China, Shanghai company Tianshu Zhixin Semiconductor Co has unveiled their new 7nm GPU is readily available. This follows the new trend of the 7 nanometre chips being developed by American companies Nvidia and AMD. The new chip is a powerful, packing in 24 billion transistors into the very tiny chip. To help put this into context, Nvidia’s GA102 GPU, which is featured in both the RTX 3080 and 3090 graphics boards, contains 28 billion transistors.
This chip is known as “Big Island” (BI), this new Graphical processing unit can output up to 147 TFLOPS of FP16 performance. AsTom’s Hardwarepoints out, that’s certainly competitive with similar products from Nvidia and AMD. Nvidia’s A100 and the AMD Instinct MI100 are capable of 77.97 TFLOPS and 184.6 TFLOPS of FP16 performance, respectively, though the Nvidia A100 also has Tensor cores with an additional 312 TFLOPS of FP16.
Tianshu Zhixin Semiconductor says Big Island is fabricated on 7nm size. The details provided seem toalign with TSMC’s 7nm node,but the foundry partner is not identified and it’s unclear if China has domestic chip production technology in that class. Images of the new GPU imply a multi-chip package with the GPU itself housed with onboard memory or cache. The target market however for the BI chip along with the AMD and Nvidia competition mentioned are all GPUs specifically made for enterprise applications, not desktop PCs or gaming.
The chips are aimed at datacentres who need the raw output power for complex algorithms and lack features you would find on commercial GPU’s aimed at the consumer market. Any GPU for gaming will need a wide array of hardware beyond the computational cores that crank out those TFLOPS, including a full pipeline of texture units, pixel processing and render outputs.
7nm isn’t the smallest chip being worked on either with Korean company Samsung actively working on a new Exynos chip ( Exynos 2100 ) which is infact as small as 5nm which they aim to utilise and power their new flash ship generation of phones for the Galaxy S21.