Category: Misc

NVIDIA Nsight Developer Tools provide comprehensive access to NVIDIA GPUs and graphics APIs for performance analysis, optimization, and debugging activities….

NVIDIA Nsight Developer Tools provide comprehensive access to NVIDIA GPUs and graphics APIs for performance analysis, optimization, and debugging activities. When using advanced rendering techniques like ray tracing or path tracing, Nsight tools are your companion for creating a smooth and polished experience. 

At SIGGRAPH 2023, NVIDIA hosted a lab exploring how to use NVIDIA Nsight Tools to debug and profile ray tracing applications. New versions of the NVIDIA Nsight Aftermath SDK, NVIDIA Nsight Graphics, and NVIDIA Nsight Systems are also available. For more information on Nsight Tools released at SIGGRAPH, check out the latest video on NVIDIA Graphics Tools.

This post explores how Nsight Aftermath SDK 2023.2 speeds up GPU crash debugging with improved event marker performance.  

Nsight Aftermath SDK GPU crash postmortem analysis

Few issues are as pressing as a GPU crash, which can abruptly block development progress until resolved. Developers and end users alike find these crashes frustrating, especially when they can’t capture useful debugging information from the GPU pipeline at the moment of failure. To shed light on hidden exceptions, the Nsight Aftermath SDK opens a window into the GPU at the moment a game fails. This helps pinpoint the source of the issue and guides the developer in resolving it.

The Nsight Aftermath SDK generates GPU crash dump files that load into NVIDIA Nsight Graphics to visualize the GPU state—revealing MMU fault information, warp details, problematic shader source, and more. Integrating Aftermath into existing crash reporters also provides more granular pipeline dumps from end-users’ machines, providing actionable reports. Today’s update to the Nsight Aftermath SDK improves the contextual data provided through low-overhead, application-specific markers.

Event marker performance has been enhanced in the Nsight Aftermath SDK for DirectX 12 applications. You can insert these markers into your CPU code at desired intervals, and the significantly reduced overhead makes them usable in shipping applications. Markers are written to the Aftermath crash dump file, indicating where in the application’s frame a GPU exception occurred. With this information, you can determine the workload executing on the GPU and view what shaders were in use at the time of the crash.

The 2023.2 version of the Nsight Aftermath SDK also supports collecting and displaying shader register values to aid in debugging streaming multiprocessor (SM) exceptions. On the SM, registers store the results of instructions as they are executing. This data is particularly relevant to determining the source of a crash if a shader workload triggered the failure. After being written to an Nsight Aftermath dump file, you can inspect the register values for faulting threads in Nsight Graphics. This helps you determine where and why the shader execution failed.

SM register data is now available for DirectX 12 and Vulkan applications. Note that viewing this data requires NVIDIA Nsight Graphics Pro. Coordinate with your NVIDIA Developer Technologies or Developer Relations contact, or reach out, to request access.

Nsight Aftermath is also now compatible with the latest applications using cutting-edge DirectX12 features through the DirectX Agility SDK.

Getting Started with Nsight Aftermath SDK and event markers

Getting started with the SDK is easy. Here are some tips to help you use GPU crash dumps and event markers. More information is included in the Read Me section of the download.

1. Download Nsight Aftermath SDK 2023.2.
2. Enable GPU crash dump creation by calling GFSDK_Aftermath_EnableGpuCrashDumps. Note that crash dumps won’t be made for devices generated before that call. Make sure it’s enabled first.
3. Set the Nsight Aftermath options to control what information is captured. 
   For example, you can enable ‌shader debug information and runtime shader error reports “flags” when you initialize Nsight Aftermath for the device. 

   Tip: To use event markers, make sure that the event marker flag is enabled at this step. You can also use the Nsight Aftermath Monitor application to enable SM register collection.

4. When your GPU dump has been collected, open it up with Nsight Graphics for rich data visualization. Nsight Graphics will help you analyze the crash and determine how to resolve it.

Tip: the Aftermath API provides a simple and lightweight solution for inserting event markers on the GPU timeline. To keep CPU overhead to a minimum, you can set dataSize=0 to instruct Aftermath to rely on the application to manage and resolve marker data itself. 

Download NVIDIA Nsight Developer Tools

Download all of the new Nsight Developer Tools announced at SIGGRAPH.

• Nsight Aftermath SDK 2023.2
• Nsight Graphics 2023.3
• Nsight Systems 2023.3

Dive deeper or ask questions in Developer Tools forums or learn more about graphics development with Nsight Tools at SIGGRAPH 2023.

NVIDIA is providing developers with an advanced platform to create scalable, branded, custom extended reality (XR) products with the new NVIDIA CloudXR Suite….

NVIDIA is providing developers with an advanced platform to create scalable, branded, custom extended reality (XR) products with the new NVIDIA CloudXR Suite.

Built on a new architecture, NVIDIA CloudXR Suite is a major step forward in scaling the XR ecosystem. It provides a platform for developers, professionals, and enterprise teams to flexibly orchestrate and scale XR workloads across operating systems, including virtual machines in Windows and Linux-based systems such as containers. 

With the NVIDIA CloudXR streaming stack, users can build flexible, high-performance cloud solutions capable of streaming the most demanding immersive experiences. Teams can also access NVIDIA streaming technology to effectively manage the quality of the streaming across large public and private networks, including the internet.

Immersive content developers have a challenge in supporting both tethered devices, driven by high-powered graphics cards, and mobile devices that have limited graphics power.  

Using NVIDIA CloudXR, developers can create high-quality versions of applications—built to take advantage of powerful GPUs—and still target users with mobile XR devices using NVIDIA CloudXR streaming. 

Additionally, cloud service providers (CSPs), orchestrators, and system integrators can extend GPU services with interactive graphics to support next-generation XR applications. 

NVIDIA CloudXR Suite is composed of three components: CloudXR Essentials, CloudXR Server Extensions, and CloudXR Client Extensions. 

CloudXR Essentials provide the underlying streaming layer, complete with new improvements such as 5G L4S optimizations, QoS algorithms, and enhanced logging tools. ‌Essentials also includes the SteamVR plug-in, along with sample clients and a new server-side API that can be directly integrated into XR applications. This removes the need for a separate XR runtime.

CloudXR Server Extensions extend server-side interfaces with a source code addition to Collabara’s Monado OpenXR runtime. The new CloudXR Server API contained in CloudXR Essentials, plus the OpenXR API, represent the gateway to scaling XR distribution for orchestration partners. 

CloudXR Client Extensions empower users to build custom CloudXR client applications. The first offering is a Unity plug-in for CloudXR. With this plug-in, Unity app developers can more easily build applications with branded custom interfaces and lobbies before connecting to the CloudXR streaming server. 

“The new CloudXR Server Extensions bring more opportunities for software developers to use Monado’s OpenXR runtime to build next generation immersive experiences,” said Frédéric Plourde, XR Lead at Collabora.

High-quality XR streaming for clients

PureWeb helps organizations across industries adopt real-time 3D technology to improve operations. Using NVIDIA CloudXR, PureWeb shows customers how to deliver complex, immersive XR workloads at scale, on their current devices.

“We want to provide our customers with access to the GPU resources and streaming technologies they need, so they can share immersive experiences without worrying about not having enough computing resources,” said Chris Jarabek, VP of Product Development at PureWeb. “With this new advancement through CloudXR Suite, we can better scale with OpenXR and build with that.” 

The team at Innoactive has integrated NVIDIA CloudXR into their VR application deployment platform, Innoactive Portal. Many Innoactive customers are using the platform to provide high-quality immersive training to users, wherever they are.

“Many of our customers are building applications and plan to stream them to all-in-one headsets or other mobile XR devices,” said Daniel Seidl, CEO of Innoactive. “With the Unity plug-in, our customers can now stream from AWS and Microsoft Azure with CloudXR, making XR streaming even more accessible from the cloud.”

Learn more and download NVIDIA CloudXR Suite. 

AI and accelerated computing were in the spotlight at SIGGRAPH — the world’s largest gathering of computer graphics experts — as NVIDIA founder and CEO Jensen Huang announced during his keynote address updates to NVIDIA Omniverse, a platform for building and connecting 3D tools and applications, as well as acceleration for Universal Scene Description (known as OpenUSD), the open and extensible ecosystem for 3D worlds.

Picture this: Creators can quickly create and customize 3D scene backgrounds with the help of generative AI, thanks to cutting-edge tools from Shutterstock. The visual-content provider is building services using NVIDIA Picasso — a cloud-based foundry for developing generative AI models for visual design. The work incorporates Picasso’s latest feature — announced today during NVIDIA Read article >

As generative AI continues to sweep an increasingly digital, hyperconnected world, NVIDIA founder and CEO Jensen Huang made a thunderous return to SIGGRAPH, the world’s premier computer graphics conference. “The generative AI era is upon us, the iPhone moment if you will,” Huang told an audience of thousands Tuesday during an in-person special address in Read article >

Machine learning helped Waseem Alshikh plow through textbooks in college. Now he’s putting generative AI to work, creating content for hundreds of companies. Born and raised in Syria, Alshikh spoke no English, but he was fluent in software, a talent that served him well when he arrived at college in Lebanon. “The first day they Read article >

Organizations across industries are using extended reality (XR) to redesign workflows and boost productivity, whether for immersive training or collaborative design reviews. With the growing use of all-in-one (AIO) headsets, more teams have adopted and integrated XR. While easing XR use, AIO headsets have modest compute and rendering power that can limit the graphics quality Read article >

Professionals, teams, creators and others can tap into the power of AI to create high-quality audio and video effects — even using standard microphones and webcams — with the help of NVIDIA Maxine. The suite of GPU-accelerated software development kits and cloud-native microservices lets users deploy AI features that enhance audio, video and augmented-reality effects Read article >

New Omniverse Cloud APIs Help Developers Adopt OpenUSD; Generative AI Model ChatUSD LLM Converses in USD; RunUSD Translates USD to Interactive Graphics, DeepSearch LLM Enables Semantic 3D …

New Platform Updates, Connections to Adobe Firefly, OpenUSD to RealityKit, Ada-Generation Systems Accelerate Interoperable 3D Workflows and Industrial DigitalizationLOS ANGELES, Aug. 08, 2023 …