Files
psxrecomp/runtime/include/gpu_render.h
T
Shokunin 70607b9873 OpenGL backend: record on the emulation thread, replay on the render thread
With the render thread running, the backend's facade table records every
state change, primitive, fill, copy, CPU->VRAM upload (payload copied)
and native-wide call, and the present, into the command ring; the render
thread replays them through the unchanged glb_* functions. With it off
gl_backend_get returns the existing table and nothing new runs.

Sync points: every other GL entry point reached on the emulation thread
(readbacks, savestate restage, render passes, OpenXR, settings,
diagnostics) drains the ring and takes the context (GL_RT_SYNC); the
emulation thread then runs the rest of that frame directly, exactly as
without the thread, and hands the context back at the frame boundary when
the frame may run asynchronously again (no depth24 display, dual-raster,
frame interpolation, render pass, netplay or OpenXR).

Guest-visible VRAM stays gpu.c's array: while the render thread owns the
context, uploads stage from a private copy that receives each payload in
command order. Guest state the backend reads while drawing (per-primitive
widescreen tags, the native-wide fast-path latch) is captured at record
time; host overlays travel with the present; a present that a newer
recorded frame already supersedes is skipped. The emulation thread answers
projective/wide-present/draw-area queries from mirrors of the recorded
calls. The per-frame display-ring readback is queued (fbo_peek_deferred)
instead of being a sync point.

The GL fixtures link render_thread.c and stub the two facade hooks; the
scale fixture also gains the gpu_ws_background_requires_full_composite
stub it was already missing (it failed to link on master).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-07 14:24:50 -07:00

224 lines
12 KiB
C

#ifndef PSX_GPU_RENDER_H
#define PSX_GPU_RENDER_H
/* Renderer facade. gpu.c (command processing) and main.cpp (present) call
* these gr_* entry points instead of a specific backend. The facade
* dispatches to a selected backend: the software rasterizer (gpu_sw_renderer.c,
* the default + fallback) or a hardware OpenGL backend (gpu_gl_renderer.c).
*
* The gr_* signatures mirror the software renderer's interface exactly, so a
* backend is just a table of the same functions. Select the backend with
* gr_set_backend() BEFORE gr_init(); gr_backend() reports the EFFECTIVE backend
* (a requested backend that fails to initialize falls back to software). */
#include <stdint.h>
#ifdef __cplusplus
extern "C" {
#endif
typedef enum {
GR_BACKEND_SOFTWARE = 0,
GR_BACKEND_OPENGL = 1,
GR_BACKEND_VULKAN = 2
} GrBackend;
void gr_set_backend(GrBackend backend); /* call before gr_init() */
GrBackend gr_backend(void); /* effective backend after init */
void gr_refresh_backend(void); /* re-fetch the GL table (render thread) */
/* Lifecycle / global state */
void gr_init(uint16_t *vram);
void gr_set_scale(int scale);
int gr_scale(void);
/* Compile-time ceiling for the OpenGL backend's internal-resolution scale. The
* effective scale is decided at GL context init from the driver's size limits
* and a memory budget (gl_scale_limits.h), so this is only an upper bound.
* Software and Vulkan stay at SW_MAX_INTERNAL_SCALE (4). */
#define GL_MAX_INTERNAL_SCALE 32
void gr_set_texture_filter(int bilinear);
int gr_texture_filter(void);
/* Per-primitive draw state */
void gr_set_semi_transparency(int enabled, int mode);
void gr_set_mask_bits(int set_bit, int check_bit);
void gr_set_texture_window(uint32_t raw);
void gr_set_color_modulation(int r, int g, int b, int raw_texture);
/* Sub-pixel vertex override for the NEXT triangle ([video] geometry_correction).
* x/y are signed 16.16 screen coordinates carrying the projection fraction the
* GTE discarded; the integer positions still passed to gr_draw_*_triangle
* remain authoritative for anything that must stay faithful (dirty-rect
* tracking, the software path's native VRAM write). enabled == 0 clears the
* override. Backends that do not implement it ignore the call, so the integer
* path is what they draw. The override is consumed by the next triangle. */
void gr_set_precise_triangle(int enabled,
int32_t x0, int32_t y0,
int32_t x1, int32_t y1,
int32_t x2, int32_t y2);
/* Perspective-correct UV weights for the NEXT triangle ([video]
* perspective_texturing). q[i] is the normalized 1/z homogeneous weight at
* vertex i. enabled == 0 restores the PS1's affine UV interpolation. */
void gr_set_perspective_triangle(int enabled, float q0, float q1, float q2);
/* Primitives */
void gr_fill_rect(int x, int y, int w, int h, uint16_t color);
void gr_copy_rect(int src_x, int src_y, int dst_x, int dst_y, int w, int h);
void gr_draw_flat_triangle(int x0, int y0, int x1, int y1, int x2, int y2,
uint16_t color);
void gr_draw_gouraud_triangle(int x0, int y0, uint16_t c0,
int x1, int y1, uint16_t c1,
int x2, int y2, uint16_t c2);
void gr_draw_textured_triangle(int x0, int y0, int u0, int v0,
int x1, int y1, int u1, int v1,
int x2, int y2, int u2, int v2,
uint16_t clut_x, uint16_t clut_y,
uint16_t texpage);
void gr_draw_shaded_textured_triangle(int x0, int y0, int u0, int v0,
uint32_t color0,
int x1, int y1, int u1, int v1,
uint32_t color1,
int x2, int y2, int u2, int v2,
uint32_t color2,
uint16_t clut_x, uint16_t clut_y,
uint16_t texpage, int raw_texture);
void gr_draw_flat_rect(int x, int y, int w, int h, uint16_t color);
void gr_draw_textured_rect(int x, int y, int w, int h,
int u, int v,
uint16_t clut_x, uint16_t clut_y,
uint16_t texpage);
void gr_draw_textured_rect_scaled(int x, int y, int w, int h,
int u0, int v0, int u1, int v1,
uint16_t clut_x, uint16_t clut_y,
uint16_t texpage);
void gr_draw_line(int x0, int y0, int x1, int y1, uint16_t color);
void gr_draw_shaded_line(int x0, int y0, uint16_t c0,
int x1, int y1, uint16_t c1);
/* Display readout (present path) */
int gr_render_display(uint32_t *out_pixels, int out_pitch,
int disp_x, int disp_y, int disp_w, int disp_h);
int gr_render_display_hires(uint32_t *out_pixels, int out_pitch,
int disp_x, int disp_y, int disp_w, int disp_h);
/* VRAM transfers */
/* A0 header invalidation precedes payload writes; an interrupted transfer
* cannot leave a prior immutable texture identity resident. */
void gr_vram_upload_begin(int x, int y, int w, int h);
void gr_vram_write(int x, int y, uint16_t pixel);
uint16_t gr_vram_read(int x, int y);
void gr_vram_transfer_in(int x, int y, int w, int h, const uint16_t *data);
void gr_vram_transfer_out(int x, int y, int w, int h, uint16_t *data);
/* Draw area / offset */
void gr_set_draw_area(int x1, int y1, int x2, int y2);
void gr_get_draw_area(int *x1, int *y1, int *x2, int *y2);
void gr_set_draw_offset(int x, int y);
/* Native-wide compositor. gr_wide_supported() reports whether the active
* backend implements it; if not, the others are no-ops and the caller keeps
* the canonical present path. */
int gr_wide_supported(void);
void gr_wide_configure(int wide_w, int offset);
/* Presentation-only origin and padding, independent of the symmetric budget.
* enabled also forbids reusing the canonical center: HUD and world may use
* different origins. Backends must flush queued draws before changing this. */
void gr_wide_set_view(int enabled, int shift, int pad_left, int pad_right);
void gr_wide_set_target(int base_x);
void gr_wide_disable_target(void);
void gr_wide_clear(int base_x, int y, int h, uint16_t color);
/* sides: bit 0 = left synthetic margin, bit 1 = right. */
void gr_wide_clear_margins(int base_x, int y, int h, uint16_t color, int sides);
int gr_wide_dump_full(uint32_t *out, int cap_pixels, int *ow, int *oh, int base_x);
int gr_render_wide_display(uint32_t *out, int pitch, int base_x,
int disp_y, int disp_h);
/* ---- Backend vtable -----------------------------------------------------
* A backend supplies the same set of functions. gpu_gl_renderer.c (Phase 2)
* provides gl_backend_get(); until it does, requesting OpenGL falls back to
* software. Members mirror the gr_* / sw_* signatures 1:1. */
typedef struct GpuRenderBackend {
const char *name;
void (*init)(uint16_t *vram);
void (*set_scale)(int scale);
int (*scale)(void);
void (*set_texture_filter)(int bilinear);
int (*texture_filter)(void);
void (*set_semi_transparency)(int enabled, int mode);
void (*set_mask_bits)(int set_bit, int check_bit);
void (*set_texture_window)(uint32_t raw);
void (*set_color_modulation)(int r, int g, int b, int raw_texture);
/* Optional (NULL = unsupported, facade no-ops): sub-pixel vertex override
* and perspective UV weights for the next triangle. See gr_* above. */
void (*set_precise_triangle)(int enabled,
int32_t x0, int32_t y0,
int32_t x1, int32_t y1,
int32_t x2, int32_t y2);
void (*set_perspective_triangle)(int enabled, float q0, float q1, float q2);
void (*fill_rect)(int x, int y, int w, int h, uint16_t color);
void (*copy_rect)(int src_x, int src_y, int dst_x, int dst_y, int w, int h);
void (*draw_flat_triangle)(int x0, int y0, int x1, int y1, int x2, int y2,
uint16_t color);
void (*draw_gouraud_triangle)(int x0, int y0, uint16_t c0,
int x1, int y1, uint16_t c1,
int x2, int y2, uint16_t c2);
void (*draw_textured_triangle)(int x0, int y0, int u0, int v0,
int x1, int y1, int u1, int v1,
int x2, int y2, int u2, int v2,
uint16_t clut_x, uint16_t clut_y,
uint16_t texpage);
void (*draw_shaded_textured_triangle)(int x0, int y0, int u0, int v0,
uint32_t color0,
int x1, int y1, int u1, int v1,
uint32_t color1,
int x2, int y2, int u2, int v2,
uint32_t color2,
uint16_t clut_x, uint16_t clut_y,
uint16_t texpage, int raw_texture);
void (*draw_flat_rect)(int x, int y, int w, int h, uint16_t color);
void (*draw_textured_rect)(int x, int y, int w, int h, int u, int v,
uint16_t clut_x, uint16_t clut_y,
uint16_t texpage);
void (*draw_textured_rect_scaled)(int x, int y, int w, int h,
int u0, int v0, int u1, int v1,
uint16_t clut_x, uint16_t clut_y,
uint16_t texpage);
void (*draw_line)(int x0, int y0, int x1, int y1, uint16_t color);
void (*draw_shaded_line)(int x0, int y0, uint16_t c0,
int x1, int y1, uint16_t c1);
int (*render_display)(uint32_t *out, int pitch,
int dx, int dy, int dw, int dh);
int (*render_display_hires)(uint32_t *out, int pitch,
int dx, int dy, int dw, int dh);
void (*vram_write)(int x, int y, uint16_t pixel);
uint16_t (*vram_read)(int x, int y);
void (*vram_transfer_in)(int x, int y, int w, int h, const uint16_t *data);
void (*vram_transfer_out)(int x, int y, int w, int h, uint16_t *data);
void (*set_draw_area)(int x1, int y1, int x2, int y2);
void (*get_draw_area)(int *x1, int *y1, int *x2, int *y2);
void (*set_draw_offset)(int x, int y);
/* Native-wide compositor (optional; NULL on backends without it — the
* facade then reports gr_wide_supported() == 0 and the caller keeps the
* canonical present). */
void (*wide_configure)(int wide_w, int offset);
void (*wide_set_view)(int enabled, int shift, int pad_left, int pad_right);
void (*wide_set_target)(int base_x);
void (*wide_disable_target)(void);
void (*wide_clear)(int base_x, int y, int h, uint16_t color);
void (*wide_clear_margins)(int base_x, int y, int h, uint16_t color, int sides);
int (*render_wide_display)(uint32_t *out, int pitch, int base_x,
int disp_y, int disp_h);
/* Dump the ENTIRE wide compositor surface for base_x (all double-buffer
* bands + both margins), g_wide_w x VRAM_H. Debug/inspection only; returns
* pixel count, writes width/height to ow/oh. NULL if unsupported. */
int (*wide_dump_full)(uint32_t *out, int cap_pixels, int *ow, int *oh,
int base_x);
} GpuRenderBackend;
#ifdef __cplusplus
}
#endif
#endif /* PSX_GPU_RENDER_H */