Aiserver Manufacturer
1 / 5
| Product Introduction: |
Tianshu Zhixin TianGai 100/BI-V100 32G is a domestically produced general-purpose GPU accelerator card focused on AI inference, scientific computing, and video encoding/decoding. It is built on a self-developed general architecture, with core specifications designed around 'high computing power, large memory, low power consumption, and wide compatibility.' The detailed specifications are as follows.
|
| Name: | Tianshu Zhixin TianGai 100 |
| INT8: | 295 TOPS |
| FP16: | 147 TFLOPS |
| FP32: | 37 TFLOPS |
| VRAM type: | HBM2E (High Bandwidth Memory, with approximately 30% higher bandwidth compared to HBM2, suitable for the high bandwidth demands of large model inference) |
| Chip fabrication process: | TSMC 7nm FinFET process, paired with 2.5D CoWoS advanced packaging (ensuring core heat dissipation and signal stability) |
| DirectX support: | Compatible with DirectX 12 (including 12_1 features), suitable for mainstream graphics rendering and video processing scenarios |
| Video memory frequency: | Effective frequency 4000MHz (native high-frequency characteristics of HBM2E, achieving low-latency data transfer with 800GB/s bandwidth) |
| Memory Bus Width: | 4096-bit (HBM2E standard bus width design, providing sufficient data channels for 32GB VRAM to avoid bandwidth bottlenecks) |
| Video memory speed: | 0.5 ns (based on the physical characteristics of HBM2E memory chips, corresponding to an equivalent frequency of 4000 MHz, with latency better than GDDR6) |
| Output Interface: | No traditional video output interfaces (DP/HDMI/VGA), focused on data center inference/computing scenarios |
| Output interface type: | The core interface is PCIe Gen4.0 x16 (bidirectional bandwidth 64GB/s), supporting x86/ARM host interconnection. |
| Form Factor: | FHFL dual - slot |
| Weight: | 1064g |
Designed for 24x7 enterprise data center operations, it features enterprise-grade components and energy-efficient hardware optimized for deployment at scale.
Supports Secure Boot with Hardware Root of Trust technology, provides an extra layer of security, and meets NEBS Level 3 standards to meet new data center standards.
The passively cooled, energy-efficient, dual-socket design fits a wide range of Tesla-Certified systems from OEM vendors and is easy to integrate into existing data center infrastructure.
