- Maxwell Michalec, Swamit Tannu, Gurindar Sohi. Reducing LLM Inference Memory Bandwidth via Frequent Exponent Value Encoding. Computer Architecture Letters, 25(1):85-88, January - June 2026.
- Heewoo Kim, Alan La, Joseph Izraelevitz. Enabling Cost-Efficient LLM Inference on Mid-Tier GPUs With NMP DIMMs. Computer Architecture Letters, 25(1):21-24, January - June 2026.
- Jinwoo Hwang, Yeongmin Hwang, Tadiwos Meaza, Hyeonbin Bae, Jongse Park. Understanding the Performance Behaviors of End-to-End Protein Design Pipelines on GPUs. Computer Architecture Letters, 25(1):9-12, January - June 2026.
- Peilin Wang, Mingyu Wang 0003, Zhirong Ye, Tao Lu, Zhiyi Yu. UniCNet: Unified Cycle-Accurate Simulation for Composable Chiplet Network With Modular Design-Integration Workflow. Computer Architecture Letters, 25(1):37-40, January - June 2026.
- Hyesung Ahn, Ranggi Hwang, Minsoo Rhu. Exploring KV Cache Quantization in Multimodal Large Language Model Inference. Computer Architecture Letters, 25(1):13-16, January - June 2026.
- Cong Thuan Do. LWAL: Lightweight Adaptive Learning-Driven Cache Bypassing for GPUs. Computer Architecture Letters, 25(1):110-113, January - June 2026.
- Junaid Ahmad Khan. De-Quantization Penalties for Interactive LLM Inference on Prosumer GPUs. Computer Architecture Letters, 25(1):45-48, January - June 2026.
- Qi Shao, Per Stenström. CrossFetch: A Prefetching Scheme for Cross-Page Prefetching in the Physical Address Space. Computer Architecture Letters, 25(1):1-4, January - June 2026.
- Vedant Kalbande, Biswabandan Panda, Alexandra Jimborean, Alberto Ros 0001. Untangling the Low Accuracy of the Entangling Instruction Prefetcher. Computer Architecture Letters, 25(1):130-133, January - June 2026.
- Mohammad M. Gharaguzlo, Mohammadamin Ajdari, Hossein Asadi 0001. Smart Prediction of I/O Accesses in Enterprise Workloads to Accelerate Data Serving During Array Reconstruction. Computer Architecture Letters, 25(1):101-104, January - June 2026.