Chip comparison
Google TPU v5e vs Huawei Ascend 910B
Side-by-side specs
Straight from each vendor's datasheet. Winner in bold: higher throughput, memory, or transistor count; lower power draw or price. Sparse (2:4) throughput roughly doubles the FP8/INT8 numbers shown.
| Field | Google TPU v5e | Huawei Ascend 910B |
|---|---|---|
| Process node | — | SMIC N+2 (~7nm) |
| TDP | 170 W | 400 W |
| Memory | 16 GB HBM2 | 64 GB HBM2e |
| Memory bandwidth | 819 GB/s | 1,600 GB/s |
| FP16 (dense) | — | 400 TFLOPS |
| BF16 (dense) | 197 TFLOPS | 400 TFLOPS |
| INT8 (dense) | 393 TOPS | 800 TOPS |
| Form factor | OAM (v5e pod, up to 256 chips) | OAM (Atlas 300T A2) |
| Announced | 2023-08-29 | 2023-08-01 |
| Released | 2023-11-01 | 2023-08-01 |
Robots running Google TPU v5e
No robots publicly running it yet.
Robots running Huawei Ascend 910B
Data centers with Google TPU v5e
Data centers with Huawei Ascend 910B
Common questions
Google TPU v5e vs Huawei Ascend 910B: which is faster for training?
Huawei Ascend 910B has 2.03x the dense FP16/BF16 throughput of the other (Google TPU v5e: 197 TFLOPS; Huawei Ascend 910B: 400 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.
Google TPU v5e vs Huawei Ascend 910B: which has more memory?
Huawei Ascend 910B carries more HBM (Google TPU v5e: 16 GB HBM2; Huawei Ascend 910B: 64 GB HBM2e). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
Google TPU v5e vs Huawei Ascend 910B: which is more power-efficient?
Dense FP16/BF16 TFLOPS per watt: Google TPU v5e 1.16 (197 ÷ 170 W); Huawei Ascend 910B 1.00 (400 ÷ 400 W). Google TPU v5e wins at the die level; system-level efficiency also depends on cooling and interconnect.
Google TPU v5e vs Huawei Ascend 910B: which is more widely used?
Google TPU v5e: 0 robots and 1 data center publicly running it. Huawei Ascend 910B: 2 robots and 1 data center. Empty here means no operator has said publicly, not zero adoption in the market.
See also: every chip comparison · Google TPU v5e full page · Huawei Ascend 910B full page.