Book a demo

In-Memory Computing Chip Architecture: 2026 Patent Landscape

In-Memory Computing Chip Architecture: 2026 Patent Landscape
Explore in Eureka
2026 Patent Landscape

In-Memory Computing Chip Architecture Patents 2026

In-memory computing has shifted from academic concept to commercial silicon, with 8 formal patent records spanning SRAM digital macros, resistive memory crossbars, and chiplet packaging architectures. A single Chinese assignee accounts for 7 of those filings, all targeting EP and US jurisdictions in 2025.

8
Formal patent records in this dataset (2014–2026)
Explore in Eureka
7
Patents filed by WitMem Technology (EP & US, 2025)
Explore in Eureka
437 TOPS/W
Peak efficiency of Arizona State 28 nm IMC prototype
Explore in Eureka
~60%
Share of retrieved results published in 2020–2022
Explore in Eureka
Published byPatSnap Insights Team··12 min readVerified by PatSnap Eureka Data
Technology Overview

How In-Memory Computing Eliminates the Memory Wall

In-memory computing directly addresses the memory wall — the performance gap in von Neumann architectures where data must shuttle repeatedly between physically separated compute and memory units. This bottleneck is cited as the motivating constraint in over 80% of the literature sources reviewed, spanning publications from 2018 through 2026.

IMC architectures span both analog and digital computation domains, utilizing charge-based memories such as SRAM and DRAM as well as emerging devices based on electrically induced material modifications. The field branches into analog IMC (AiMC), digital IMC (DIMC), processing-in-memory (PIM), and chiplet-based IMC disaggregated via 2.5D, 3D, and fan-out packaging.

Patent Filings by Assignee — In-Memory Computing Dataset (2014–2026)
Patent filings by assignee: WitMem 7, Princeton 3, D-Matrix 2, Applied Intelligence 2, Arizona State 1Horizontal bar chart showing patent filing counts per assignee within the in-memory computing dataset, 2014–2026. Source: PatSnap Eureka IMC landscape dataset.WitMem Technology7Princeton University3D-Matrix Corporation2Applied Intelligence Semi.2↗ Click bars to explore

SRAM remains the dominant substrate for digital IMC due to its prevalence in logic process nodes, mature bitcell designs, and compatibility with conventional CMOS toolchains. The 28 nm Arizona State prototype integrates 108 capacitive-coupling-based IMC SRAM macros totaling 3.4 MB, achieving 4.9 TOPS and 437 TOPS/W peak efficiency with a custom SIMD ISA.

As monolithic IMC faces area, yield, and routing constraints at scale, chiplet disaggregation has emerged as the dominant scaling path. WitMem Technology filed at minimum 7 patent families in EP and US in June 2025 alone, covering dual-chip, triple-chip with DRAM, and triple-chip with NAND configurations — all carrying Chinese priority dates from December 2023.

PatSnap Eureka Patent filing counts derived from 8 formal patent records retrieved in the PatSnap Eureka IMC dataset, 2014–2026.Explore the data ↗
Filing Trends & Clusters

Patent Activity by Technology Cluster and Filing Period

The IMC dataset spans 2014 to 2026, with approximately 60% of all sources concentrated in 2020–2022 and a shift toward commercial IP consolidation from 2023 onward. Four dominant technology clusters — SRAM digital IMC, resistive/NVM IMC, chiplet-based IMC, and scalable array fabric — structure the patent landscape.

Patent Records by Technology Cluster — IMC Dataset 2014–2026

Chiplet-based and SRAM digital IMC clusters jointly account for the largest share of formal patent filings, reflecting commercial consolidation around packaging and precision compute.

IMC patent records by technology cluster: Chiplet/3D 4, SRAM Digital 3, Scalable Array/Fabric 3, Resistive/NVM 2, Edge/Other 1Horizontal bar chart of patent and literature records per IMC technology cluster in the PatSnap Eureka dataset.Chiplet / 3D Packaged IMC4SRAM Digital IMC3Scalable Array / Fabric3Resistive / NVM IMC2Edge / Other IMC1↗ Click bars to explore

IMC Patent Filing Activity by Period (2014–2026)

Filing and publication density surged in 2020–2022, representing approximately 60% of all retrieved results, with a second wave of commercial patent filings emerging from 2023 onward.

IMC filing activity by period: Pre-2019 foundational 2 records, 2020-2022 rapid proliferation ~60% of sources, 2023-2026 commercial consolidation patent filings spikeVertical bar chart illustrating relative density of IMC patent and literature records across three publication/filing periods in the PatSnap Eureka dataset.0102030Pre-201932020–2022~212023–2026~11↗ Click bars to explore
PatSnap Eureka Filing period distribution derived from publication and filing dates across all retrieved IMC patent and literature records in the PatSnap Eureka dataset.Explore the data ↗
Application Domains

Key IMC Application Domains Across AI, Edge, and HPC

IMC architectures are being deployed across five distinct application domains identified in the retrieved literature and patent records: AI inference, edge intelligence, high-performance computing, cryptography, and hyperdimensional computing.

SRAM IMC · Chiplet Accelerator · Transformer Models

AI Inference and Deep Neural Networks

The largest and most consistently cited application domain across retrieved results. The Arizona State 28 nm prototype achieves 4.9 TOPS and 437 TOPS/W benchmarked on DNN layer types including convolution, pooling, and fully connected layers. D-Matrix’s 2025 US patent explicitly targets NLP, generative AI, and agentic AI workloads via hierarchical DIMC chiplet systems.

AI Inference
Analog IMC · RISC-V · TinyML

Edge Intelligence and IoT Devices

A heterogeneous IMC cluster integrating 8 RISC-V cores and an analog IMC accelerator was benchmarked on battery-constrained TinyML applications (2022). A time-multiplexing CIM architecture demonstrated 18.4× energy savings over conventional analog CIM with 0.136 pJ/MAC efficiency for edge deployment, also published in 2022.

Edge Intelligence
PIM · CXL Fabric · Heterogeneous Memory Pool

High-Performance Computing and Data Centers

PIM architectures targeting graph analytics, databases, and neural network inference in server environments were benchmarked in a 2022 experimental analysis of a real processing-in-memory system. Applied Intelligence Semiconductors’ 2025 WO patent discloses a CXL-connected architecture comprising a primary chip, memory pool chip, IO complex chip, and AI tensor node chip for data center adaptability.

High-Performance Computing
In-SRAM Hash · ReRAM · IoT Security

Cryptography and Hyperdimensional Computing

In-SRAM cryptographic hash computation for IoT security was demonstrated in a 2022 study on both SRAM and ReRAM substrates, enabling data integrity and authentication hardware via in-memory architectures. Separately, a 2022 paper demonstrated IMC for hypervector similarity search across physically distributed IMC cores, representing a non-neural-network AI application for IMC.

Security & Cognitive AI
PatSnap Eureka Application domain descriptions derived from patent and literature records in the PatSnap Eureka IMC dataset, 2018–2026.Explore insights ↗
Key Patent Assignees

Who Holds the Core IMC Architecture IP in 2026

Among the 8 formal patent records with explicit assignee data, Hangzhou Zhicun (WitMem) Technology accounts for 7 filings targeting EP and US jurisdictions in 2025, while Princeton University holds 3 filings across WO, US, IN, and JP jurisdictions spanning 2019–2023.

IMC Patent Filings by Top Assignees (Dataset 2014–2026)

IMC assignee filings: WitMem Technology 7, Princeton University 3, D-Matrix Corporation 2, Applied Intelligence Semiconductors 2Horizontal bar chart of patent filing counts for top IMC assignees in the PatSnap Eureka dataset.Hangzhou Zhicun (WitMem) Technology Co., Ltd.7The Trustees of Princeton University3D-Matrix Corporation2Applied Intelligence Semiconductors Private Limited2↗ Click bars to explore
CIM Chip Packaging · Multi-Chip DRAM/NAND Architectures

Hangzhou Zhicun (WitMem) Technology

WitMem Technology holds 7 patent records in this dataset, all filed in EP and US jurisdictions in June 2025, carrying Chinese priority dates from December 2023. The portfolio covers dual-chip and triple-chip CIM architectures incorporating CIM cell array chips, peripheral analog/digital circuit chips, and either DRAM or NAND flash memory tiers depending on capacity vs. latency requirements. All filings are currently pending, establishing broad coverage over multi-chip CIM packaging with heterogeneous memory tiers.

China — EP/US filings
Scalable IMC Array · Configurable On-Chip Networks

The Trustees of Princeton University

Princeton University holds 3 filed/granted patents in this dataset spanning WO, US, IN, and JP jurisdictions across 2019–2023. The portfolio covers configurable IMC cores interconnected by a configurable on-chip network (US 2023, pending), a reshaping buffer for massively parallel bitwise input signals with near-memory computing paths (WO 2019), and a scalable array architecture for in-memory computing (WO 2021, IN 2022). These foundational academic patents provide broad coverage over mesh-connected IMC core arrays and programmable IMC SoC fabrics.

United States — WO/US/IN/JP
🔍
Unlock Full Assignee Profiles for D-Matrix, Arizona State, and South China University
D-Matrix Corporation’s 2025–2026 US filings target stacked DIMC chiplet accelerators for LLM inference latency. South China University of Technology’s 2024 CN patent addresses workload-general CIM — a critical gap in current architectures.
D-Matrix chiplet stacking South China University CIM + more
Unlock full assignee analysis →
PatSnap Eureka Assignee data derived from 8 formal patent records in the PatSnap Eureka IMC dataset, 2014–2026.Explore players ↗
Emerging Directions

Four Emerging IMC Architecture Directions Identified in 2024–2026 Filings

The most recent filings from 2024 to 2026 in this dataset signal four distinct directions: heterogeneous multi-chip CIM packaging, stacked digital IMC chiplets for generative AI, topology-aware interconnect optimization, and workload-general programmable CIM fabrics.

Multi-Chip CIM Packaging with Heterogeneous Memory Tiers

WitMem Technology’s 2025 EP/US patent family introduces architectures incorporating three distinct chip types within a single CIM package: CIM cell arrays, a peripheral analog/digital circuit chip, and either a DRAM tier (US 2025) or a NAND flash tier (EP 2025), depending on the application’s capacity vs. latency requirements. The Chinese priority dates from December 2023 predate most Western commercial CIM product announcements, giving WitMem a potential first-mover IP position in multi-tier CIM packaging.

Stacked Digital IMC Chiplets for Generative AI Inference

D-Matrix Corporation’s Stacked apparatus using in-memory compute chiplet devices for inference-time compute acceleration (US 2026, pending) explicitly targets latency-bounded throughput as the optimization metric for transformer model inference. This filing reflects commercial pressure from large language model serving economics, where token generation latency — not peak FLOPS — is the binding constraint. D-Matrix has now filed three related US patents between 2025 and 2026 covering hierarchical DIMC chiplet systems.

🔒
Access Full Analysis of All Four Emerging IMC Directions and Their IP Implications
The topology-aware interconnect and workload-general CIM directions carry significant freedom-to-operate implications for commercial IMC SoC developers — full analysis available in Eureka.
Topology-aware IMC interconnectWorkload-general CIM fabrics+ more
Unlock full analysis →
PatSnap Eureka Emerging direction analysis derived from 2024–2026 patent filings in the PatSnap Eureka IMC dataset.Explore emerging trends ↗
Architecture Comparison

SRAM Digital IMC vs. Resistive NVM IMC: Key Architectural Dimensions

Click any row to explore further.

DimensionSRAM Digital IMCResistive / NVM IMC
Computation DomainDigital bitwise logic and arithmetic; no ADC/DAC requiredAnalog multiply-accumulate (MAC) via continuous conductance states; ADC required
Representative Device6T or 9T SRAM bitcell (28 nm demonstrated)RRAM, PCM, STT-MRAM, SOT-MRAM crossbar arrays
Peak Energy Efficiency437 TOPS/W (Arizona State 28 nm prototype, 2025); 0.68–8.09 TOPS/W (6T SRAM, 2020)0.136 pJ/MAC for edge CIM (2022); RRAM-CIM shows area/power advantages over SRAM for same data volume
Precision SupportReconfigurable bit-precision (0.6V–1.1V); FP64 via SOT-MRAM MDCIM (2023)Primarily low-precision inference; FP64 achieved only with MRAM-based DCIM
Primary ApplicationAI inference DNN layers (convolution, pooling, FC); generative AI; NLP workloadsBinary neural networks, matrix-vector multiplication for CNN inference
Scalability PathChiplet disaggregation (D-Matrix 2025–2026); scalable mesh-connected IMC arrays (Princeton 2023)Chiplet benchmarking via SIAM simulator (2021); monolithic 128×64 RRAM + 90 nm CMOS (2020)
Process CompatibilityStandard CMOS logic process; mature bitcell design toolchainRequires backend integration of resistive elements; monolithic CMOS demonstrated at 90 nm
Key IP HoldersArizona State University (US 2025, active); D-Matrix Corporation (US 2025–2026, pending); Princeton University (WO/US 2019–2023)Literature-dominant; no dominant single patent assignee identified in this dataset
PatSnap Eureka Comparison derived from patent and literature records in the PatSnap Eureka IMC dataset, 2018–2026.Compare in Eureka ↗
Frequently asked questions

Frequently Asked Questions: In-Memory Computing Chip Architecture

Still have questions? PatSnap Eureka can answer them instantly from patent and research data.Ask Eureka ↗
PatSnap Eureka

Run Your Own IMC Freedom-to-Operate Search in Eureka

Join 18,000+ innovators using PatSnap Eureka to generate reports like this one for any technology area.

Data and insights on this page are based on a limited patent and literature dataset and are for reference only. Figures may not represent the complete technology landscape.

Powered by PatSnap Eureka
Link copied to clipboard

Help us improve this page

Found incorrect or outdated information? Let us know and we'll get it fixed.