DEPLOYDatabase

Chip comparison

AWS Trainium (Trn1) vs Cerebras WSE-3 (Wafer-Scale Engine 3)

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 (Trn1)Cerebras WSE-3 (Wafer-Scale Engine 3)
Process nodeTSMC N7TSMC N5
Transistors (B)4000
Die size46225 mm²
TDP500 W23000 W
Memory32 GB HBM2e44 GB on-die SRAM
Memory bandwidth820 GB/s21,000,000 GB/s
FP16 (dense)62,500 TFLOPS
BF16 (dense)210 TFLOPS
Form factorTrn1 EC2 instancewafer-scale (single-wafer system)
Announced2020-12-012024-03-13
Released2022-10-012024-04-01

Robots running AWS Trainium (Trn1)

No robots publicly running it yet.

Robots running Cerebras WSE-3 (Wafer-Scale Engine 3)

No robots publicly running it yet.

Data centers with AWS Trainium (Trn1)

No data centers publicly running it yet.

Data centers with Cerebras WSE-3 (Wafer-Scale Engine 3)

No data centers publicly running it yet.

Common questions

AWS Trainium (Trn1) vs Cerebras WSE-3 (Wafer-Scale Engine 3): which is faster for training?

Cerebras WSE-3 (Wafer-Scale Engine 3) has 297.62x the dense FP16/BF16 throughput of the other (AWS Trainium (Trn1): 210 TFLOPS; Cerebras WSE-3 (Wafer-Scale Engine 3): 62,500 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

AWS Trainium (Trn1) vs Cerebras WSE-3 (Wafer-Scale Engine 3): which has more memory?

Cerebras WSE-3 (Wafer-Scale Engine 3) carries more HBM (AWS Trainium (Trn1): 32 GB HBM2e; Cerebras WSE-3 (Wafer-Scale Engine 3): 44 GB on-die SRAM). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

AWS Trainium (Trn1) vs Cerebras WSE-3 (Wafer-Scale Engine 3): which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: AWS Trainium (Trn1) 0.42 (210 ÷ 500 W); Cerebras WSE-3 (Wafer-Scale Engine 3) 2.72 (62,500 ÷ 23000 W). Cerebras WSE-3 (Wafer-Scale Engine 3) wins at the die level; system-level efficiency also depends on cooling and interconnect.

See also: every chip comparison · AWS Trainium (Trn1) full page · Cerebras WSE-3 (Wafer-Scale Engine 3) full page.