Register file prefetching
The memory wall continues to limit the performance of modern out-of-order (OOO)
processors, despite the expensive provisioning of large multi-level caches and …
processors, despite the expensive provisioning of large multi-level caches and …
Constable: Improving Performance and Power Efficiency by Safely Eliminating Load Instruction Execution
Load instructions often limit instruction-level parallelism (ILP) in modern processors due to
data and resource dependences they cause. Prior techniques like Load Value Prediction …
data and resource dependences they cause. Prior techniques like Load Value Prediction …
Speculative Code Compaction: Eliminating Dead Code via Speculative Microcode Transformations
The computing landscape has been increasingly characterized by processor architectures
with increasing core counts, while a majority of the software applications remain inherently …
with increasing core counts, while a majority of the software applications remain inherently …
[PDF][PDF] 处理器值预测技术研究
黄立波, 杨凌, 杨乾明, 马胜, 王永文, 隋兵才, 沈立… - 电子学报, 2023 - ejournal.org.cn
当今的处理器性能与存储器带宽和延迟严重失衡的问题限制了计算系统的整体性能,
而存储器的性能对制程工艺不敏感, 在后摩尔时代下很难再通过集成电路制造工艺的迭代获得 …
而存储器的性能对制程工艺不敏感, 在后摩尔时代下很难再通过集成电路制造工艺的迭代获得 …
Improving the Representativeness of Simulation Intervals for the Cache Memory System
Accurate simulation techniques are indispensable to efficiently propose new memory or
architectural organizations. As implementing new hardware concepts in real systems is often …
architectural organizations. As implementing new hardware concepts in real systems is often …
Cost-Effective Value Predictor for ILP processors through Design Space Exploration
Value prediction is a microarchitectural technique that enhances processor performance by
speculatively breaking true data dependencies. It has demonstrated improved performance …
speculatively breaking true data dependencies. It has demonstrated improved performance …
Dynamic Ineffectuality-based Clustered Architectures
R Kalayappan, S Chandran - arXiv preprint arXiv:2304.12762, 2023 - arxiv.org
The direction of conditional branches is predicted correctly in modern processors with great
accuracy. We find several instructions in the dynamic instruction stream that contribute only …
accuracy. We find several instructions in the dynamic instruction stream that contribute only …
Improving the representativeness of simulation intervals for the cache memory system
N Bueno Mora, F Castro Rodríguez, L Piñuel Moreno… - 2024 - docta.ucm.es
Accurate simulation techniques are indispensable to efficiently propose new memory or
architectural organizations. As implementing new hardware concepts in real systems is often …
architectural organizations. As implementing new hardware concepts in real systems is often …