debuggerx/eden
1
0
Fork 0
mirror of https://git.eden-emu.dev/eden-emu/eden.git synced 2026-09-07 12:48:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

[vulkan] Removal of QCOM sampler limiters + CustomBorderColor and ColorBorderSwizzle adjustments (#4301)

Browse Source 
This PR removes the artificial limit added for QCOM drivers based on a sampler budget limit (based on #3280 work), removes the ban on CustomBorderColor/BorderColorSwizzle for also QCOM driver, reduce the amount of combination required to created a sampler with custom border color/ color border swizzle; adds cases on R16 formats not able to swizzle on BGR565 formats; degrades samplers and color combinations when there's no color border swizzle available; fixes the srgb (LUT) values from legacy and now all the color variations are cached in the same key, instead of having 7 different handlers for them. In resume, rather than performance (due to the reduced amount of process on duplicated/ synced code on pipeline/texture cache), it's a graphica accuracy work that will improve image quality at the cost of almost 0 performance hit, rather than certain hitch if the color combination wasn't cached before. This applies to all platform.

Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4301
Reviewed-by: Samuel <lizzie@eden-emu.dev>
Reviewed-by: MaranBr <maranbr@eden-emu.dev>
This commit is contained in:
CamilleLaVey
2026-08-25 20:03:18 +02:00
committed by crueter
parent 60a474b8df
commit 0295dc5fff
9 changed files with 376 additions and 264 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/video_core/texture_cache/texture_cache.h
-57
View File
@@ -1896,67 +1896,10 @@ SamplerId TextureCache<P>::FindSampler(const TSCEntry& config, bool compute) {
const auto [pair, is_new] = channel_state->samplers.try_emplace(config);
if (is_new) {
pair->second = slot_samplers.insert(runtime, config);
EnforceSamplerBudget();
}
return pair->second;
}
template <class P>
std::optional<size_t> TextureCache<P>::QuerySamplerBudget() const {
if constexpr (requires { runtime.GetSamplerHeapBudget(); }) {
return runtime.GetSamplerHeapBudget();
} else {
return std::nullopt;
}
}
template <class P>
void TextureCache<P>::EnforceSamplerBudget() {
if (auto const budget = QuerySamplerBudget(); budget) {
if (slot_samplers.size() < *budget) {
return;
}
if (!channel_state) {
return;
}
if (last_sampler_gc_frame == frame_tick) {
return;
}
last_sampler_gc_frame = frame_tick;
TrimInactiveSamplers(*budget);
}
}
template <class P>
void TextureCache<P>::TrimInactiveSamplers(size_t budget) {
if (channel_state->samplers.size() > 0) {
constexpr size_t SAMPLER_GC_SLACK = 1024;
ankerl::unordered_dense::set<SamplerId> active_sampler_ids;
for (auto const& e : channel_state->sampler_ids)
active_sampler_ids.insert(e.second);
// Elements in the map must be necesarily valid
size_t removed = 0;
for (auto it = channel_state->samplers.begin(); it != channel_state->samplers.end();) {
const SamplerId sampler_id = it->second;
if (!sampler_id || sampler_id == CORRUPT_ID) {
it = channel_state->samplers.erase(it);
} else if (std::ranges::find(active_sampler_ids, sampler_id) != active_sampler_ids.end()) {
++it;
} else {
slot_samplers.erase(sampler_id);
it = channel_state->samplers.erase(it);
++removed;
if (slot_samplers.size() + SAMPLER_GC_SLACK <= budget) {
break;
}
}
}
if (removed != 0) {
LOG_WARNING(HW_GPU, "Sampler cache exceeded {} entries on this driver; reclaimed {} inactive samplers", budget, removed);
}
}
}
template <class P>
ImageViewId TextureCache<P>::FindColorBuffer(size_t index) {
const auto& regs = maxwell3d->regs;
src/video_core/texture_cache/texture_cache_base.h
-4
View File
@@ -420,9 +420,6 @@ private:
void QueueAsyncDecode(Image& image, ImageId image_id);
void TickAsyncDecode();
void EnforceSamplerBudget();
void TrimInactiveSamplers(size_t budget);
std::optional<size_t> QuerySamplerBudget() const;
void QueueAsyncUnswizzle(Image& image, ImageId image_id);
void TickAsyncUnswizzle();
@@ -509,7 +506,6 @@ private:
u64 modification_tick = 0;
u64 frame_tick = 0;
u64 last_sampler_gc_frame = (std::numeric_limits<u64>::max)();
Common::ThreadWorker texture_decode_worker{1, "TextureDecoder", {},
Common::ThreadPlacement::Efficiency};