The upcoming next-gen Pascal-based GPUs by Nvidia are now in the testing and validation phase. The Pascal GPU architecture is certainly one of Nvidia's most-awaited products in 2016 and the latest news adds more to the excitement caused by its impending release.
The said GPUs are being sent from the fabrication plants of Taiwan Semiconductor Manufacturing Company (TSMC) to Nvidia's testing facilities in India.
It should be noted that TSMC won the contract against Samsung in the bid to mass-produce the Pascal GPUs using the company's 16nm FinFET production process.
The Pascal GPU is Nvidia's follow-up to Maxwell and will feature new technologies that include NVLink, HBM2 and Mixed Precision Support.
At least four different Pascal GPUs are now being tested and seem to carry the same serial number of 699. These four different GPUs are the following:
The first three units all seem like derivatives or variants that belong to one basic board which makes the last 12914 label as an entirely different board. All of the GPUs cited will feature very similar per unit values, with the GP100 GPU being the largest and the most powerful among the Pascal graphics chips from Nvidia.
Apart from having Pascal graphics architecture, the flagship GP100 GPU will also feature four 4-Hi HBM2 stacks to achieve 16 GB of VRAM in total and 8-Hi stacks to reach up to 32 GB meant for the professional compute SKUs.
Other highlights of the GP100 GPU include the following:
• up to twice the performance per watt estimated improvement compared to Maxwell
• DirectX 12 feature level 12_1 or even higher
• built on TSMC's 16nm FinFET manufacturing process
• a total of 17 billion transistors, which is more than twice the number found in the GM200
• comes with a 4096-bit memory bus interface
• features NVLink
• supports half precision FP16 compute, which is two times the rate performed by full precision FP32
The flagship GP100 GPU will be the successor to the GM200 GPU, which is found in the GTX 980 Ti and the GTX Titan X.
Nvidia is expected to give more details on its next-gen GPUs at the company's GPU Technology Conference that is slated to occur in early April.