mirror of
https://github.com/tangerineturtle1/NX2navi.git
synced 2026-11-16 18:09:58 -04:00
Correct what a review of this intake's commits found.
A second reading of the commits taken in from pull requests found these, each traced in the code: - heap_lazy: the camera speed's search read the whole heap, which with the setting on committed every page and undid what it saves; a scan now steps over the pages the lazy heap never committed (mem_untouched_run). tests/frame_step_check.py and tests/save_share_check.py no longer linked (frame_rate.c and fs_host.c call the new memory functions; the second also missed mem_probing before); both pass again. The settings text says that with the setting on a PC out of commit ends the game in play, not at start, and the census comment is back over its own function. - Pipeline libraries on AMD's older Windows driver: the condition is the driver for RDNA 2 and older (RX 400 to RX 6000), not RX 5000 and RX 6000 only, and the texts named a price the code does not have. With libraries off a new pipeline is built by a worker while its draw is left out, and the start waits for every recorded pipeline instead of 20 s at most. The texts say so, and that the finding is one player's on one card. The menu strings nothing shows are as they were. - Page file hint: it comes only when Windows sizes every page file, and it names the initial size and the automatic management that must be unticked first. - Frame generation note: it keeps "needs an RTX 40 or newer" for the players it is right for and points the others to the log; the bridge's line says it is Streamline's general support check. - Comments and settings texts that still described the old behaviour: the process commit bound, the wait with shadow storage, the scratch's least size, the action prompt under auto. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com> (cherry picked from commit 19f03aa01b26d6e17fb5fc70ad987aa8c68e8225)
This commit is contained in:
@@ -1,6 +1,8 @@
|
||||
// The action prompt's diamond of face buttons for the pad layout at start. The action prompt (top right) shows the
|
||||
// four face buttons as a diamond in the Switch's places, A on the right. Under a layout by label (NX2NAVI_PAD_LAYOUT =
|
||||
// xbox, playstation or auto; input_map.c input_pad_layout_pick) A is the bottom button, so romfs.c
|
||||
// xbox or playstation; input_map.c input_pad_layout_pick) A is the bottom button, and auto is treated the same at
|
||||
// start, when no pad is open yet: a pad that labels its right button A then plays by position under auto and sees
|
||||
// the diamond the other way round, which docs/controls.md says and nintendo avoids. So romfs.c
|
||||
// (action_prompt_overlay) serves the shared interface layouts with the diamond laid out as such a pad has its buttons:
|
||||
// A bottom, B right, X left, Y top. The game reads the layouts once at start, so a change of layout shows after a
|
||||
// restart.
|
||||
|
||||
@@ -183,6 +183,11 @@ static int rewrite(float k, float to, int fresh) {
|
||||
continue;
|
||||
}
|
||||
while (a < stop) {
|
||||
uint64_t skip = mem_untouched_run(a, stop); // heap pages the lazy heap never committed hold nothing
|
||||
if (skip) {
|
||||
a = skip;
|
||||
continue;
|
||||
}
|
||||
uint64_t n = stop - a < PIECE ? stop - a : PIECE;
|
||||
if (n >= len && mem_read_hold(a, n)) {
|
||||
const uint8_t *p = (const uint8_t *)(uintptr_t)a, *e = p + n;
|
||||
|
||||
@@ -254,7 +254,7 @@ static const CfgMeta metas[] = {
|
||||
{"GATE_WAIT_MS", "10", "0..100", RESTART}, // vk_exec.c vk_exec_gate_wait
|
||||
{"LIB_PREBUILD", "1", "0|1", RESTART}, {"LIB_PREBUILD_THREADS", "", "1..64", RESTART},
|
||||
{"LIB_WARM", "1", "0|1|force", RESTART}, // vk_pipeline.c lw_start: the driver's cache of stage libraries, warmed when cold
|
||||
{"PIPE_PREBUILD", "1", "0|1", RESTART}, {"PREWARM_XLATE", "", "1..64", RESTART}, {"GPL", "", "0|1", RESTART}, // vk_caps.c vk_caps_gpl: by the driver, off with AMD's for RDNA 1 and 2
|
||||
{"PIPE_PREBUILD", "1", "0|1", RESTART}, {"PREWARM_XLATE", "", "1..64", RESTART}, {"GPL", "", "0|1", RESTART}, // vk_caps.c vk_caps_gpl: by the driver, off with AMD's for RDNA 2 and older
|
||||
{"LIB_PREBUILD_BIG_BG", "1", "0|1", RESTART}, {"PIPE_FEEDBACK", "1", "0|1|2", RESTART},
|
||||
{"PIPELINE_CACHE_MAX_MB", "512", "0..65536", RESTART}, {"PIPE_BINARIES", "0", "0|1", RESTART}, {"ONESHOT_WAIT_MS", "30000", "0..60000", RESTART}, {"ONESHOT_BUDGET", "1", "0|1", RESTART}, {"PIPE_BINARIES_MAX_MB", "1024", "0..65536", RESTART}, {"BIG_BUILD_FREE_MB", "8192", "0..262144", RESTART},
|
||||
{"BIG_BUILD_MAX_MB", "4096", "0..262144", RESTART},
|
||||
|
||||
@@ -165,7 +165,7 @@ extern "C" NX2SL_API void nx2sl_log_unavailable(VkPhysicalDevice physical) {
|
||||
sl::AdapterInfo adapter{};
|
||||
adapter.vkPhysicalDevice = physical;
|
||||
sl::Result r = supported(sl::kFeatureDLSS_G, adapter);
|
||||
say("dlssg: frame generation support on the selected Vulkan adapter: %s (%d)", sl::getResultAsStr(r), (int)r);
|
||||
say("dlssg: Streamline's support check for frame generation: %s (%d)", sl::getResultAsStr(r), (int)r);
|
||||
}
|
||||
|
||||
// Streamline sets Reflex's mode on the swapchain it was told of last (VK_NV_low_latency2) and drops it while there is
|
||||
|
||||
@@ -44,7 +44,8 @@ typedef PFN_vkGetInstanceProcAddr (*PFN_nx2sl_instance_proc)(void);
|
||||
typedef PFN_vkGetDeviceProcAddr (*PFN_nx2sl_device_proc)(void);
|
||||
// 1 when DLSS-G loaded and supports this GPU (after the device exists)
|
||||
typedef int (*PFN_nx2sl_available)(void);
|
||||
// Optional: log Streamline's support result on the selected Vulkan device after availability failed.
|
||||
// Optional: log Streamline's support result for frame generation after availability failed (its general check of
|
||||
// the system, driver and adapters: Streamline looks at one adapter only when given its LUID, which Vulkan has not).
|
||||
typedef void (*PFN_nx2sl_log_unavailable)(VkPhysicalDevice physical);
|
||||
// Reflex's low-latency mode, 0 off, 1 on, 2 on with boost: after the device, and after each swapchain the game creates
|
||||
// through the interposer (the mode is the swapchain's)
|
||||
|
||||
@@ -227,6 +227,8 @@ void mem_thaw(uint64_t a, uint64_t n); // makes the frozen r
|
||||
// also commits pages the lazy heap left reserved
|
||||
void mem_kernel_access(uint64_t a, uint64_t n); // NX2NAVI_HEAP_LAZY: commits the reserved heap pages of
|
||||
// [a, a+n) before the kernel reads them (a file write)
|
||||
uint64_t mem_untouched_run(uint64_t a, uint64_t end); // NX2NAVI_HEAP_LAZY: the end of the run of heap pages at a
|
||||
// that were never committed (a scan steps over it), else 0
|
||||
int mem_host_readable(uint64_t a, uint64_t n); // plat_mem_readable that first commits the untouched
|
||||
// pages of the lazy heap in [a, a+n), which read zero
|
||||
void mem_freeze_stats(uint64_t *frozen, uint64_t *freezes, uint64_t *fault_thaws, uint64_t *other_thaws);
|
||||
|
||||
@@ -658,6 +658,15 @@ void mem_kernel_access(uint64_t a, uint64_t n) {
|
||||
plat_mutex_unlock(&frz_lock);
|
||||
}
|
||||
|
||||
// For a host scan of guest memory (camera_speed.c rewrite): the end of the run of pages at a that the lazy heap left
|
||||
// reserved, at most end, or 0 when the page at a is not such a page. Nothing was ever written there, so a scan steps
|
||||
// over the run; reading it would commit every page of the heap and undo what the setting saves.
|
||||
uint64_t mem_untouched_run(uint64_t a, uint64_t end) {
|
||||
if (!heap_lazy || a < L.heap.base || a >= L.heap.base + L.heap.size) return 0;
|
||||
uint64_t y, x = a & ~(PAGE - 1);
|
||||
return plat_mem_state(x, end, &y) == PLAT_MEM_RESERVED && y > a ? y : 0;
|
||||
}
|
||||
|
||||
// plat_mem_readable for a pointer the host is about to read: untouched heap pages of a lazy heap count as readable
|
||||
// (they are committed here, and read zero as they would have).
|
||||
int mem_host_readable(uint64_t a, uint64_t n) {
|
||||
@@ -1417,9 +1426,6 @@ void mem_kernel_free(void *p, uint64_t size) {
|
||||
plat_mutex_unlock(&klock);
|
||||
}
|
||||
|
||||
// NX2NAVI_TRACE=perf: how many bytes of each guest region are committed, so a process that has grown says which region
|
||||
// holds the memory. A region is reserved whole at start-up and committed page by page, so the walk reads each run of
|
||||
// pages of the same state; the alias window is the largest and costs the most steps when it is full.
|
||||
// NX2NAVI_TRACE=perf: what the lazy heap's first-use faults cost since the last line (perf.c, every perf window that had
|
||||
// some), so that a hitch can be told from them: the time includes the wait for frz_lock.
|
||||
void mem_lazy_heap_report(uint64_t frame) {
|
||||
@@ -1437,6 +1443,9 @@ void mem_lazy_heap_report(uint64_t frame) {
|
||||
faults_prv = faults, bytes_prv = bytes;
|
||||
}
|
||||
|
||||
// NX2NAVI_TRACE=perf: how many bytes of each guest region are committed, so a process that has grown says which region
|
||||
// holds the memory. A region is reserved whole at start-up and committed page by page, so the walk reads each run of
|
||||
// pages of the same state; the alias window is the largest and costs the most steps when it is full.
|
||||
void mem_guest_census(uint64_t frame) {
|
||||
const RtGuestLayout *g = mem_layout();
|
||||
const struct { const char *name; RtRange r; } reg[] = {
|
||||
|
||||
@@ -700,8 +700,10 @@ NVN_API(nvnQueueSubmitCommands) {
|
||||
// NX2NAVI_SUBMIT_FINISH=<mask>: bit i waits after the i-th submission of a frame (default 0x1); a plain 1 waits
|
||||
// after every submission, 0 never.
|
||||
// The wait is for the submission's passes, which is what the rewrite races with: exec_wait leaves out the
|
||||
// write-backs of what they wrote (vk_sync.c exec_tl), which nothing here needs before the game goes on. The fences
|
||||
// the game itself waits on cover them as before.
|
||||
// write-backs of what they wrote (vk_sync.c exec_tl), which nothing here needs before the game goes on where the
|
||||
// pools are imports or mirrors. With shadow storage the write-backs reach guest memory later and the game must
|
||||
// not rewrite a pool before them, so there the wait covers them (vk_sync_exec_wait). The fences the game itself
|
||||
// waits on cover them as before.
|
||||
static long long finish_mask = -2;
|
||||
if (finish_mask == -2) {
|
||||
const char *e = cfg_get("NX2NAVI_SUBMIT_FINISH");
|
||||
|
||||
@@ -2229,7 +2229,7 @@ int plat_commit_note(char *out, size_t cap) {
|
||||
// The cgroup's memory.current and MemAvailable count system memory only: a graphics card's own memory is in neither.
|
||||
int plat_commit_counts_vram(void) { return 0; }
|
||||
|
||||
// Swap is not a page file Windows sizes; the limits plat_commit_info reads do not grow with it.
|
||||
// Swap is not a page file Windows sizes, and nothing here advises on its size.
|
||||
int plat_page_file_managed(void) { return -1; }
|
||||
|
||||
// ---- child processes
|
||||
|
||||
@@ -488,7 +488,7 @@ int plat_commit_note(char *out, size_t cap);
|
||||
// Whether a discrete GPU's own memory counts against that limit: on Windows the driver charges device memory to the
|
||||
// system's commit; Linux's limits count system memory only.
|
||||
int plat_commit_counts_vram(void);
|
||||
// Whether Windows sizes a page file by itself (System managed size): 1; 0 when every page file has a size set; -1
|
||||
// Whether Windows sizes every page file by itself (System managed size): 1; 0 when a page file has its sizes set; -1
|
||||
// when unknown, there is none, or not Windows.
|
||||
int plat_page_file_managed(void);
|
||||
// This process's memory in bytes: resident (the working set) and private (Windows: committed private bytes; Linux: the
|
||||
|
||||
@@ -1938,7 +1938,7 @@ int plat_page_file_managed(void) {
|
||||
wchar_t *sp = wcschr(e, L' ');
|
||||
unsigned long lo = sp ? wcstoul(sp, &sp, 10) : 0, hi = sp ? wcstoul(sp, NULL, 10) : 0;
|
||||
int own = e[0] == L'?' || (!lo && !hi);
|
||||
r = own ? 1 : r < 0 ? 0 : r;
|
||||
r = own && r != 0 ? 1 : 0; // a page file with its sizes set is the user's choice: no advice then
|
||||
}
|
||||
}
|
||||
return managed = r;
|
||||
|
||||
@@ -434,8 +434,7 @@ static const char *const text_en[UI_TEXT_COUNT] = {
|
||||
[UI_MENU_PREWARM_XLATE] = "Translator prewarm",
|
||||
[UI_MENU_PREWARM_XLATE_DESC] = "Threads that translate known shaders at start; Automatic takes half the CPU threads, at most 16.",
|
||||
[UI_MENU_GPL] = "Graphics pipeline library",
|
||||
[UI_MENU_GPL_DESC] = "Uses the Vulkan pipeline library extension. Default: off on AMD's driver for RDNA 1 and 2, "
|
||||
"which crashes when it links a burst of new pipelines, on elsewhere.",
|
||||
[UI_MENU_GPL_DESC] = "Uses the Vulkan pipeline library extension; turn off if your driver misbehaves with it.",
|
||||
[UI_MENU_ASTC] = "ASTC texture decoding", [UI_MENU_ASTC_DESC] = "Where compressed ASTC textures are decoded.",
|
||||
[UI_MENU_ASTC_AUTO] = "Automatic", [UI_MENU_ASTC_GPU] = "GPU shader", [UI_MENU_ASTC_NATIVE] = "Native",
|
||||
[UI_MENU_ASTC_CPU] = "CPU",
|
||||
@@ -593,7 +592,7 @@ static const char *const text_en[UI_TEXT_COUNT] = {
|
||||
[UI_MENU_FRAMEGEN_MULT_RTX50] = "3x and 4x need an RTX 50 GPU",
|
||||
[UI_MENU_FRAMEGEN_MULT_UPTO] = "up to %dx on this GPU and driver",
|
||||
[UI_MENU_FRAMEGEN_MULT_OLD_DLL] = "2x only: update the DLSS frame generation files",
|
||||
[UI_MENU_FRAMEGEN_UNAVAILABLE] = "in use: off, see dlssg in the game log",
|
||||
[UI_MENU_FRAMEGEN_UNAVAILABLE] = "in use: off: it needs an RTX 40 or newer; if you have one, see dlssg in the log",
|
||||
[UI_MENU_FRAMEGEN_OFF_FILES] = "in use: off, its files are missing",
|
||||
[UI_MENU_GAME_RES] = "Resolution",
|
||||
[UI_MENU_GAME_RES_DESC] = "Height of the game's picture. Higher is sharper but costs more GPU power.",
|
||||
@@ -1008,8 +1007,7 @@ static const char *const text_ru[UI_TEXT_COUNT] = {
|
||||
[UI_MENU_PREWARM_XLATE] = "Прогрев транслятора",
|
||||
[UI_MENU_PREWARM_XLATE_DESC] = "Потоки, которые при запуске переводят известные шейдеры; «Автоматически» — половина потоков процессора, не больше 16.",
|
||||
[UI_MENU_GPL] = "Библиотека графических конвейеров",
|
||||
[UI_MENU_GPL_DESC] = "Использует расширение Vulkan для библиотек конвейеров. По умолчанию выключено на драйвере AMD "
|
||||
"для RDNA 1 и 2, который падает, когда связывает много новых конвейеров, включено везде.",
|
||||
[UI_MENU_GPL_DESC] = "Использует расширение Vulkan для библиотек конвейеров; выключите, если драйвер с ним сбоит.",
|
||||
[UI_MENU_ASTC] = "Распаковка текстур ASTC", [UI_MENU_ASTC_DESC] = "Где распаковываются сжатые текстуры ASTC.",
|
||||
[UI_MENU_ASTC_AUTO] = "Автоматически", [UI_MENU_ASTC_GPU] = "Шейдер GPU", [UI_MENU_ASTC_NATIVE] = "Аппаратно",
|
||||
[UI_MENU_ASTC_CPU] = "Процессор",
|
||||
@@ -1399,8 +1397,7 @@ static const char *const text_pt_br[UI_TEXT_COUNT] = {
|
||||
[UI_MENU_PREWARM_XLATE] = "Pré-aquecimento do tradutor",
|
||||
[UI_MENU_PREWARM_XLATE_DESC] = "Threads que traduzem os shaders conhecidos ao iniciar; Automático usa metade das threads da CPU, no máximo 16.",
|
||||
[UI_MENU_GPL] = "Biblioteca de pipelines gráficos",
|
||||
[UI_MENU_GPL_DESC] = "Usa a extensão de biblioteca de pipelines do Vulkan. Padrão: desligado no driver da AMD para "
|
||||
"RDNA 1 e 2, que trava ao vincular uma rajada de pipelines novos, ligado nos demais.",
|
||||
[UI_MENU_GPL_DESC] = "Usa a extensão de biblioteca de pipelines do Vulkan; desligue se o seu driver tiver problemas com ela.",
|
||||
[UI_MENU_ASTC] = "Decodificação de texturas ASTC",
|
||||
[UI_MENU_ASTC_DESC] = "Onde as texturas comprimidas em ASTC são decodificadas.",
|
||||
[UI_MENU_ASTC_AUTO] = "Automático", [UI_MENU_ASTC_GPU] = "Shader da GPU", [UI_MENU_ASTC_NATIVE] = "Nativo",
|
||||
@@ -2061,8 +2058,7 @@ static const char *const text_zh_hans[UI_TEXT_COUNT] = {
|
||||
[UI_MENU_PREWARM_XLATE_DESC] = "启动时转译已知着色器的线程数;自动取 CPU 线程数的一半,"
|
||||
"最多 16。",
|
||||
[UI_MENU_GPL] = "图形管线库",
|
||||
[UI_MENU_GPL_DESC] = "使用 Vulkan 管线库扩展。默认:在 AMD RDNA 1 和 2 驱动上关闭,因为驱动在链接大量新管线时会崩溃,"
|
||||
"其他平台默认开启。",
|
||||
[UI_MENU_GPL_DESC] = "使用 Vulkan 管线库扩展;驱动对此有问题时请关闭。",
|
||||
[UI_MENU_ASTC] = "ASTC 纹理解码",
|
||||
[UI_MENU_ASTC_DESC] = "压缩的 ASTC 纹理在哪里解码。",
|
||||
[UI_MENU_ASTC_AUTO] = "自动",
|
||||
|
||||
@@ -58,7 +58,7 @@ typedef struct {
|
||||
uint32_t sbuf_align; // nonzero: storage buffers bind at their address rounded down to this
|
||||
uint32_t sg_size; // requiredSubgroupSize on sg_pin_stages (32)
|
||||
VkShaderStageFlags sg_pin_stages; // 0: no pin, stages run at the device's subgroupSize
|
||||
int gpl; // VK_EXT_graphics_pipeline_library enabled with fast linking (NX2NAVI_GPL=0/1; unset: off on AMD RDNA 1/2)
|
||||
int gpl; // VK_EXT_graphics_pipeline_library enabled with fast linking (NX2NAVI_GPL=0/1; unset: off on AMD's driver for RDNA 2 and older)
|
||||
int amd; // an AMD GPU (vendor 0x1002), any driver
|
||||
int amd_sc; // AMD's Windows driver branch for RDNA 1 and 2 ("AMD proprietary shader compiler")
|
||||
int amd_llpc; // AMD's own driver for RDNA 3 and newer (its driverInfo names LLPC)
|
||||
|
||||
@@ -435,7 +435,8 @@ static void mem_barrier(VkCommandBuffer cb, VkPipelineStageFlags2 src, VkAccessF
|
||||
// So each is kept to half a VMA block (vk_vma_block_size's default 64 MiB), where VMA still places it in a block, not in
|
||||
// memory of its own: 16 MiB of texels, their blocks and BC3 fit in 32 MiB.
|
||||
#define CHUNK_OUT (16ull << 20)
|
||||
#define SCRATCH_MIN (32ull << 20) // the shared scratch's least size: one chunk's texels plus its blocks and BC3
|
||||
#define SCRATCH_MIN (32ull << 20) // the shared scratch's usual least size: one chunk's texels plus its blocks and BC3
|
||||
// (smaller only after the device ran out of memory: scratch_get's second try)
|
||||
|
||||
// The shared scratch and the command buffer it was last recorded into. An upload batch's command buffer is used again
|
||||
// only after that batch completed (vk_memory.c: completed batches go to the spare list), so the same handle means the
|
||||
|
||||
@@ -6,8 +6,8 @@
|
||||
// - minStorageBufferOffsetAlignment above 4 (NX2NAVI_VK_SSBO_ALIGN=<power of two> raises it): the translator computes
|
||||
// storage offsets from the guest address rounded down to that alignment (the translator's unaligned storage path), and
|
||||
// vk_exec_draw.c ssbo_info binds the rounded-down address, so shader writes reach guest memory instead of a copy.
|
||||
// - no graphics pipeline library with fast linking (NX2NAVI_GPL=0 forces it; it also defaults off on AMD's RDNA 1/2
|
||||
// Windows driver branch, see vk_caps_gpl): vk_caps.gpl = 0, the extension stays disabled, and pipelines are built whole.
|
||||
// - no graphics pipeline library with fast linking (NX2NAVI_GPL=0 forces it; it also defaults off on AMD's Windows
|
||||
// driver for RDNA 2 and older, see vk_caps_gpl): vk_caps.gpl = 0, the extension stays disabled, and pipelines are built whole.
|
||||
// - no 32-lane pin (no subgroupSizeControl, 32 outside min..max, or NX2NAVI_VK_SUBGROUP_PIN=0): stages run at the
|
||||
// device's subgroupSize (SPIR-V 1.3 without a required size) and the translator is told that size.
|
||||
// NX2NAVI_VK_SUBGROUP=<n> pins n instead of 32 where the driver allows it.
|
||||
@@ -56,14 +56,16 @@ void vk_caps_driver(VkPhysicalDevice p) {
|
||||
}
|
||||
|
||||
// NX2NAVI_GPL=0 turns graphics pipeline libraries off and 1 turns them on; unset, they are on wherever the driver has
|
||||
// fast linking, except on AMD's Windows driver for RDNA 1 and 2 (vk_caps.amd_sc). That driver faults inside
|
||||
// vkCreateGraphicsPipelines when it links the stage libraries of a burst of new pipelines, which the game asks for when
|
||||
// an enemy dies and its effects are drawn for the first time: the game ended with code 71 at every kill on an RX 6700 XT
|
||||
// and an RX 5700 XT (issue #418), and no longer with gpl = 0. The price there is that a new pipeline is built whole on
|
||||
// the draw's path (frames of 0.5-1.2 s on an RX 6600 while an area is new). The same driver had libraries off before,
|
||||
// for device losses at boot (issue #5), whose cause was GPU writes past 3D BC images (vk_exec.c, "3D BC render
|
||||
// targets"); it boots with them since that was fixed, so gpl = 1 is there to try on a newer driver. RDNA 4 under RADV
|
||||
// is reported to hang the GPU at the title screen with GPL.
|
||||
// fast linking, except on AMD's Windows driver for RDNA 2 and older (vk_caps.amd_sc: RX 400 to RX 6000). On an
|
||||
// RX 6700 XT the game ended with code 71 at every enemy killed, from 0.5 on, and no longer with gpl = 0; an RX 5700 XT
|
||||
// showed the same ending (issue #418). Where in the driver it faults is not established: a kill draws its effects
|
||||
// for the first time, which asks for a burst of new pipelines linked from stage libraries, and building them whole
|
||||
// avoids it. The price there: with libraries off a pipeline the game needs for the first time is built whole by a
|
||||
// worker while its draw is left out (vk_exec_draw.c, "pipeline still building"), so new things appear some frames
|
||||
// late, and the start waits for every recorded pipeline instead of 20 s at most (vk_pipeline.c prewarm_run). The
|
||||
// same driver had libraries off before, for device losses at boot (issue #5), whose cause was GPU writes past 3D BC
|
||||
// images (vk_exec.c, "3D BC render targets"); it boots with them since that was fixed, so gpl = 1 is there to try on
|
||||
// a newer driver. RDNA 4 under RADV is reported to hang the GPU at the title screen with GPL.
|
||||
int vk_caps_gpl(const VkPhysicalDeviceGraphicsPipelineLibraryFeaturesEXT *f,
|
||||
const VkPhysicalDeviceGraphicsPipelineLibraryPropertiesEXT *p) {
|
||||
gpl_lib = f->graphicsPipelineLibrary;
|
||||
@@ -74,7 +76,7 @@ int vk_caps_gpl(const VkPhysicalDeviceGraphicsPipelineLibraryFeaturesEXT *f,
|
||||
gpl_off = vk_caps.gpl ? NULL
|
||||
: !gpl_lib || !gpl_fast ? "the driver has no fast linking"
|
||||
: e && *e ? "NX2NAVI_GPL=0"
|
||||
: "default on AMD's driver for RDNA 1 and 2 (NX2NAVI_GPL=1 turns it on)";
|
||||
: "default on AMD's driver for RDNA 2 and older (NX2NAVI_GPL=1 turns it on)";
|
||||
return vk_caps.gpl;
|
||||
}
|
||||
|
||||
|
||||
@@ -1555,6 +1555,9 @@ static int idle(const Tex *e, uint64_t now);
|
||||
// or the page file, and the VRAM pressure and tex_disuse already bound it. Counted in, it held the bound all through
|
||||
// Hyrule Field on a 16 GB PC with a 16 GB card (RTX 5060 Ti): the process at 28.9 to 30.7 GB, 9 to 10 GB of it video
|
||||
// memory, while the system had 8 to 10 GB of its 49 GB limit free, and the ground flickered white as textures gave way.
|
||||
// So on such a PC the 42 GB process above, half of it device memory, no longer reaches this bound: the system's
|
||||
// figure and the VRAM pressure are what act there. The part of a card's memory the driver has moved into shared
|
||||
// system memory is subtracted too, which it should not be; the driver does not report it apart.
|
||||
#define COMMIT_LOW_KEEP ((uint64_t)256 << 20)
|
||||
#define PROC_COMMIT_MIN_MB 24576
|
||||
static uint64_t released_cap; // bytes; 0 = not read yet, UINT64_MAX = no limit
|
||||
@@ -1616,8 +1619,9 @@ static int commit_is_low(void) {
|
||||
char note[2048]; // the platform layer's own lines go to stderr only, so the log file gets this through here
|
||||
if (plat_commit_note(note, sizeof note)) rt_log("platform: %s", note);
|
||||
if (proc_commit_mb)
|
||||
rt_log("vk: textures give way as under low commit while this process's commit is above %lld MB "
|
||||
"(NX2NAVI_TEX_PROC_COMMIT_MB; 0 = off)", proc_commit_mb);
|
||||
rt_log("vk: textures give way as under low commit while this process's commit%s is above %lld MB "
|
||||
"(NX2NAVI_TEX_PROC_COMMIT_MB; 0 = off)",
|
||||
plat_commit_counts_vram() ? ", less the video memory in use on a discrete card," : "", proc_commit_mb);
|
||||
}
|
||||
if (!commit_free_mb && !proc_commit_mb) return 0;
|
||||
double proc, used, limit;
|
||||
@@ -1655,9 +1659,10 @@ static int commit_is_low(void) {
|
||||
static int hinted;
|
||||
if (low && !hinted && plat_page_file_managed() == 1) {
|
||||
hinted = 1;
|
||||
rt_log("vk: the page file is sized by Windows, which grows it only slowly: a fixed page file of at least "
|
||||
"32 GB keeps the system's commit from running low (System > About > Advanced system settings > "
|
||||
"Performance Settings > Advanced > Virtual memory > Change: Custom size, then restart Windows)");
|
||||
rt_log("vk: the page file is sized by Windows, which grows it only slowly: a fixed page file whose initial "
|
||||
"size is at least 32 GB keeps the system's commit from running low (System > About > Advanced system "
|
||||
"settings > Performance Settings > Advanced > Virtual memory > Change: untick the automatic "
|
||||
"management, Custom size with an initial size of 32768 MB or more, Set, then restart Windows)");
|
||||
}
|
||||
}
|
||||
sys_low = low;
|
||||
|
||||
Reference in New Issue
Block a user