Arm Community
Arm Community
  • Site
  • User
  • Site
  • Search
  • User
Arm Community blogs
Arm Community blogs
Mobile, Graphics, and Gaming blog Vulkan SDK update
  • Blogs
  • Mentions
  • Sub-Groups
  • Tags
  • Jump...
  • Cancel
More blogs in Arm Community blogs
  • AI blog

  • Announcements

  • Architectures and Processors blog

  • Automotive blog

  • Embedded and Microcontrollers blog

  • Internet of Things (IoT) blog

  • Laptops and Desktops blog

  • Mobile, Graphics, and Gaming blog

  • Operating Systems blog

  • Servers and Cloud Computing blog

  • SoC Design and Simulation blog

  • Tools, Software and IDEs blog

Tags
Actions
  • RSS
  • More
  • Cancel
Related blog posts
Related forum threads

Vulkan SDK update

Gemma Paris
Gemma Paris
May 3, 2017
2 minute read time.

Our team has updated the Vulkan SDK with new sample code and tutorials. All sample code is released in github, under an MIT license. This latest SDK update includes two new Vulkan features with ARM Mali sample code and tutorials, which will help you to optimize your mobile graphics apps:

Vulkan Multipass

The Multipass feature in Vulkan enables developers to implement intense bandwidth requests without the need to access external memory. In the past, deferred shading on mobile was not feasible due to high bandwidth requirements on writing out a full G-Buffer to memory and then being read back as textures in the lighting pass. Extensions like GL_EXT_shader_pixel_local_storage in Open GL ES enabled developers to keep the G-Buffer on-tile to avoid these extra bandwidth requirements. However, now with Vulkan Multipass, there is no need of vendor-specific code paths to enable on-tile rendering anymore.

Multipass allows a render pass to contain multiple subpasses. This enables tiled-based GPUs like ARM Mali to merge two or more subpasses into one render pass, where the results from one subpass can be kept on-tile in-between the two subpasses. The resulting benefits are the removal of the need to access external memory, and so, making the implementation faster and reducing power consumption.

Adaptative Scalable Texture Compression

Texture compression is vital to reduce the size of games and other applications which rely heavily on textures. Furthermore, texture compression reduces bandwidth on the GPU which can improve performance and significantly reduce power consumption.

Adaptative Scalable Texture Compression (ASTC) produces high quality compressed textures at very low bit rates and in many different types of image format configurations. ASTC is the most flexible and efficient texture compression format, making it the leading edge texture compression standard for GPUs.

Figure 1: Game texture comparison: Original, traditional ETC format, newest ASTC format

ASTC was first released as an extension in OpenGL ES, as well as it was also included in the Google’s Android Extension Pack. In Vulkan, ASTC is available in the core API.

ASTC supports the following textures in Vulkan API:

  • LDR and HDR textures, although only LDR textures are part of the core Vulkan API
  • 2D and 3D textures, although only 2D textures are part of the core Vulkan API
  • Any number of colour channels and uncorrelated channels for special purpose texture data
  • Supports a wide range of quality settings ranging from 8bpp all the way down to less than 1bpp for 2D images in fine grained steps
  • In LDR mode, UNORM and SRGB are supported

To know more about ASTC visit the ASTC page on developer.arm.com.

Anonymous
Mobile, Graphics, and Gaming blog
  • Unlock the power of SVE and SME with SIMD Loops

    Vidya Praveen
    Vidya Praveen
    SIMD Loops is an open-source project designed to help developers learn SVE and SME through hands-on experimentation. It offers a clear, practical pathway to mastering Arm’s most advanced SIMD technologies…
    • September 19, 2025
  • What is Arm Performance Studio?

    Jai Schrem
    Jai Schrem
    Arm Performance Studio gives developers free tools to analyze performance, debug graphics, and optimize apps on Arm platforms.
    • August 27, 2025
  • How Neural Super Sampling works: Architecture, training, and inference

    Liam O'Neil
    Liam O'Neil
    A deep dive into a practical, ML-powered approach to temporal super sampling.
    • August 12, 2025