The partnership has successfully managed to increase the overall performance of PowerVR Series6 GPU core by over 25 percent and key blocks showed a 30 percent improvement when compared with existing design flows.
Imagination explained that its PowerVR SGX Graphics Processing Unit (GPU) IP core family is a series of OpenGL ES 1.1/2.0 and OpenVG 1.1 compliant graphics acceleration IP cores that meets the multimedia requirements of a wide range of next generation consumer, communications and computing applications. The GPUs’ architecture is fully scalable for a wide range of area and performance requirements, catering to the requirements of both low cost feature-rich mobile multimedia products to very high performance consoles and computing devices.
Imagination, a member of TSMC’s Soft-IP Alliance program, was already working with TSMC to develop highly optimized reference design flows and silicon implementations using the combined prowess of the PowerVR Series6 GPUs and TSMC’s advanced process technologies, including 16-nanometer FinFET process technology.
Tony King-Smith, executive vice president of marketing at Imagination, said, “The growing reliance on graphics processors to power the best user experiences means the GPU has become the new silicon process driver for the coming decade. It occupies as much as 50% or more of leading edge SoCs, and demands the highest performance memory bandwidth while always delivering high performance at low power. These characteristics are critical to defining the key device parameters of future generation processes. We’re delighted to be working closely with TSMC to ensure future silicon technologies are fully tuned to the needs of next generation’s most advanced SoCs.”
TSMC added that its collaboration with Imagination is helping to optimize future generations of its most advanced process technologies and system design techniques.