DEPLOYDatabase

Chip comparison

Biren BR100 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.

FieldBiren BR100Cambricon MLU370-X8
Process nodeTSMC N7TSMC N7
Transistors (B)77
TDP550 W250 W
Memory64 GB HBM2e48 GB LPDDR5
Memory bandwidth2,300 GB/s
FP16 (dense)1,024 TFLOPS96 TFLOPS
BF16 (dense)1,024 TFLOPS
INT8 (dense)2,048 TOPS256 TOPS
Form factorOAMPCIe
Announced2022-08-092022-03-25

Robots running Biren BR100

No robots publicly running it yet.

Robots running Cambricon MLU370-X8

No robots publicly running it yet.

Data centers with Biren BR100

No data centers publicly running it yet.

Data centers with Cambricon MLU370-X8

No data centers publicly running it yet.

Common questions

Biren BR100 vs Cambricon MLU370-X8: which is faster for training?

Biren BR100 has 10.67x the dense FP16/BF16 throughput of the other (Biren BR100: 1,024 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.

Biren BR100 vs Cambricon MLU370-X8: which has more memory?

Biren BR100 carries more HBM (Biren BR100: 64 GB HBM2e; Cambricon MLU370-X8: 48 GB LPDDR5). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

Biren BR100 vs Cambricon MLU370-X8: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Biren BR100 1.86 (1,024 ÷ 550 W); Cambricon MLU370-X8 0.38 (96 ÷ 250 W). Biren BR100 wins at the die level; system-level efficiency also depends on cooling and interconnect.

See also: every chip comparison · Biren BR100 full page · Cambricon MLU370-X8 full page.