The WWDC videos like the new "Boost your graphics performance with the M5 and A19 GPUs" contain extremely valuable information and tips on how to discover, diagnose and remedy performance issues. They seem to serve as quick reminders and distilled summaries of more comprehensive documentation that I assume can be found somewhere. Where do we find the underlying comprehensive documentation that explains Apple Silicon GPU architecture? How can I learn to understand the basis of the data presented by the Xcode Metal Debugger? Any hints at external literature and resources are welcome.

The WWDC videos like the new "Boost your graphics performance with the M5 and A19 GPUs" contain extremely valuable information and tips on how to discover, diagnose and remedy performance issues. They seem to serve as quick reminders and distilled summaries of more comprehensive documentation that I assume can be found somewhere. Where do we find the underlying comprehensive documentation that explains Apple Silicon GPU architecture? How can I learn to understand the basis of the data presented by the Xcode Metal Debugger? Any hints at external literature and resources are welcome.

I am processing large images where each output pixel depends on a large neighborhood of surrounding pixels. As a result, the shader performs a very high number of texture sampling operations, which appears to cause cache misses and becomes a performance bottleneck. Since neighboring threads often process adjacent pixels, many of the sampled pixels overlap between threads. Although each thread operates on a slightly different output pixel, a large portion of the texture accesses are effectively identical. Does Metal provide mechanisms that allow neighboring threads to share or synchronize intermediate results in order to reduce redundant texture fetches? Are there recommended approaches for exploiting data reuse across threads, for example through threadgroup memory or other Metal-specific features? In this type of workload, how effective is texture gathering (gather) for reducing sampling overhead, especially when only the RGB channels of an RGBA texture are required? Would using gather generally improve cache utilization and performance in this scenario? When using gather, what is the preferred way to handle texture borders and edge conditions without introducing per-thread branching (e.g., explicit if statements)? Any recommendations for optimizing large-radius neighborhood operations in Metal would be greatly appreciated.

Are there opportunities for developers to use Apple Intelligence models through Metal in ways that unlock new rendering, simulation, or real-time content generation techniques?

At which time does Metal allocate and deallocate memory for textures? I've observed that the textures live for the whole time of the commandBuffer. So, if I have multiple large textures that I need in subsequent shaders, it would make sense to work with multiple commandBuffers to enable deallocation in order to reduce peak memory usage. Is that correct? Do you have any other suggestions on how to reduce peak memory usage when working with large metal textures? Hint: I am using compute shaders only.

Hi, What's the best way to handle drastic changes in scene charateristics with the new MTLFXTemporalDenoisedScaler? Let's say a visible object of the scene radically changes its material properties. I can modify the albedo and roughness textures consequently. But I suspect the history will be corrupted. Blending visual information between the new frame and the previous ones might be a nonsense. I guess the problem should be the same when objects appear or disappear instantly. Is the upsacler manage these events for us (by lowering blending), or should we use the reactive or the denoise strength mask or something like that to handle them?

The documentation is unclear. I need a clarification on metal shader converter library distribution. Am I allowed to distribute the library as a part of my macos app bundle?

Metal GPU Driver Crash on M5 Pro + macOS 26.5 — kIOGPUCommandBufferCallbackErrorOutOfMemory with <2GB working sets Summary The Metal driver AGXMetalG17X 351.2 on macOS 26.5 (25F71) for the M5 Pro chip crashes with kIOGPUCommandBufferCallbackErrorOutOfMemory (00000008) when running LLM inference workloads with working sets as small as ~1.5GB, despite 24GB of unified memory being available and Apple Diagnostics confirming the hardware is fully functional. This affects multiple tools: MLX, llama.cpp (Metal backend), and native apps using Metal for inference. System Component Value Model MacBook Pro (Mac17,9) Chip Apple M5 Pro (applegpu_g17s) GPU Cores 16 RAM 24 GB LPDDR5 macOS 26.5 (25F71) Metal Metal 4 GPU Driver AGXMetalG17X 351.2 Xcode 26.5 (17F42) Reproduction MLX (Python) pip install mlx mlx-lm python -m mlx_lm.generate \ --model mlx-community/Qwen2.5-3B-Instruct-4bit \ --max-tokens 10 \ --prompt "Hello" Expected: Normal text generation Actual: Crash with: libc++abi: terminating due to uncaught exception of type std::runtime_error: [METAL] Command buffer execution failed: Insufficient Memory (00000008:kIOGPUCommandBufferCallbackErrorOutOfMemory) llama.cpp brew install llama.cpp llama-cli --model model.gguf --prompt "Hello" --n-predict 20 --n-gpu-layers 99 Expected: Fast GPU generation Actual: Process hangs indefinitely Test Results Tool Model Peak Memory Result MLX Qwen2.5-0.5B-4bit 0.36 GB ✅ Works MLX Qwen2.5-1.5B-4bit 0.98 GB ✅ Works MLX Qwen3-1.7B-4bit 1.01 GB ✅ Works MLX Qwen2.5-3B-4bit ~1.5 GB ❌ Metal OOM crash MLX Qwen3-4B-4bit ~2.1 GB ❌ Metal OOM crash MLX Qwen3-8B-4bit ~4.5 GB ❌ Metal OOM crash llama.cpp Qwen2.5-0.5B GGUF ~0.5 GB ❌ Hangs with GPU llama.cpp Qwen2.5-0.5B GGUF ~0.5 GB ✅ Works with CPU only Key Evidence Hardware is healthy — Apple Diagnostics passed all tests Basic Metal works — matmul, array ops work fine CPU inference works — llama.cpp with -ngl 0 runs correctly The error is NOT about actual memory exhaustion — kIOGPUCommandBufferCallbackErrorOutOfMemory means the kernel rejects the Metal memory commit, not that physical memory is full. The system reports 17.76GB available for Metal working set. Crash Log Extract Thread 31 Crashed: 0 libsystem_kernel.dylib __pthread_kill + 8 1 libsystem_pthread.dylib pthread_kill + 296 2 libsystem_c.dylib abort + 148 3 Metal MTLReportFailure.cold.1 + 48 4 Metal MTLReportFailure + 576 5 Metal -[_MTLCommandBuffer addCompletedHandler:] + 104 ... Exception Type: EXC_CRASH (SIGABRT) Termination Reason: Namespace SIGNAL, Code 6, Abort trap: 6 Related Issues ml-explore/mlx#3586 — Metal compiler regression on macOS 26.5 ml-explore/mlx#3534 — M5 float32 precision issue ml-explore/mlx#3568 — M5 random divergence ml-explore/mlx#3539 — Metal residency OOM (M4 Max) Request Please investigate the AGXMetalG17X driver for M5 Pro on macOS 26.5. The driver appears to incorrectly reject Metal memory commits for LLM inference workloads, even when the working set is well within the system's reported limits (1.5GB requested vs 17.76GB available). Happy to provide full crash logs, sysdiagnose archives, or run additional tests.

Hi all, I'm working on updating my audio visualizer app. I'm adding new visualizers based on Metal 4 compute shaders. They worked in iOS 26.4 and iOS 26.5 up until beta 3. However, after that, the visualizers started crashing the phone and forcing a restart. On the latest version of iOS 26.5, the crash is still there. I submitted feedback, but haven't heard anything back just yet. I was wondering if others have faced this same issue, and if there are any workarounds. Here is my repo if you want to look at the code (forgive me if it's sloppy, I'm quite new to graphics programming and Metal): https://github.com/aabagdi/VisualMan/tree/main Thank you!

I'm updating our app to support metal 4, but the metal 4 types don't seem to get recognized when targeting simulator. Is it known if metal 4 will be supported in the near future, or am I setting up the app wrong?

When using index primitives is there a method to provide the indices using a temp buffer like setVertexBytes? Right now I have to create a temp metal buffer even for a small number of vertices and toss it after rendering using drawIndexedPrimitives.

I’m trying to use MTL4FXTemporalDenoisedScaler, and I’m seeing a crash during initialization even with a very simple sample app. I created a minimal sample here: https://github.com/tatsuya-ogawa/MetalFXInitExample The exception is: NSException: "-[AGXG16XFamilyHeap baseObject]: unrecognized selector sent to instance ..." What I found is: • This works: descriptor.makeTemporalDenoisedScaler(device: device) • This crashes: descriptor.makeTemporalDenoisedScaler(device: device, compiler: metal4Compiler) So the issue seems to happen only with the Metal4FX version. For testing, I’m using an iPhone 15 Pro. According to the Metal Feature Set Tables, MetalFX denoised upscaling should be supported on Apple9 and later, so I believe the device itself should meet the requirements. Reference: https://developer.apple.com/metal/Metal-Feature-Set-Tables.pdf Has anyone seen this before, or knows what might be causing it? I’d appreciate any advice. Thanks.

After watching WWDC 2025 session "Combine Metal 4 machine learning and graphics", I have decided to give it a shot to integrate the latest MTL4MachineLearningCommandEncoder to my existing render pipeline. After a lot of trial and errors, I managed to set up the pipeline and have the app compiled. However, I am now stuck on creating a MTLLibrary with .mtlpackage. Here is the code I have to create a MTLLibrary according the WWDC session https://developer.apple.com/videos/play/wwdc2025/262/?time=550: let coreMLFilePath = bundle.path(forResource: "my_model", ofType: "mtlpackage")! let coreMLURL = URL(string: coreMLFilePath)! do { metalDevice.makeLibrary(URL: coreMLURL) } catch { print("error: \(error)") } With the above code, I am getting error: Error Domain=MTLLibraryErrorDomain Code=1 "Invalid metal package" UserInfo={NSLocalizedDescription=Invalid metal package} What is the correct way to create a MTLLibrary with .mtlpackage? Do I see this error because the .mtlpackage I am using is incorrect? How should I go with debugging this? I'd really appreciate if I could get some help on this as I have been stuck with it for some time now. Thanks in advance!

I'm new to graphics and game design and I just wanted to know if a compute pipeline could be as efficient as a render pipeline for rasterization and an explanation on how and why. Also is it possible to manually perform rasterization with a render pipeline as in manipulate individual pixel data in a metal texture yourself but do it with a render pipeline?

I think if your buffer is less than 4k its recommended to use setVertexBytes, the question I have is can I keep hammering on setVertexBytes as the primary method to issue multiple draw calls within a render buffer and rely on Metal to figure out how to orphan and replace the target buffer? A lot of the primitives I am drawing are less than 4k and the process of wiring down larger segments of memory for individual buffers for each draw primitive call seems to be a negative. And it's just simpler to copy, submit and forget about buffer synchronization.

Death Stranding 2: On the Beach (v1.0.48.0, Steam) crashes during rendering initialization when running through CrossOver 26 with D3DMetal 3.0 on an Apple M2 Max Mac Studio running macOS Sequoia. The game successfully initializes Streamline, NVAPI, DLSS (Result::eOk), DLSSG (Result::eOk), Reflex, and XeSS — all subsystems report success. The crash occurs immediately after, during rendering pipeline creation, before the game reaches NXStorage initialization or window creation. Minidump analysis confirms the crash is an access violation (0xc0000005) at DS2.exe+0x67233d, writing to address 0x0. RAX=0x0 (null pointer being dereferenced), R12=0xFFFFFFFFFFFFFFFF (error/invalid handle return). The game appears to call a D3D12 API — likely CheckFeatureSupport or a pipeline state creation function — that D3DMetal acknowledges as supported but returns null or invalid data for. The game trusts the response and dereferences the null pointer. Two other Nixxes titles using the same engine and D3DMetal setup run without issue: Spider-Man 2 (~50 FPS) and Horizon Zero Dawn Remastered (~34 FPS). DS2 uses newer technology versions (DLSS 4, FSR 4, XeSS 2) and a newer DirectX 12 Agility SDK, which likely queries D3D12 features that D3DMetal does not yet fully implement. The crash also reproduces when D3DMetal reports as AMD vendor (1002) instead of NVIDIA (10de), crashing at the same executable offset, confirming it is a D3D12 feature reporting gap in D3DMetal rather than a vendor-specific issue. How To Reproduce Install Crossover 26+ on MacOS 26.4 Install Steam and download Death Stranding 2 Run Death Stranding 2 and check logs after crash in Documents\DEATH STRANDING 2 ON THE BEACH Feedback Requests FB22285513 — Game Porting Toolkit 3 issue with Modern Pipeline Creation

Got a broken frame when using Xcode to capture a frame and replay it from a Unity game. It seems like the vertex buffer is broken; I see a bunch of "nan"s in the vertex buffer. However, the game displays correct when running, and it only happend when I upgrade my Xcode and iphone to Xcode26 and IOS26 ios26

I want to address the missing or incomplete DirectX calls from D3DMetal and Game Porting Toolkit 3. These missing calls have in part caused issue with our porting process and we are reconsidering. Missing or Incomplete Calls DXGI_FEATURE_PRESENT_ALLOW_TEARING — IDXGIFactory5::CheckFeatureSupport — this calls has to do with how VSync is handled and some modern games require it to initialize. Currently D3DMetal return 0 maybe by design but most likely because it’s not integrated. Adding a stub that returns 1 can fix this. I’m my use case I simply Noped the check and forced it to continue. D3D12_FEATURE_D3D12_OPTIONS2.DepthBoundsTestSupported — this call is also not present. Which causes games to not initialize rendering. Thankfully this was fixed by once again skipping the check. But this is essential for water rendering. This could be one reason currently water is not rendering in our game. IDXGIOutput6::GetDesc1().ColorSpace — returns DXGI_COLOR_SPACE_RGB_FULL_G22_NONE_P709 (SDR) on external HDR compatible displays. We were able to fix this by forcing HDR to be enabled. It should return HDR support. These calls may exist but they need to be updated to return the correct values. Specifically for depth bound test you can reference MoltenVK which sets it up on top of Metal since it’s not a native feature. The water issue could be also an issue with how the shaders are compiled. But I’m unable to check because of the closed source nature of GPTK and its debuggers. What is a better way we can debug our game to see why the water isn’t rendering. Does D3DMetal have some debug options or something similar? Feedback Number FB22330617 - Missing DirectX Calls for Tearing and Depth Bound Test in D3DMetal and GPTK 3 We hope these issues are resolved quickly because we were thinking of a simultaneous release with our Windows version, but we can't ship with such large bugs.

Hi everyone, We’re currently porting a high-fidelity AA+ PC title built on Unreal Engine 5.7 to macOS (Apple Silicon), and we’re looking for guidance from anyone with experience in this area. At the moment, the game is already runnable on Mac, but not yet at a playable level — we’re seeing performance around 10–15 FPS on an M4 device. We’re actively analyzing and defining the work needed to reach production-quality performance on macOS. One of the key areas we’re exploring is leveraging MetalFX to improve frame rate. However, it seems there’s no official MetalFX plugin or direct integration available for Unreal Engine. Has anyone here successfully integrated MetalFX into a UE5 rendering pipeline, or found a recommended approach to do so? Any insights on best practices, workflows, or references (docs, samples, etc.) would be greatly appreciated. Thanks in advance!

The sample code just draw a triangle and sample texture. both sample code can draw a correct triangle and sample texture as expected. there are no error message from terminal. Sample code using constexpr Sampler can capture and replay well. Sample code using a argumentTable to bind a MTLSamplerState was crashed when using Metal capture and replay on Xcode. Here are sample codes. Sample Code Test Environment: M1 Pro MacOS 26.3 (25D125) Xcode Version 26.2 (17C52) Feedback ID: FB22031701