DEPLOYDatabase

Chip comparison

Huawei Ascend 910B vs NVIDIA H100 Tensor Core GPU

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 910BNVIDIA H100 Tensor Core GPU
Process nodeSMIC N+2 (~7nm)TSMC 4N
Transistors (B)80
Die size814 mm²
TDP400 W700 W
Memory64 GB HBM2e80 GB HBM3
Memory bandwidth1,600 GB/s3,350 GB/s
FP16 (dense)400 TFLOPS989 TFLOPS
BF16 (dense)400 TFLOPS989 TFLOPS
FP8 (dense)1,979 TFLOPS
INT8 (dense)800 TOPS1,979 TOPS
Launch price (list)$30,000
Form factorOAM (Atlas 300T A2)SXM5
Announced2023-08-012022-03-22
Released2023-08-012022-10-13

Robots running Huawei Ascend 910B

Robots running NVIDIA H100 Tensor Core GPU

No robots publicly running it yet.

Data centers with Huawei Ascend 910B

Common questions

Huawei Ascend 910B vs NVIDIA H100 Tensor Core GPU: which is faster for training?

NVIDIA H100 Tensor Core GPU has 4.95x the dense FP16/BF16 throughput of the other (Huawei Ascend 910B: 400 TFLOPS; NVIDIA H100 Tensor Core GPU: 1,979 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 NVIDIA H100 Tensor Core GPU: which has more memory?

NVIDIA H100 Tensor Core GPU carries more HBM (Huawei Ascend 910B: 64 GB HBM2e; NVIDIA H100 Tensor Core GPU: 80 GB HBM3). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

Huawei Ascend 910B vs NVIDIA H100 Tensor Core GPU: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Huawei Ascend 910B 1.00 (400 ÷ 400 W); NVIDIA H100 Tensor Core GPU 2.83 (1,979 ÷ 700 W). NVIDIA H100 Tensor Core GPU wins at the die level; system-level efficiency also depends on cooling and interconnect.

Huawei Ascend 910B vs NVIDIA H100 Tensor Core GPU: which is more widely used?

Huawei Ascend 910B: 2 robots and 1 data center publicly running it. NVIDIA H100 Tensor Core GPU: 0 robots and 7 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 · NVIDIA H100 Tensor Core GPU full page.