Cervell™

Atrevido
All-In-One RISC-V NPU

Optimized Neural Processing for Next-Generation Machine Learning with High-Efficiency and Scalable AI compute

A high-performance CPU core designed for demanding AI and HPC applications

Scalable AI Performance

Configurable from C8 to C64 and beyond,
delivering 8 to 64 TOPS at INT8, 1GHz
or 256 TOPS at INT4, 2GHz

C8
C16**
C32
C64**
C8
  INT8 INT4
1GHz 8 TOPS 16 TOPS
2GHz 16 TOPS 32 TOPS
C16
  INT8 INT4
1GHz 16 TOPS 32 TOPS
2GHz 32 TOPS 64 TOPS
** On demand configurations
C32
  INT8 INT4
1GHz 32 TOPS 64 TOPS
2GHz 64 TOPS 128 TOPS
C64
  INT8 INT4
1GHz 64 TOPS 128 TOPS
2GHz 128 TOPS 256 TOPS
** On demand configurations

Key Features

Next-Gen AI Computing:
Powerful, Flexible, and Vendor-Free.

All-in-One Processing

CPU, Vector, and Tensor seamlessly combined for zero-latency AI workload

Standard RISC-V AI Acceleration

Fully programmable, no vendor lock-in.

Ideal for

LLMs, Deep Learning, Edge AI, AI Datacenters.

High Efficiency

AI acceleration optimized for LLMs, Recommendation Systems, and Deep Learning.

Characteristics

Scalable NPU Core for AI
RISC-V Based All-In-One architecture (CPU, Vector, and Tensor)
Configurable from 8-64 TOPS