A reading list for SRAM-based Compute-In-Memory (CIM) research.
IHP26a TinyTapeout implementation of a RISC-V CPU with an integrated SRAM-based compute-in-memory (CIM) accelerator for performing efficient analog matrix multiplications.
LLM inference SoC
DUB Sparsity for Crossbars
Minimal PyTorch examples for the four-stage structural evolution from ANN to event-driven SNN: Stage 0 (baseline ANN) → Stage 1 (binarization) → Stage 2 (temporal expansion) → Stage 3 (temporal accumulation) → Stage 4 (reset & sparsity control).
PSumSim: A Simulator for Partial-Sum Quantization in Analog Matrix-Vector Multipliers
从零诞生的存算一体编程语言与基座 ⚛ 一切语言的源头也是尽头。10语言源头汇合(C/C#/Rust/Python/Lisp/Haskell/Erlang/APL/Q#/J)、统一XL01字节码、自研编译器栈、自举、从零训练10M参数线性注意力基座。The origin and the end of all languages. Storage-compute unity, born from scratch.
Two brains on one analog substrate from ~80% unsupervised SCFF bulk + ~20% closed-form SLDA namer: the math model for a forward-only, on-chip continual learner. Behavioral simulation, no silicon. Draft 6.0 = the "baby neocortex," validated across 11 phases.
Some experiments to perform parallel data operations (compute-in-memory) on a 1980ies DRAM chip controlled with a CH32V003 RISC-V MCU
HyperMR: Efficient Hypergraph-enhanced Matrix Storage on Compute-in-Memory Architecture. This work is presented at SIGMOD 2025.
Closed-loop HW/SW co-design for compute-in-memory accelerators — NSGA-II searches per-layer weight precision and column pruning, verified by real PyTorch QAT and physics simulation. The LLM explains the search; it never produces the numbers.
Witmem Technology / 知存科技 employee referral, careers and recruiting information
houmo — independent third-party profile of a public API surface, by API Evangelist. HOUMO.AI (后摩智能) is a Chinese fabless semiconductor company founded in 2020 that develops compute-in-memory (CIM / storage-and-computation integrated) edge AI chips for running large language models and other AI workloads on endpoint devices.
Mythic — independent third-party profile of a public API surface, by API Evangelist. Mythic is a high-performance analog computing company building Analog Processing Units (APUs) for energy-efficient AI inference. Its compute-in-memory architecture stores AI model parameters directly in the processor to eliminate the memory bottleneck of traditiona
Visual system design interview atlas for backend, systems, hardware, embedded, and ACiM NPU design
In-Synapse Activation: physical activation and compute-in-memory FFNs for vision, language, and device-level studies.
Enable mask-free visual dubbing with robust generative bootstrapping for image editing and inpainting
To associate your repository with the compute-in-memory topic, visit your repo's landing page and select "manage topics."