Compare commits

..

8 Commits

Author SHA1 Message Date
lizzie 5e230b4257 license 2026-08-29 08:57:57 +02:00
lizzie e72f528bd8 fx 2026-08-29 08:57:57 +02:00
lizzie 99c77fe4cc x5 faster anchordIndex for BC7 2026-08-29 08:57:57 +02:00
lizzie 6b7aff1a70 better anchorIndex 2026-08-29 08:57:57 +02:00
lizzie 5f6017467b better table set 2026-08-29 08:57:57 +02:00
lizzie 3ab734bc61 oops bcn format 2026-08-29 08:57:57 +02:00
lizzie bcb739c9c0 fix ffs 2026-08-29 08:57:57 +02:00
lizzie 29e2d09ebf [bcn] ternary compose and simplify subsetIndex & anchordIndex 2026-08-29 08:57:57 +02:00
9 changed files with 804 additions and 651 deletions
+329 -544
View File
File diff suppressed because it is too large Load Diff
+12 -32
View File
@@ -1,43 +1,23 @@
// SPDX-License-Identifier: MPL-2.0
// Copyright © 2022 Skyline Team and Contributors (https://github.com/skyline-emu/)
// Copyright 2022 Skyline Team and Contributors (https://github.com/skyline-emu/)
#pragma once
#include <cstdint>
namespace bcn {
/**
* @brief Decodes a BC1 encoded image to R8G8B8A8
*/
void DecodeBc1(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
/**
* @brief Decodes a BC2 encoded image to R8G8B8A8
*/
void DecodeBc2(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
/**
* @brief Decodes a BC3 encoded image to R8G8B8A8
*/
void DecodeBc3(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
/**
* @brief Decodes a BC4 encoded image to R8
*/
/// @brief Decodes a BC1 encoded image to R8G8B8A8
void DecodeBc1(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
/// @brief Decodes a BC2 encoded image to R8G8B8A8
void DecodeBc2(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
//// @brief Decodes a BC3 encoded image to R8G8B8A8
void DecodeBc3(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
/// @brief Decodes a BC4 encoded image to R8
void DecodeBc4(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
/**
* @brief Decodes a BC5 encoded image to R8G8
*/
//// @brief Decodes a BC5 encoded image to R8G8
void DecodeBc5(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
/**
* @brief Decodes a BC6 encoded image to R16G16B16A16
*/
//// @brief Decodes a BC6 encoded image to R16G16B16A16
void DecodeBc6(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
/**
* @brief Decodes a BC7 encoded image to R8G8B8A8
*/
void DecodeBc7(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
/// @brief Decodes a BC7 encoded image to R8G8B8A8
void DecodeBc7(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
}
+2
View File
@@ -63,6 +63,8 @@ add_library(
fs/path_util.cpp
fs/path_util.h
hash.h
heap_tracker.cpp
heap_tracker.h
hex_util.cpp
hex_util.h
host_memory.cpp
+282
View File
@@ -0,0 +1,282 @@
// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
#include <fstream>
#include "common/heap_tracker.h"
#include "common/logging.h"
#include "common/assert.h"
namespace Common {
namespace {
s64 GetMaxPermissibleResidentMapCount() {
// Default value.
s64 value = 65530;
// Try to read how many mappings we can make.
std::ifstream s("/proc/sys/vm/max_map_count");
s >> value;
// Print, for debug.
LOG_INFO(HW_Memory, "Current maximum map count: {}", value);
// Allow 20000 maps for other code and to account for split inaccuracy.
return std::max<s64>(value - 20000, 0);
}
} // namespace
HeapTracker::HeapTracker(Common::HostMemory& buffer)
: m_buffer(buffer), m_max_resident_map_count(GetMaxPermissibleResidentMapCount()) {}
HeapTracker::~HeapTracker() = default;
void HeapTracker::Map(size_t virtual_offset, size_t host_offset, size_t length,
MemoryPermission perm, bool is_separate_heap) {
// When mapping other memory, map pages immediately.
if (!is_separate_heap) {
m_buffer.Map(virtual_offset, host_offset, length, perm, false);
return;
}
{
// We are mapping part of a separate heap.
std::scoped_lock lk{m_lock};
auto* const map = new SeparateHeapMap{
.vaddr = virtual_offset,
.paddr = host_offset,
.size = length,
.tick = m_tick++,
.perm = perm,
.is_resident = false,
};
// Insert into mappings.
m_map_count++;
m_mappings.insert(*map);
}
// Finally, map.
this->DeferredMapSeparateHeap(virtual_offset);
}
void HeapTracker::Unmap(size_t virtual_offset, size_t size, bool is_separate_heap) {
// If this is a separate heap...
if (is_separate_heap) {
std::scoped_lock lk{m_lock};
const SeparateHeapMap key{
.vaddr = virtual_offset,
};
// Split at the boundaries of the region we are removing.
this->SplitHeapMapLocked(virtual_offset);
this->SplitHeapMapLocked(virtual_offset + size);
// Erase all mappings in range.
auto it = m_mappings.find(key);
while (it != m_mappings.end() && it->vaddr < virtual_offset + size) {
// Get underlying item.
auto* const item = std::addressof(*it);
// If resident, erase from resident map.
if (item->is_resident) {
ASSERT(--m_resident_map_count >= 0);
m_resident_mappings.erase(m_resident_mappings.iterator_to(*item));
}
// Erase from map.
ASSERT(--m_map_count >= 0);
it = m_mappings.erase(it);
// Free the item.
delete item;
}
}
// Unmap pages.
m_buffer.Unmap(virtual_offset, size, false);
}
void HeapTracker::Protect(size_t virtual_offset, size_t size, MemoryPermission perm) {
// Ensure no rebuild occurs while reprotecting.
std::shared_lock lk{m_rebuild_lock};
// Split at the boundaries of the region we are reprotecting.
this->SplitHeapMap(virtual_offset, size);
// Declare tracking variables.
const VAddr end = virtual_offset + size;
VAddr cur = virtual_offset;
while (cur < end) {
VAddr next = cur;
bool should_protect = false;
{
std::scoped_lock lk2{m_lock};
const SeparateHeapMap key{
.vaddr = next,
};
// Try to get the next mapping corresponding to this address.
const auto it = m_mappings.nfind(key);
if (it == m_mappings.end()) {
// There are no separate heap mappings remaining.
next = end;
should_protect = true;
} else if (it->vaddr == cur) {
// We are in range.
// Update permission bits.
it->perm = perm;
// Determine next address and whether we should protect.
next = cur + it->size;
should_protect = it->is_resident;
} else /* if (it->vaddr > cur) */ {
// We weren't in range, but there is a block coming up that will be.
next = it->vaddr;
should_protect = true;
}
}
// Clamp to end.
next = (std::min)(next, end);
// Reprotect, if we need to.
if (should_protect) {
m_buffer.Protect(cur, next - cur, perm);
}
// Advance.
cur = next;
}
}
bool HeapTracker::DeferredMapSeparateHeap(u8* fault_address) {
if (m_buffer.IsInVirtualRange(fault_address)) {
return this->DeferredMapSeparateHeap(fault_address - m_buffer.VirtualBasePointer());
}
return false;
}
bool HeapTracker::DeferredMapSeparateHeap(size_t virtual_offset) {
bool rebuild_required = false;
{
std::scoped_lock lk{m_lock};
// Check to ensure this was a non-resident separate heap mapping.
const auto it = this->GetNearestHeapMapLocked(virtual_offset);
if (it == m_mappings.end() || it->is_resident) {
return false;
}
// Update tick before possible rebuild.
it->tick = m_tick++;
// Check if we need to rebuild.
if (m_resident_map_count > m_max_resident_map_count) {
rebuild_required = true;
}
// Map the area.
m_buffer.Map(it->vaddr, it->paddr, it->size, it->perm, false);
// This map is now resident.
it->is_resident = true;
m_resident_map_count++;
m_resident_mappings.insert(*it);
}
if (rebuild_required) {
// A rebuild was required, so perform it now.
this->RebuildSeparateHeapAddressSpace();
}
return true;
}
void HeapTracker::RebuildSeparateHeapAddressSpace() {
std::scoped_lock lk{m_rebuild_lock, m_lock};
ASSERT(!m_resident_mappings.empty());
// Dump half of the mappings.
//
// Despite being worse in theory, this has proven to be better in practice than more
// regularly dumping a smaller amount, because it significantly reduces average case
// lock contention.
std::size_t const desired_count = (std::min)(m_resident_map_count, m_max_resident_map_count) / 2;
std::size_t const evict_count = m_resident_map_count - desired_count;
auto it = m_resident_mappings.begin();
for (size_t i = 0; i < evict_count && it != m_resident_mappings.end(); i++) {
// Unmark and unmap.
it->is_resident = false;
m_buffer.Unmap(it->vaddr, it->size, false);
// Advance.
ASSERT(--m_resident_map_count >= 0);
it = m_resident_mappings.erase(it);
}
}
void HeapTracker::SplitHeapMap(VAddr offset, size_t size) {
std::scoped_lock lk{m_lock};
this->SplitHeapMapLocked(offset);
this->SplitHeapMapLocked(offset + size);
}
void HeapTracker::SplitHeapMapLocked(VAddr offset) {
const auto it = this->GetNearestHeapMapLocked(offset);
if (it == m_mappings.end() || it->vaddr == offset) {
// Not contained or no split required.
return;
}
// Cache the original values.
auto* const left = std::addressof(*it);
const size_t orig_size = left->size;
// Adjust the left map.
const size_t left_size = offset - left->vaddr;
left->size = left_size;
// Create the new right map.
auto* const right = new SeparateHeapMap{
.vaddr = left->vaddr + left_size,
.paddr = left->paddr + left_size,
.size = orig_size - left_size,
.tick = left->tick,
.perm = left->perm,
.is_resident = left->is_resident,
};
// Insert the new right map.
m_map_count++;
m_mappings.insert(*right);
// If resident, also insert into resident map.
if (right->is_resident) {
m_resident_map_count++;
m_resident_mappings.insert(*right);
}
}
HeapTracker::AddrTree::iterator HeapTracker::GetNearestHeapMapLocked(VAddr offset) {
const SeparateHeapMap key{
.vaddr = offset,
};
return m_mappings.find(key);
}
} // namespace Common
+98
View File
@@ -0,0 +1,98 @@
// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
#pragma once
#include <atomic>
#include <mutex>
#include <set>
#include <shared_mutex>
#include "common/host_memory.h"
#include "common/intrusive_red_black_tree.h"
namespace Common {
struct SeparateHeapMap {
Common::IntrusiveRedBlackTreeNode addr_node{};
Common::IntrusiveRedBlackTreeNode tick_node{};
VAddr vaddr{};
PAddr paddr{};
size_t size{};
size_t tick{};
MemoryPermission perm{};
bool is_resident{};
};
struct SeparateHeapMapAddrComparator {
static constexpr int Compare(const SeparateHeapMap& lhs, const SeparateHeapMap& rhs) {
if (lhs.vaddr < rhs.vaddr) {
return -1;
} else if (lhs.vaddr <= (rhs.vaddr + rhs.size - 1)) {
return 0;
} else {
return 1;
}
}
};
struct SeparateHeapMapTickComparator {
static constexpr int Compare(const SeparateHeapMap& lhs, const SeparateHeapMap& rhs) {
if (lhs.tick < rhs.tick) {
return -1;
} else if (lhs.tick > rhs.tick) {
return 1;
} else {
return SeparateHeapMapAddrComparator::Compare(lhs, rhs);
}
}
};
class HeapTracker {
public:
explicit HeapTracker(Common::HostMemory& buffer);
~HeapTracker();
void Map(size_t virtual_offset, size_t host_offset, size_t length, MemoryPermission perm,
bool is_separate_heap);
void Unmap(size_t virtual_offset, size_t size, bool is_separate_heap);
void Protect(size_t virtual_offset, size_t length, MemoryPermission perm);
u8* VirtualBasePointer() {
return m_buffer.VirtualBasePointer();
}
bool DeferredMapSeparateHeap(u8* fault_address);
bool DeferredMapSeparateHeap(size_t virtual_offset);
private:
using AddrTreeTraits =
Common::IntrusiveRedBlackTreeMemberTraitsDeferredAssert<&SeparateHeapMap::addr_node>;
using AddrTree = AddrTreeTraits::TreeType<SeparateHeapMapAddrComparator>;
using TickTreeTraits =
Common::IntrusiveRedBlackTreeMemberTraitsDeferredAssert<&SeparateHeapMap::tick_node>;
using TickTree = TickTreeTraits::TreeType<SeparateHeapMapTickComparator>;
AddrTree m_mappings{};
TickTree m_resident_mappings{};
private:
void SplitHeapMap(VAddr offset, size_t size);
void SplitHeapMapLocked(VAddr offset);
AddrTree::iterator GetNearestHeapMapLocked(VAddr offset);
void RebuildSeparateHeapAddressSpace();
private:
Common::HostMemory& m_buffer;
const s64 m_max_resident_map_count;
std::shared_mutex m_rebuild_lock{};
std::mutex m_lock{};
s64 m_map_count{};
s64 m_resident_map_count{};
size_t m_tick{};
};
} // namespace Common
+40 -6
View File
@@ -16,6 +16,7 @@
#include "common/assert.h"
#include "common/atomic_ops.h"
#include "common/common_types.h"
#include "common/heap_tracker.h"
#include "common/logging.h"
#include "common/page_table.h"
#include "common/scope_exit.h"
@@ -54,24 +55,36 @@ struct Memory::Impl {
} else {
current_page_table->fastmem_arena = nullptr;
}
#ifdef __ANDROID__
heap_tracker.emplace(system.DeviceMemory().buffer);
host_buffer = std::addressof(*heap_tracker);
#else
host_buffer = std::addressof(system.DeviceMemory().buffer);
#endif
}
void MapMemoryRegion(Common::PageTable& page_table, Common::ProcessAddress base, u64 size, Common::PhysicalAddress target, Common::MemoryPermission perms, bool separate_heap) {
void MapMemoryRegion(Common::PageTable& page_table, Common::ProcessAddress base, u64 size,
Common::PhysicalAddress target, Common::MemoryPermission perms,
bool separate_heap) {
ASSERT_MSG((size & YUZU_PAGEMASK) == 0, "non-page aligned size: {:016X}", size);
ASSERT_MSG((base & YUZU_PAGEMASK) == 0, "non-page aligned base: {:016X}", GetInteger(base));
ASSERT_MSG(target >= DramMemoryMap::Base, "Out of bounds target: {:016X}", GetInteger(target));
MapPages(page_table, base / YUZU_PAGESIZE, size / YUZU_PAGESIZE, target, Common::PageType::Memory);
ASSERT_MSG(target >= DramMemoryMap::Base, "Out of bounds target: {:016X}",
GetInteger(target));
MapPages(page_table, base / YUZU_PAGESIZE, size / YUZU_PAGESIZE, target,
Common::PageType::Memory);
if (current_page_table->fastmem_arena) {
host_buffer->Map(GetInteger(base), GetInteger(target) - DramMemoryMap::Base, size, perms, separate_heap);
}
}
void UnmapRegion(Common::PageTable& page_table, Common::ProcessAddress base, u64 size, bool separate_heap) {
void UnmapRegion(Common::PageTable& page_table, Common::ProcessAddress base, u64 size,
bool separate_heap) {
ASSERT_MSG((size & YUZU_PAGEMASK) == 0, "non-page aligned size: {:016X}", size);
ASSERT_MSG((base & YUZU_PAGEMASK) == 0, "non-page aligned base: {:016X}", GetInteger(base));
MapPages(page_table, base / YUZU_PAGESIZE, size / YUZU_PAGESIZE, 0, Common::PageType::Unmapped);
MapPages(page_table, base / YUZU_PAGESIZE, size / YUZU_PAGESIZE, 0,
Common::PageType::Unmapped);
if (current_page_table->fastmem_arena) {
host_buffer->Unmap(GetInteger(base), size, separate_heap);
@@ -754,7 +767,12 @@ struct Memory::Impl {
std::array<Common::ScratchBuffer<u32>, Core::Hardware::NUM_CPU_CORES> scratch_buffers{};
std::span<Core::GPUDirtyMemoryManager> gpu_dirty_managers;
std::mutex sys_core_guard;
#ifdef __ANDROID__
std::optional<Common::HeapTracker> heap_tracker;
Common::HeapTracker* host_buffer{};
#else
Common::HostMemory* host_buffer{};
#endif
};
Memory::Memory(Core::System& system_) : system{system_} {
@@ -947,14 +965,30 @@ bool Memory::InvalidateNCE(Common::ProcessAddress vaddr, size_t size) {
u8* const ptr = impl->GetPointerImpl(
GetInteger(vaddr),
[&] {
LOG_ERROR(HW_Memory, "Unmapped InvalidateNCE for {} bytes @ {:#x}", size, GetInteger(vaddr));
LOG_ERROR(HW_Memory, "Unmapped InvalidateNCE for {} bytes @ {:#x}", size,
GetInteger(vaddr));
mapped = false;
},
[&] { rasterizer = true; });
if (rasterizer) {
impl->InvalidateGPUMemory(ptr, size);
}
#ifdef __ANDROID__
if (!rasterizer && mapped) {
impl->host_buffer->DeferredMapSeparateHeap(GetInteger(vaddr));
}
#endif
return mapped && ptr != nullptr;
}
bool Memory::InvalidateSeparateHeap(void* fault_address) {
#ifdef __ANDROID__
return impl->host_buffer->DeferredMapSeparateHeap(static_cast<u8*>(fault_address));
#else
return false;
#endif
}
} // namespace Core::Memory
+6 -1
View File
@@ -1,4 +1,4 @@
// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: 2014 Citra Emulator Project
@@ -490,8 +490,13 @@ public:
* marked as debug or non-debug.
*/
void MarkRegionDebug(Common::ProcessAddress vaddr, u64 size, bool debug);
void SetGPUDirtyManagers(std::span<Core::GPUDirtyMemoryManager> managers);
bool InvalidateNCE(Common::ProcessAddress vaddr, size_t size);
bool InvalidateSeparateHeap(void* fault_address);
private:
Core::System& system;
+25 -51
View File
@@ -1,4 +1,4 @@
// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
@@ -9,6 +9,7 @@
#include <span>
#include <bc_decoder.h>
#include "common/assert.h"
#include "common/common_types.h"
#include "video_core/texture_cache/decode_bc.h"
@@ -22,11 +23,8 @@ using VideoCore::Surface::PixelFormat;
constexpr bool IsSigned(PixelFormat pixel_format) {
switch (pixel_format) {
case PixelFormat::BC4_SNORM:
case PixelFormat::BC4_UNORM:
case PixelFormat::BC5_SNORM:
case PixelFormat::BC5_UNORM:
case PixelFormat::BC6H_SFLOAT:
case PixelFormat::BC6H_UFLOAT:
return true;
default:
return false;
@@ -62,9 +60,28 @@ u32 ConvertedBytesPerBlock(VideoCore::Surface::PixelFormat pixel_format) {
}
}
template <auto decompress, PixelFormat pixel_format>
void DecompressBlocks(std::span<const u8> input, std::span<u8> output, BufferImageCopy& copy,
bool is_signed = false) {
void DecompressBCn(std::span<const u8> input, std::span<u8> output, BufferImageCopy& copy, VideoCore::Surface::PixelFormat pixel_format) {
auto const f = [pixel_format]{
switch (pixel_format) {
case PixelFormat::BC1_RGBA_UNORM:
case PixelFormat::BC1_RGBA_SRGB: return &bcn::DecodeBc1;
case PixelFormat::BC2_UNORM:
case PixelFormat::BC2_SRGB: return &bcn::DecodeBc2;
case PixelFormat::BC3_UNORM:
case PixelFormat::BC3_SRGB: return &bcn::DecodeBc3;
case PixelFormat::BC4_SNORM:
case PixelFormat::BC4_UNORM: return &bcn::DecodeBc4;
case PixelFormat::BC5_SNORM:
case PixelFormat::BC5_UNORM: return &bcn::DecodeBc5;
case PixelFormat::BC6H_SFLOAT:
case PixelFormat::BC6H_UFLOAT: return &bcn::DecodeBc6;
case PixelFormat::BC7_SRGB:
case PixelFormat::BC7_UNORM: return &bcn::DecodeBc7;
default:
UNREACHABLE_MSG("Unimplemented BCn decompression {}", pixel_format);
return &bcn::DecodeBc1;
}
}();
const u32 out_bpp = ConvertedBytesPerBlock(pixel_format);
const u32 block_size = BlockSize(pixel_format);
const u32 width = copy.image_extent.width;
@@ -82,11 +99,7 @@ void DecompressBlocks(std::span<const u8> input, std::span<u8> output, BufferIma
for (u32 x = 0; x < width; x += block_width) {
const u8* src = input.data() + src_offset;
u8* const dst = output.data() + dst_offset;
if constexpr (IsSigned(pixel_format)) {
decompress(src, dst, x, y, width, height, is_signed);
} else {
decompress(src, dst, x, y, width, height);
}
f(src, dst, x, y, width, height, IsSigned(pixel_format));
src_offset += block_size;
dst_offset += block_width * out_bpp;
}
@@ -96,43 +109,4 @@ void DecompressBlocks(std::span<const u8> input, std::span<u8> output, BufferIma
}
}
void DecompressBCn(std::span<const u8> input, std::span<u8> output, BufferImageCopy& copy,
VideoCore::Surface::PixelFormat pixel_format) {
switch (pixel_format) {
case PixelFormat::BC1_RGBA_UNORM:
case PixelFormat::BC1_RGBA_SRGB:
DecompressBlocks<bcn::DecodeBc1, PixelFormat::BC1_RGBA_UNORM>(input, output, copy);
break;
case PixelFormat::BC2_UNORM:
case PixelFormat::BC2_SRGB:
DecompressBlocks<bcn::DecodeBc2, PixelFormat::BC2_UNORM>(input, output, copy);
break;
case PixelFormat::BC3_UNORM:
case PixelFormat::BC3_SRGB:
DecompressBlocks<bcn::DecodeBc3, PixelFormat::BC3_UNORM>(input, output, copy);
break;
case PixelFormat::BC4_SNORM:
case PixelFormat::BC4_UNORM:
DecompressBlocks<bcn::DecodeBc4, PixelFormat::BC4_UNORM>(
input, output, copy, pixel_format == PixelFormat::BC4_SNORM);
break;
case PixelFormat::BC5_SNORM:
case PixelFormat::BC5_UNORM:
DecompressBlocks<bcn::DecodeBc5, PixelFormat::BC5_UNORM>(
input, output, copy, pixel_format == PixelFormat::BC5_SNORM);
break;
case PixelFormat::BC6H_SFLOAT:
case PixelFormat::BC6H_UFLOAT:
DecompressBlocks<bcn::DecodeBc6, PixelFormat::BC6H_UFLOAT>(
input, output, copy, pixel_format == PixelFormat::BC6H_SFLOAT);
break;
case PixelFormat::BC7_SRGB:
case PixelFormat::BC7_UNORM:
DecompressBlocks<bcn::DecodeBc7, PixelFormat::BC7_UNORM>(input, output, copy);
break;
default:
LOG_WARNING(HW_GPU, "Unimplemented BCn decompression {}", pixel_format);
}
}
} // namespace VideoCommon
+10 -17
View File
@@ -1,4 +1,4 @@
// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
@@ -922,8 +922,7 @@ boost::container::small_vector<BufferImageCopy, 16> UnswizzleImage(Tegra::Memory
return copies;
}
void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8> output,
std::span<BufferImageCopy> copies) {
void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8> output, std::span<BufferImageCopy> copies) {
u32 output_offset = 0;
Common::ScratchBuffer<u8> decode_scratch;
@@ -955,10 +954,10 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
} else if (astc) {
// BC1 uses 0.5 bytes per texel
// BC3 uses 1 byte per texel
const auto compress = recompression_setting == Settings::AstcRecompression::Bc1
? Tegra::Texture::BCN::CompressBC1
: Tegra::Texture::BCN::CompressBC3;
const auto bpp_div = recompression_setting == Settings::AstcRecompression::Bc1 ? 2 : 1;
auto const compress = recompression_setting == Settings::AstcRecompression::Bc1
? Tegra::Texture::BCN::CompressBC1
: Tegra::Texture::BCN::CompressBC3;
const auto bpp_div = compress == Tegra::Texture::BCN::CompressBC1 ? 2 : 1;
const u32 plane_dim = copy.image_extent.width * copy.image_extent.height;
const u32 level_size = plane_dim * copy.image_extent.depth *
@@ -975,18 +974,12 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
copy.image_subresource.num_layers * copy.image_extent.depth,
output.subspan(output_offset));
const u32 aligned_plane_dim = Common::AlignUp(copy.image_extent.width, 4) *
Common::AlignUp(copy.image_extent.height, 4);
copy.buffer_size =
(aligned_plane_dim * copy.image_extent.depth * copy.image_subresource.num_layers) /
bpp_div;
output_offset += static_cast<u32>(copy.buffer_size);
const u32 aligned_plane_dim = Common::AlignUp(copy.image_extent.width, 4) * Common::AlignUp(copy.image_extent.height, 4);
copy.buffer_size = (aligned_plane_dim * copy.image_extent.depth * copy.image_subresource.num_layers) / bpp_div;
output_offset += u32(copy.buffer_size);
} else {
DecompressBCn(input_offset, output.subspan(output_offset), copy, info.format);
output_offset += copy.image_extent.width * copy.image_extent.height *
copy.image_subresource.num_layers *
ConvertedBytesPerBlock(info.format);
output_offset += copy.image_extent.width * copy.image_extent.height * copy.image_subresource.num_layers * ConvertedBytesPerBlock(info.format);
}
copy.buffer_row_length = mip_size.width;