MacKwnoX/NX2navi
1
0
Fork 0
mirror of https://github.com/tangerineturtle1/NX2navi.git synced 2026-11-15 19:19:58 -04:00
Code Issues Packages Projects Releases Wiki Activity

Make the wait on the GPU's signal the default again after a frame's first submission.

Browse Source 
The fence's wait cost about 4.5 % of the frames a second, and the player who reported the flicker still sees it and black frames with it. wb_split = 0 keeps the fence's wait for whoever wants to compare.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
This commit is contained in:
chrg6
2026-11-11 05:18:37 -05:00
parent b55d2eb3e1
commit f38428fa4d
3 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
nx2navi.ini.example
View File

@@ -841,7 +841,7 @@
# about 0.7 ms less of every frame in the open (6 % at 85 frames a second), but the game then reads visibility
# results that may be a frame old, and things near the camera can come and go from frame to frame. With shadow
# storage (Linux, Wine) 1 changes nothing; 2 forces it there as well, for tests.
# wb_split = 0
# wb_split = 1
# 1: what the game's shaders write into its memory is copied back from the video card once, and after that only when
# the game's CPU code touches it (most of it never is: 66 MiB a frame in Hyrule Field), for about a third more frames
# a second in open areas. 0: copied back at the end of every GPU submission, as in 0.7.0.

2
runtime/cfg.c
View File

@@ -310,7 +310,7 @@ static const CfgMeta metas[] = {
{"VK_NOOPT", "0", "0|1", RESTART}, // vk_pipeline.c noopt_flag
// diagnostics
{"TRACE", "", NULL, RESTART}, {"FLIGHT", "0", "0|1", RESTART}, {"FLIGHT_SPIKE_MS", "100", "0..60000", RESTART},
{"WB_FENCE_LIMIT", "65536", "0..1073741824", RESTART}, {"WB_MERGE", "1", "0|1", RESTART}, {"WB_EXACT", "1", "0|1", RESTART}, {"MEM_CENSUS", "0", "0|1", RESTART}, {"WB_NO_REUP", "1", "0|1", RESTART}, {"WB_PROBE", "0", "0|1", RESTART}, {"WB_SPLIT", "0", "0|1|2", RESTART}, {"WB_LAZY", WB_LAZY_DEFAULT, "0|1", RESTART}, {"HEAP_LAZY", "0", "0|1", RESTART}, {"WB_LAZY_TOUCH", "0", "0..16", RESTART}, {"WB_LAZY_CHUNK", "0", "0|1", RESTART}, {"FLUSH_UPLOAD", "0", "0|1", RESTART}, {"GPA_TWIN_MAX_KB", "0", "0..1048576", RESTART},
{"WB_FENCE_LIMIT", "65536", "0..1073741824", RESTART}, {"WB_MERGE", "1", "0|1", RESTART}, {"WB_EXACT", "1", "0|1", RESTART}, {"MEM_CENSUS", "0", "0|1", RESTART}, {"WB_NO_REUP", "1", "0|1", RESTART}, {"WB_PROBE", "0", "0|1", RESTART}, {"WB_SPLIT", "1", "0|1|2", RESTART}, {"WB_LAZY", WB_LAZY_DEFAULT, "0|1", RESTART}, {"HEAP_LAZY", "0", "0|1", RESTART}, {"WB_LAZY_TOUCH", "0", "0..16", RESTART}, {"WB_LAZY_CHUNK", "0", "0|1", RESTART}, {"FLUSH_UPLOAD", "0", "0|1", RESTART}, {"GPA_TWIN_MAX_KB", "0", "0..1048576", RESTART},
{"WB_MERGE_MAX", "32", "1..256", RESTART}, {"TEXUP_LOG_MS", "0", "0..60000", RESTART}, // vk_texture.c vk_texstat_frame
{"VMA_BLOCK_MB", "64", "16..256", RESTART}, // vk_headroom.c vk_vma_block_size
{"ASTC_BC_PROBE", "0", "0|1", RESTART}, // vk_texture.c astc_probe_alpha

5
runtime/vk_sync.c
View File

@@ -74,8 +74,9 @@ static int hold_max = -1;
// ---- the executed timeline
// The wait after a frame's first submission (nvn_api_core.c nvnQueueSubmitCommands) is there so that the GPU has run
// that submission's passes before the game rewrites what they read. It is the fence's wait (NX2NAVI_WB_SPLIT=0, the
// default). NX2NAVI_WB_SPLIT=1 makes it a wait on exec_tl, a second timeline that reaches a submission's value when
// that submission's passes before the game rewrites what they read. With NX2NAVI_WB_SPLIT=0 it is the fence's wait.
// The default is 1 again: the fence's wait cost about 4.5 % of the frames a second and the flicker it was put in
// against was still reported with it. NX2NAVI_WB_SPLIT=1 makes it a wait on exec_tl, a second timeline that reaches a submission's value when
// the GPU has executed its own commands: the replay ends the part before the write-backs (vk_exec.c,
// vk_sync_split_exec; vk_memory.c vk_mem_mirror_end: what the shaders wrote into VRAM mirrors goes back to guest
// memory), that part signals exec_tl, and the write-backs follow in a part of their own, which signals the timeline