Ramulator 2.0: A Modern, Modular, and Extensible DRAM Simulator
Not on the map. Why?
Abstract (arXiv)
We present Ramulator 2.0, a highly modular and extensible DRAM simulator that enables rapid and agile implementation and evaluation of design changes in the memory controller and DRAM to meet the increasing research effort in improving the performance, security, and reliability of memory systems. Ramulator 2.0 abstracts and models key components in a DRAM-based memory system and their interactions into shared interfaces and independent implementations. Doing so enables easy modification and extension of the modeled functions of the memory controller and DRAM in Ramulator 2.0. The DRAM specification syntax of Ramulator 2.0 is concise and human-readable, facilitating easy modifications and extensions. Ramulator 2.0 implements a library of reusable templated lambda functions to model the functionalities of DRAM commands to simplify the implementation of new DRAM standards, including DDR5, LPDDR5, HBM3, and GDDR6. We showcase Ramulator 2.0's modularity and extensibility by implementing and evaluating a wide variety of RowHammer mitigation techniques that require different memory controller design changes. These techniques are added modularly as separate implementations without changing any code in the baseline memory controller implementation. Ramulator 2.0 is rigorously validated and maintains a fast simulation speed compared to existing cycle-accurate DRAM simulators. Ramulator 2.0 is open-sourced under the permissive MIT license at https://github.com/CMU-SAFARI/ramulator2
Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Aug 2023.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2024: 3; 2025: 9; 2026: 18.
30 papers.
Sort:
By area:
- 2024Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batchingcited by 34
- 2025PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inferencecited by 22
- 2025PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing Systemcited by 20
- 2024MARCA: Mamba Accelerator with ReConfigurable Architecturecited by 13
- 2025Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Servingcited by 7
- 2025Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIMcited by 3
- 2026NPU Design for Diffusion Language Model Inferencecited by 3
- 2025A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integrationcited by 2
- 2026AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantizationcited by 2
- 2024PIFS-Rec: Process-In-Fabric-Switch for Large-Scale Recommendation System Inferencescited by 1
- 2025BitStopper: An Efficient Transformer Attention Accelerator via Stage-fusion and Early Terminationcited by 1
- 2026LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIMcited by 1
18 more
- 2026DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reductioncited by 1
- 2025FuseFlow: A Fusion-Centric Compilation Framework for Sparse Deep Learning on Streaming Dataflowcited by 0
- 2025Streaming Tensor Programs: A Streaming Abstraction for Dynamic Parallelismcited by 0
- 2025DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architecturescited by 0
- 2026A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systemscited by 0
- 2026From Buffers to Registers: Unlocking Fine-Grained FlashAttention with Hybrid-Bonded 3D NPU Co-Designcited by 0
- 2026Hardware-Software Co-design for 3D-DRAM-based LLM Serving Acceleratorcited by 0
- 2026ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Servingcited by 0
- 2026Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Modelscited by 0
- 2026ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Accelerationcited by 0
- 2026Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Schedulingcited by 0
- 2026APEX: Adaptive Expert Prefetching for Memory-Efficient Edge MoE Inferencecited by 0
- 2026HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloadscited by 0
- 2026NOVA: Technology-Architecture Co-Design of Near-Memory Processing for Attention-SSM-MoE Hybrid LLM Inferencecited by 0
- 2026FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Accelerationcited by 0
- 2026FlexPosit: Tunable Fractional Precision for LLM Inference Acceleratorscited by 0
- 2026SAGE: Semantic-Aware Geographic Error Recovery for AI Data Movementcited by 0
- 2026MiX: Micro-Inverted-Scaling for End-to-End Low-Bit Vision-Language Model Accelerationcited by 0
- 2026MiX: Micro-Inverted-Scaling for End-to-End Low-Bit Vision-Language Model Acceleration17 Sep 2026
- 2026SAGE: Semantic-Aware Geographic Error Recovery for AI Data Movement9 Sep 2026
- 2026FlexPosit: Tunable Fractional Precision for LLM Inference Accelerators4 Sep 2026
- 2026FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Acceleration25 Aug 2026
- 2026NOVA: Technology-Architecture Co-Design of Near-Memory Processing for Attention-SSM-MoE Hybrid LLM Inference23 Aug 2026
- 2026HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloads19 Aug 2026
- 2026APEX: Adaptive Expert Prefetching for Memory-Efficient Edge MoE Inference12 Aug 2026
- 2026Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Scheduling28 Jul 2026
- 2026DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reduction17 Jul 2026
- 2026ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration21 May 2026
- 2026Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Models11 May 2026
- 2026AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization20 Apr 2026
18 more
- 2026ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving16 Apr 2026
- 2026LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM6 Apr 2026
- 2026Hardware-Software Co-design for 3D-DRAM-based LLM Serving Accelerator5 Mar 2026
- 2026From Buffers to Registers: Unlocking Fine-Grained FlashAttention with Hybrid-Bonded 3D NPU Co-Design11 Feb 2026
- 2026NPU Design for Diffusion Language Model Inference28 Jan 2026
- 2026A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems7 Jan 2026
- 2025BitStopper: An Efficient Transformer Attention Accelerator via Stage-fusion and Early Termination6 Dec 2025
- 2025DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architectures19 Nov 2025
- 2025Streaming Tensor Programs: A Streaming Abstraction for Dynamic Parallelism11 Nov 2025
- 2025FuseFlow: A Fusion-Centric Compilation Framework for Sparse Deep Learning on Streaming Dataflow6 Nov 2025
- 2025A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integration25 Jul 2025
- 2025Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving14 Jul 2025
- 2025Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIM9 May 2025
- 2025PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System21 Feb 2025
- 2025PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference11 Feb 2025
- 2024PIFS-Rec: Process-In-Fabric-Switch for Large-Scale Recommendation System Inferences25 Sep 2024
- 2024MARCA: Mamba Accelerator with ReConfigurable Architecture16 Sep 2024
- 2024Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching2 Sep 2024
- 2025PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inferencecited by 22
- 2025PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing Systemcited by 20
- 2025Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIMcited by 3
- 2026Hardware-Software Co-design for 3D-DRAM-based LLM Serving Acceleratorcited by 0
- 2026Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Schedulingcited by 0
- 2026HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloadscited by 0
- 2026FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Accelerationcited by 0
- 2026FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Acceleration25 Aug 2026
- 2026HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloads19 Aug 2026
- 2026Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Scheduling28 Jul 2026
- 2026Hardware-Software Co-design for 3D-DRAM-based LLM Serving Accelerator5 Mar 2026
- 2025Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIM9 May 2025
- 2025PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System21 Feb 2025
- 2025PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference11 Feb 2025
- 2024Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batchingcited by 34
- 2025A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integrationcited by 2
- 2026A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systemscited by 0
- 2026ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Servingcited by 0
- 2026Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Modelscited by 0
- 2026APEX: Adaptive Expert Prefetching for Memory-Efficient Edge MoE Inferencecited by 0
- 2026NOVA: Technology-Architecture Co-Design of Near-Memory Processing for Attention-SSM-MoE Hybrid LLM Inferencecited by 0
- 2026NOVA: Technology-Architecture Co-Design of Near-Memory Processing for Attention-SSM-MoE Hybrid LLM Inference23 Aug 2026
- 2026APEX: Adaptive Expert Prefetching for Memory-Efficient Edge MoE Inference12 Aug 2026
- 2026Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Models11 May 2026
- 2026ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving16 Apr 2026
- 2026A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems7 Jan 2026
- 2025A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integration25 Jul 2025
- 2024Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching2 Sep 2024
- 2024MARCA: Mamba Accelerator with ReConfigurable Architecturecited by 13
- 2025Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Servingcited by 7
- 2026AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantizationcited by 2
- 2024PIFS-Rec: Process-In-Fabric-Switch for Large-Scale Recommendation System Inferencescited by 1
- 2025BitStopper: An Efficient Transformer Attention Accelerator via Stage-fusion and Early Terminationcited by 1
- 2026LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIMcited by 1
- 2026DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reductioncited by 1
- 2025FuseFlow: A Fusion-Centric Compilation Framework for Sparse Deep Learning on Streaming Dataflowcited by 0
- 2025Streaming Tensor Programs: A Streaming Abstraction for Dynamic Parallelismcited by 0
- 2025DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architecturescited by 0
- 2026From Buffers to Registers: Unlocking Fine-Grained FlashAttention with Hybrid-Bonded 3D NPU Co-Designcited by 0
- 2026FlexPosit: Tunable Fractional Precision for LLM Inference Acceleratorscited by 0
12 most cited of 13 All 13 (JSON)
- 2026SAGE: Semantic-Aware Geographic Error Recovery for AI Data Movement9 Sep 2026
- 2026FlexPosit: Tunable Fractional Precision for LLM Inference Accelerators4 Sep 2026
- 2026DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reduction17 Jul 2026
- 2026AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization20 Apr 2026
- 2026LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM6 Apr 2026
- 2026From Buffers to Registers: Unlocking Fine-Grained FlashAttention with Hybrid-Bonded 3D NPU Co-Design11 Feb 2026
- 2025BitStopper: An Efficient Transformer Attention Accelerator via Stage-fusion and Early Termination6 Dec 2025
- 2025DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architectures19 Nov 2025
- 2025Streaming Tensor Programs: A Streaming Abstraction for Dynamic Parallelism11 Nov 2025
- 2025FuseFlow: A Fusion-Centric Compilation Framework for Sparse Deep Learning on Streaming Dataflow6 Nov 2025
- 2025Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving14 Jul 2025
- 2024PIFS-Rec: Process-In-Fabric-Switch for Large-Scale Recommendation System Inferences25 Sep 2024
12 newest of 13 All 13 (JSON)