DEPLOYDatabase

Chip comparison

AWS Inferentia 2 vs Cambricon MLU370-X8

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 2Cambricon MLU370-X8
Process nodeTSMC N7TSMC N7
TDP250 W250 W
Memory32 GB HBM348 GB LPDDR5
Memory bandwidth820 GB/s
FP16 (dense)96 TFLOPS
BF16 (dense)190 TFLOPS
FP8 (dense)380 TFLOPS
INT8 (dense)256 TOPS
Form factorInf2 EC2 instancePCIe
Announced2022-12-012022-03-25
Released2023-04-01

Robots running AWS Inferentia 2

No robots publicly running it yet.

Robots running Cambricon MLU370-X8

No robots publicly running it yet.

Data centers with AWS Inferentia 2

No data centers publicly running it yet.

Data centers with Cambricon MLU370-X8

No data centers publicly running it yet.

Common questions

AWS Inferentia 2 vs Cambricon MLU370-X8: which is faster for training?

AWS Inferentia 2 has 3.96x the dense FP16/BF16 throughput of the other (AWS Inferentia 2: 380 TFLOPS; Cambricon MLU370-X8: 96 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 Cambricon MLU370-X8: which has more memory?

Cambricon MLU370-X8 carries more HBM (AWS Inferentia 2: 32 GB HBM3; Cambricon MLU370-X8: 48 GB LPDDR5). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

AWS Inferentia 2 vs Cambricon MLU370-X8: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: AWS Inferentia 2 1.52 (380 ÷ 250 W); Cambricon MLU370-X8 0.38 (96 ÷ 250 W). AWS Inferentia 2 wins at the die level; system-level efficiency also depends on cooling and interconnect.

See also: every chip comparison · AWS Inferentia 2 full page · Cambricon MLU370-X8 full page.