diff --git a/src/core/core_timing.cpp b/src/core/core_timing.cpp
index b216dc2094..871189596c 100644
--- a/src/core/core_timing.cpp
+++ b/src/core/core_timing.cpp
@@ -21,6 +21,8 @@
 #include "core/core_timing.h"
 #include "core/hardware_properties.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace Core::Timing {
 
 constexpr s64 MAX_SLICE_LENGTH = 10000;
@@ -235,15 +237,20 @@ std::optional<s64> CoreTiming::Advance() {
 
                 basic_lock.unlock();
 
+                { TRACY_ZONE_SCOPEDN("CoreTiming::event_callback")
                 event_type->callback(
                     evt_time, std::chrono::nanoseconds{GetGlobalTimeNs().count() - evt_time});
+                }
 
                 basic_lock.lock();
             } else {
                 basic_lock.unlock();
 
-                const auto new_schedule_time{event_type->callback(
-                    evt_time, std::chrono::nanoseconds{GetGlobalTimeNs().count() - evt_time})};
+                std::optional<std::chrono::nanoseconds> new_schedule_time;
+                { TRACY_ZONE_SCOPEDN("CoreTiming::event_callback")
+                new_schedule_time = event_type->callback(
+                    evt_time, std::chrono::nanoseconds{GetGlobalTimeNs().count() - evt_time});
+                }
 
                 basic_lock.lock();
 
diff --git a/src/core/cpu_manager.cpp b/src/core/cpu_manager.cpp
index 10fdcdf8a2..e2016acdac 100644
--- a/src/core/cpu_manager.cpp
+++ b/src/core/cpu_manager.cpp
@@ -18,6 +18,8 @@
 #include "core/hle/kernel/physical_core.h"
 #include "video_core/gpu.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace Core {
 
 CpuManager::CpuManager(System& system_) : system{system_} {}
@@ -101,6 +103,9 @@ void CpuManager::MultiCoreRunIdleThread() {
             physical_core.Idle();
         }
 
+    #if TRACY_ENABLE
+        TRACY_ZONE_SCOPEDN("IdleThread::HandleInterrupt");
+    #endif
         HandleInterrupt();
     }
 }
@@ -184,6 +189,10 @@ void CpuManager::ShutdownThread() {
 }
 
 void CpuManager::RunThread(std::stop_token token, std::size_t core) {
+#if TRACY_ENABLE
+    TRACY_ZONE_SCOPEDN("RunThread");
+#endif
+
     /// Initialization
     system.RegisterCoreThread(core);
     std::string name = is_multicore ? ("CPUCore_" + std::to_string(core)) : std::string{"CPUThread"};
diff --git a/src/core/hle/kernel/physical_core.cpp b/src/core/hle/kernel/physical_core.cpp
index 77cdab76d7..023c67cf75 100644
--- a/src/core/hle/kernel/physical_core.cpp
+++ b/src/core/hle/kernel/physical_core.cpp
@@ -14,6 +14,8 @@
 #include "core/hle/kernel/physical_core.h"
 #include "core/hle/kernel/svc.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace Kernel {
 
 PhysicalCore::PhysicalCore(KernelCore& kernel, std::size_t core_index)
@@ -217,6 +219,10 @@ void PhysicalCore::LogBacktrace() {
 }
 
 void PhysicalCore::Idle() {
+#if TRACY_ENABLE
+    ZoneScopedC(0xc0c0c0);
+#endif
+
     std::unique_lock lk{m_guard};
     m_on_interrupt.wait(lk, [this] { return m_is_interrupted; });
 }
diff --git a/src/core/hle/service/vi/conductor.cpp b/src/core/hle/service/vi/conductor.cpp
index 801a135dd7..dd79b53895 100644
--- a/src/core/hle/service/vi/conductor.cpp
+++ b/src/core/hle/service/vi/conductor.cpp
@@ -12,6 +12,8 @@
 #include "core/hle/service/vi/display_list.h"
 #include "core/hle/service/vi/vsync_manager.h"
 
+#include "common/tracy_instrumentation.h"
+
 constexpr auto FrameNs = std::chrono::nanoseconds{1000000000 / 60};
 
 namespace Service::VI {
@@ -27,6 +29,7 @@ Conductor::Conductor(Core::System& system, Container& container, DisplayList& di
             "ScreenComposition",
             [this](s64 time,
                    std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+                TRACY_ZONE_SCOPEDN("Conductor vsync callback")
                 m_signal.Set();
                 return std::chrono::nanoseconds(this->GetNextTicks());
             });
@@ -38,6 +41,7 @@ Conductor::Conductor(Core::System& system, Container& container, DisplayList& di
             "ScreenComposition",
             [this](s64 time,
                    std::chrono::nanoseconds ns_late) -> std::optional<std::chrono::nanoseconds> {
+                TRACY_ZONE_SCOPEDN("Conductor vsync callback")
                 this->ProcessVsync();
                 return std::chrono::nanoseconds(this->GetNextTicks());
             });
@@ -68,6 +72,8 @@ void Conductor::UnlinkVsyncEvent(u64 display_id, Event* event) {
 }
 
 void Conductor::ProcessVsync() {
+    TRACY_ZONE_SCOPED
+
     for (auto& [display_id, manager] : m_vsync_managers) {
         m_container.ComposeOnDisplay(&m_swap_interval, &m_compose_speed_scale, display_id);
         manager.SignalVsync();
diff --git a/src/video_core/buffer_cache/buffer_cache.h b/src/video_core/buffer_cache/buffer_cache.h
index 014b4a318e..e77eaeb777 100644
--- a/src/video_core/buffer_cache/buffer_cache.h
+++ b/src/video_core/buffer_cache/buffer_cache.h
@@ -16,6 +16,8 @@
 #include "video_core/host1x/gpu_device_memory_manager.h"
 #include "video_core/texture_cache/util.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace VideoCommon {
 
 using Core::DEVICE_PAGESIZE;
@@ -337,6 +339,7 @@ void BufferCache<P>::DisableGraphicsUniformBuffer(size_t stage, u32 index) {
 
 template <class P>
 void BufferCache<P>::UpdateGraphicsBuffers(bool is_indexed) {
+    TRACY_ZONE_SCOPED
     do {
         channel_state->has_deleted_buffers = false;
         DoUpdateGraphicsBuffers(is_indexed);
@@ -353,6 +356,8 @@ void BufferCache<P>::UpdateComputeBuffers() {
 
 template <class P>
 void BufferCache<P>::BindHostGeometryBuffers(bool is_indexed) {
+    TRACY_ZONE_SCOPED
+
     if (is_indexed) {
         BindHostIndexBuffer();
     } else if constexpr (!HAS_FULL_INDEX_AND_PRIMITIVE_SUPPORT) {
@@ -372,6 +377,8 @@ void BufferCache<P>::BindHostGeometryBuffers(bool is_indexed) {
 
 template <class P>
 void BufferCache<P>::BindHostStageBuffers(size_t stage) {
+    TRACY_ZONE_SCOPED
+
     BindHostGraphicsUniformBuffers(stage);
     BindHostGraphicsStorageBuffers(stage);
     BindHostGraphicsTextureBuffers(stage);
diff --git a/src/video_core/dma_pusher.cpp b/src/video_core/dma_pusher.cpp
index 3844a8e2f9..7c50f75f55 100644
--- a/src/video_core/dma_pusher.cpp
+++ b/src/video_core/dma_pusher.cpp
@@ -18,6 +18,8 @@
 #include <intrin.h>
 #endif
 
+#include "common/tracy_instrumentation.h"
+
 namespace Tegra {
 
 constexpr u32 MacroRegistersStart = 0xE00;
@@ -31,6 +33,8 @@ DmaPusher::DmaPusher(Core::System& system_, GPU& gpu_, MemoryManager& memory_man
 DmaPusher::~DmaPusher() = default;
 
 void DmaPusher::DispatchCalls() {
+    TRACY_ZONE_SCOPED
+
 
     dma_pushbuffer_subindex = 0;
 
@@ -46,6 +50,8 @@ void DmaPusher::DispatchCalls() {
 }
 
 bool DmaPusher::Step() {
+    TRACY_ZONE_SCOPED
+
     if (!ib_enable || dma_pushbuffer.empty()) {
         return false;
     }
diff --git a/src/video_core/engines/draw_manager.cpp b/src/video_core/engines/draw_manager.cpp
index 971025cb55..cf85fc9177 100644
--- a/src/video_core/engines/draw_manager.cpp
+++ b/src/video_core/engines/draw_manager.cpp
@@ -6,6 +6,8 @@
 #include "video_core/engines/draw_manager.h"
 #include "video_core/rasterizer_interface.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace Tegra::Engines {
 DrawManager::DrawManager(Maxwell3D* maxwell3d_) : maxwell3d(maxwell3d_) {}
 
@@ -263,6 +265,7 @@ void DrawManager::UpdateTopology() {
 void DrawManager::ProcessDraw(bool draw_indexed, u32 instance_count) {
     LOG_TRACE(HW_GPU, "called, topology={}, count={}", draw_state.topology,
               draw_indexed ? draw_state.index_buffer.count : draw_state.vertex_buffer.count);
+    TRACY_ZONE_SCOPED
 
     UpdateTopology();
 
@@ -277,6 +280,7 @@ void DrawManager::ProcessDrawIndirect() {
         "called, topology={}, is_indexed={}, includes_count={}, buffer_size={}, max_draw_count={}",
         draw_state.topology, indirect_state.is_indexed, indirect_state.include_count,
         indirect_state.buffer_size, indirect_state.max_draw_counts);
+    TRACY_ZONE_SCOPED
 
     UpdateTopology();
 
diff --git a/src/video_core/engines/engine_upload.cpp b/src/video_core/engines/engine_upload.cpp
index ba21eec4c4..c3691b8b67 100644
--- a/src/video_core/engines/engine_upload.cpp
+++ b/src/video_core/engines/engine_upload.cpp
@@ -14,6 +14,8 @@
 #include "video_core/rasterizer_interface.h"
 #include "video_core/textures/decoders.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace Tegra::Engines::Upload {
 
 State::State(MemoryManager& memory_manager_, Registers& regs_)
@@ -26,6 +28,8 @@ void State::BindRasterizer(VideoCore::RasterizerInterface* rasterizer_) {
 }
 
 void State::ProcessExec(const bool is_linear_) {
+    TRACY_ZONE_SCOPED
+
     write_offset = 0;
     copy_size = regs.line_length_in * regs.line_count;
     inner_buffer.resize_destructive(copy_size);
@@ -33,6 +37,8 @@ void State::ProcessExec(const bool is_linear_) {
 }
 
 void State::ProcessData(const u32 data, const bool is_last_call) {
+    TRACY_ZONE_SCOPED
+
     const u32 sub_copy_size = (std::min)(4U, copy_size - write_offset);
     std::memcpy(&inner_buffer[write_offset], &data, sub_copy_size);
     write_offset += sub_copy_size;
diff --git a/src/video_core/engines/maxwell_3d.cpp b/src/video_core/engines/maxwell_3d.cpp
index e48f294a5a..4fc94902fe 100644
--- a/src/video_core/engines/maxwell_3d.cpp
+++ b/src/video_core/engines/maxwell_3d.cpp
@@ -20,6 +20,8 @@
 #include "video_core/rasterizer_interface.h"
 #include "video_core/textures/texture.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace Tegra::Engines {
 
 /// First register id that is actually a Macro call.
@@ -324,6 +326,10 @@ void Maxwell3D::ProcessDirtyRegisters(u32 method, u32 argument) {
         dirty.flags[flag0] = true;
         if (flag1 != flag0)
             dirty.flags[flag1] = true;
+
+        if (flag0 == VideoCommon::Dirty::RenderTargets || flag1 == VideoCommon::Dirty::RenderTargets) {
+            TRACY_MSG_C("BindRendertarget", 0x4040ff);
+        }
     }
 }
 
diff --git a/src/video_core/gpu_thread.cpp b/src/video_core/gpu_thread.cpp
index 8d8d857a02..91ec163985 100644
--- a/src/video_core/gpu_thread.cpp
+++ b/src/video_core/gpu_thread.cpp
@@ -17,6 +17,8 @@
 #include "video_core/host1x/host1x.h"
 #include "video_core/renderer_base.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace VideoCommon::GPUThread {
 
 /// Runs the GPU thread
@@ -37,13 +39,20 @@ static void RunThread(std::stop_token stop_token, Core::System& system,
         if (stop_token.stop_requested()) {
             break;
         }
+
+        //TRACY_ZONE_SCOPEDN("Process Gpu Command");
+
         if (auto* submit_list = std::get_if<SubmitListCommand>(&next.data)) {
+            TRACY_ZONE_SCOPEDN("Push Command List");
             scheduler.Push(submit_list->channel, std::move(submit_list->entries));
         } else if (std::holds_alternative<GPUTickCommand>(next.data)) {
+            TRACY_ZONE_SCOPEDN("TickWork");
             system.GPU().TickWork();
         } else if (const auto* flush = std::get_if<FlushRegionCommand>(&next.data)) {
+            TRACY_ZONE_SCOPEDN("FlushRegion");
             rasterizer->FlushRegion(flush->addr, flush->size);
         } else if (const auto* invalidate = std::get_if<InvalidateRegionCommand>(&next.data)) {
+            TRACY_ZONE_SCOPEDN("OnCacheInvalidation");
             rasterizer->OnCacheInvalidation(invalidate->addr, invalidate->size);
         } else {
             ASSERT(false);
diff --git a/src/video_core/macro.cpp b/src/video_core/macro.cpp
index 66cea5afbd..61a7b3abf2 100644
--- a/src/video_core/macro.cpp
+++ b/src/video_core/macro.cpp
@@ -45,6 +45,8 @@
 #endif
 #include "video_core/engines/maxwell_3d.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace Tegra {
 
 using Maxwell3D = Engines::Maxwell3D;
@@ -77,6 +79,9 @@ bool IsTopologySafe(Maxwell3D::Regs::PrimitiveTopology topology) {
 } // Anonymous namespace
 
 void HLE_DrawArraysIndirect::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("DrawArraysIndirect", 0xff4040)
+
     auto topology = static_cast<Maxwell3D::Regs::PrimitiveTopology>(parameters[0]);
     if (!maxwell3d.AnyParametersDirty() || !IsTopologySafe(topology)) {
         Fallback(maxwell3d, parameters);
@@ -136,6 +141,9 @@ void HLE_DrawArraysIndirect::Fallback(Engines::Maxwell3D& maxwell3d, std::span<c
 }
 
 void HLE_DrawIndexedIndirect::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("DrawIndexedIndirect", 0xff4040)
+
     auto topology = static_cast<Maxwell3D::Regs::PrimitiveTopology>(parameters[0]);
     if (!maxwell3d.AnyParametersDirty() || !IsTopologySafe(topology)) {
         Fallback(maxwell3d, parameters);
@@ -197,6 +205,9 @@ void HLE_DrawIndexedIndirect::Fallback(Engines::Maxwell3D& maxwell3d, std::span<
     }
 }
 void HLE_MultiLayerClear::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("MultiLayerClear", 0xff4040)
+
     maxwell3d.RefreshParameters();
     ASSERT(parameters.size() == 1);
 
@@ -209,6 +220,9 @@ void HLE_MultiLayerClear::Execute(Engines::Maxwell3D& maxwell3d, std::span<const
     maxwell3d.draw_manager->Clear(num_layers);
 }
 void HLE_MultiDrawIndexedIndirectCount::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("MultiDrawIndexedIndirectCount", 0xff4040)
+
     const auto topology = Maxwell3D::Regs::PrimitiveTopology(parameters[2]);
     if (!IsTopologySafe(topology)) {
         Fallback(maxwell3d, parameters);
@@ -284,6 +298,9 @@ void HLE_MultiDrawIndexedIndirectCount::Fallback(Engines::Maxwell3D& maxwell3d,
     }
 }
 void HLE_DrawIndirectByteCount::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("DrawIndirectByteCount", 0xff4040)
+
     const bool force = maxwell3d.Rasterizer().HasDrawTransformFeedback();
     auto topology = Maxwell3D::Regs::PrimitiveTopology(parameters[0] & 0xFFFFU);
     if (!force && (!maxwell3d.AnyParametersDirty() || !IsTopologySafe(topology))) {
@@ -316,6 +333,9 @@ void HLE_DrawIndirectByteCount::Fallback(Engines::Maxwell3D& maxwell3d, std::spa
         maxwell3d.regs.draw_auto_byte_count / maxwell3d.regs.draw_auto_stride, 0, 1);
 }
 void HLE_C713C83D8F63CCF3::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("ConstBuffer_1", 0xff4040)
+
     maxwell3d.RefreshParameters();
     const u32 offset = (parameters[0] & 0x3FFFFFFF) << 2;
     const u32 address = maxwell3d.regs.shadow_scratch[24];
@@ -326,6 +346,9 @@ void HLE_C713C83D8F63CCF3::Execute(Engines::Maxwell3D& maxwell3d, std::span<cons
     const_buffer.offset = offset;
 }
 void HLE_D7333D26E0A93EDE::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("ConstBuffer_2", 0xff4040)
+
     maxwell3d.RefreshParameters();
     const size_t index = parameters[0];
     const u32 address = maxwell3d.regs.shadow_scratch[42 + index];
@@ -336,6 +359,9 @@ void HLE_D7333D26E0A93EDE::Execute(Engines::Maxwell3D& maxwell3d, std::span<cons
     const_buffer.address_low = address << 8;
 }
 void HLE_BindShader::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("BindShader", 0x40ff40)
+
     maxwell3d.RefreshParameters();
     auto& regs = maxwell3d.regs;
     const u32 index = parameters[0];
@@ -360,6 +386,9 @@ void HLE_BindShader::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32>
     maxwell3d.ProcessCBBind(bind_group_id);
 }
 void HLE_SetRasterBoundingBox::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("SetRasterBoundingBox", 0xff4040)
+
     maxwell3d.RefreshParameters();
     const u32 raster_mode = parameters[0];
     auto& regs = maxwell3d.regs;
@@ -369,6 +398,9 @@ void HLE_SetRasterBoundingBox::Execute(Engines::Maxwell3D& maxwell3d, std::span<
     regs.raster_bounding_box.pad.Assign(scratch_data & raster_enabled);
 }
 void HLE_ClearConstBuffer::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("ClearConstBuffer", 0xff4040)
+
     static constexpr std::array<u32, 0x7000> zeroes{}; //must be bigger than either 7000 or 5F00
     maxwell3d.RefreshParameters();
     auto& regs = maxwell3d.regs;
@@ -379,6 +411,9 @@ void HLE_ClearConstBuffer::Execute(Engines::Maxwell3D& maxwell3d, std::span<cons
     maxwell3d.ProcessCBMultiData(zeroes.data(), parameters[2] * 4);
 }
 void HLE_ClearMemory::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("ClearMemory", 0xff4040)
+
     maxwell3d.RefreshParameters();
     const u32 needed_memory = parameters[2] / sizeof(u32);
     if (needed_memory > zero_memory.size()) {
@@ -393,6 +428,9 @@ void HLE_ClearMemory::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32
     maxwell3d.CallMultiMethod(size_t(MAXWELL3D_REG_INDEX(inline_data)), zero_memory.data(), needed_memory, needed_memory);
 }
 void HLE_TransformFeedbackSetup::Execute(Engines::Maxwell3D& maxwell3d, std::span<const u32> parameters, [[maybe_unused]] u32 method) {
+    //TRACY_ZONE_SCOPED
+    TRACY_MSG_C("TransformFeedbackSetup", 0xff4040)
+
     maxwell3d.RefreshParameters();
     auto& regs = maxwell3d.regs;
     regs.transform_feedback_enabled = 1;
diff --git a/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp b/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp
index e989bf6b31..615d804869 100644
--- a/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp
+++ b/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp
@@ -29,6 +29,8 @@
 #include "video_core/gpu_logging/gpu_logging.h"
 #include "common/settings.h"
 
+#include "common/tracy_instrumentation.h"
+
 #if defined(_MSC_VER) && defined(NDEBUG)
 #define LAMBDA_FORCEINLINE [[msvc::forceinline]]
 #else
@@ -310,6 +312,8 @@ void GraphicsPipeline::AddTransition(GraphicsPipeline* transition) {
 
 template <typename Spec>
 bool GraphicsPipeline::ConfigureImpl(bool is_indexed) {
+    TRACY_ZONE_SCOPED
+
     std::array<VideoCommon::ImageViewInOut, MAX_IMAGE_ELEMENTS> views;
     std::array<VideoCommon::SamplerId, MAX_IMAGE_ELEMENTS> samplers;
     size_t sampler_index{};
@@ -509,6 +513,8 @@ bool GraphicsPipeline::ConfigureImpl(bool is_indexed) {
 
 void GraphicsPipeline::ConfigureDraw(const RescalingPushConstant& rescaling,
                                      const RenderAreaPushConstant& render_area) {
+    TRACY_ZONE_SCOPED
+
     scheduler.RequestRenderpass(texture_cache.GetFramebuffer());
     if (!is_built.load(std::memory_order::relaxed)) {
         // Wait for the pipeline to be built
diff --git a/src/video_core/renderer_vulkan/vk_rasterizer.cpp b/src/video_core/renderer_vulkan/vk_rasterizer.cpp
index f867980a6f..4675232728 100644
--- a/src/video_core/renderer_vulkan/vk_rasterizer.cpp
+++ b/src/video_core/renderer_vulkan/vk_rasterizer.cpp
@@ -43,6 +43,8 @@
 #include "video_core/vulkan_common/vulkan_device.h"
 #include "video_core/vulkan_common/vulkan_wrapper.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace Vulkan {
 
 using Maxwell = Tegra::Engines::Maxwell3D::Regs;
@@ -238,6 +240,8 @@ void RasterizerVulkan::PrepareDraw(bool is_indexed, Func&& draw_func) {
 }
 
 void RasterizerVulkan::Draw(bool is_indexed, u32 instance_count) {
+    TRACY_ZONE_SCOPED
+
     PrepareDraw(is_indexed, [this, is_indexed, instance_count] {
         const auto& draw_state = maxwell3d->draw_manager->GetDrawState();
         const u32 num_instances{instance_count};
@@ -298,6 +302,8 @@ void RasterizerVulkan::Draw(bool is_indexed, u32 instance_count) {
 }
 
 void RasterizerVulkan::DrawIndirect() {
+    TRACY_ZONE_SCOPED
+
     const auto& params = maxwell3d->draw_manager->GetIndirectParams();
     buffer_cache.SetDrawIndirect(&params);
     PrepareDraw(params.is_indexed, [this, &params] {
diff --git a/src/video_core/renderer_vulkan/vk_scheduler.cpp b/src/video_core/renderer_vulkan/vk_scheduler.cpp
index 947de6a80e..b17b27d5af 100644
--- a/src/video_core/renderer_vulkan/vk_scheduler.cpp
+++ b/src/video_core/renderer_vulkan/vk_scheduler.cpp
@@ -25,6 +25,8 @@
 #include "video_core/vulkan_common/vulkan_device.h"
 #include "video_core/vulkan_common/vulkan_wrapper.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace Vulkan {
 
 
@@ -223,7 +225,10 @@ void Scheduler::WorkerThread(std::stop_token stop_token) {
             // Perform the work, tracking whether the chunk was a submission
             // before executing.
             const bool has_submit = work->HasSubmit();
+
+            { TRACY_ZONE_SCOPEDN("Vulkan::Scheduler::ExecuteAll")
             work->ExecuteAll(current_cmdbuf, current_upload_cmdbuf);
+            }
 
             // If the chunk was a submission, reallocate the command buffer.
             if (has_submit) {
diff --git a/src/video_core/texture_cache/image_base.cpp b/src/video_core/texture_cache/image_base.cpp
index 077df28fb3..daaa785523 100644
--- a/src/video_core/texture_cache/image_base.cpp
+++ b/src/video_core/texture_cache/image_base.cpp
@@ -17,6 +17,8 @@
 #include "video_core/texture_cache/image_view_info.h"
 #include "video_core/texture_cache/util.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace VideoCommon {
 
 using VideoCore::Surface::DefaultBlockHeight;
@@ -159,6 +161,8 @@ void ImageBase::CheckAliasState() {
 }
 
 bool AddImageAlias(ImageBase& lhs, ImageBase& rhs, ImageId lhs_id, ImageId rhs_id) {
+    TRACY_ZONE_SCOPED
+
     static constexpr auto OPTIONS = RelaxedOptions::Size | RelaxedOptions::Format;
     ASSERT(lhs.info.type == rhs.info.type);
     std::optional<SubresourceBase> base;
diff --git a/src/video_core/texture_cache/texture_cache.h b/src/video_core/texture_cache/texture_cache.h
index 71210ffe6e..5a4c641edd 100644
--- a/src/video_core/texture_cache/texture_cache.h
+++ b/src/video_core/texture_cache/texture_cache.h
@@ -25,6 +25,8 @@
 #include "video_core/texture_cache/util.h"
 #include "video_core/textures/decoders.h"
 
+#include "common/tracy_instrumentation.h"
+
 namespace VideoCommon {
 
 using Tegra::Texture::TICEntry;
@@ -275,12 +277,14 @@ void TextureCache<P>::MarkModification(ImageId id) noexcept {
 template <class P>
 template <bool has_blacklists>
 void TextureCache<P>::FillGraphicsImageViews(std::span<ImageViewInOut> views) {
+    TRACY_ZONE_SCOPED
     FillImageViews<has_blacklists>(channel_state->graphics_image_table,
                                    channel_state->graphics_image_view_ids, views);
 }
 
 template <class P>
 void TextureCache<P>::FillComputeImageViews(std::span<ImageViewInOut> views) {
+    TRACY_ZONE_SCOPED
     FillImageViews<true>(channel_state->compute_image_table, channel_state->compute_image_view_ids,
                          views);
 }
@@ -442,6 +446,8 @@ void TextureCache<P>::SynchronizeComputeDescriptors() {
 
 template <class P>
 bool TextureCache<P>::RescaleRenderTargets() {
+    TRACY_ZONE_SCOPED
+
     auto& flags = maxwell3d->dirty.flags;
     u32 scale_rating = 0;
     bool rescaled = false;
@@ -538,6 +544,8 @@ bool TextureCache<P>::RescaleRenderTargets() {
 
 template <class P>
 void TextureCache<P>::UpdateRenderTargets(bool is_clear) {
+    TRACY_ZONE_SCOPED
+
     using namespace VideoCommon::Dirty;
     auto& flags = maxwell3d->dirty.flags;
     if (!flags[Dirty::RenderTargets]) {
@@ -549,6 +557,7 @@ void TextureCache<P>::UpdateRenderTargets(bool is_clear) {
         PrepareImageView(depth_buffer_id, true, is_clear && IsFullClear(depth_buffer_id));
         return;
     }
+    TRACY_ZONE_NAMEDN(_tracy_zone, "UpdateRenderTargets_Dirty")
 
     const VideoCommon::RenderTargets previous_render_targets = render_targets;
     const bool rescaled = RescaleRenderTargets();
@@ -1200,6 +1209,8 @@ void TextureCache<P>::RefreshContents(Image& image, ImageId image_id) {
         return;
     }
 
+    TRACY_ZONE_SCOPEDN("RefreshContents_CpuModified")
+
     TrackImage(image, image_id);
 
     if (image.info.num_samples > 1 && !runtime.CanUploadMSAA()) {
@@ -1608,6 +1619,8 @@ bool TextureCache<P>::ScaleDown(Image& image) {
 template <class P>
 ImageId TextureCache<P>::InsertImage(const ImageInfo& info, GPUVAddr gpu_addr,
                                      RelaxedOptions options) {
+    TRACY_ZONE_SCOPED
+
     std::optional<DAddr> cpu_addr = gpu_memory->GpuToCpuAddress(gpu_addr);
     if (!cpu_addr) {
         const auto size = CalculateGuestSizeInBytes(info);
@@ -2689,6 +2702,8 @@ void TextureCache<P>::SynchronizeAliases(ImageId image_id) {
     if (aliased_images.empty()) {
         return;
     }
+    TRACY_ZONE_SCOPEDN("SynchronizeAliases_has_modified_aliases")
+
     const bool can_rescale = ImageCanRescale(image);
     if (any_rescaled) {
         if (can_rescale) {