DEPLOYDatabase

Chip comparison

Google TPU v5e 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.

FieldGoogle TPU v5eTesla Dojo D1
Process nodeTSMC N7
Transistors (B)50
Die size645 mm²
TDP170 W400 W
Memory16 GB HBM2
Memory bandwidth819 GB/s
BF16 (dense)197 TFLOPS362 TFLOPS
FP8 (dense)362 TFLOPS
INT8 (dense)393 TOPS
Form factorOAM (v5e pod, up to 256 chips)Training tile (25 D1 chips per tile)
Announced2023-08-292021-08-19
Released2023-11-012023-07-01

Robots running Google TPU v5e

No robots publicly running it yet.

Robots running Tesla Dojo D1

No robots publicly running it yet.

Data centers with Tesla Dojo D1

No data centers publicly running it yet.

Common questions

Google TPU v5e vs Tesla Dojo D1: which is faster for training?

Tesla Dojo D1 has 1.84x the dense FP16/BF16 throughput of the other (Google TPU v5e: 197 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.

Google TPU v5e vs Tesla Dojo D1: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Google TPU v5e 1.16 (197 ÷ 170 W); Tesla Dojo D1 0.91 (362 ÷ 400 W). Google TPU v5e wins at the die level; system-level efficiency also depends on cooling and interconnect.

Google TPU v5e vs Tesla Dojo D1: which is more widely used?

Google TPU v5e: 0 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 · Google TPU v5e full page · Tesla Dojo D1 full page.