NVIDIA Announces Pascal, the Follow-up to Maxwell; Coming 2016
NVIDIA just launched its first Maxwell-based GPUs last month and isn't even done with Kepler (see today's GTX TITAN Z announcement), but the company is already looking to the future. During the keynote speech at NVIDIA's annual GPU Technology Conference, CEO Jen-Hsun announced the company's follow-up to the Maxwell architecture, Pascal, named after the famous 17th century French mathematical Blaise Pascal.
Due to arrive in 2016, Pascal-based GPUs will include three key new features: stacked DRAM, unified memory, and NVLink. Here are the descriptions of those features in NVIDIA's words:
- 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.
If you'd like to learn more about how stacked memory and NVLink work from a more technical standpoint, check the second link below. In addition to the above features, the module used to house Pascal GPUs is "one-third the size of standard boards used today," which means we can expect high-end NVIDIA GPUs in more compact form factors.