Vendor: Semidynamics Technology Services Category: Edge AI Accelerator

Fully-coherent RISC-V Tensor Unit

Fully-coherent RISC-V Tensor Unit Directly connected to the Vector Unit.

Contact Provider Request Datasheet

Overview

Fully-coherent RISC-V Tensor Unit Directly connected to the Vector Unit.

What is the Tensor Unit?

The bulk of computations in Large Language Models (LLMs) is in fully-connected layers that can be efficiently implemented as matrix multiplication. The Tensor Unit provides hardware specifically tailored to matrix multiplication workloads, resulting in a huge performance boost for AI without a big power consumption.

The Tensor Unit is designed to fully integrate with our other innovative technologies to provide solutions with outstanding AI performance.

First, at the heart, is our 64-bit fully customisable RISC-V core. Then our Vector Unit which is constantly fed data by our Gazzillion Misses™ technology, effectively hiding memory latency. And then the Tensor Unit is directly connected to the vector registers in the vector unit. The Tensor unit performs matrix multiplications required by AI. Every stage of this solution has been designed to be fully integrated with the others for optimal AI performance and very easy programming. The result is a performance increase of 128x compared to just running the AI software on the scalar core.

The world wants super-fast AI solutions and that is what our unique set of technologies can now provide.

Semidynamics Vector Unit

The Tensor Unit is built on top of the Semidynamics RVV1.0 Vector Processing Unit and leverages the existing vector registers to store matrices as shown below. This enables the Tensor Unit to be used for layers that require matrix multiply capabilities, such as Fully Connected and Convolution, and use the Vector Unit for the activation function layers (ReLU, Sigmoid, Softmax, etc), which is a big improvement over stand-alone NPUs that usually have trouble dealing with activation layers.

The Tensor Unit leverages both the Vector Unit capabilities as well as the Atrevido-423 Gazzillion Misses™ capabilities to fetch the data it needs from memory. Tensor Units consume data at an astounding rate and, without Gazzillion, a normal core would not keep up with the Tensor Unit’s demands. Other solutions rely on difficult-to-program DMAs to solve this problem. Instead, Semidynamics seamlessly integrates the Tensor Unit into its cache-coherent subsystem, opening a new era of programming simplicity for AI software.

In addition, because the Tensor Unit uses the vector registers to store its data and does not include new, architecturally-visible state, it seamlessly works under any RISC-V vector-enabled Linux without any changes.

Key features

  • Ultra-Fast AI: Delivers Ultra-Fast AI solutions
  • 64-bit Core Integration: Optimised to integrate with our 64-bit cores
  • Vector Unit and Gazzillion Misses™ Integration: Seamless integration with our Vector Unit and Gazzillion Misses™
  • Universal RISC-V Compatibility: Works under any RISC-V vector-enabled Linux without any changes
  • DMA-Free Programming: Easy to program as no DMAs needed
  • Power Efficiency: Low power consumption

Block Diagram

RISC-V Tensor Unit block diagram

Specifications

Identity

Part Number
RISC-V Tensor Unit
Vendor
Semidynamics Technology Services
Type
Silicon IP

Files

Product Sheet Download

Note: some files may require an NDA depending on provider policy.

Provider

Semidynamics Technology Services
HQ: Spain
Semidynamics is a European supplier of RISC-V IP cores, specializing in high bandwidth high performance cores with vector units targeted at machine learning and artificial intelligence applications. Proud participant in the European Processor Initiative (EPI). With an extraordinary team with fifteen years of experience in the semiconductor industry, we can help you succeed in your next project, from specification to design and verification. We can also partner with your in-house team and provide staff augmentation services, both on-site and remotely.
Contact Semidynamics Technology Services

Learn more about Edge AI Accelerator IP core

RISC-V Based TinyML Accelerator for Depthwise Separable Convolutions in Edge AI

While lightweight architectures like MobileNetV2 employ Depthwise Separable Convolutions (DSC) to reduce computational complexity, their multi-stage design introduces a critical performance bottleneck inherent to layer-by-layer execution: the high energy and latency cost of transferring intermediate feature maps to either large on-chip buffers or off-chip DRAM. To address this memory wall, this paper introduces a novel hardware accelerator architecture that utilizes a fused pixel-wise dataflow.

Accelerating Your Development: Simplify SoC I/O with a Single Multi-Protocol SerDes IP

Enter the Multi-Protocol SerDes (Serializer/Deserializer)—a flexible, reusable IP block that allows a single PHY to support multiple serial communication protocols, such as PCIe, SATA, Ethernet, USB, and more. This approach enables SoC vendors to meet diverse customer requirements and application needs without redesigning I/O for each target market.

Frequently asked questions about Edge AI Accelerator IP cores

What is Fully-coherent RISC-V Tensor Unit?

Fully-coherent RISC-V Tensor Unit is a Edge AI Accelerator IP core from Semidynamics Technology Services listed on Semi IP Hub.

How should engineers evaluate this Edge AI Accelerator?

Engineers should review the overview, key features, supported foundries and nodes, maturity, deliverables, and provider information before shortlisting this Edge AI Accelerator IP.

Can this semiconductor IP be compared with similar products?

Yes. Buyers can compare this product with similar semiconductor IP cores or IP families based on category, provider, process options, and structured technical specifications.

×
Semiconductor IP