive */
|
|
} GlCohEvent;
|
|
|
|
uint64_t gl_renderer_coh_total(void);
|
|
/* Fetch event by absolute sequence number; 0 if evicted or out of range. */
|
|
int gl_renderer_coh_get(uint64_t seq, GlCohEvent *out);
|
|
|
|
/* frame_perf: aggregate the per-frame GPU/CPU phase-timing ring (debug server
|
|
* "frame_perf"). wide_filter: -1 = all frames, 0 = 4:3 present, 1 = native-wide.
|
|
* Fills out[9]: [0]=count, [1]=total_ms avg, [2]=total_ms max, [3]=emu_cpu_ms avg
|
|
* (frame minus the present call), [4]=present_wall_ms avg, [5]=scene_gpu_ms avg,
|
|
* [6]=scene_gpu_ms max, [7]=present_gpu_ms avg, [8]=present_gpu_ms max,
|
|
* [9]=scene primitives/frame avg (pre double-draw). GPU phases are true
|
|
* GL_TIME_ELAPSED times (CPU-overhead independent). Returns the count. */
|
|
int gl_renderer_perf_aggregate(int wide_filter, double out[10]);
|
|
|
|
/* Cumulative textured fraction of scene primitives since boot (flat vs textured
|
|
* batching decision). Sets *out_tex_frac; returns total prim count. */
|
|
uint64_t gl_renderer_perf_prim_split(double *out_tex_frac);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* PSX_GPU_GL_RENDERER_H */
|