DEPLOYDatabase

Chip comparison

Huawei Ascend 910B vs Tesla Dojo D1

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.

FieldHuawei Ascend 910BTesla Dojo D1
Process nodeSMIC N+2 (~7nm)TSMC N7
Transistors (B)50
Die size645 mm²
TDP400 W400 W
Memory64 GB HBM2e
Memory bandwidth1,600 GB/s
FP16 (dense)400 TFLOPS
BF16 (dense)400 TFLOPS362 TFLOPS
FP8 (dense)362 TFLOPS
INT8 (dense)800 TOPS
Form factorOAM (Atlas 300T A2)Training tile (25 D1 chips per tile)
Announced2023-08-012021-08-19
Released2023-08-012023-07-01

Robots running Huawei Ascend 910B

Robots running Tesla Dojo D1

No robots publicly running it yet.

Data centers with Huawei Ascend 910B

Data centers with Tesla Dojo D1

No data centers publicly running it yet.

Common questions

Huawei Ascend 910B vs Tesla Dojo D1: which is faster for training?

Huawei Ascend 910B has 1.10x the dense FP16/BF16 throughput of the other (Huawei Ascend 910B: 400 TFLOPS; Tesla Dojo D1: 362 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

Huawei Ascend 910B vs Tesla Dojo D1: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Huawei Ascend 910B 1.00 (400 ÷ 400 W); Tesla Dojo D1 0.91 (362 ÷ 400 W). Huawei Ascend 910B wins at the die level; system-level efficiency also depends on cooling and interconnect.

Huawei Ascend 910B vs Tesla Dojo D1: which is more widely used?

Huawei Ascend 910B: 2 robots and 1 data center publicly running it. Tesla Dojo D1: 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 · Huawei Ascend 910B full page · Tesla Dojo D1 full page.