DEPLOYDatabase

Chip comparison

AWS Inferentia 2 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.

FieldAWS Inferentia 2Huawei Ascend 910B
Process nodeTSMC N7SMIC N+2 (~7nm)
TDP250 W400 W
Memory32 GB HBM364 GB HBM2e
Memory bandwidth820 GB/s1,600 GB/s
FP16 (dense)400 TFLOPS
BF16 (dense)190 TFLOPS400 TFLOPS
FP8 (dense)380 TFLOPS
INT8 (dense)800 TOPS
Form factorInf2 EC2 instanceOAM (Atlas 300T A2)
Announced2022-12-012023-08-01
Released2023-04-012023-08-01

Robots running AWS Inferentia 2

No robots publicly running it yet.

Robots running Huawei Ascend 910B

Data centers with AWS Inferentia 2

No data centers publicly running it yet.

Data centers with Huawei Ascend 910B

Common questions

AWS Inferentia 2 vs Huawei Ascend 910B: which is faster for training?

Huawei Ascend 910B has 1.05x the dense FP16/BF16 throughput of the other (AWS Inferentia 2: 380 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.

AWS Inferentia 2 vs Huawei Ascend 910B: which has more memory?

Huawei Ascend 910B carries more HBM (AWS Inferentia 2: 32 GB HBM3; Huawei Ascend 910B: 64 GB HBM2e). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

AWS Inferentia 2 vs Huawei Ascend 910B: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: AWS Inferentia 2 1.52 (380 ÷ 250 W); Huawei Ascend 910B 1.00 (400 ÷ 400 W). AWS Inferentia 2 wins at the die level; system-level efficiency also depends on cooling and interconnect.

AWS Inferentia 2 vs Huawei Ascend 910B: which is more widely used?

AWS Inferentia 2: 0 robots and 0 data centers 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 · AWS Inferentia 2 full page · Huawei Ascend 910B full page.