Fixed Sacred 2 Remaster - added indexed texture handles support

src/shader_recompiler/environment.h

@@ -40,9 +40,10 @@ struct HandleKey {
     u32 sec_index, sec_offset, sec_shift_left;
     u32 count;
     bool has_secondary;
+    u32 mask, sec_mask;
     constexpr bool operator==(const HandleKey& o) const noexcept {
-        return std::tie(index, offset, shift_left, sec_index, sec_offset, sec_shift_left, count, has_secondary)
-            == std::tie(o.index, o.offset, o.shift_left, o.sec_index, o.sec_offset, o.sec_shift_left, o.count, o.has_secondary);
+        return std::tie(index, offset, shift_left, sec_index, sec_offset, sec_shift_left, count, has_secondary, mask, sec_mask)
+            == std::tie(o.index, o.offset, o.shift_left, o.sec_index, o.sec_offset, o.sec_shift_left, o.count, o.has_secondary, o.mask, o.sec_mask);
     }
 };
 struct HandleKeyHash {
@@ -52,6 +53,7 @@ struct HandleKeyHash {
         h ^= (size_t(k.sec_index) << 33) ^ (size_t(k.sec_offset) << 2);
         h ^= (size_t(k.sec_shift_left) << 3);
         h ^= (size_t(k.count) << 7);
+        h ^= (size_t(k.mask) << 11) ^ (size_t(k.sec_mask) << 13);
         return h ^ (k.has_secondary ? 0x9e3779b97f4a7c15ULL : 0ULL);
     }
 };
@@ -66,6 +68,14 @@ struct ConstBufferAddr {
     IR::U32 dynamic_offset;
     u32 count;
     bool has_secondary;
+    /// The dynamic offset is a constant buffer value shifted left, the same for the whole draw
+    bool has_index_cbuf;
+    u32 index_cbuf_index;
+    u32 index_cbuf_offset;
+    u32 index_shift;
+    /// Applied after the shifts
+    u32 mask = 0xffffffff;
+    u32 secondary_mask = 0xffffffff;
 };
 
 class Environment {

src/shader_recompiler/frontend/maxwell/translate/impl/floating_point_conversion_integer.cpp

@@ -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 2021 yuzu Emulator Project
@@ -41,9 +41,9 @@ union F2I {
     BitField<39, 2, Rounding> rounding;
     BitField<41, 1, u64> half;
     BitField<44, 1, u64> ftz;
-    BitField<45, 1, u64> abs;
+    BitField<45, 1, u64> neg;
     BitField<47, 1, u64> cc;
-    BitField<49, 1, u64> neg;
+    BitField<49, 1, u64> abs;
 };
 
 size_t BitSize(DestFormat dest_format) {

src/shader_recompiler/ir_opt/texture_pass.cpp

@@ -43,7 +43,8 @@ u32 DynamicDescriptorSizeShift(const IR::U32& dynamic_offset) {
     if (!shift.IsImmediate())
         return DESCRIPTOR_SIZE_SHIFT;
     const u32 size_shift = shift.U32();
-    return size_shift >= DESCRIPTOR_SIZE_SHIFT && size_shift < 31 ? size_shift : DESCRIPTOR_SIZE_SHIFT;
+    // Separate texture and sampler handles are 4 bytes apart
+    return size_shift >= 2 && size_shift < 31 ? size_shift : DESCRIPTOR_SIZE_SHIFT;
 }
 
 u32 DynamicDescriptorCount(u32 base_offset, u32 size_shift, u32 max_descriptors) {
@@ -59,6 +60,37 @@ u32 DynamicDescriptorCount(u32 base_offset, u32 size_shift, u32 max_descriptors)
     return std::min(descriptor_limit, available_count);
 }
 
+struct UniformIndex {
+    u32 cbuf_index;
+    u32 cbuf_offset;
+    u32 shift;
+};
+
+/// Matches a dynamic handle offset that is a constant buffer value, optionally shifted left
+std::optional<UniformIndex> TrackUniformIndex(const IR::U32& dynamic_offset) {
+    if (dynamic_offset.IsImmediate()) {
+        return std::nullopt;
+    }
+    const IR::Inst* inst = dynamic_offset.InstRecursive();
+    u32 shift = 0;
+    if (inst->GetOpcode() == IR::Opcode::ShiftLeftLogical32) {
+        if (!inst->Arg(1).IsImmediate() || inst->Arg(0).IsImmediate()) {
+            return std::nullopt;
+        }
+        shift = inst->Arg(1).U32();
+        inst = inst->Arg(0).InstRecursive();
+    }
+    if (inst->GetOpcode() != IR::Opcode::GetCbufU32 || !inst->Arg(0).IsImmediate() ||
+        !inst->Arg(1).IsImmediate() || shift >= 32) {
+        return std::nullopt;
+    }
+    return UniformIndex{
+        .cbuf_index = inst->Arg(0).U32(),
+        .cbuf_offset = inst->Arg(1).U32(),
+        .shift = shift,
+    };
+}
+
 u32 SaturatingSub(u32 lhs, u32 rhs) {
     return lhs > rhs ? lhs - rhs : 0;
 }
@@ -273,14 +305,15 @@ static inline u32 GetTextureHandleCached(Environment& env, const ConstBufferAddr
     // If has secondary, then it will be cbuf.secondary_{index|offset}, else its 0.
     // So we can just hand it out the raw variable without using sec_idx or sec_off
     // because comparing 0 against 0 will yield true.
-    const HandleKey hk{cbuf.index, cbuf.offset, cbuf.shift_left, cbuf.secondary_index, cbuf.secondary_offset, cbuf.secondary_shift_left, cbuf.count, cbuf.has_secondary};
+    const HandleKey hk{cbuf.index, cbuf.offset, cbuf.shift_left, cbuf.secondary_index, cbuf.secondary_offset, cbuf.secondary_shift_left, cbuf.count, cbuf.has_secondary, cbuf.mask, cbuf.secondary_mask};
     if (auto it = env.handle_cache.find(hk); it != env.handle_cache.end())
         return it->second;
-    const u32 sec_idx = cbuf.has_secondary ? cbuf.secondary_index  : cbuf.index;
-    const u32 sec_off = cbuf.has_secondary ? cbuf.secondary_offset : cbuf.offset;
-    const u32 lhs = ReadCbufCached(env, cbuf.index, cbuf.offset) << cbuf.shift_left;
-    const u32 rhs = ReadCbufCached(env, sec_idx, sec_off) << cbuf.secondary_shift_left;
-    const u32 handle = lhs | rhs;
+    u32 handle = (ReadCbufCached(env, cbuf.index, cbuf.offset) << cbuf.shift_left) & cbuf.mask;
+    if (cbuf.has_secondary) {
+        handle |= (ReadCbufCached(env, cbuf.secondary_index, cbuf.secondary_offset)
+                   << cbuf.secondary_shift_left) &
+                  cbuf.secondary_mask;
+    }
     env.handle_cache.emplace(hk, handle);
     return handle;
 }
@@ -352,10 +385,22 @@ std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environme
         if (lhs->has_secondary || rhs->has_secondary) {
             return std::nullopt;
         }
-        if (lhs->count > 1 || rhs->count > 1) {
+        if (lhs->count > 1 && rhs->count > 1) {
             return std::nullopt;
         }
-        if (lhs->shift_left > 0 || lhs->index > rhs->index || lhs->offset > rhs->offset) {
+        if (rhs->has_index_cbuf || lhs->has_index_cbuf) {
+            if (rhs->has_index_cbuf && lhs->has_index_cbuf) {
+                return std::nullopt;
+            }
+            if (rhs->has_index_cbuf) {
+                std::swap(lhs, rhs);
+            }
+        } else if (rhs->count > 1) {
+            // An indexed handle array combined with a single handle (e.g. texture indices with
+            // a shared sampler), only the primary handle is indexed
+            std::swap(lhs, rhs);
+        } else if (lhs->count == 1 &&
+                   (lhs->shift_left > 0 || lhs->index > rhs->index || lhs->offset > rhs->offset)) {
             std::swap(lhs, rhs);
         }
         return ConstBufferAddr{
@@ -365,9 +410,15 @@ std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environme
             .secondary_index = rhs->index,
             .secondary_offset = rhs->offset,
             .secondary_shift_left = rhs->shift_left,
-            .dynamic_offset = {},
-            .count = 1,
+            .dynamic_offset = lhs->dynamic_offset,
+            .count = lhs->count,
             .has_secondary = true,
+            .has_index_cbuf = lhs->has_index_cbuf,
+            .index_cbuf_index = lhs->index_cbuf_index,
+            .index_cbuf_offset = lhs->index_cbuf_offset,
+            .index_shift = lhs->index_shift,
+            .mask = lhs->mask,
+            .secondary_mask = rhs->mask,
         };
     }
     case IR::Opcode::ShiftLeftLogical32: {
@@ -378,6 +429,8 @@ std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environme
         std::optional lhs{TrackCached(inst->Arg(0), env, host_info)};
         if (lhs) {
             lhs->shift_left = shift.U32();
+            // A mask applied before the shift moves with the value
+            lhs->mask <<= shift.U32();
         }
         return lhs;
     }
@@ -405,7 +458,7 @@ std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environme
         }
         std::optional lhs{TrackCached(op1, env, host_info)};
         if (lhs) {
-            lhs->shift_left = static_cast<u32>(std::countr_zero(op2.U32()));
+            lhs->mask &= op2.U32();
         }
         return lhs;
         break;
@@ -435,12 +488,12 @@ std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environme
         };
     }
     IR::Inst* const offset_inst{offset.InstRecursive()};
-    if (offset_inst->GetOpcode() != IR::Opcode::IAdd32) {
-        return std::nullopt;
-    }
     u32 base_offset{};
     IR::U32 dynamic_offset;
-    if (offset_inst->Arg(0).IsImmediate()) {
+    if (offset_inst->GetOpcode() != IR::Opcode::IAdd32) {
+        // The handle array starts at the beginning of the constant buffer
+        dynamic_offset = IR::U32{offset};
+    } else if (offset_inst->Arg(0).IsImmediate()) {
         base_offset = offset_inst->Arg(0).U32();
         dynamic_offset = IR::U32{offset_inst->Arg(1)};
     } else if (offset_inst->Arg(1).IsImmediate()) {
@@ -450,6 +503,7 @@ std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environme
         return std::nullopt;
     }
     auto const size_shift = DynamicDescriptorSizeShift(dynamic_offset);
+    const std::optional<UniformIndex> uniform_index{TrackUniformIndex(dynamic_offset)};
     auto const sampled_limit = (std::max)(1U, (std::min)(host_info.max_per_stage_descriptor_sampled_images,
                                                          host_info.max_descriptor_set_sampled_images));
     auto const resource_limit = (std::max)(1U, host_info.max_per_stage_resources);
@@ -463,6 +517,10 @@ std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environme
         .dynamic_offset = dynamic_offset,
         .count = DynamicDescriptorCount(base_offset, size_shift, (std::min)({DESCRIPTOR_MAX_COUNT, sampled_limit, resource_limit})),
         .has_secondary = false,
+        .has_index_cbuf = uniform_index.has_value(),
+        .index_cbuf_index = uniform_index ? uniform_index->cbuf_index : 0,
+        .index_cbuf_offset = uniform_index ? uniform_index->cbuf_offset : 0,
+        .index_shift = uniform_index ? uniform_index->shift : 0,
     };
 }
 
@@ -497,12 +555,13 @@ TextureInst MakeInst(Environment& env, IR::Block* block, IR::Inst& inst, const H
 }
 
 u32 GetTextureHandle(Environment& env, const ConstBufferAddr& cbuf) {
-    const u32 secondary_index{cbuf.has_secondary ? cbuf.secondary_index : cbuf.index};
-    const u32 secondary_offset{cbuf.has_secondary ? cbuf.secondary_offset : cbuf.offset};
-    const u32 lhs_raw{env.ReadCbufValue(cbuf.index, cbuf.offset) << cbuf.shift_left};
-    const u32 rhs_raw{env.ReadCbufValue(secondary_index, secondary_offset)
-                      << cbuf.secondary_shift_left};
-    return lhs_raw | rhs_raw;
+    u32 handle{(env.ReadCbufValue(cbuf.index, cbuf.offset) << cbuf.shift_left) & cbuf.mask};
+    if (cbuf.has_secondary) {
+        handle |= (env.ReadCbufValue(cbuf.secondary_index, cbuf.secondary_offset)
+                   << cbuf.secondary_shift_left) &
+                  cbuf.secondary_mask;
+    }
+    return handle;
 }
 
 [[maybe_unused]] TextureType ReadTextureType(Environment& env, const ConstBufferAddr& cbuf) {
@@ -536,7 +595,8 @@ public:
                    desc.secondary_cbuf_offset == existing.secondary_cbuf_offset &&
                    desc.secondary_shift_left == existing.secondary_shift_left &&
                    desc.count == existing.count && desc.size_shift == existing.size_shift &&
-                   desc.has_secondary == existing.has_secondary;
+                   desc.has_secondary == existing.has_secondary && desc.mask == existing.mask &&
+                   desc.secondary_mask == existing.secondary_mask;
         });
     }
 
@@ -562,7 +622,12 @@ public:
                    desc.secondary_cbuf_index == existing.secondary_cbuf_index &&
                    desc.secondary_cbuf_offset == existing.secondary_cbuf_offset &&
                    desc.secondary_shift_left == existing.secondary_shift_left &&
-                   desc.count == existing.count && desc.size_shift == existing.size_shift;
+                   desc.count == existing.count && desc.size_shift == existing.size_shift &&
+                   desc.has_index_cbuf == existing.has_index_cbuf &&
+                   desc.index_cbuf_index == existing.index_cbuf_index &&
+                   desc.index_cbuf_offset == existing.index_cbuf_offset &&
+                   desc.index_shift == existing.index_shift && desc.mask == existing.mask &&
+                   desc.secondary_mask == existing.secondary_mask;
         })};
         // TODO: Read this from TIC
         texture_descriptors[index].is_multisample |= desc.is_multisample;
@@ -808,9 +873,12 @@ void TexturePass(Environment& env, IR::Program& program, const HostTranslateInfo
                     .secondary_shift_left = cbuf.secondary_shift_left,
                     .count = count,
                     .size_shift = size_shift,
+                    .mask = cbuf.mask,
+                    .secondary_mask = cbuf.secondary_mask,
                 });
             } else {
-                count = std::min(count, sampled_dynamic_cap);
+                // A uniform index is resolved when drawing, so a single descriptor is enough
+                count = cbuf.has_index_cbuf ? 1 : std::min(count, sampled_dynamic_cap);
                 const bool is_integer{is_texture_pixel_format_integer(cbuf)};
                 index = descriptors.Add(TextureDescriptor{
                     .type = flags.type,
@@ -826,6 +894,12 @@ void TexturePass(Environment& env, IR::Program& program, const HostTranslateInfo
                     .secondary_shift_left = cbuf.secondary_shift_left,
                     .count = count,
                     .size_shift = size_shift,
+                    .has_index_cbuf = cbuf.has_index_cbuf,
+                    .index_cbuf_index = cbuf.index_cbuf_index,
+                    .index_cbuf_offset = cbuf.index_cbuf_offset,
+                    .index_shift = cbuf.index_shift,
+                    .mask = cbuf.mask,
+                    .secondary_mask = cbuf.secondary_mask,
                 });
                 flags.is_integer.Assign(is_integer ? 1 : 0);
             }

src/shader_recompiler/shader_info.h

@@ -186,6 +186,8 @@ struct TextureBufferDescriptor {
     u32 secondary_shift_left;
     u32 count;
     u32 size_shift;
+    u32 mask = 0xffffffff;
+    u32 secondary_mask = 0xffffffff;
 
     auto operator<=>(const TextureBufferDescriptor&) const = default;
 };
@@ -219,6 +221,13 @@ struct TextureDescriptor {
     u32 secondary_shift_left;
     u32 count;
     u32 size_shift;
+    /// The handle offset is moved by a constant buffer value read when drawing
+    bool has_index_cbuf;
+    u32 index_cbuf_index;
+    u32 index_cbuf_offset;
+    u32 index_shift;
+    u32 mask = 0xffffffff;
+    u32 secondary_mask = 0xffffffff;
 
     auto operator<=>(const TextureDescriptor&) const = default;
 };

src/video_core/buffer_cache/buffer_cache.h

@@ -948,9 +948,14 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
             return alignment > 1 && (offset % alignment) != 0;
         }
     }();
+    // Uniform data rewritten by the CPU between draws would need a transfer copy into the cached
+    // buffer, which ends the current render pass. Read it from the stream buffer instead.
+    static constexpr u32 MAX_STREAMED_UNIFORM_BYTES = static_cast<u32>(16_KiB);
     const bool use_fast_buffer = needs_alignment_stream
-        || (has_host_buffer && size <= channel_state->uniform_buffer_skip_cache_size
-            && !memory_tracker.IsRegionGpuModified(device_addr, size));
+        || (has_host_buffer && !memory_tracker.IsRegionGpuModified(device_addr, size)
+            && (size <= channel_state->uniform_buffer_skip_cache_size
+                || (size <= MAX_STREAMED_UNIFORM_BYTES
+                    && memory_tracker.IsRegionCpuModified(device_addr, size))));
     if (use_fast_buffer) {
         if constexpr (IS_OPENGL) {
             if (runtime.HasFastBufferSubData()) {

src/video_core/buffer_cache/buffer_cache_base.h

@@ -259,6 +259,23 @@ public:
 
     void BindHostComputeBuffers();
 
+    /// Calls func(buffer, offset, device_addr, size) for each storage buffer the current compute
+    /// dispatch writes through a single host buffer
+    template <typename Func>
+    void ForEachWrittenComputeStorageBuffer(Func&& func) {
+        const u32 written = channel_state->enabled_compute_storage_buffers &
+                            channel_state->written_compute_storage_buffers;
+        ForEachEnabledBit(written, [&](u32 index) {
+            const Binding& binding = channel_state->compute_storage_buffers[index];
+            if (binding.buffer_id == NULL_BUFFER_ID || binding.segment_count != 0 ||
+                binding.size == 0) {
+                return;
+            }
+            Buffer& buffer = slot_buffers[binding.buffer_id];
+            func(buffer, buffer.Offset(binding.device_addr), binding.device_addr, binding.size);
+        });
+    }
+
     void SetUniformBuffersState(const std::array<u32, NUM_STAGES>& mask,
                                 const UniformBufferSizes* sizes);
 

src/video_core/host_shaders/CMakeLists.txt

@@ -83,6 +83,7 @@ set(SHADER_FILES
     ${CMAKE_CURRENT_SOURCE_DIR}/vulkan_present.vert
     ${CMAKE_CURRENT_SOURCE_DIR}/vulkan_present_scaleforce_fp16.frag
     ${CMAKE_CURRENT_SOURCE_DIR}/vulkan_present_scaleforce_fp32.frag
+    ${CMAKE_CURRENT_SOURCE_DIR}/vulkan_block_linear_unswizzle_2d_buffer.comp
     ${CMAKE_CURRENT_SOURCE_DIR}/vulkan_quad_indexed.comp
     ${CMAKE_CURRENT_SOURCE_DIR}/vulkan_turbo_mode.comp
     ${CMAKE_CURRENT_SOURCE_DIR}/vulkan_uint8.comp

src/video_core/host_shaders/vulkan_block_linear_unswizzle_2d_buffer.comp

@@ -0,0 +1,62 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
+#version 460 core
+
+// Copies a block linear 2D image from a buffer into a tightly packed linear buffer, 4 bytes at a
+// time. 16 byte chunks of a row are contiguous in a GOB, so any texel size works as long as the
+// row size is a multiple of 4 bytes.
+
+layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
+
+layout(std430, set = 0, binding = 0) readonly buffer InputBuffer {
+    uint swizzled[];
+};
+
+layout(std430, set = 0, binding = 1) writeonly buffer OutputBuffer {
+    uint linear[];
+};
+
+layout(push_constant) uniform PushConstants {
+    uint src_word_offset;
+    uint row_words;
+    uint height;
+    uint layer_stride;
+    uint block_size;
+    uint x_shift;
+    uint block_height;
+    uint block_height_mask;
+};
+
+const uint GOB_SIZE_X_SHIFT = 6;
+const uint GOB_SIZE_Y_SHIFT = 3;
+const uint GOB_SIZE_SHIFT = GOB_SIZE_X_SHIFT + GOB_SIZE_Y_SHIFT;
+
+uint SwizzleTable(uint pos) {
+    const uint t[8] = uint[](
+        0x12100200, 0x13110301, 0x16140604, 0x17150705,
+        0x1a180a08, 0x1b190b09, 0x1e1c0e0c, 0x1f1d0f0d
+    );
+    const uint i = pos >> 4;
+    const uint h = (t[i / 4] >> ((i % 4) * 8)) & 0xff;
+    return (h << 4) | (pos & 0xf);
+}
+
+void main() {
+    const uint word = gl_GlobalInvocationID.x;
+    const uint y = gl_GlobalInvocationID.y;
+    const uint layer = gl_GlobalInvocationID.z;
+    if (word >= row_words || y >= height) {
+        return;
+    }
+    const uint x = word * 4;
+    const uint block_y = y >> GOB_SIZE_Y_SHIFT;
+
+    uint offset = layer * layer_stride;
+    offset += (block_y >> block_height) * block_size;
+    offset += (block_y & block_height_mask) << GOB_SIZE_SHIFT;
+    offset += (x >> GOB_SIZE_X_SHIFT) << x_shift;
+    offset += SwizzleTable((y & 7) * 64 + (x & 63));
+
+    linear[(layer * height + y) * row_words + word] = swizzled[src_word_offset + offset / 4];
+}

src/video_core/renderer_opengl/gl_compute_pipeline.cpp

@@ -107,22 +107,36 @@ void ComputePipeline::Configure() {
     const auto read_handle{[&](const auto& desc, u32 index) {
         ASSERT(((qmd.const_buffer_enable_mask >> desc.cbuf_index) & 1) != 0);
         const u32 index_offset{index << desc.size_shift};
-        const u32 offset{desc.cbuf_offset + index_offset};
+        u32 offset{desc.cbuf_offset + index_offset};
+        if constexpr (std::is_same_v<decltype(desc), const Shader::TextureDescriptor&>) {
+            if (desc.has_index_cbuf) {
+                ASSERT(((qmd.const_buffer_enable_mask >> desc.index_cbuf_index) & 1) != 0);
+                offset += gpu_memory->Read<u32>(cbufs[desc.index_cbuf_index].Address() +
+                                                desc.index_cbuf_offset)
+                          << desc.index_shift;
+            }
+        }
         const GPUVAddr addr{cbufs[desc.cbuf_index].Address() + offset};
         if constexpr (std::is_same_v<decltype(desc), const Shader::TextureDescriptor&> ||
                       std::is_same_v<decltype(desc), const Shader::TextureBufferDescriptor&>) {
             if (desc.has_secondary) {
                 ASSERT(((qmd.const_buffer_enable_mask >> desc.secondary_cbuf_index) & 1) != 0);
-                const u32 secondary_offset{desc.secondary_cbuf_offset + index_offset};
+                const u32 secondary_offset{desc.secondary_cbuf_offset};
                 const GPUVAddr separate_addr{cbufs[desc.secondary_cbuf_index].Address() +
                                              secondary_offset};
-                const u32 lhs_raw{gpu_memory->Read<u32>(addr) << desc.shift_left};
-                const u32 rhs_raw{gpu_memory->Read<u32>(separate_addr)
-                                  << desc.secondary_shift_left};
+                const u32 lhs_raw{(gpu_memory->Read<u32>(addr) << desc.shift_left) & desc.mask};
+                const u32 rhs_raw{(gpu_memory->Read<u32>(separate_addr)
+                                   << desc.secondary_shift_left) &
+                                  desc.secondary_mask};
                 return TexturePair(lhs_raw | rhs_raw, via_header_index);
             }
         }
-        return TexturePair(gpu_memory->Read<u32>(addr), via_header_index);
+        u32 raw{gpu_memory->Read<u32>(addr)};
+        if constexpr (std::is_same_v<decltype(desc), const Shader::TextureDescriptor&> ||
+                      std::is_same_v<decltype(desc), const Shader::TextureBufferDescriptor&>) {
+            raw &= desc.mask;
+        }
+        return TexturePair(raw, via_header_index);
     }};
     const auto add_image{[&](const auto& desc, bool blacklist) {
         for (u32 index = 0; index < desc.count; ++index) {

src/video_core/renderer_opengl/gl_graphics_pipeline.cpp

@@ -308,23 +308,37 @@ bool GraphicsPipeline::ConfigureImpl(bool is_indexed) {
         const auto read_handle{[&](const auto& desc, u32 index) {
             ASSERT(cbufs[desc.cbuf_index].enabled);
             const u32 index_offset{index << desc.size_shift};
-            const u32 offset{desc.cbuf_offset + index_offset};
+            u32 offset{desc.cbuf_offset + index_offset};
+            if constexpr (std::is_same_v<decltype(desc), const TextureDescriptor&>) {
+                if (desc.has_index_cbuf) {
+                    ASSERT(cbufs[desc.index_cbuf_index].enabled);
+                    offset += gpu_memory->Read<u32>(cbufs[desc.index_cbuf_index].address +
+                                                    desc.index_cbuf_offset)
+                              << desc.index_shift;
+                }
+            }
             const GPUVAddr addr{cbufs[desc.cbuf_index].address + offset};
             if constexpr (std::is_same_v<decltype(desc), const TextureDescriptor&> ||
                           std::is_same_v<decltype(desc), const TextureBufferDescriptor&>) {
                 if (desc.has_secondary) {
                     ASSERT(cbufs[desc.secondary_cbuf_index].enabled);
-                    const u32 second_offset{desc.secondary_cbuf_offset + index_offset};
+                    const u32 second_offset{desc.secondary_cbuf_offset};
                     const GPUVAddr separate_addr{cbufs[desc.secondary_cbuf_index].address +
                                                  second_offset};
-                    const u32 lhs_raw{gpu_memory->Read<u32>(addr) << desc.shift_left};
-                    const u32 rhs_raw{gpu_memory->Read<u32>(separate_addr)
-                                      << desc.secondary_shift_left};
+                    const u32 lhs_raw{(gpu_memory->Read<u32>(addr) << desc.shift_left) & desc.mask};
+                    const u32 rhs_raw{(gpu_memory->Read<u32>(separate_addr)
+                                       << desc.secondary_shift_left) &
+                                      desc.secondary_mask};
                     const u32 raw{lhs_raw | rhs_raw};
                     return TexturePair(raw, via_header_index);
                 }
             }
-            return TexturePair(gpu_memory->Read<u32>(addr), via_header_index);
+            u32 raw{gpu_memory->Read<u32>(addr)};
+            if constexpr (std::is_same_v<decltype(desc), const TextureDescriptor&> ||
+                          std::is_same_v<decltype(desc), const TextureBufferDescriptor&>) {
+                raw &= desc.mask;
+            }
+            return TexturePair(raw, via_header_index);
         }};
         const auto add_image{[&](const auto& desc, bool blacklist) LAMBDA_FORCEINLINE {
             for (u32 index = 0; index < desc.count; ++index) {

src/video_core/renderer_vulkan/fixed_pipeline_state.cpp

@@ -129,7 +129,13 @@ void FixedPipelineState::Refresh(Tegra::Engines::Maxwell3D& maxwell3d, DynamicFe
     topology.Assign(can_collapse_topology_class
                         ? TOPOLOGY_CLASS_REPRESENTATIVE_LUT[static_cast<size_t>(topology_)]
                         : topology_);
-    msaa_mode.Assign(regs.anti_alias_samples_mode);
+    // Target-independent rasterization rasterizes (and depth tests) at the raster sample count
+    if (regs.tir_mode == Maxwell::TIRMode::RasterNTargetM &&
+        regs.anti_alias_raster != Maxwell::AntiAliasRaster::Mode1x1) {
+        msaa_mode.Assign(static_cast<Tegra::Texture::MsaaMode>(regs.anti_alias_raster));
+    } else {
+        msaa_mode.Assign(regs.anti_alias_samples_mode);
+    }
     attachment0_dual_source_blend.Assign(ComputeAttachment0DualSourceBlend(regs) ? 1 : 0);
 
     raw2 = 0;

src/video_core/renderer_vulkan/vk_compute_pass.cpp

@@ -20,6 +20,7 @@
 #include "video_core/host_shaders/queries_prefix_scan_sum_comp_spv.h"
 #include "video_core/host_shaders/queries_prefix_scan_sum_nosubgroups_comp_spv.h"
 #include "video_core/host_shaders/resolve_conditional_render_comp_spv.h"
+#include "video_core/host_shaders/vulkan_block_linear_unswizzle_2d_buffer_comp_spv.h"
 #include "video_core/host_shaders/vulkan_quad_indexed_comp_spv.h"
 #include "video_core/host_shaders/vulkan_uint8_comp_spv.h"
 #include "video_core/host_shaders/block_linear_unswizzle_3d_bcn_comp_spv.h"
@@ -31,6 +32,7 @@
 #include "video_core/renderer_vulkan/vk_update_descriptor.h"
 #include "video_core/texture_cache/accelerated_swizzle.h"
 #include "video_core/texture_cache/types.h"
+#include "video_core/texture_cache/util.h"
 #include "video_core/textures/decoders.h"
 #include "video_core/vulkan_common/vulkan_device.h"
 #include "video_core/vulkan_common/vulkan_wrapper.h"
@@ -640,6 +642,143 @@ struct alignas(16) BlockLinearUnswizzle3DPushConstants {
 };
 static_assert(sizeof(BlockLinearUnswizzle3DPushConstants) <= 128);
 
+struct BlockLinearUnswizzle2DBufferPushConstants {
+    u32 src_word_offset;
+    u32 row_words;
+    u32 height;
+    u32 layer_stride;
+    u32 block_size;
+    u32 x_shift;
+    u32 block_height;
+    u32 block_height_mask;
+};
+
+BlockLinearUnswizzle2DBufferPass::BlockLinearUnswizzle2DBufferPass(
+    const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+    StagingBufferPool& staging_buffer_pool_,
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue_)
+    : ComputePass(device_, scheduler_, descriptor_pool_, INPUT_OUTPUT_DESCRIPTOR_SET_BINDINGS,
+                  INPUT_OUTPUT_DESCRIPTOR_UPDATE_TEMPLATE, INPUT_OUTPUT_BANK_INFO,
+                  COMPUTE_PUSH_CONSTANT_RANGE<sizeof(BlockLinearUnswizzle2DBufferPushConstants)>,
+                  VULKAN_BLOCK_LINEAR_UNSWIZZLE_2D_BUFFER_COMP_SPV),
+      scheduler{scheduler_}, staging_buffer_pool{staging_buffer_pool_},
+      compute_pass_descriptor_queue{compute_pass_descriptor_queue_} {}
+
+BlockLinearUnswizzle2DBufferPass::~BlockLinearUnswizzle2DBufferPass() = default;
+
+bool BlockLinearUnswizzle2DBufferPass::IsSupported(const Image& image) {
+    const VideoCommon::ImageInfo& info = image.info;
+    if (info.type != VideoCommon::ImageType::e2D || info.num_samples != 1 ||
+        VideoCore::Surface::GetFormatType(info.format) != VideoCore::Surface::SurfaceType::ColorTexture ||
+        VideoCore::Surface::DefaultBlockWidth(info.format) != 1 ||
+        VideoCore::Surface::DefaultBlockHeight(info.format) != 1 ||
+        True(image.flags & VideoCommon::ImageFlagBits::Converted) ||
+        True(image.flags & VideoCommon::ImageFlagBits::Rescaled)) {
+        return false;
+    }
+    const u32 bytes_per_block = VideoCore::Surface::BytesPerBlock(info.format);
+    for (const VideoCommon::SwizzleParameters& swizzle : VideoCommon::FullUploadSwizzles(info)) {
+        if ((swizzle.num_tiles.width * bytes_per_block) % 4 != 0 || swizzle.num_tiles.depth != 1) {
+            return false;
+        }
+    }
+    return true;
+}
+
+std::pair<VkBuffer, boost::container::small_vector<VkBufferImageCopy, 16>>
+BlockLinearUnswizzle2DBufferPass::Unswizzle(Image& image, VkBuffer src_buffer,
+                                            VkDeviceSize src_offset) {
+    const VideoCommon::ImageInfo& info = image.info;
+    const auto swizzles = VideoCommon::FullUploadSwizzles(info);
+    const u32 bytes_per_block = VideoCore::Surface::BytesPerBlock(info.format);
+    const u32 layers = static_cast<u32>(info.resources.layers);
+    const VkDeviceSize alignment = (std::max<VkDeviceSize>)(device.GetStorageBufferAlignment(), 4);
+
+    VkDeviceSize total_size = 0;
+    for (const VideoCommon::SwizzleParameters& swizzle : swizzles) {
+        total_size = Common::AlignUp(total_size, alignment);
+        total_size += VkDeviceSize{swizzle.num_tiles.width} * bytes_per_block *
+                      swizzle.num_tiles.height * layers;
+    }
+    const StagingBufferRef linear = staging_buffer_pool.Request(total_size, MemoryUsage::DeviceLocal);
+
+    scheduler.RequestOutsideRenderPassOperationContext();
+    scheduler.Record([](vk::CommandBuffer cmdbuf) {
+        static constexpr VkMemoryBarrier READ_BARRIER{
+            .sType = VK_STRUCTURE_TYPE_MEMORY_BARRIER,
+            .pNext = nullptr,
+            .srcAccessMask = VK_ACCESS_SHADER_WRITE_BIT | VK_ACCESS_TRANSFER_WRITE_BIT,
+            .dstAccessMask = VK_ACCESS_SHADER_READ_BIT,
+        };
+        cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_ALL_COMMANDS_BIT,
+                               VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, 0, READ_BARRIER);
+    });
+
+    boost::container::small_vector<VkBufferImageCopy, 16> copies;
+    VkDeviceSize linear_offset = 0;
+    for (const VideoCommon::SwizzleParameters& swizzle : swizzles) {
+        linear_offset = Common::AlignUp(linear_offset, alignment);
+        const auto params = VideoCommon::Accelerated::MakeBlockLinearSwizzle2DParams(swizzle, info);
+        const u32 row_words = swizzle.num_tiles.width * bytes_per_block / 4;
+        const u32 height = swizzle.num_tiles.height;
+        const VkDeviceSize level_size = VkDeviceSize{row_words} * 4 * height * layers;
+        const VkDeviceSize level_src = src_offset + swizzle.buffer_offset;
+        const VkDeviceSize aligned_src = level_src & ~(alignment - 1);
+        const VkDeviceSize src_size = image.guest_size_bytes - swizzle.buffer_offset +
+                                      (level_src - aligned_src);
+
+        compute_pass_descriptor_queue.Acquire(scheduler, 2);
+        compute_pass_descriptor_queue.AddBuffer(src_buffer, aligned_src, src_size);
+        compute_pass_descriptor_queue.AddBuffer(linear.buffer, linear.offset + linear_offset,
+                                                level_size);
+        const void* const descriptor_data{compute_pass_descriptor_queue.UpdateData()};
+        const BlockLinearUnswizzle2DBufferPushConstants push{
+            .src_word_offset = static_cast<u32>((level_src - aligned_src) / 4),
+            .row_words = row_words,
+            .height = height,
+            .layer_stride = params.layer_stride,
+            .block_size = params.block_size,
+            .x_shift = params.x_shift,
+            .block_height = params.block_height,
+            .block_height_mask = params.block_height_mask,
+        };
+        scheduler.Record([this, descriptor_data, push, layers](vk::CommandBuffer cmdbuf) {
+            static constexpr u32 WORKGROUP_SIZE_X = 64;
+            const VkDescriptorSet set = descriptor_allocator.Commit();
+            device.GetLogical().UpdateDescriptorSet(set, *descriptor_template, descriptor_data);
+            cmdbuf.BindPipeline(VK_PIPELINE_BIND_POINT_COMPUTE, *pipeline);
+            cmdbuf.BindDescriptorSets(VK_PIPELINE_BIND_POINT_COMPUTE, *layout, 0, set, {});
+            cmdbuf.PushConstants(*layout, VK_SHADER_STAGE_COMPUTE_BIT, push);
+            cmdbuf.Dispatch(Common::DivCeil(push.row_words, WORKGROUP_SIZE_X), push.height, layers);
+        });
+        copies.push_back(VkBufferImageCopy{
+            .bufferOffset = linear.offset + linear_offset,
+            .bufferRowLength = 0,
+            .bufferImageHeight = 0,
+            .imageSubresource{
+                .aspectMask = VK_IMAGE_ASPECT_COLOR_BIT,
+                .mipLevel = static_cast<u32>(swizzle.level),
+                .baseArrayLayer = 0,
+                .layerCount = layers,
+            },
+            .imageOffset{0, 0, 0},
+            .imageExtent{swizzle.num_tiles.width, height, 1},
+        });
+        linear_offset += level_size;
+    }
+    scheduler.Record([](vk::CommandBuffer cmdbuf) {
+        static constexpr VkMemoryBarrier WRITE_BARRIER{
+            .sType = VK_STRUCTURE_TYPE_MEMORY_BARRIER,
+            .pNext = nullptr,
+            .srcAccessMask = VK_ACCESS_SHADER_WRITE_BIT,
+            .dstAccessMask = VK_ACCESS_TRANSFER_READ_BIT,
+        };
+        cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
+                               VK_PIPELINE_STAGE_TRANSFER_BIT, 0, WRITE_BARRIER);
+    });
+    return {linear.buffer, std::move(copies)};
+}
+
 BlockLinearUnswizzle3DPass::BlockLinearUnswizzle3DPass(
     const Device& device_, Scheduler& scheduler_,
     DescriptorPool& descriptor_pool_,

src/video_core/renderer_vulkan/vk_compute_pass.h

@@ -10,6 +10,8 @@
 #include <span>
 #include <utility>
 
+#include <boost/container/small_vector.hpp>
+
 #include "common/common_types.h"
 #include "video_core/engines/maxwell_3d.h"
 #include "video_core/renderer_vulkan/vk_descriptor_pool.h"
@@ -137,6 +139,28 @@ private:
     MemoryAllocator& memory_allocator;
 };
 
+class BlockLinearUnswizzle2DBufferPass final : public ComputePass {
+public:
+    explicit BlockLinearUnswizzle2DBufferPass(
+        const Device& device_, Scheduler& scheduler_, DescriptorPool& descriptor_pool_,
+        StagingBufferPool& staging_buffer_pool_,
+        ComputePassDescriptorQueue& compute_pass_descriptor_queue_);
+    ~BlockLinearUnswizzle2DBufferPass();
+
+    /// Returns true when the guest layout of the image can be unswizzled by this pass
+    [[nodiscard]] static bool IsSupported(const Image& image);
+
+    /// Unswizzles the block linear guest data of the image, read from a GPU buffer, into a linear
+    /// buffer. Returns the linear buffer and the copies that upload it into the image.
+    std::pair<VkBuffer, boost::container::small_vector<VkBufferImageCopy, 16>> Unswizzle(
+        Image& image, VkBuffer src_buffer, VkDeviceSize src_offset);
+
+private:
+    Scheduler& scheduler;
+    StagingBufferPool& staging_buffer_pool;
+    ComputePassDescriptorQueue& compute_pass_descriptor_queue;
+};
+
 class BlockLinearUnswizzle3DPass final : public ComputePass {
 public:
     explicit BlockLinearUnswizzle3DPass(const Device& device_, Scheduler& scheduler_,

src/video_core/renderer_vulkan/vk_compute_pipeline.cpp

@@ -174,21 +174,36 @@ bool ComputePipeline::Configure(Tegra::Engines::KeplerCompute& kepler_compute,
     const auto read_handle{[&](const auto& desc, u32 index) {
         ASSERT(((qmd.const_buffer_enable_mask >> desc.cbuf_index) & 1) != 0);
         const u32 index_offset{index << desc.size_shift};
-        const u32 offset{desc.cbuf_offset + index_offset};
+        u32 offset{desc.cbuf_offset + index_offset};
+        if constexpr (std::is_same_v<decltype(desc), const Shader::TextureDescriptor&>) {
+            if (desc.has_index_cbuf) {
+                ASSERT(((qmd.const_buffer_enable_mask >> desc.index_cbuf_index) & 1) != 0);
+                offset += gpu_memory.Read<u32>(cbufs[desc.index_cbuf_index].Address() +
+                                               desc.index_cbuf_offset)
+                          << desc.index_shift;
+            }
+        }
         const GPUVAddr addr{cbufs[desc.cbuf_index].Address() + offset};
         if constexpr (std::is_same_v<decltype(desc), const Shader::TextureDescriptor&> ||
                       std::is_same_v<decltype(desc), const Shader::TextureBufferDescriptor&>) {
             if (desc.has_secondary) {
                 ASSERT(((qmd.const_buffer_enable_mask >> desc.secondary_cbuf_index) & 1) != 0);
-                const u32 secondary_offset{desc.secondary_cbuf_offset + index_offset};
+                const u32 secondary_offset{desc.secondary_cbuf_offset};
                 const GPUVAddr separate_addr{cbufs[desc.secondary_cbuf_index].Address() +
                                              secondary_offset};
-                const u32 lhs_raw{gpu_memory.Read<u32>(addr) << desc.shift_left};
-                const u32 rhs_raw{gpu_memory.Read<u32>(separate_addr) << desc.secondary_shift_left};
+                const u32 lhs_raw{(gpu_memory.Read<u32>(addr) << desc.shift_left) & desc.mask};
+                const u32 rhs_raw{(gpu_memory.Read<u32>(separate_addr)
+                                   << desc.secondary_shift_left) &
+                                  desc.secondary_mask};
                 return TexturePair(lhs_raw | rhs_raw, via_header_index);
             }
         }
-        return TexturePair(gpu_memory.Read<u32>(addr), via_header_index);
+        u32 raw{gpu_memory.Read<u32>(addr)};
+        if constexpr (std::is_same_v<decltype(desc), const Shader::TextureDescriptor&> ||
+                      std::is_same_v<decltype(desc), const Shader::TextureBufferDescriptor&>) {
+            raw &= desc.mask;
+        }
+        return TexturePair(raw, via_header_index);
     }};
     const auto add_image{[&](const auto& desc, bool blacklist) {
         for (u32 index = 0; index < desc.count; ++index) {

src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp

@@ -377,23 +377,37 @@ bool GraphicsPipeline::ConfigureImpl(bool is_indexed) {
         const auto read_handle{[&](const auto& desc, u32 index) {
             ASSERT(cbufs[desc.cbuf_index].enabled);
             const u32 index_offset{index << desc.size_shift};
-            const u32 offset{desc.cbuf_offset + index_offset};
+            u32 offset{desc.cbuf_offset + index_offset};
+            if constexpr (std::is_same_v<decltype(desc), const Shader::TextureDescriptor&>) {
+                if (desc.has_index_cbuf) {
+                    ASSERT(cbufs[desc.index_cbuf_index].enabled);
+                    offset += gpu_memory->Read<u32>(cbufs[desc.index_cbuf_index].address +
+                                                    desc.index_cbuf_offset)
+                              << desc.index_shift;
+                }
+            }
             const GPUVAddr addr{cbufs[desc.cbuf_index].address + offset};
             if constexpr (std::is_same_v<decltype(desc), const Shader::TextureDescriptor&> ||
                           std::is_same_v<decltype(desc), const Shader::TextureBufferDescriptor&>) {
                 if (desc.has_secondary) {
                     ASSERT(cbufs[desc.secondary_cbuf_index].enabled);
-                    const u32 second_offset{desc.secondary_cbuf_offset + index_offset};
+                    const u32 second_offset{desc.secondary_cbuf_offset};
                     const GPUVAddr separate_addr{cbufs[desc.secondary_cbuf_index].address +
                                                  second_offset};
-                    const u32 lhs_raw{gpu_memory->Read<u32>(addr) << desc.shift_left};
-                    const u32 rhs_raw{gpu_memory->Read<u32>(separate_addr)
-                                      << desc.secondary_shift_left};
+                    const u32 lhs_raw{(gpu_memory->Read<u32>(addr) << desc.shift_left) & desc.mask};
+                    const u32 rhs_raw{(gpu_memory->Read<u32>(separate_addr)
+                                       << desc.secondary_shift_left) &
+                                      desc.secondary_mask};
                     const u32 raw{lhs_raw | rhs_raw};
                     return TexturePair(raw, via_header_index);
                 }
             }
-            return TexturePair(gpu_memory->Read<u32>(addr), via_header_index);
+            u32 raw{gpu_memory->Read<u32>(addr)};
+            if constexpr (std::is_same_v<decltype(desc), const Shader::TextureDescriptor&> ||
+                          std::is_same_v<decltype(desc), const Shader::TextureBufferDescriptor&>) {
+                raw &= desc.mask;
+            }
+            return TexturePair(raw, via_header_index);
         }};
         const auto add_image{[&](const auto& desc, bool blacklist) LAMBDA_FORCEINLINE {
             for (u32 index = 0; index < desc.count; ++index) {

src/video_core/renderer_vulkan/vk_rasterizer.cpp

@@ -596,6 +596,12 @@ void RasterizerVulkan::DispatchCompute() {
         return;
     }
 
+    const auto update_images_written_by_buffers = [this] {
+        buffer_cache.ForEachWrittenComputeStorageBuffer(
+            [this](auto& buffer, u32 offset, DAddr device_addr, u32 size) {
+                texture_cache.UpdateImagesFromBuffer(device_addr, size, buffer.Handle(), offset);
+            });
+    };
     const auto& qmd{kepler_compute->launch_description};
     auto indirect_address = kepler_compute->GetIndirectComputeAddress();
     if (indirect_address) {
@@ -612,6 +618,7 @@ void RasterizerVulkan::DispatchCompute() {
             }
             cmdbuf.DispatchIndirect(indirect_buffer, indirect_offset);
         });
+        update_images_written_by_buffers();
         return;
     }
     const std::array<u32, 3> dim{qmd.grid_dim_x, qmd.grid_dim_y, qmd.grid_dim_z};
@@ -634,6 +641,7 @@ void RasterizerVulkan::DispatchCompute() {
         }
         cmdbuf.Dispatch(dim[0], dim[1], dim[2]);
     });
+    update_images_written_by_buffers();
 
     // Log compute dispatch
     if (GPU::Logging::IsActive() &&

src/video_core/renderer_vulkan/vk_texture_cache.cpp

@@ -946,6 +946,8 @@ TextureCacheRuntime::TextureCacheRuntime(const Device& device_, Scheduler& sched
         astc_decoder_pass.emplace(device, scheduler, descriptor_pool, staging_buffer_pool,
                                   compute_pass_descriptor_queue, memory_allocator);
     }
+    bl2d_buffer_unswizzle_pass.emplace(device, scheduler, descriptor_pool, staging_buffer_pool,
+                                       compute_pass_descriptor_queue);
     if (!device.IsKhrImageFormatListSupported()) {
         return;
     }
@@ -1089,6 +1091,58 @@ VkImageView TextureCacheRuntime::GetOrCreateResolveShadow(VkImage msaa_image, Vk
     return *shadow.view;
 }
 
+VkImageView TextureCacheRuntime::GetOrCreateTirColorScratch(VkImage color_image, VkFormat format,
+                                                            VkExtent2D extent, u32 layers,
+                                                            VkSampleCountFlagBits samples) {
+    TirColorScratch& scratch = tir_color_scratch[color_image];
+    if (scratch.image && scratch.format == format && scratch.extent.width == extent.width &&
+        scratch.extent.height == extent.height && scratch.layers == layers &&
+        scratch.samples == samples) {
+        return *scratch.view;
+    }
+    if (scratch.image) {
+        scheduler.Finish();
+    }
+    scratch.image = memory_allocator.CreateImage(VkImageCreateInfo{
+        .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO,
+        .pNext = nullptr,
+        .flags = 0,
+        .imageType = VK_IMAGE_TYPE_2D,
+        .format = format,
+        .extent = {extent.width, extent.height, 1},
+        .mipLevels = 1,
+        .arrayLayers = layers,
+        .samples = samples,
+        .tiling = VK_IMAGE_TILING_OPTIMAL,
+        .usage = VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT | VK_IMAGE_USAGE_TRANSFER_SRC_BIT,
+        .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
+        .queueFamilyIndexCount = 0,
+        .pQueueFamilyIndices = nullptr,
+        .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED,
+    });
+    scratch.view = device.GetLogical().CreateImageView(VkImageViewCreateInfo{
+        .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO,
+        .pNext = nullptr,
+        .flags = 0,
+        .image = *scratch.image,
+        .viewType = layers > 1 ? VK_IMAGE_VIEW_TYPE_2D_ARRAY : VK_IMAGE_VIEW_TYPE_2D,
+        .format = format,
+        .components{},
+        .subresourceRange{
+            .aspectMask = VK_IMAGE_ASPECT_COLOR_BIT,
+            .baseMipLevel = 0,
+            .levelCount = 1,
+            .baseArrayLayer = 0,
+            .layerCount = layers,
+        },
+    });
+    scratch.format = format;
+    scratch.extent = extent;
+    scratch.layers = layers;
+    scratch.samples = samples;
+    return *scratch.view;
+}
+
 const TextureCacheRuntime::ResolveShadow* TextureCacheRuntime::GetValidResolveShadow(
     VkImage msaa_image) const {
     const auto it = resolve_shadows.find(msaa_image);
@@ -2068,6 +2122,27 @@ void Image::UploadMemory(VkBuffer buffer, VkDeviceSize offset,
     }
 }
 
+bool Image::UploadSwizzledFromBuffer(VkBuffer buffer, VkDeviceSize offset) {
+    if (runtime == nullptr || !runtime->bl2d_buffer_unswizzle_pass || offset % 4 != 0 ||
+        guest_size_bytes > runtime->device.GetMaxStorageBufferRange() ||
+        !BlockLinearUnswizzle2DBufferPass::IsSupported(*this)) {
+        return false;
+    }
+    if (ENABLE_MSAA_RESOLVE_CONSUME) {
+        runtime->InvalidateResolveShadow(Handle());
+    }
+    auto [linear_buffer, copies] =
+        runtime->bl2d_buffer_unswizzle_pass->Unswizzle(*this, buffer, offset);
+    const VkImage vk_image = *original_image;
+    const VkImageAspectFlags vk_aspect_mask = aspect_mask;
+    const bool was_initialized = std::exchange(initialized, true);
+    scheduler->Record([linear_buffer, vk_image, vk_aspect_mask, was_initialized,
+                       copies = std::move(copies)](vk::CommandBuffer cmdbuf) {
+        CopyBufferToImage(cmdbuf, linear_buffer, vk_image, vk_aspect_mask, was_initialized, copies);
+    });
+    return true;
+}
+
 void Image::UploadMemory(const StagingBufferRef& map, std::span<const BufferImageCopy> copies) {
     UploadMemory(map.buffer, map.offset, copies);
 }
@@ -2970,6 +3045,26 @@ Framebuffer::Framebuffer(TextureCacheRuntime& runtime, ImageView* color_buffer,
 
 Framebuffer::~Framebuffer() = default;
 
+/// Single-sampled color targets with a multisampled depth buffer, as used by target-independent
+/// rasterization. Vulkan requires matching sample counts for these attachments.
+static bool IsMixedSamplesTarget(std::span<ImageView*, NUM_RT> color_buffers,
+                                 const ImageView* depth_buffer) {
+    if (depth_buffer == nullptr || depth_buffer->Samples() == VK_SAMPLE_COUNT_1_BIT) {
+        return false;
+    }
+    bool has_color = false;
+    for (const ImageView* const color_buffer : color_buffers) {
+        if (color_buffer == nullptr) {
+            continue;
+        }
+        if (color_buffer->Samples() != VK_SAMPLE_COUNT_1_BIT) {
+            return false;
+        }
+        has_color = true;
+    }
+    return has_color;
+}
+
 void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime,
                                     std::span<ImageView*, NUM_RT> color_buffers,
                                     ImageView* depth_buffer, bool is_rescaled_) {
@@ -3024,6 +3119,13 @@ void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime,
     } else {
         renderpass_key.depth_format = PixelFormat::Invalid;
     }
+    if (IsMixedSamplesTarget(color_buffers, depth_buffer)) {
+        const VkExtent2D extent{(std::min)(render_area.width, width),
+                                (std::min)(render_area.height, height)};
+        CreateMixedSamplesFramebuffer(runtime, color_buffers, attachments, renderpass_key,
+                                      static_cast<u32>((std::max)(num_layers, 1)), extent);
+        return;
+    }
     renderpass_key.samples = samples;
     const bool do_resolve_color = ENABLE_MSAA_TILER_RESOLVE &&
         samples != VK_SAMPLE_COUNT_1_BIT && num_colors > 0 && runtime.device.IsTiler();
@@ -3040,10 +3142,7 @@ void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime,
     discard_msaa_depth_stencil = ENABLE_MSAA_RESOLVE_CONSUME &&
                                  ENABLE_MSAA_DEPTH_STENCIL_DISCARD && do_resolve_depth_stencil;
 
-    renderpass = runtime.render_pass_cache.Get(renderpass_key);
-    render_pass_key = renderpass_key;
-    render_pass_cache = &runtime.render_pass_cache;
-    runtime_ptr = &runtime;
+    UseRenderPass(runtime, renderpass_key);
     render_area.width = (std::min)(render_area.width, width);
     render_area.height = (std::min)(render_area.height, height);
 
@@ -3075,6 +3174,53 @@ void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime,
     }
 
     num_color_buffers = static_cast<u32>(num_colors);
+    CreateVkFramebuffer(runtime, attachments, static_cast<u32>((std::max)(num_layers, 1)));
+}
+
+void Framebuffer::CreateMixedSamplesFramebuffer(TextureCacheRuntime& runtime,
+                                                std::span<ImageView*, NUM_RT> color_buffers,
+                                                std::span<const VkImageView> attachments,
+                                                RenderPassKey renderpass_key, u32 layers,
+                                                VkExtent2D extent) {
+    // attachments holds the real color targets followed by the depth buffer
+    const size_t num_colors = attachments.size() - 1;
+    boost::container::small_vector<VkImageView, NUM_RT * 2 + 2> mixed_attachments;
+    for (const ImageView* const color_buffer : color_buffers) {
+        if (!color_buffer) {
+            continue;
+        }
+        const VkFormat vk_format = MaxwellToVK::SurfaceFormat(runtime.device, FormatType::Optimal,
+                                                              true, color_buffer->format)
+                                       .format;
+        mixed_attachments.push_back(runtime.GetOrCreateTirColorScratch(
+            color_buffer->ImageHandle(), vk_format, extent, layers, samples));
+    }
+    mixed_attachments.push_back(attachments[num_colors]);
+    for (size_t index = 0; index < num_colors; ++index) {
+        mixed_attachments.push_back(attachments[index]);
+    }
+    // Multisampled scratch color + depth, resolving color into the real single-sampled targets
+    renderpass_key.samples = samples;
+    renderpass_key.resolve_color = true;
+    renderpass_key.resolve_depth_stencil = false;
+    discard_msaa_color = false;
+    discard_msaa_depth_stencil = false;
+    UseRenderPass(runtime, renderpass_key);
+    render_area = extent;
+    num_color_buffers = static_cast<u32>(num_colors);
+    CreateVkFramebuffer(runtime, mixed_attachments, layers);
+}
+
+void Framebuffer::UseRenderPass(TextureCacheRuntime& runtime,
+                                const RenderPassKey& renderpass_key) {
+    renderpass = runtime.render_pass_cache.Get(renderpass_key);
+    render_pass_key = renderpass_key;
+    render_pass_cache = &runtime.render_pass_cache;
+    runtime_ptr = &runtime;
+}
+
+void Framebuffer::CreateVkFramebuffer(TextureCacheRuntime& runtime,
+                                      std::span<const VkImageView> attachments, u32 layers) {
     framebuffer = runtime.device.GetLogical().CreateFramebuffer({
         .sType = VK_STRUCTURE_TYPE_FRAMEBUFFER_CREATE_INFO,
         .pNext = nullptr,
@@ -3084,7 +3230,7 @@ void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime,
         .pAttachments = attachments.data(),
         .width = render_area.width,
         .height = render_area.height,
-        .layers = static_cast<u32>((std::max)(num_layers, 1)),
+        .layers = layers,
     });
 }
 

src/video_core/renderer_vulkan/vk_texture_cache.h

@@ -133,6 +133,11 @@ public:
 
     [[nodiscard]] const ResolveShadow* GetValidResolveShadow(VkImage msaa_image) const;
 
+    /// Multisampled stand-in for a single-sampled color target rendered with a TIR depth buffer
+    [[nodiscard]] VkImageView GetOrCreateTirColorScratch(VkImage color_image, VkFormat format,
+                                                         VkExtent2D extent, u32 layers,
+                                                         VkSampleCountFlagBits samples);
+
     void InvalidateResolveShadow(VkImage msaa_image);
 
     void MarkResolveShadowUpToDate(VkImage msaa_image);
@@ -159,6 +164,7 @@ public:
     std::optional<ASTCDecoderPass> astc_decoder_pass;
 
     std::optional<BlockLinearUnswizzle3DPass> bl3d_unswizzle_pass;
+    std::optional<BlockLinearUnswizzle2DBufferPass> bl2d_buffer_unswizzle_pass;
     const Settings::ResolutionScalingInfo& resolution;
     std::array<std::vector<VkFormat>, VideoCore::Surface::MaxPixelFormat> view_formats;
 
@@ -187,6 +193,15 @@ public:
 
     std::vector<MsaaScratchImage> msaa_scratch_images;
     ::Common::unordered_map<VkImage, ResolveShadow> resolve_shadows;
+    struct TirColorScratch {
+        vk::Image image;
+        vk::ImageView view;
+        VkFormat format = VK_FORMAT_UNDEFINED;
+        VkExtent2D extent{};
+        u32 layers = 0;
+        VkSampleCountFlagBits samples = VK_SAMPLE_COUNT_1_BIT;
+    };
+    ::Common::unordered_map<VkImage, TirColorScratch> tir_color_scratch;
     std::vector<std::pair<u64, ResolveShadow>> pending_resolve_shadows;
 };
 
@@ -279,6 +294,22 @@ public:
     void MarkResolveShadowsUpToDate() const;
 
 private:
+    /// Builds a framebuffer for single-sampled color targets drawn with a multisampled depth
+    /// buffer (target-independent rasterization). Color is rendered into multisampled scratch
+    /// images that resolve into the real targets at the end of the pass.
+    void CreateMixedSamplesFramebuffer(TextureCacheRuntime& runtime,
+                                       std::span<ImageView*, NUM_RT> color_buffers,
+                                       std::span<const VkImageView> attachments,
+                                       RenderPassKey renderpass_key, u32 layers,
+                                       VkExtent2D extent);
+
+    /// Fetches the render pass for the key from the cache and remembers it for variants.
+    void UseRenderPass(TextureCacheRuntime& runtime, const RenderPassKey& renderpass_key);
+
+    /// Creates the Vulkan framebuffer for the current render pass and render area.
+    void CreateVkFramebuffer(TextureCacheRuntime& runtime,
+                             std::span<const VkImageView> attachments, u32 layers);
+
     static constexpr size_t NUM_MEMOIZED_RENDER_PASS_VARIANTS = 8;
 
     vk::Framebuffer framebuffer;
@@ -325,6 +356,10 @@ public:
     void UploadMemory(const StagingBufferRef& map,
                       std::span<const VideoCommon::BufferImageCopy> copies);
 
+    /// Replaces the image contents with its block linear guest data held in a GPU buffer.
+    /// Returns false when the image layout is not supported.
+    bool UploadSwizzledFromBuffer(VkBuffer buffer, VkDeviceSize offset);
+
     void DownloadMemory(VkBuffer buffer, size_t offset,
                         std::span<const VideoCommon::BufferImageCopy> copies);
 

src/video_core/renderer_vulkan/vk_texture_cache_base.cpp

@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -6,4 +9,6 @@
 
 namespace VideoCommon {
 template class VideoCommon::TextureCache<Vulkan::TextureCacheParams>;
+template void VideoCommon::TextureCache<Vulkan::TextureCacheParams>::UpdateImagesFromBuffer<VkBuffer>(
+    DAddr, size_t, VkBuffer, u64);
 }

src/video_core/texture_cache/texture_cache.h

@@ -595,6 +595,36 @@ void TextureCache<P>::WriteMemory(DAddr cpu_addr, size_t size) {
     });
 }
 
+template <class P>
+template <typename BufferHandle>
+void TextureCache<P>::UpdateImagesFromBuffer(DAddr cpu_addr, size_t size, BufferHandle buffer,
+                                             u64 buffer_offset) {
+    if constexpr (requires(Image& image) { image.UploadSwizzledFromBuffer(buffer, buffer_offset); }) {
+        // The guest can write a render target through a storage buffer bound over its memory
+        // (e.g. a compute clear). Only images the binding matches exactly are replaced, a larger
+        // binding may hold unrelated live images in the parts the shader does not write.
+        static constexpr size_t MAX_BINDING_PADDING = 64 * 1024;
+        ForEachImageInRegion(cpu_addr, size, [&](ImageId image_id, Image& image) {
+            if (image.cpu_addr != cpu_addr || size < image.guest_size_bytes ||
+                size - image.guest_size_bytes > MAX_BINDING_PADDING ||
+                True(image.flags & ImageFlagBits::Remapped) ||
+                True(image.flags & ImageFlagBits::Sparse)) {
+                return;
+            }
+            if (!image.UploadSwizzledFromBuffer(buffer, buffer_offset)) {
+                return;
+            }
+            if (True(image.flags & ImageFlagBits::CpuModified)) {
+                image.flags &= ~ImageFlagBits::CpuModified;
+                if (False(image.flags & ImageFlagBits::Tracked)) {
+                    TrackImage(image, image_id);
+                }
+            }
+            MarkModification(image);
+        });
+    }
+}
+
 template <class P>
 bool TextureCache<P>::IsDownloadable(const ImageBase& image) const noexcept {
     if (!image.IsSafeGpuCopy()) {
@@ -1928,7 +1958,26 @@ ImageViewId TextureCache<P>::FindDepthBuffer() {
     if (gpu_addr == 0) {
         return ImageViewId{};
     }
-    const ImageInfo info(regs.zeta, regs.zeta_size, regs.anti_alias_samples_mode);
+    // Target-independent rasterization: the depth buffer keeps the raster sample count while
+    // the color targets use anti_alias_samples_mode.
+    Tegra::Texture::MsaaMode zeta_msaa_mode = regs.anti_alias_samples_mode;
+    if (regs.anti_alias_raster != Tegra::Engines::Maxwell3D::Regs::AntiAliasRaster::Mode1x1) {
+        const auto raster_mode = static_cast<Tegra::Texture::MsaaMode>(regs.anti_alias_raster);
+        bool use_raster = regs.tir_mode == Tegra::Engines::Maxwell3D::Regs::TIRMode::RasterNTargetM;
+        if (!use_raster && regs.anti_alias_samples_mode == Tegra::Texture::MsaaMode::Msaa1x1) {
+            // Clears can be issued before tir_mode is enabled. Only a depth buffer sized for the
+            // raster samples relative to the color target is treated as multisampled, otherwise
+            // it ping-pongs between a 1x and a multisampled image every frame.
+            const auto& rt0 = regs.rt[0];
+            use_raster = rt0.Address() != 0 && rt0.format != Tegra::RenderTargetFormat::NONE &&
+                         regs.zeta_size.width == rt0.width * NumSamplesX(raster_mode) &&
+                         regs.zeta_size.height == rt0.height * NumSamplesY(raster_mode);
+        }
+        if (use_raster) {
+            zeta_msaa_mode = raster_mode;
+        }
+    }
+    const ImageInfo info(regs.zeta, regs.zeta_size, zeta_msaa_mode);
     return FindRenderTargetView(info, gpu_addr);
 }
 

src/video_core/texture_cache/texture_cache_base.h

@@ -203,6 +203,12 @@ public:
     /// Mark images in a range as modified from the CPU
     void WriteMemory(DAddr cpu_addr, size_t size);
 
+    /// Replaces the contents of the images fully inside a range that a GPU buffer wrote, with the
+    /// data of that buffer
+    template <typename BufferHandle>
+    void UpdateImagesFromBuffer(DAddr cpu_addr, size_t size, BufferHandle buffer,
+                                u64 buffer_offset);
+
     /// Download contents of host images to guest memory in a region
     void DownloadMemory(DAddr cpu_addr, size_t size);