Flopper.io GPU Specification Sheet
September 26, 2026
flopper.io/gpu/huawei-ascend-910aHuawei Ascend 910A
Da Vinci OAM 2019 TSMC 7nm
Overview
16.0
FP32 TFLOPS
32 GB
Memory HBM2
1.2 TB/s
Memory Bandwidth
310 W
TDP
Performance Metrics
| Precision | Peak (dense) | Bits | Type |
|---|---|---|---|
| FP64 | — | — | Standard |
| FP32 | 16.0 | 32 | Standard |
| TF32 | — | — | Standard |
| BF16 | — | — | Standard |
| FP16 | 256.0 | 16 | Standard |
| FP8 | — | — | Standard |
| FP6 | — | — | Standard |
| FP4 | — | — | Standard |
| INT8 | 512.0 | 8 | Standard |
Memory Specifications
- Capacity
- 32 GB
- Type
- HBM2
- Bandwidth
- 1.2 TB/s
- Interface Width
- —
Power & Efficiency
- TDP
- 310 W
- Max power (Flopper estimate)
- ~357 W est.
- FP32 dense TFLOPS per W of TDP
- 0.05 TFLOPS/W
- FP16 dense TFLOPS per W of TDP
- 0.83 TFLOPS/W
Flopper estimate: 310 W TDP x 1.15. The vendor publishes no maximum board power for this part. Per W of TDP figures divide dense peak by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead.
Hardware Details
Vendor: Huawei
Architecture: Da Vinci
Process Node: TSMC 7nm
Form Factor: OAM
Launch Year: 2019
Interconnect
GPU-to-GPU: HCCS
Bandwidth: 90 GB/s direction and scope not stated by vendor