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 at www.khronos.org/opencl/.

Caustic Graphics is the company behind the OpenRL SDK (software development kit), a cross-platform, industry-standard API focused on unique raytracing extensions built on top of the OpenGL standard and OpenGL Shading Language (GLSL) APIs. Since Imagination Technologies supplies Apple with its technology in many iOS devices it is likely only a matter of time before the benefits of Caustic Graphics’ OpenRL reach future Apple devices. This will further propel Apple’s iPad and iPhone as both gaming and business-enterprise devices, particularly visual industries like medical imagining, engineering, scientific and architecture and construction.

Imagination and OpenRL

Apple is already a major investor in Imagination Technologies, a British fabless chip design company, holding nearly 10 percent of the company. The system-on-chip design of the Apple A4 processor in the iPhone 4 and iPad is reportedly based on the Imagination PowerVR SGX 535 GPU blueprint. It will be interesting to see if Apple stays with its current investment or further invest in Imagination.

OpenRL is a new proposed standard that aims to unify development of raytracing applications for software developers, which currently must program “to the metal” or accept GPU hardware “vendor lock-in” by using a limited specific subset of the hardware.

OpenRL works across platforms including Mac OS X, Windows and Linux, utilizes all OpenCL-based GPUs (eg: AMD/ATI, Nvidia, S3) and x86 CPUs simultaneously. The goal of OpenRL is to bring cinematic quality graphics to every day graphics display.

Last month Gizmodo wrote a brief piece about this acquisition as well.

Highlights

Here are some of the highlights from Peebler’s talk:

• Post Siggraph 2010 Event – Luxology Does its homework
• Brad says Luxology has always been looking at parallel computing
• Luxology works with its CPU partner, Intel, on some research
• Intel and Luxology research begets some CPU optimizations for future modo 501
• Luxology compares Octane Render  vs modo 501
• GPU rendering has promise with brute force rendering but has many more limitations
• Peepler believes Luxology’s CPU code is pretty darn fast!
• Luxology is not pro CPU or anti GPU
• Luxology sees the GPU as additional cores, not alternate cores
• Luxology looks to the “cloud” for additional cores – does pure research on this avenue

Peepler’s talk is very interesting. The bottom line is that Luxology is doing its homework thoroughly to get at the possible futures of rendering with both CPU and GPU cores.

01 - modo with CPU rendering vs Octane with GPU rendering. Brad Peebler shows the results of their internal research to find the best options for faster rendering by utilizing GPU cores in addition to CPU cores.

Even if you don’t use modo for your modeling, rendering and animation needs, this video is a very informative and useful type of content. I am sure you will find it as interesting as we did.

To check it out go here.

sdfs

OpenGL 4.0 and OpenCL

Apple-invented open industry standard OpenCL is now more closely aligned and interoperable with OpenGL via OpenGL 4.0. New new features in OpenGL 4.0 include:

• Core and Compatibility OpenGL 3.2 profiles retain backwards compatibility;
• two new shader stages that enable the GPU to offload geometry tessellation from the CPU;
• per-sample fragment shaders and programmable fragment shaders,
• drawing of data generated by OpenGL or external APIs such as OpenCL without main CPU intervention;
• shader subroutines for better programming flexibility;
• new object type called “sampler objects” provide separation of texture state and texture data;
• 64-bit double precision floating point shader operations and quality;
• performance improvements, included instanced geometry, instanced shaders, instanced arrays and a new timer query.

The Khronos Group has also released an OpenGL 3.3 specification, together with the set of ARB extensions, to enable some OpenGL 4.0 functionality in previous generation GPU hardware.

It is unclear at this time when operating systems vendors will support the new OpenGL 4.0 standard. For more information visit this link.

Interesting post about Intel’s work on cracking the issue of sharing data between Core and Xeon CPUs and Larrabee GPU co-processors. Future Core and Xeon chips will be able to create a “virtual” shared memory pool that both the CPU and GPU can access so datasets are nto crunched down, serialized, and moved over the slower PCI-Express bus from CPU to GPU, this report discusses.

We know that Apple is working within the OS level to speed up standardized operations so they can be efficiently distributed among available processing cores on both the CPU and GPU levels simultaneously.

There is also a recent post at the same link above about Apple’s OpenCL FFT lib producing very high performance.

OpenCL conformance tests are now available with new conformant products now shipping. Additionally, the OpenCL Working Group membership has expanded to 33 members in the areas of high-performance computing, gaming, middleware, system and silicon vendors. Participating at SC09, an international conference for high-performance computing, Khronos Group members will be highlighting the power and scalability of OpenCL.

OpenCL Products – Trademark Use and Conformance

Before a product can use the OpenCL trademark it must pass a conformance test suite by Khronos for OpenCL 1.0. This suite was released in May 2009 and a number of shipping products have successfully passed including products from AMD, Apple and Nvidia.

In the case of Apple its latest operating system, Snow Leopard, utilizes OpenCL. Apple created OpenCL and opened it up as an industry standard giving control of the standard to the Khronos Group.

“By enabling cross-platform development for heterogeneous architectures, OpenCL is helping to bring GPU compute capability to mainstream applications,” said Patricia Harrell, director of stream computing at AMD.

“Nvidia cares deeply about ensuring that OpenCL developers have the tools they need to easily develop and deploy mainstream applications on more than 150 million Nvidia OpenCL 1.0-capable GPUs,” said Sanford Russell, general manager, GPU Computing software at Nvidia.

The latest list of conforming products for OpenCL 1.0 support can be found here at this web page. So far most products are operating systems and GPUs.

OpenCL Expands Significantly But No Microsoft

With 33 key industry members OpenCL is well on its way to becoming an industry standard as significant as OpenGL–a graphics technology standardized across an array of industry segments and device platforms.

In the gaming industry key members include Activision Blizzard, Electronic Arts and Nvidia and Apple. In terms of silicon systems makers they all the major vendors such as: AMD, ARM, Broadcom, Freescale, IBM, Intel, Nvidia, Samsung, STMicroelectronics, and Texas Instruments.

Key mobile phone makers are also behind OpenCL including: Ericsson, Motorola and Nokia (not to mention Apple). And the US government’s Los Alamos National Laboratory is also a key member.

IBM has released its own OpenCL Development Kit for Linux on Power on AlphaWorks. The company’s Power Architecture processors are used in workstations, servers, mainframe computers and supercomputers. Additionally, IBM is a partner with Sony in Cell processors and is exploring OpenCL on Cell and BE processors as well.

For more information about the Khronos Group’s efforts with OpenCL visit them here.

OpenGL 3.2

OpenGL 3.2 is the third major update in twelve months to the most widely adopted 2D and 3D graphics API (application programming interface). This new release continues the rapid evolution of the OpenGL standard to enable graphics developers to portably access cutting-edge GPU functionality across diverse operating systems and platforms. 

OpenGL 3.2 adds features for enhanced performance, increased visual quality, accelerated geometry processing and easier portability of Direct3D applications. In addition, the evolution of OpenGL and other standards within the Khronos, including OpenCL for parallel computing, OpenGL ES, and the new WebGL standard for 3D on the Web, are being coordinated to create a powerful graphics and compute ecosystem that spans many applications, markets and devices. The installed base of OpenGL 3.2 compatible GPUs already exceeds 150 million units. New features include:

• increased performance for vertex arrays and fence sync objects to avoid idling while waiting for resource shared by between CPU and GPU, or multiple CPU threads
• Improved pipeline programmability, including geometry shaders in the OpenGL core,
• Boosted cube map visual quality and multisampling rendering flexibility by enabling shaders to directly process texture samples

To learn more you can read this report link at the Khronos Group website.

Building on CrossFire

ATI (AMD’s graphics subsidiary) developed CrossFire as an interconnect technology to enable multiple GPUs to work together on single problems. CrossFire accelerates applications by tasking each GPU with a portion of a rendering workload. AMD (ATI) is building on its experience with by releasing the new WGL_AMD_GPU_association. This extension allows applications to make decisions about what portion of the work to task to what GPU (in the case of multiple GPU systems). 

New workstation class applications, like CAD, CAE, DCC (digital content creation), now make use of this extension to determine what types of GPUs are in a given system (computer) and pick which contexts to allocate on each GPU. This allows a workstation application to process multiple images and datasets simultaneously and combine the final image for display. 

GPU Association is currently available in Catalyst 9.1. The extension specification can be found in the OpenGL extension registry. 

To learn more about OpenGL click here.

2008 may turn out to be a watershed year for advanced industrial societies due to the collision of two major forces: the near total collapse of global financial markets and the rapid uptake in interest in alternative and renewable sources of energy. Both play into the adoption and interest in BIM for several reasons. Most notably BIM, unlike CAD, enables a better understanding (vis-a-vis analytical software tools) of building energy use and capture much earlier on in the design process. 

And in this time of marked “economic downturn” architecture firms, according to a recent AIA Economics report, are stepping back and looking for ways to optimize workflow and gain new efficiencies. Into this picture fits BIM (building information modeling) and with that ArchiCAD 12. Let’s take a look. 

ArchiCAD 12

With ArchiCAD 12 Graphisoft — which is now apart of the German Nemetschek Group – has done major work on a new underlying “systems technology” as well as optimized their code base for today’s multi-core processors from Intel and AMD. ArchiCAD 12 is the world’s first multi-threaded BIM application. The Hungarian developer also has addressed a broad range of BIM functionalities with a series of engaging new features and functional improvements.

So what’s new…?

First and foremost is the new Curtain Wall tool, based on the new systems technology mentioned earlier. Because this technology underlies significant future changes to ArchiCAD this will be our main focus in this review. However, there are several other important new features that warrant attention. First and foremost is the new Partial Structure Display and the related new feature 3D Document capability. Both of these make dramatic improvements to the core program. 

Secondly, Graphisoft has dramatically improved the StairMarker tool and the Hotlink Module. Finally there are several smaller improvements of which we will briefly touch on near the end of the review. 

A New System – Curtain Wall Tool

By far the biggest new feature in ArchiCAD 12 is the new Curtain Wall tool, which Graphisoft has told me is based on new “systems technology.” Developed internally Graphisoft’s new systems technology differs from its intelligent objects technology behind things like doors, windows, and stairs. 

The main distinction visible to the end user is that Curtain Walls — based on the new systems technology — can be edited at the “component member” level without dissembling the whole system or element. Also unique is that when you edit Curtain Walls at this level you do so within a dedicated 3D work environment complete with its own tools specific to the purpose of editing curtain walls. This is entirely different than the way in which you edit other building objects within ArchiCAD and it is a welcome change. (see image 01).

01 - ArchiCAD 12's new 3D Edit Curtain Wall Environment.

A key defining aspect of this new “systems technology” is that in the case of the new Curtain Wall tool there is introduced a new schema or set of “constructs” for understanding how the curtain walls you create are actually made and controlled by the program. These constructs include things like “reference line”, “reference plane”, “grid” and “base plane” and other constructs more closely aligned to real-world components like “panel” and “frame.” We are not going to talk about these specifically in this review but it bears mentioning that we hope Graphisoft can implement its systems technology going forward with a directness and simplicity consistent with the best aspects of the program. 

Imagine an updated version of this machine in all aluminum.

• All aluminum updated version of the original Macintosh – The product would be a “limited edition” run modern Mac redone that had a full blown emulator of all the classic software available on the original Mac. Part collector’s item, part novelty, part modern computer, such a machine would enable you run the old classic stuff side by side with the modern environment of OS X. Original Macs are collectors items; a special aluminum version would be both a homage to the Mac’s beginnings and to its current success and shiny future! How much could such a machine really fetch?  It depends on the size of the limited run. A 100k limited run might see machines fly off the shelf at very high prices, while a larger limited run at reasonable prices could see it become a “must have” Mac darling for macolytes around the globe. 
• New Mac Pro Ultra -  A dream power machine that would represent the “state-of-the-art” in technical capabilities possible. For starters it wouldn’t ship until Snow Leopard because it would need Grand Central and OpenCL. It would be the fastest computer in the world and hold that title for more than a year. Why? Because the PA Semi guys crafted an amazing energy efficient, multi-core processor based on the Power Architecture for which they hold unique expertise and capability. It would feature not four but eight (8) multi-core processors and run so cool you would think Apple found a way to pack the North Pole into it. It would feature multiple Nvidia Quadro GPU’s (making it the ultimate OpenCL dream machine) and it would come with new multi-touch capable monitors that could be positioned for touch-based drawing and input functionalities or run in conventional stand-up mode. Every engineer, scientist and architect would drool and lust for one. And though very expensive…they would sell like hot cakes! 
• New Mac touch – Back to a more Earth-based dream scenario, what Apple very well might introduce at Macworld Expo this January is the Mac touch. We have written about it here. The multi-touch patents that keep coming up in expanded and more elaborate form are, we think, somehow connected to the very existence of this machine. The Mac touch would be Apple’s answer to the rapid rise in the popularity of Netbooks. It would be very affordable. It would be multi-touch based but have a keyboard like an iPhone has a keyboard. It would make a wonderful media entertainment machine and work beautifully in ruggedized mode for specific industries like medicine and AEC (architecture/engineering/construction). We think the Mac touch has serious legs in verticals that need touch-based computing but today are poorly served by a clunky and worrisome Windows OS infrastructure. They would be much better served by OS X and Apple’s future. 

The Quadra had a special feeling to it. It was the ultimate Macintosh...wouldn't a new ultimate Mac be fitting for a Silver Anniversary?

 

“While the OpenCL spec is announced today, there are conformance tests that need to be developed and then final implementations will be released around Q2 next year.” These comments were made to AppleInsider from Manju Hedge, General Manager of CUDA at Nvidia. 

Snow Leopard’s Grand Central technologies allow developers to tune code to take advantage of parallelism across multi-core processors and GPUs. Both Grand Central and OpenCL are listed on Apple’s Snow Leopard webpage as key big features in the planned release. If Nvidia says final implementations of OpenCL are planned for Q2 of 2009 than Snow Leopard will not arrive early as some reports have indicated. Instead it may arrive around the time of Apple’s 2009 WWDC.

Apple’s OpenCL Embraced by Industry

Apple developed OpenCL and sponsored its adoption as an industry-open standard. OpenCL (Open Computing Language) greatly improves speed and responsiveness for a wide spectrum of applications in numerous market categories from gaming and entertainment to scientific and medical software. 

Proposed only six months ago, OpenCL was at the heart of Apple’s Snow Leopard operating system preview at its worldwide developer’s conference back in June of 2008. The draft specification became rapidly embraced by the tech world’s biggest names in semiconductors including: IBM, Intel, AMD, Nvidia, ARM, Freescale, Ericsson, Broadcom, Texas Instruments and Samsung. 

Other key players endorsing their OpenCL include gaming software giants EA (Electronic Arts) and Activision Blizzard. Notably absent the from big list of companies embracing OpenCL is Microsoft. However, with both Intel and AMD, the two largest PC chip makers in the industry, supporting it there is a likelihood that Microsoft will eventually add support to OpenCL. 

Microsoft says it has its own proprietary parallel programming technologies in the works. This technology is slated to be apart of DirectX technologies going forward. It should be noted that Microsoft’s Windows-only DirectX technologies are highly adopted in the world of PC gaming but Microsoft has failed to drive OpenGL out of the professional CAD and 3D content creation industries where both UNIX, Linux and Mac OS X are widely deployed and critical for support. Microsoft’s own parallel computing technologies may face a similar fate.

Both OpenGL and OpenCL are managed by the Khronos Group. To learn more visit their site here.

OpenCL is software technology that enables developers to tap the vast amounts of un-used power in graphics cards (GPUs) for tasks not related to graphics. The industry in general has taken well to OpenCL and the number of companies behind it include tech giants like Intel, Nvidia, AMD/ATI, Qualcomm, 3DLabs, Electronic Arts, Blizzard and many others. 

As we remarked this report, the one company that is not behind OpenCL — which will be managed independent of Apple and will be a royalty-free industry standard — is Microsoft, which seeks to compete with OpenCL using proprietary Microsoft technology.

“If you go to some other larger standards bodies, it’s quite normal for a standard to take five years or more,” said Neil Trevett, CEO of Khronos. The team pushed the limit in order to meet Apple’s time-frame for consideration in the next release of OS X, Snow Leopard. 

“The fact that if we could hit this impossible deadline [Apple] would support it in Snow Leopard was a huge plus to us,” said Tim Mattson of Intel who has worked on the standard. 

OpenCL, which stands for Open Computing Language enables compute-intensive applications to take advantage of both multi-core CPU’s and today’s very powerful GPU’s (graphics processing units). It is C-based (language) for wide inclusion within the programming market and is fully open and royalty-free. OpenCL is managed by the Khronos Group (like OpenGL is) and is backed by leading tech giants such as Apple, Intel, AMD, ARM, Freescale, Qualcomm, 3DLabs and others.

Bunkspeed (booth 311) will be showcasing its revolutionary CGI applications at SIGGRAPH in Los Angeles from August 12-14, 2008. Throughout the show Bunkspeed will be demonstrating its “CGI Made Simple” with HyperShot and will also have HyperShot on 70 workstations at the SIGGRAPH Studio, an on-site computer lab. Architosh will be covering more Bunkspeed at SIGGRAPH news during our show coverage.

Autodesk’s New App

Autodesk has released a new 3D digital sculpting and texture painting tool calledMudbox. The Windows-only tool allows powerful 3D painting and texturing to high-poly models, using organic brush-based 3D technology. Learn more here.

e-on Software and SIGGRAPH

The e-on Software folks will be at SIGGRAPH in a week showing the new Vue 7 Professional Solutions. The Oregon-based developer will be in booth #1129. Vue is the leading solution for natural 3D environmental creations and works seamlessly with leading 3D software packages. To learn more go here.

OpenCL Apple Article at Washington Post

Peter Cohen of Macworld fame has written a good summary piece on OpenCL and Apple coming up in Snow Leopard, the next iteration of Apple’s industry-leading operating system.

Now software developers have realized that the GPUs behind their computer’s ability to display graphics are far more capable of just that. Using these sophisticated GPU programming languages certain types of software programs — like solving weather analysis — now run on the GPU rather than on far more expensive supercomputers using hundreds or even thousands of more conventional CPUs (main processors).

Apple and OpenCL

However having a bunch of proprietary languages for Nvidia’s cards versus ATi’s cards makes it hard for the software developers looking to take advantage of GPUs and hence the industry was looking for an open industry standard. This is where Apple comes in.

Apple developed and proposed a standard called OpenCL and donated its specification to the Khronos Group, an industry association leading many of the standards for 3D graphics on personal computers. The big news is that nearly all the big hitters in the graphics hardware world have decided to back this standard.

AMD, Intel, ARM, IBM and Nokia — along with Apple — are some of its chief backers and will allow this open industry standard to bloom.

Chris Edwards reminds the reader in his article that graphics processing units (GPUs) essentially utilize many many simple processor cores, cores designed to do one thing very well, and when arrayed are capable of vast “computational parallelism.” It is in this sense that they are the piranhas of processing units.

Supercomputing on future iPhones

Despite all the industry support around Apple’s OpenCL standard Microsoft is missing from this picture. Redmond is going it alone with a team at Microsoft Research working on an experimental system called Accelerator. The tech giant has made no formal announcement about whether it will support or compete against OpenCL.

The hardware heavy-weights apparently don’t really care either. That’s because the vision for OpenCL goes far beyond the desktop but to mobile computing devices, things like smartphones for instance. Using a GPU can be 10 times more power-efficient to compute a task than using the main CPU. And power savings is hugely important to battery-driven devices, devices like the iPhone for instance.

Grand Central Puts It All Together

Apple’s plans for its next Mac operating system, called Snow Leopard, include a new set of technologies called “Grand Central” which some have begun to theorize will also manage the parallelization of computation across not just multi-core main processors but also the GPUs inside Macs.

Snow Leopard and Apple’s new developer tools will provide the API infrastructure to allow data-intensive computation-based applications to essentially stream operations in parallel, taking full advantage of the SIMD architecture found on GPUs, ie, the hundreds of parallel compute cores they are comprised of.

We see OpenCL having applicability with BIM (building information modeling) and the types of data analysis applied to the BIM model, such as energy analysis. Naturally OpenCL will likely play a role in visualization and other 3D intensive tasks.

Related Articles

Computing and mobiles: The piranhas of processing await (Guardian)

Apple joins working group to hammer out OpenCL spec(ArsTechnica)