The Khronos Group OpenCL API is a SIMD programming model which maps well to the GPU but mostly bypass the fixed graphics-specific logic. The latest Radeon GPU Profiler 1.4 (RGP) now has the ability to profile OpenCL workloads in RGP. Most of the major RGP features that you’re used to using for profiling graphics workloads generated by Vulkan and DirectX 12 are there when profiling OpenCL applications, including the workload and barrier overviews.
Valve released the Beta of a new and improved version of Steam Play to all Linux users. The Beta version includes a modified distribution of Wine, called Proton, to provide compatibility with Windows game titles. Windows games with no Linux version currently available can now be installed and run directly from the Linux Steam client, complete with native Steamworks and OpenVR support. DirectX 11 and 12 implementations are now based on Vulkan, resulting in improved game compatibility and reduced performance impact. There are a lot of details in this announcement, be sure to read the entry over on the Steam Community website.
Cloud Imperium Games developer Ali Brown indicated that Star Citizen will be dropping DirectX support in favor of Vulkan. Specifically, Brown mentioned that CIG had been developing on DX11, with an intent to support DX12. However, because Vulkan enables single-API support for older version of Windows (and Linux) without sacrificing performance and features, the plan now is to move away from DirectX completely.
GizmoSphere, a not-for-profit embedded specialist, has announced the launch of a next-generation development board featuring a 1GHz dual-core AMD system-on-chip with Radeon HD8210E graphics on-board. The GPU supports OpenGL 4.2, OpenCL 1.2 and DirectX 11.1.
AnandTech has opened the debate on DirectX vs OpenGL. This time with DirectX 12 low-level programming and the recent “Approaching Zero Driver Overhead” talk at GDC 2014 by Cass Everitt, Graham Sellers, John McDonald and Tim Foley.
Amazon launched a new type of instance for its EC2 cloud computing platform that is specifically designed for applications that require 3D graphics capabilities. Using these new instances, Amazon argues, its users can now “build high-performance DirectX, OpenGL, CUDA, and OpenCL applications and services without making expensive up-front capital investments.” Amazon is making two of these new GPU instance types available for now. The g2.2xlarge version comes with 15 GB memory, 60 GB of local storage, 26 EC2 Compute Units (that’s an Intel Sandy Bridge processor running at 2.6 GHz) and a single NVIDIA Kepler GK104 graphics card (with 1536 CUDA cores). The larger cg1.4xlarge version comes with 22 GB of memory, 1690 GB of local storage, 33.5 EC2 Compute Units and two NVIDIA Tesla “Fermi” M2050 GPUs.
Valve Software has updated their Linux blog to report that the OpenGL version of Left 4 Dead 2 is now running fastest on Linux (315 fps). Surprisingly, given all the attention Valve has paid to Direct3D tuning over the years, even on Windows, the OpenGL version of the game now runs faster than Direct3D (304 fps vs. 270 fps) due to "overhead per batch in Direct3D which does not affect OpenGL on Windows".
NVIDIA announces the dual-chip GeForce GTX 690, powered by two Kepler-generation GK104 graphics processors. With the help of 3072 stream processors, the device is set to establish new performance records. The card supportsOpenGL 4.2, OpenCL 1.2 and DirectX 11.1.
The Khronos Group today announced the ratification and public release of the OpenCL 1.2 specification, providing enhanced performance and functionality to the industry-standard for heterogeneous, high-performance computing. A new conformance test suite was also made available to the developer community. New features in OpenCL 1.2 include seamless sharing of media and surfaces with DirectX® 9 and 11, enhanced image support, custom devices and kernels, device partitioning and separate compilation and linking of objects. The OpenCL 1.2 specifications, online reference pages and reference cards are all available on the Khronos website.
Neil Trevett, president of The Khronos Group, met with Japanese media at SIGGRAPH 2011 in Vancouver, to discuss the recent OpenGL 4.2 announcement and the momentum of the OpenGL advantage against DirectX.
SIGGRAPH 2011 in Vancouver last week had a very high level of interest in OpenCL™ as demonstrated by SIGGRAPH attendees. The Exhibitor Tech Talk on “OpenCL and OpenGL/DirectX interoperability” presented by Olivier Zegdoun of AMD’s ISV Workstation team had seating for over 90 attendees and was standing room only. The OpenCL Birds-of-a-Feather with presentations from AMD, Intel, Nvidia and Codeplay over 200 attendees, and when asked who was already using OpenCL approximately half of the attendees raised their hands.
AMD’s new Radeon HD 6990M is based on the TeraScale 2 unified processor architecture and the Barts GPU core. This is a mobile equivalent to the company’s high-end Radeon HD 6990 PCI Express graphics card design and features 1,120 stream processing units, 56 texture units, 128 Z/stencil ROP units, and 32 colour ROP units. AMD has included support for OpenGL 4.1, OpenCL 1.1 and MicroSoft’s DirectX 11 and DirectCompute 11. There was no mention of the Thermal Design Point, so it is unclear how much power will be required to run this new chip.
Opera just announced that its latest Opera 11 beta has WebGL support for Windows. Currently only Windows is support, but a promise of WebGL on Opera for other platforms has been made. As well, Opera claims they are working on WebGL for Windows using DirectX. This should be interesting, as WebGL is built on top of OpenGL. Opera 11 for Windows is available for download today.
The Khronos Group did a great job in the last few years to once again prove that OpenGL is still in game and that it can become the ultimate graphics API of choice, if it is not that already. However, we must note that it is not quite yet true that OpenGL 4.1 is a superset of its competitor, DirectX 11. We still have some holes that still have to be filled and I think the ARB should not stop just there as there is much more potential in the current hardware architectures than that is currently exposed by any graphics API so establishing the future of OpenGL should start by going one step further than DX11. In this article I would like to present my vision of items of importance that should be included in the next revision of the specification and how I see the future of OpenGL.