Archive

Posts Tagged ‘vulkan’

Qualcomm Snapdragon 845 Octa Core Kryo 385 SoC to Power Premium Smartphones, XR Headsets, Windows Laptops

December 7th, 2017 9 comments

Qualcomm Snapdragon 845 processor was expected since May 2017 with four custom Cortex A75 cores, four Cortex A53 cores, Adreno 630 GPU, and X20 LTE modem. with the launch planned for Q1 2018. At least, that what the leaks said.

Qualcomm has now formally launched Snapdragon 845 Mobile Platform and rumors were mostly right, as the the octa-core processor comes with four Kryo 385 Gold cores (custom Cortex A75), four Kryo 385 Silver cores (custom Cortex A55) leveraging DynamIQ technology, an Adreno 630 “Visual Processing System”, and Snapdragon X20 modem supporting LTE Cat18/13.

The processor is said to use more advanced artificial intelligence (AI) allowing what the company calls “extended reality (XR)” applications, and will soon be found in flagship smartphones, XR headsets, mobile PCs, and more.

Qualcomm Snapdragon 845 (SDM845) specifications:

  • Processor
    • 4x Kryo 385 Gold performance cores @ up to 2.80 GHz (custom ARM Cortex A75 cores)
    • 4x Kryo 385 Silver efficiency cores @ up to 1.80 GHz (custom ARM Cortex A55 cores)
    • DynamIQ technology
  • GPU (Visual Processing Subsystem) – Adreno 630 supporting OpenGL ES 3.2, OpenCL 2.0,Vulkan 1.x, DxNext
  • DSP
    • Hexagon 685 with 3rd Gen Vector Extensions, Qualcomm All-Ways Aware Sensor Hub.
    • Supports Snapdragon Neural Processing Engine (NPE) SDK, Caffe, Caffe2, and Tensorflow
  • Memory I/F – LPDDR4x, 4×16 bit up to 1866MHz, 8GB RAM
  • Storage I/F – TBD (Likely UFS 2.1, but maybe UFS 3.0?)
  • Display
    • Up to 4K Ultra HD, 60 FPS, or dual 2400×2400 @ 120 FPS (VR); 10-bit color depth
    • DisplayPort and USB Type-C support
  • Audio
    • Qualcomm Aqstic audio codec and speaker amplifier
    • Qualcomm aptX audio playback with support for aptX Classic and HD
    • Native DSD support, PCM up to 384kHz/32bit
  • Camera
    • Spectra 280 ISP with dual 14-bit ISPs
    • Up to 16 MP dual camera, up to 32 MP single camera
    • Support for 16MP image sensor operating up to 60 frames per second
    • Hybrid Autofocus, Zero Shutter Lag, Multi-frame Noise Reduction (MFNR)
    • Video Capture – Up to 4K @ 60fps HDR (H.265), up to 720p @ 480fps (slow motion)
  • Connectivity
    • Cellular Modem – Snapdragon X20 with peak download speed: 1.2 Gbps (LTE Cat 18), peak upload speed: 150 Mbps (LTE Cat 13)
    • Qualcomm Wi-Fi 802.11ad Multi-gigabit, integrated 802.11ac 2×2 with MU-MIMO, 2.4 GHz, 5 GHz and 60 GHz
    • Qualcomm TrueWireless Bluetooth 5
  • Location – Support for 6 satellite systems: GPS, GLONASS, Beidou, Galileo, QZSS, SBAS; low power geofencing and tracking, sensor-assisted navigation
  • Security – Qualcomm Secure Processing Unit (SPU), Qualcomm Processor Security, Qualcomm Mobile Security, Qualcomm Content Protection
  • Charging – Qualcomm Quick Charge 4/4+ technology
  • Process – 10nm LPP

The company will provide support for Android and Windows operating systems. eXtended Reality (XR) is enabled with features such as room-scale 6DoF with simultaneous localization and mapping (SLAM), advanced visual inertial odometry (VIO), and Adreno Foveation. Maybe I don’t follow the phone market closely enough, but I can’t remember seeing odometry implemented in any other phones, and Adreon Foveation is not quite self-explaining, so the company explains it combines graphics rendering with eye tracking, and directs the highest graphics resources to where you’re physically looking, while using less resources for rendering other areas. This improves the experience, performance, and lower power consumption.

 

Click to Enlarge

Compared to Snapdragon 835, the new processor is said to be around 25 to 30% faster, the Spectra camera and Adreno graphics architectures are claimed to boost power efficiency by up to 30 percent, and the LTE modem is a bit faster (1.2 Gbps/150Mbps vs 1.0 Gbps/150Mbps). Quick Charge 4+ technology should deliver up  to 50 percent charge in 15 minutes. Earlier this year when SD835 was officially launched, there was virtually no mention of artificial intelligence support in mobile APs, but now NNA (Neural Network Accelerator) or NPE (Neural Processing Engine) are part of most high-end mobile processors, which in SD845 appears to be done though the Hexagon 685 DSP. High Dynamic Range (HDR) for video playback and capture is also a novelty in the new Snapdragon processor.

One of the first device powered by Snapdragon 845 will be Xiaomi Mi 7 smartphone, and according to leaks it will come with a 6.1″ display, up to 8GB RAM, dual camera, 3D facial recognition, and more. Further details about the phone are expected for Mobile World Congress 2018. Considering the first Windows 10 laptop based on Snapdragon 835 processor are expected in H1 2018, we may have to wait until the second part of the year for the launch of Snapdragon 845 mobile PCs.

More details may be found on Qualcomm Snapdragon 845 mobile platform product page.

Imagination PowerVR “Furian” Series8XT GT8525 GPU Targets High-end Smartphones, Virtual Reality and Automotive Products

May 11th, 2017 No comments

Imagination Technologies has unveiled their first GPU based on PowerVR Furian architecture with Series8XT GT8525 GPU equipped with two clusters and designed for SoCs going to into products such as high-end smartphones and tablets, mid-range dedicated VR and AR devices, and mid- to high-end automotive infotainment and ADAS systems.

Block Diagram for PowerVR Furian GT8525 GPU – Click to Enlarge

The Furian architecture is said to allow for improvements in performance density, GPU efficiency, and system efficiency, features a new 32-wide ALU cluster design, and can be manufactured using sub-14nm (e.g. 7nm process once available). PowerVR GT8525 GPU supports compute APIs such as OpenCL 2.0, Vulkan 1.0 and OpenVX 1.1.

Compared to the previous Series7XT GPU family, Series8XT GT8525 GPU delivers 80% higher fps in Trex benchmark, an extra 50% fps in GFXbench Manhattan benchmark, 50% higher fps in Antutu, doubles the fillrate throughput for GUI, and increases GFLOPs for compute applications by over 50%.

GT8525 GPU is available for licensing now, and has already been delivered to lead customers. More details should eventually surface on PowerVR Series8XT Core page.

ARM Introduces Bifrost Mali-G51 GPU, and Mali-V61 4K H.265 & VP9 Video Processing Unit

November 1st, 2016 4 comments

Back in May of this year, ARM unveiled Mali-G71 GPU for premium devices, and the first GPU of the company based on Bifrost architecture. The company has now introduced the second Bifrost GPU with Mali-G51 targeting augmented & virtual reality and higher resolution screens to be found in mainstream devices in 2018, as well as Mali-V61 VPU with 4K H.265 & VP9 video decode and encode capabilities, previously unknown under the codename “Egil“.

Mali-G51 GPU

Click to Enlarge

Click to Enlarge

ARM Mali-G51 will be 60% more energy efficiency, and have 60% more performance density compared to Mali-T830 GPU, making the new GPU the most efficient ARM GPU to date. It will also be 30% smaller, and support 1080p to 4K displays.

Under the hood, Mali-G51 include an updated Bifrost’s low level instruction set, a dual-pixel shader core per GPU core to deliver twice the texel and pixel rates, features the latest ARM Frame Buffer Compression (AFBC) 1.2, and supports Vulkan, OpenGL ES 3.2, and OpenCL 2.0 APIs.

More information can be found on the product page, and an ARM community blog post entitled “The Mali-G51 GPU brings premium performance to mainstream mobile“.

Mali-V61 VPU

mali-v61-4k-120hz

Mali-V61 can scale from 1 to 8 cores to handle 1080p60 up to 4K @ 120 fps, supports 8-/10-bit HEVC & 8-/10-bit VP9 up to 4K UHD video encoding and decoding, making it ideal for 4K video conference and chat, as well as 32MP multi-shot @ 20 fps.

The company claims H.265 and VP9 video encoding quality is about the same for a given bitrate with Mali-V61 as shown in the diagram below.

Click to Enlarge

VP9 vs HEVC vs H.264 – Click to Enlarge

Beside the capability of selecting 1 to 8 cores, silicon vendors can also decide whether they need encoding or decoding block for their SoC. For example camera SoC may not need video decoding support, while STB SoCs might do without encoding. While Mali-V61 is a premium IP block, ARM is also expecting it in mainstream devices possibly also featuring Cortex A53 processor cores and Mali-G51 GPU.

You’ll find more details on the product page, and ARM community “Mali-V61 – Premium video processing for Generation Z and beyond” blog post.

This Video Shows Vulkan API’s Higher Power Efficiency Compared to OpenGL ES API on ARM SoCs

October 20th, 2016 1 comment

Vulkan was introduced as the successor of OpenGL ES in March 2015, promising to take less CPU resources, and support multiple command buffers that can be created in parallel and distributed over several cores, at the cost of slightly more complex application programming since less software work in done inside the GPU drivers themselves with app developers needing to handle memory allocation and thread management.

opengl-es-vs-vulkanThis was just a standard at the time, so it still needed some time to implement Vulkan, and work is still in program but ARM showcased the power efficiency of Vulkan over OpenGL ES in the video embedded at the end of this post.

The demo has the same graphics details and performance using both OpenGL ES and Vulkan, but since the load on the CPU in that demo can be distributed over several CPU cores with Vulkan against a single core for OpenGL ES, it’s possible to use low power cores (e.g. Cortex A53) operating at a lower frequency and voltage, hence reducing power consumption.

ARM also measured that the complete OpenGL ES demo would use 1270 joules against 1123 Joules for the Vulkan demo, resulting in about 15% energy savings in this “early stage” demo.

Categories: Android, Video Tags: gpu, opengl, power, vulkan

PowerVR GT7200 Plus and GT7400 Plus GPUs Support OpenCL 2.0, Better Computer Vision Features

January 7th, 2016 3 comments

Imagination Technologies introduced PowerVR Series7XT GPU family with up to 512 cores at the end of 2014, and at CES 2016, they’ve announced Series7XT Plus family with GT7200 Plus and GT7400 Plus GPUs, with many of the same features of Series7XT family, plus the addition of OpenCL 2.0 API support, and improvements for computer vision with a new Image Processing Data Master, and support for 8-bit and 16-bit integer data paths, instead of just 32-bit in the previous generation, for example leading to up to 4 times more performance for applications, e.g. deep learning, leveraging OpenVX computer vision API.

Block Diagram (Click to Enlarge)

Block Diagram (Click to Enlarge)

GT7200 Plus GPU features 64 ALU cores in two clusters, and GT7400 Plus 128 ALU cores in a quad-cluster configuration. Beside OpenCL2.0, and improvements for computer vision, they still support OpenGL ES 3.2, Vulkan, hardware virtualization, advanced security, and more. The company has also made some microarchitectural enhancements to improve performance and reduce power consumption:

  • Support for the latest bus interface features including requestor priority support
  • Doubled memory burst sizes, matching the latest system fabrics, memory controllers and memory components
  • Tuned the size of caches and improved their efficiency, leading to a ~10% reduction in bandwidth

The new features and improvements of PowerVR Series7XT Plus GPUs should help designed better systems for image classification, face/body/gesture tracking, smart video surveillance, HDR rendering, advanced driver assistance systems (ADAS), object and scene reconstruction, augmented reality, visual inspection, robotics, etc…

You can find more details on Imagination Tech Blog.

ARM TechCon 2015 Schedule – IoT, Servers, 64-bit ARM, Power Usage Optimization, and More

October 1st, 2015 No comments

ARM_TechCon_2015The ARM Technology Conference (ARM TechCon) will take place on November 10 – 12, 2015, in Santa Clara Convention Center, and just like every year, there will be a free exposition for companies to showcase their latest innovation and/or products, as well as a technical conference with sessions and workshops sorted into various tracks:

  • Automotive/Embedded Vision
  • Embedded
  • IoT
  • Mobile/Connectivity
  • Networking Infrastructure/Servers
  • Tools & Implementation
  • Wearables/Sensors
  • ARM Training Day
  • Sponsored Vendor Training
  • Special Event
  • General Event
  • Software Developers Workshop

You can find the complete schedule on ARM TechCon website. Although I won’t attend, I’ve created my own virtual schedule with some of the sessions I found interesting.

Tuesday – November 10

  • 8:30 – 9:20 – ARM Vision for Thermal Management and Energy Aware Scheduling on Linux by Ian Rickards (ARM), Charles Garcia-Tobin (ARM), Bobby Batacharia (ARM)

This talk will cover the history and where are we going, for ARM’s Power Software (IPA, EAS, and some concepts for the future).

ARM will detail the latest update on our thermal control software Intelligent Power Allocation (IPA) which has just been released in mainline Linux 4.2. The tuning and implementation flow allow IPA to be easily deployed in Linux-based devices including Android.

We will also introduce ‘Energy Aware Scheduling’ (EAS) which is a new development by ARM/Linaro to allow the Linux scheduler to make the most energy efficient decisions using a generic energy model based approach. EAS includes improved upstream Linux support for ARM “big.LITTLE” systems and other advanced multi-cpu topologies.

  • 9:30 – 10:30 – Innovation is Thriving in Semiconductors by Mike Muller (ARM)

The human capacity to find a path past difficult challenges is astonishing. Though traditional silicon scaling is more complex at advanced geometries, electronics design innovation is more robust than ever as engineers devise new ways to improve the latest chips. ARM CTO Mike Muller will describe advances in design innovation spanning low power, trust, and architectural innovation all the way from sensors to server and beyond. And he’ll unveil the latest technology achievements from ARM in his signature lively, humorous and engaging style.

  • 10:30 – 11:20 – IoT Prototyping 101: The All-in-One Platform by Steven Si (MediaTek)

Power efficiency, connectivity and size are top priorities for any developer looking to prototype innovative IoT devices. Best utilizing these key features with ARM’s technology will be the spotlight of this session a live demonstration of how a developer at any level can create the next big thing in IoT. Skills to be shown: connecting sensors; using a cloud interface to build a virtual device; sending data from the device to the cloud and communicating with other smart devices. (cnxsoft: possibly using LinkIt ONE platform)

  • 11:30 – 12:20 – Khronos APIs for Fast and Cool Graphics, Compute and Vision by Neil Trevett (Khronos)

Discover how 100 companies cooperate at the Khronos Group to create open, royalty free standards that enable developers to access the power of hardware to accelerate the demanding tasks in cutting-edge mobile applications including heterogeneous parallel computation, 3D graphics and vision processing. This session includes the latest updates to API standards including OpenGL, OpenCL, OpenVX, and the recent Vulkan new generation graphics and compute API. The session will explore how modern APIs will accelerate the availability of compelling experiences such as neural-net based driver assistance, virtual and augmented reality, and advanced environmental tracking and 3D reconstruction on ARM-based devices

  • 13:00 – 15:00 – Boosting Performance from ‘C’ to Sky with Custom Accelerators on ARM-based FPGAs by Shaun Purvis (Hardent)

Offloading tasks to specialized hardware, such as a GPU or FPU, is a common approach to boosting software performance. However, the fixed nature (i.e. hard-silicon) of such hardware places an upper limit on just how much performance can be boosted. In order to break down this barrier, some modern SoCs have combined ARM processing power with programmable logic allowing software to be offloaded to custom, scalable, accelerators. With accelerators that can be tailored to specific needs, suddenly the sky’s the limit! But that’s not all. Combining these SoCs with modern tools allows designers to migrate high-level functions directly to hardware, skipping all the hardware design in between. This presentation will introduce one such tool and discuss the design methodology that takes a software-defined system and turns it into a custom hardware accelerated one.

  • 15:30 – 16:20 – Bringing Mali, the Android GPU of Choice, to Wearables by Dan Wilson (ARM Ltd.)

In this talk we will look at the trends for the use of graphics processors in Wearable devices and how the technical requirements of this space differ from that of smartphones and other segments. We look specifically at the ARM Mali GPU Utgard architecture which provides the perfect fit for Wearable designs and describe how this architecture has been implemented to create ARM’s latest ultra-low-power Mali GPU.

  • 16:30 – 18:00 – Efficient Interrupts on ARM Cortex-M Microcontrollers by Chris Shore (ARM)

Most real-time embedded systems make extensive use of interrupts to provide real-time response to external events. The design of the interrupt architecture is crucial to achieve maximum system efficiency. When designing software for devices based on ARM’s Cortex-M microcontroller cores, it is important to understand the interaction between interrupt priority, sub-priority, tail-chaining and pre-emption to achieve the most efficient design. This session will examine various use cases and give practical advice to software developers.

Wednesday – November 11

  • 8:30 – 9:20 – How (Not) to Generate Misleading Performance Results for ARM Servers by Markus Levy (EEMBC) & Bryan Chin (Cavium)

Cloud workloads are putting unique demands on SoCs and other system-level hardware being integrated into scale-out servers. Traditional benchmarks address the suitability of processors for different tasks. However, many factors contribute to the whole system performance memory, disks, OS, network interfaces, and network stack. In addition, the manner of generating workloads can affect the results. This session uses a case study from Cavium’s ARM-based Thunder X system and the EEMBC cloud and server benchmark, to present results that demonstrate how subtle test environment variations can obfuscate benchmark results and how a properly designed benchmark can overcome these obstacles.

  • 9:30 – 10:30 – Keynote by Simon Segars (ARM’s CEO)
  • 10:30 – 11:20 – Pentralux Flexible Digital Displays on Paper, Plastic, Cloth & Synthetics by Mathew Gilliat-Smith (DST Innovations), Anthony Miles (DST Innovations)

DST Innovations has created a flexible digital display proof of concept produced on plastic, paper, cloth or synthetic substrates. It’s integrated with the ARM mbed OS and will be suitable for developers and designers to integrate into third party products. Initially the digital screens will be for informational or promotional data and video. Being bright, safe, robust and requiring little power, the design parameters will be significant and far reaching for the wearable sector in thousands of clothing, fashion, promotional and other commercial concepts. The screens will offer inter-connectivity through the mbed ecosystem to receive transmitted IoT cloud generated data.

  • 11:30 – 12:20 – Are you ready for USB Type-C? by Ravi Shah (NXP Semiconductors) & Andy Lin (NXP Semiconductors)

USB Type-C offers new features and benefits like reversible plug orientation, improved data rates up to 10 Gbps as well as an unprecedented, scalable, 100 W power-delivery capability that can power higher wattage devices and support faster charging. This session will review the features, benefits and applications it is being designed into today. In addition, design considerations and lessons learned from the field will be reviewed.

  • 12:30 – 13:20 – From Concept to Reality: Advancing ARM-based Enterprise SoCs – Presented by Applied Micro Circuits Corporation by Dr. Paramesh Gopi (Allied Micro Circuits Corporation)

No abstract…

  • 14:30 – 17:20 – STM32L7 Hands-On Workshop by James Lombard & Steve Miller (STMicroelectronics)

Thursday – November 12

  • 8:30 – 9:20 – All Things Data: Healthcare by Pierre Roux (Atmel)

Examples of IoT are everywhere, including digital home, remote resourcing monitoring and automation, but what gets less attention is how the IoT will impact healthcare with the combination of technologies that leverages big data and analytics that go along with it.

This talk will look at opportunities, hurdles and the skills required to make the most of this intersection of Internet-connected physical objects and the deluge of data. It will examine new generation of data analytics for use cases associated with our changing world and, examine the role big data analytics will play in the future of the healthcare industry.

  • 10:30 – 11:20 – The ARM Cortex-A72 processor: Delivering high efficiency for Server Networking and HPC by Ian Forsyth,  Director of Marketing, ARM

New content-rich features, services and evolving business models are transforming network architectures, giving rise to the Intelligent Flexible Cloud (IFC). Architects are decentralizing intelligence to deliver required flexibility and to cope with increased traffic demands. This, in turn, is driving new classes of SoCs, enabled by technology standards including software-defined networking (SDN) and network functional virtualization (NFV). These require significant throughput-per-watt efficiencies within networking and servers. This talk will explore how the latest Cortex-A72 CPU offers compelling performance and throughput to meet the requirements of these future workloads.

  • 11:30 – 12:20 – Porting to 64-bit on ARM by Chris Shore (ARM)

With the introduction of the A64 instruction set in ARMv8-A, many developers need to port existing code to work in a 64-bit environment. At the coding level, this presentation will cover porting C code, assembly code and NEON code. Issues covered will include data typing and type conversion, pointers, bitwise operations, differences in the SIMD register bank layout, mapping of assembly instructions. At a system level, we will cover maintenance operations and extensions to the security architecture.

  • 13:30 – 14:20 – Keynote- The Hard Things About the Internet of Things by Colt McAnlis (Google)
  • 14:30 – 15:20 – Wearable System Power Analysis and Optimization by Greg Steiert (Maxim Integrated), Jesse Marroquin (Maxim Integrated)

This session will demonstrate how to extend battery life by showing the real world impact of system level architecture decisions. The session will introduce a technique for measuring battery current and then use that technique to compare the power efficiency of different system implementations. Tradeoffs analyzed will include: power architecture, operating voltage, sensor data interfaces, DMA, SIMD.

Takeaway: a method for measuring real time power consumption,  advantage of operating at the lowest voltage possible with efficient regulators, tradeoffs of different sensor interfaces and of different micro-controller architectures (peripherals/M0+/M3/M4)

  • 15:30 – 16:20 – Improving Software Security through Standards Compliance and Structural Coverage Analysis by Shan Bhattacharya (LDRA)

This presentation will focus on secure software best practices. Ensuring the security of embedded devices involves more than simply using vulnerability preventive programming. However, paying attention to and leveraging security standards such as CWE/CVE, CERT C and even CERT Java, will certainly improve the probability of delivering a secure and effective system.

  • 16:30 – 17:20 – Top Android Performance Problems of 2015 by Colt McAnlis (Google)

When you look at performance problems all day, you’re bound to lose your hair. So rather than balding early yourself, Colt McAnlis will walk you through the top performance problems that dominated 2015. This talk will cover the range of issues from Memory, to Rendering, to Networking, listing specific topics that have shown up in many of the top apps in Google Play. We’ll even take some time to look at the differences in some form factors, and how you should plan around that.

  • 17:30 – 18:30 – Happy Hour 🙂

If you are going to attend, you can register online. While as usual, going to the expo and attending vendor’s sponsored sessions is free, there are different passes to join the conference sessions, ARM training day, and software developers workshops. The earlier you register, the cheaper.

Conference Pass ARM Training Day Software Developers
Workshop
Expo Pass
Super Early Bird
(Ends July 24)
$599 $199 $99 Free
Early Bird
(Ends Sept. 4)
$799 $249 $149 Free
Advanced
(Ends Oct. 30)
$999 $299 $199 Free
Regular/Onsite $1249 $349 $249 Free

There are also discounts for groups, students, press & media, and government employees. You can check details on ARm TechCon 2015’s Passes & Prices page.

Google Plans Vulkan API Support for Android, Imagination Shows a Demo

August 11th, 2015 No comments

Vulkan graphics API is the successors to OpenGL and OpenGL ES API, which will support multi-threaded rendering, move some of the complexity to the applications, and simplify graphics drivers, which may not be a bad things since these tend to be closed source, and bugs may be hard to get fixed. Google, which is now a subsidiary of a new company called Alphabet,  has recently announced that Vulkan will be implemented in future versions of Android, although OpenGL ES will still be supported, so developers can select their preferred graphics API for their apps, as Vulkan will be more complex for application programmers than OpenGL ES.

OpenGL_ES_vs_VulkanSeparately, Imagination technologies showcased their Vulkan driver for PowerVR Rogue GPU on the Nexus Player powered by an Intel SoC including a PowerVR G6430 GPU, and compare the Vulkan demo to the same demo using OpenGL ES 3.0 drivers.


The difference between Vulkan and OpenGL ES 3.0 looks amazing, with Vulkan performing much better, but Imagination explains that this demo is an “exaggerated scenario that is intended to highlight and amplify Vulkan’s strengths. It is not intended to show OpenGL ES in a bad light – we are deliberately using OpenGL ES in a way that it was not designed for.” So I’m not sure if we can draw that many conclusions from the demo.

Imagination Technologies blog post explains the implementation and Vulkan advantage in much more details, such as lower CPU usage, and multi-threading support.

Meet Vulkan, The Successor of OpenGL and OpenGL ES 3D Graphics APIs

March 4th, 2015 6 comments

So far embedded systems are typically using SoCs with GPU supporting OpenGL ES, a subset of the full fledge OpenGL API used in desktop computers and workstations. These royalty-free standards are defined by Khronos Group non-profit organization, and as features in the embedded space and traditional computers merge, the group has now revealed the next-generation OpenGL specs will be called Vulkan. The new API will run on GPUs supporting OpenGL ES 3.1 or greater, take less CPU resources than its predecessors, and support multiple command buffers that can be created in parallel.

OpenGL_ES_vs_Vulkan

More work will be required at the application level, but direct GPU control by the drivers will apparently result in less memory copies improving performance, or at least off-loading the CPU. It might be transparent to developers using game engines. GPU drivers will also be less complex.

Vulkan will also use the new SPIR-V language shared with OpenCL 2.1 for graphics and compute. A (possibly open source) GLSL shader source to SPIR-V translator / compiler will be provided for legacy code.

Vulkan_SPIR-V

Vulkan Language Ecosystem

You’ll find more technical details, and some information about tools on Khronos Vulkan page.

I understand that Vulkan is still work-in-progress, but Imagination Technologies has already written alpha Vulkan compatible drivers for their PowerVR GPU, and run their Library demo on Android 5.0, so progress appears to be good, but it looks like more work has to be done to improve performance.