NVIDIA reveals Pascal GPU design, won't be out until 2016

[sujith]

In 2013, NVIDIA said that its next GPU design beyond its current Kepler products would be called Maxwell for a launch in 2014. Today, NVIDIA didn't talk a lot about Maxwell during its annual GPU Technology Conference but it did discuss its successor, which has the name Pascal.

The company's press announcement said that the design, which was named after the 17th century French mathematician Blaise Pascal, will stack DRAM into dense modules and place them inside the GPU itself. NVIDIA says this will allow the chip to gain access to memory faster and make the designs smaller. The final result should allow for Pascal-based GPUs to have much more bandwidth combined with better energy efficiency and over twice the memory capacity.

Pascal GPUs will also allow games and apps to give the CPU access to the GPU's memory, and vise versa. Finally, the design will put in what's being called NVLink, which will allow data to flow as fast as 80GB a second between the GPU and CPU, compared to the current limit of 16GB.

Named for 17th century French mathematician Blaise Pascal, our next-generation family of GPUs will include three key new features: stacked DRAM, unified memory, and NVLink.

3D Memory: Stacks DRAM chips into dense modules with wide interfaces, and brings them inside the same package as the GPU. This lets GPUs get data from memory more quickly – boosting throughput and efficiency – allowing us to build more compact GPUs that put more power into smaller devices. The result: several times greater bandwidth, more than twice the memory capacity and quadrupled energy efficiency.

Unified Memory: This will make building applications that take advantage of what both GPUs and CPUs can do quicker and easier by allowing the CPU to access the GPU’s memory, and the GPU to access the CPU’s memory, so developers don’t have to allocate resources between the two.

NVLink: Today’s computers are constrained by the speed at which data can move between the CPU and GPU. NVLink puts a fatter pipe between the CPU and GPU, allowing data to flow at more than 80GB per second, compared to the 16GB per second available now. Pascal Module: NVIDIA has designed a module to house Pascal GPUs with NVLink. At one-third the size of the standard boards used today, they’ll put the power of GPUs into more compact form factors than ever before.

SOurce

Official Announcement By NVidia

[rudrax]

Kepler's gone

Pascal's coming

Who's next - Alex Jones?

Edited March 26, 2014 by rudrax