HU
Huawei Ascend 910A
Da Vinci OAM 2019 TSMC 7nm
FP32
16.0
TFLOPS
VRAM
32 GB
HBM2
TDP
310 W
51.6 TFLOPS/kW
Bandwidth
1.2 TB/s
memory
Performance Metrics
Peak theoretical throughput by precision type
| Precision | Description | Bits | Peak TFLOPS | Efficiency |
|---|---|---|---|---|
| INT8 | 8-bit integer | 8 | 512.0 | 1.652 TFLOPS/W |
| FP16 | 16-bit floating point | 16 | 256.0 | 0.826 TFLOPS/W |
| FP32 | 32-bit floating point | 32 | 16.0 | 0.052 TFLOPS/W |
FP16 Efficiency
0.826 TFLOPS/W
256.0 TFLOPS / 310W
FP32 Efficiency
0.052 TFLOPS/W
16.0 TFLOPS / 310W
Power Specifications
TDP
310 W
Max Power
357 W
Power Connector
PCIe 16-pin
Cooling
Air
Memory Specifications
Capacity
32 GB
Type
HBM2
Bandwidth
1228 GB/s
Interface
--
Hardware & Design
Form Factor
OAM
Architecture
Da Vinci
Process Node
TSMC 7nm
Launch Year
2019
Variant
Standard
Market Segment
Data Center
Full Specifications
| Memory | |
|---|---|
| VRAM | 32 GB |
| Memory Type | HBM2 |
| Bandwidth | 1.2 TB/s |
| Interconnect & I/O | |
| GPU-to-GPU | HCCS |
| Interconnect Bandwidth | 90 GB/s |
| Power & Thermal | |
| TDP | 310 W |
| General | |
| Form Factor | OAM |
| Architecture | Da Vinci |
| Launch Year | 2019 |
Documentation & Resources
Common Use Cases
General Compute AI/ML Workloads Data Processing
The Huawei Ascend 910A is optimized for high-performance computing tasks with Da Vinci architecture delivering 16 TFLOPS of compute power.
Where to Rent
Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.
Browse GPU Cloud ProvidersStay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
Loading verification...
No spam, unsubscribe anytime.