Looking at the global chip crisis and increase in demand for semiconductors, the chip manufacturing fabs worldwide are looking to establish and increase production capacity to become the leading chip manufacturer in the silicon market.
As such, China’s Shanghai Tianshu Intellectual Semiconductor, a cloud and HPC system provider, has unveiled its first 7nm ‘Big Island’ GPU-based graphics card. According to sources, the card is currently in mass production will offer nearly twice the performance mainstream offerings from competitors in half the die area and with much lower power consumption.
The chip was unveiled during a board meeting by the company’s founder Zheng Jinshan. Reportedly, the GPU is based on the TSMC 7nm FinFET process node & has the 2.5D CoWoS design considering it packs the GPU and DRAM on the same die. It is made up of 24 Billion Transistors and features up to 37 TFLOPs of FP32, 147 TFLOPs of FP16/BF16, 371.0 TOPs INT32, 147 TOPs INT16, and 295 TOPs INT8 calculations per second.
If you compare it with a premium industry chip like the AMD Instinct MI100, the MI100 has a peak FP32 rate of 23.1 TFLOPs and a peak BFLOAT16 rate of 92.3 TFLOPs. NVIDIA’s A100 GPU on the other hand has a peak FP32 rate of 19.5 TFLOPs with Tensor cores pushing it to 156 TFLOPs and 312 TFLOPs with sparsity.
The clock speeds of the GPU are kept a secret until the official launch of the company.
China Big Island GPU Specs Comparison
| GPU Name | AMD Instinct MI100 | NVIDIA A100 | Big Island |
| Process Node | TSMC 7nm | TSMC 7nm | TSMC 7nm |
| Architecture | CDNA 1 | Ampere | Unknown |
| Transistors | 50 Billion | 54 Billion | 24 Billion |
| Cores | 7680 | 6912 | TBC |
| Memory | 32 GB HBM2 | 40 GB HBM2 | 32 GB HBM2 |
| Memory Bandwidth | 1.2 TB/s | 1.6 TB/s | 1.2 TB/s |
| FP32 Compute | 23.1 TFLOPs 46.1 TFLOPs (Matrix) | 19.5 TFLOPs 156 TFLOPs (Tensor) 312 TFLOPs (sparsity) | 37 TFLOPs |
| BFLOAT16 Compute | 92.3 TFLOPs | 312 TFLOPs 624 TFLOPs (sparsity) | 147 TFLOPs |
| TDP | 300W | 400W | 300W |
