mirror of
https://github.com/tangerineturtle1/NX2navi.git
synced 2026-11-15 19:19:58 -04:00
a710c6193d
The overlay's rate, lows and graph were fed from the game's present calls. With the replay on the submitting thread, work held for an event is replayed with the next frame, so the calls come in uneven steps although each frame costs about the same: 36 and 9 ms apart in turn in a village, a sawtooth in the graph and a 1% low of 14 fps, while the pictures went out 19.7 ms apart on average and changed by 3.9 ms from one to the next. The present thread now reports each picture (perfmon_shown) and the overlay takes its intervals from that; the game's calls are used only where no present thread reports. A picture that arrives early now waits until seven eighths of the recent interval have passed since the one before (vk_backend.c pace_smooth, NX2NAVI_PACE_SMOOTH, on by default; not with frame generation). In that village the change from one picture to the next went from 3.9 to 3.0 ms at 51 fps both ways, in a graveyard from 3.1 to 2.6 ms at 54. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
63 lines
3.4 KiB
C
63 lines
3.4 KiB
C
// Performance overlay numbers (runtime/perfmon.c): the game's frame rate and frame times, the render thread's waits
|
|
// from the perf counters, and the machine's CPU, memory and GPU load and temperatures. A value the machine does not give
|
|
// is negative.
|
|
//
|
|
// Contains code Copyright (c) 2026 Revivedx and the Savage Wind Recomp contributors, Copyright (c) 2026 Peiikai (MIT; see
|
|
// THIRD_PARTY_NOTICES.md).
|
|
#pragma once
|
|
#include <stdint.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define PERF_HISTORY 120 // frame times kept for the graph
|
|
|
|
typedef struct {
|
|
// the game's frames (presents), over the last second
|
|
float fps, frame_ms_avg, frame_ms_max;
|
|
// fps of the slowest 1% and 0.1% of the frames over the last ten seconds (-1: too few frames yet)
|
|
float low1_fps, low01_fps;
|
|
float frame_ms[PERF_HISTORY]; // oldest first
|
|
// CPU: the whole machine and this process, percent of all logical processors
|
|
char cpu_name[64];
|
|
float cpu_total_pct, cpu_game_pct, cpu_temp_c;
|
|
// memory, MB
|
|
float ram_used_mb, ram_total_mb, ram_game_mb;
|
|
// GPU: load and dedicated memory from the system's counters, temperature, power and clock from NVML (NVIDIA) or
|
|
// ADL (AMD)
|
|
char gpu_name[96];
|
|
float gpu_pct, gpu_temp_c, gpu_power_w, gpu_clock_mhz, vram_used_mb, vram_total_mb;
|
|
// of vram_used_mb, which counts every program on the card, what this process holds (the driver's figure for
|
|
// the device-local heaps, perfmon_set_vram_game); -1 unknown
|
|
float vram_game_mb;
|
|
// per frame, averaged over the last half second: replay (NVN to Vulkan recording), GPU busy time (timestamps; -1
|
|
// without them), the render thread's waits for pipeline builds, shader translation and texture uploads, and the
|
|
// textures uploaded
|
|
float replay_ms, gpu_ms, pipe_wait_ms, xlate_ms, tex_ms, tex_uploads;
|
|
} PerfStats;
|
|
|
|
// Overlay mode 0 off, 1 fps, 2 full (NX2NAVI_PERF_OVERLAY), from the present path when the setting changes. Full starts
|
|
// the machine sampling thread (twice a second) and turns on the event counts and GPU timestamps; leaving full stops
|
|
// them. Off: perf_present skips perfmon_frame and nothing samples.
|
|
void perfmon_mode(int mode);
|
|
// The Vulkan device the game renders on: its name, its LUID (8 bytes; NULL when the driver gives none), its PCI bus
|
|
// (-1 unknown) and its device-local memory. Before the first perfmon_mode(2).
|
|
void perfmon_set_gpu(const char *name, const uint8_t *luid, int pci_bus, float vram_total_mb);
|
|
// How the sampling thread asks for the device-local memory this process holds, in MB (vk_memory.c
|
|
// vk_mem_device_used_mb; negative when the driver does not report it). Called twice a second while the overlay is full.
|
|
void perfmon_set_vram_game(float (*used_mb)(void));
|
|
// A game frame was presented (perf_present, the render thread, only while the overlay is on): the time since the last
|
|
// one, the render thread's waits of this frame (PERF_N entries, host.h), its replay time and the running count of
|
|
// texture uploads.
|
|
// A picture went out (the present thread, vk_backend.c): the overlay's frame times are the intervals between these.
|
|
void perfmon_shown(uint64_t now_ns);
|
|
void perfmon_frame(uint64_t now_ns, uint64_t interval_ns, const uint64_t *wait_ns, uint64_t replay_ns,
|
|
int64_t tex_uploads);
|
|
// The latest numbers (the overlay, present path).
|
|
void perfmon_snapshot(PerfStats *out);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|