Khronos Compute Working Group Evaluating Apple’s OpenCL

The Khronos Group announced on Monday that they will form a Compute Working Group to create open standards for parallel computing across multiple GPUs and CPUs. Members include AMD, Apple, Freescale, NVIDIA and IBM. Apple has presented its OpenCL specification to the group.

The Compute Working Group will "create royalty-free, open standards for programming heterogeneous data and task parallel computing across GPUs and CPUs. The creation of this open standard is intended to enable and encourage diverse applications to leverage all available platform compute resources on a wide range of platforms," according to the Khronos Group.

The current members include: 3Dlabs, AMD, Apple, ARM, Codeplay, Ericsson, Freescale, Graphic Remedy, IBM, Imagination Technologies, Intel, Nokia, NVIDIA, Motorola, QNX, Qualcomm, Samsung, Seaweed, TI, and Umea University.

The Apple OpenCL specification, announced by Apple at the recent Worldwide Developers Conference, will enable any application to equally tap into the vast gigaflops of GPU and CPU resources through an approachable C-based language.

"The Compute Working Group potentially will be one of the most significant standardization efforts at Khronos. Highly-accelerated parallel computation across GPUs and CPUs is essential to many emerging rich consumer applications that will transform the computing experience of diverse users," said Neil Trevett, president of the Khronos Group. "Significantly, this initiative is aimed at both desktop and embedded devices -- the day when you will be able to hold a supercomputer in the palm of your hand is perhaps not so far away."

The Khronos Group also announced that representatives of the Compute Working Group will be available in person at SIGGRAPH in Los Angeles, August 11-15.

One result of the initiative will be that developers and scientists will be able to tap the vast potential of GPUs which, while very fast for graphics operations, are not well suited for general purpose computing until an abstraction layer like OpenCL is made available. The payoff is that while fast desktop systems are in the 100 gigaflop range, modern GPUs can range from many hundreds of gigaflops up to a teraflop (single precision) like the AMD Firestream 9250 announced on Monday.