HomeProducts & solutionsProfileNews
VIENKO
CONTACT US
NEXT-GENERATION EDGE AI SEMICONDUCTORS

ENGINEERING SEMICONDUCTORS FOR THE AI ERA

Pebble Vina researches and develops AI semiconductor technologies — from chip architecture and compute-in-memory (CIM) to software and applied AI solutions.

EXPLORE THE TECHNOLOGY →
RESEARCHEXPERIMENTATIONDEVELOPMENTTRAININGCOMPUTE-IN-MEMORYEDGE AION-DEVICE AIAI INFERENCE
01 — COMPUTE IN MEMORY

THE COMPUTING FOUNDATION FOR AI

CIM (Compute-in-Memory) brings computation close to where data is stored, cutting the volume of data that has to move between memory and processor.

Pebble Vina develops two CIM directions — Analog and Digital — to serve different AI computing needs.

01ANALOG CIM
A custom Analog CIM chip with an exposed compute array, set on a technical drawing with a continuous waveform passing through the chip.
Computing inside the memory array

An eFlash synapse network computes right inside the memory array at ultra-low power, suited to devices with very limited energy. It serves small AI models, sensors, Edge AI, AI IoT and always-on applications.

EXPLORE THE ANALOG CHIP
02DIGITAL CIM
A custom Digital CIM chip with four compute tiles, set on a technical drawing with a square-pulse signal passing through the chip.
High performance that scales

High-speed SRAM paired with digital logic alongside it delivers high compute performance and large scalability, plus accuracy for complex models. It serves large language models (LLMs), generative AI, heavy image processing and tasks that need high memory bandwidth.

EXPLORE THE DIGITAL CHIP

WHY DOES CIM MATTER FOR AI?

As AI models grow, the challenge is not only raw compute but moving data. In a traditional architecture, data constantly shuttles between memory (DRAM) and the processor (NPU), creating a bottleneck in both speed and energy.

DRAM · MEMORYNPU · PROCESSOR

CIM (Compute-in-Memory) solves this by building compute directly into the memory structure, shortening the distance data has to travel for suitable AI workloads.

Lower power draw

Cuts the energy spent on moving data back and forth between memory and processor — one of the significant sources of power draw in AI systems.

Optimised compute performance

Eases the pressure on memory bandwidth through parallel computation in place, speeding up processing for AI models with very large parameter counts.

Opening a new era of AI

Paves the way for Edge AI, on-device AI and AI inference, bringing capable AI models to end devices with limited resources.

02 — CORE CAPABILITY

CORE CAPABILITIES OF THE CHIP TECHNOLOGY

Pebble Vina builds AI semiconductor technology on four core capabilities: CIM, a dual Analog and Digital architecture, full-stack integration and silicon validation.

01CIM · IMC

Computing inside memory

CIM (Compute-in-Memory) / IMC (In-Memory Computing) is the key technology foundation: instead of constantly moving data between memory and processor, computation happens right where the data is stored.

  • LATENCYLower latency
  • POWERLower power consumption
02DUAL ARCHITECTURE

Dual architecture

Mastery of both CIM directions: Analog on eFlash and Digital on SRAM, serving different AI computing needs.

  • ANALOG · eFlashEdge AI, sensors and ultra-low-power AI
  • DIGITAL · SRAMHigh performance for large models and LLMs
03FULL-STACK

Full-stack integration

Beyond chip design: capability spans hardware, software and systems, through to complete solutions for customers.

  • HARDWAREAnalog and Digital CIM chip design
  • SOFTWAREPebble AI Studio — an SDK to optimise models and deploy them on the hardware
  • SYSTEMChips integrated into modules, cards and complete solutions
04SILICON VALIDATION

Silicon-proven

The move from theory to reality is proven by measured results on real silicon.

  • MINTIn mass production since 05/2023
  • PAPAYASilicon-verified (PoC 2024)
  • ESPRESSOMeasured on MPW silicon; product expected Q3/2026
03 — COLLABORATION FOR THE FUTURE

NEWS & PARTNERSHIPS

Pebble Vina actively expands strategic collaboration with leading partners, customers and institutions to drive technological innovation and create lasting value.

MOU signed with a leading Korean technology partner

Joint research and development of CIM AI solutions, targeting higher performance and broader applications.

Meeting with our strategic partner in Japan

Discussing on-device AI trends and opportunities to develop the next-generation semiconductor market together.

Deploying AI solutions with Vietnamese enterprises

Building custom AI systems that fit each industry's specifics and real operating needs.

Strategic partnership with an international partner

Accelerating AI innovation together and bringing advanced solutions to the global market.

01 / 04
04 — CONTACT

LET'S BUILD BREAKTHROUGH EDGE-AI SEMICONDUCTOR SOLUTIONS TOGETHER

We are always ready to listen and work alongside you to turn ideas into practical value and shape the future of technology.

Trusted collaborationLong-term partnership
Pioneering technologyOptimised solutions
Absolute confidentialityWork with peace of mind
Your information is kept confidential and used only to support your request.