DEPLOYDatabase

Chip comparison

AWS Trainium 2 vs Huawei Ascend 910D

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 Trainium 2Huawei Ascend 910D
Process nodeTSMC N5SMIC N+2 (~7nm)
TDP500 W800 W
Memory96 GB HBM3192 GB HBM3
Memory bandwidth2,900 GB/s4,000 GB/s
FP16 (dense)1,200 TFLOPS
BF16 (dense)667 TFLOPS1,200 TFLOPS
FP8 (dense)1,300 TFLOPS2,400 TFLOPS
INT8 (dense)1,300 TOPS
Form factorAWS Neuron 2 (Trn2 UltraServer with 64 chips per unit)OAM
Announced2024-12-032025-04-01
Released2025-01-012025-12-01

Robots running AWS Trainium 2

No robots publicly running it yet.

Robots running Huawei Ascend 910D

No robots publicly running it yet.

Data centers with Huawei Ascend 910D

No data centers publicly running it yet.

Common questions

AWS Trainium 2 vs Huawei Ascend 910D: which is faster for training?

Huawei Ascend 910D has 1.85x the dense FP8 throughput of the other (AWS Trainium 2: 1,300 TFLOPS; Huawei Ascend 910D: 2,400 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

AWS Trainium 2 vs Huawei Ascend 910D: which has more memory?

Huawei Ascend 910D carries more HBM (AWS Trainium 2: 96 GB HBM3; Huawei Ascend 910D: 192 GB HBM3). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

AWS Trainium 2 vs Huawei Ascend 910D: which is more power-efficient?

Dense FP8 TFLOPS per watt: AWS Trainium 2 2.60 (1,300 ÷ 500 W); Huawei Ascend 910D 3.00 (2,400 ÷ 800 W). Huawei Ascend 910D wins at the die level; system-level efficiency also depends on cooling and interconnect.

AWS Trainium 2 vs Huawei Ascend 910D: which is more widely used?

AWS Trainium 2: 0 robots and 3 data centers publicly running it. Huawei Ascend 910D: 0 robots and 0 data centers. Empty here means no operator has said publicly, not zero adoption in the market.

See also: every chip comparison · AWS Trainium 2 full page · Huawei Ascend 910D full page.