A reading list for SRAM-based Compute-In-Memory (CIM) research.
accelerator in-memory sram reading-list pim literature cim paper-list process-in-memory compute-in-memory
-
Updated
Oct 29, 2025
#
compute-in-memory
Here are 19 public repositories matching this topic...
IHP26a TinyTapeout implementation of a RISC-V CPU with an integrated SRAM-based compute-in-memory (CIM) accelerator for performing efficient analog matrix multiplications.
machine-learning asic cpu fpga riscv neuromorphic risc-v neuromorphic-computing analog-computing tinytapeout compute-in-memory
-
Updated
Mar 24, 2026 - Python
LLM inference SoC
-
Updated
Aug 8, 2026 - Python
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).
pytorch mnist event-driven snn neuromorphic-computing reram spiking-neural-network ann-to-snn compute-in-memory hardware-aware-ai surrogate-gradient analog-ai
-
Updated
Jun 8, 2026 - Python
DUB Sparsity for Crossbars
pruning crossbar analog-to-digital-converter process-in-memory hardware-software-codesign compute-in-memory
-
Updated
Mar 21, 2024 - Python
PSumSim: A Simulator for Partial-Sum Quantization in Analog Matrix-Vector Multipliers
numpy histogram neural-networks histograms quantization matrix-vector-multiplication stochastic-simulation stochastic-modeling compute-in-memory partial-sum
-
Updated
May 5, 2026 - Python
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.
python programming-language rust open-source bytecode csharp compiler llvm openmp agi cargo quantum-computing language-design self-hosting from-scratch qsharp llm compute-in-memory future-computing storage-computing
-
Updated
Sep 10, 2026 - C
Some experiments to perform parallel data operations (compute-in-memory) on a 1980ies DRAM chip controlled with a CH32V003 RISC-V MCU
-
Updated
May 20, 2025 - C
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.
neuromorphic bio-inspired lifelong-learning brain-inspired continual-learning catastrophic-forgetting self-supervised-learning analog-computing edge-ai contrastive-learning forward-forward compute-in-memory on-chip-learning
-
Updated
Aug 10, 2026 - Python
HyperMR: Efficient Hypergraph-enhanced Matrix Storage on Compute-in-Memory Architecture. This work is presented at SIGMOD 2025.
-
Updated
Jan 8, 2025 - C++
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.
design-space-exploration quantization-aware-training hardware-software-codesign langgraph compute-in-memory
-
Updated
Sep 2, 2026 - Python
Witmem Technology / 知存科技 employee referral, careers and recruiting information
-
Updated
Aug 28, 2026
Visual system design interview atlas for backend, systems, hardware, embedded, and ACiM NPU design
distributed-systems embedded-systems computer-architecture interview-preparation systems-engineering system-design npu system-design-interview compute-in-memory
-
Updated
Sep 13, 2026 - HTML
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
company artificial-intelligence semiconductors analog-computing edge-ai apis-json ai-inference ai-hardware compute-in-memory
-
Updated
Sep 12, 2026
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.
machine-learning company hardware artificial-intelligence semiconductors edge-computing ai-chips apis-json compute-in-memory
-
Updated
Sep 12, 2026
In-Synapse Activation: physical activation and compute-in-memory FFNs for vision, language, and device-level studies.
-
Updated
Aug 9, 2026 - Python
Enable mask-free visual dubbing with robust generative bootstrapping for image editing and inpainting
spring-boot swagger sentinel github-profile pruning restful-api dubbo soul crossbar nacos analog-to-digital-converter seata process-in-memory hardware-software-codesign compute-in-memory
-
Updated
Sep 14, 2026
Add this topic to your repo
To associate your repository with the compute-in-memory topic, visit your repo's landing page and select "manage topics."