Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 121 for “"Memory Access Patterns"”.

  1. Cache Memory Access Patterns in the GPU Architecture

    … The characterization of data and cache memory access patterns differ between a CPU and a GPU. The motivation of this research is to analyze the cache memory access patterns of GPU architectures and to potentially improve data exchange between a CPU and GPU. The methodology of this work …

    rit Repository record for Cache Memory Access Patterns in the GPU Architecture (opens in a new tab)

  2. Memory Access Patterns for Cellular Automata Using GPGPUs

    … realize the potential of a GPU, specialized memory techniques and patterns must be employed to account for their unique architecture. Several techniques are presented which not only dramatically improve performance, but, in many cases, also simplify implementation. Many of the approaches …

    denver Repository record for Memory Access Patterns for Cellular Automata Using GPGPUs (opens in a new tab)

  3. Analysis of Memory Access Patterns for Large Language Model Inference

    The use of tiered heterogeneous memory systems in HPC workloads is growing in popularity as the increasing memory requirements for these workloads outpace the decline in the cost- per-gigabyte of fast DRAM; however, the Linux kernel has no intelligent strategy to manage these tiered memory systems. …

    vt Repository record for Analysis of Memory Access Patterns for Large Language Model Inference (opens in a new tab)

  4. Memory access patterns and page promotion in hybrid memory systems

    Hybrid heterogeneous memory systems are becoming increasingly popular as traditional memory systems are hitting performance and energy walls in processing data-intensive applications, which are becoming the norm with the resurgence of machine learning, big data, graph analytics, and database …

    uiuc Repository record for Memory access patterns and page promotion in hybrid memory systems (opens in a new tab)

  5. Compiler Optimizations for Irregular Memory Access Patterns in the PGAS Programming Model

    … graphs and matrices exhibit fine-grain irregular memory accesses patterns, leading to both performance and productivity challenges on today's distributed-memory systems. The Partitioned Global Address Space (PGAS) model attempts to address these challenges by combining the memory of physically …

    maryland Repository record for Compiler Optimizations for Irregular Memory Access Patterns in the PGAS Programming Model (opens in a new tab)

  6. Exploiting cache locality at run-time

    … gap between the speeds of the processor and memory system, memory access has become a major performance bottleneck in modern computer systems. Recently, Symmetric Multi-Processor (SMP) systems have emerged as a major class of high-performance platforms. Improving the memory performance of …

    wm-mary Repository record for Exploiting cache locality at run-time (opens in a new tab)

  7. Oblivious RAM in Scalable SGX

    … the encrypted ciphertext as well as a program's memory access patterns. As the attacks grow in complexity and accuracy, innovative protection methods must be de- signed to secure data. This thesis proposes and implements an ORAM controller primitive in TEE and protects it from all potential …

    vt Repository record for Oblivious RAM in Scalable SGX (opens in a new tab)

  8. Automating the derivation of memory allocations for acceleration of polyhedral programs

    … power keeps increasing, so do their demands in memory accesses: some computations will require a higher bandwidth and exhibit regular memory access patterns, others will require a lower access latency and exhibit random access patterns. To cope with all demands, memory technologies are becoming …

    colostate Repository record for Automating the derivation of memory allocations for acceleration of polyhedral programs (opens in a new tab)

  9. Reliability Techniques for Data Communication and Storage in FPGA-Based Circuits

    … also studies the reliability of block random access memory (BRAM) on FPGAs. By investigating several previous reliability models for single-error correction/double-error detection (SEC/DED) memory with scrubbing, this dissertation proposes two novel MTTF models that are suitable for FPGA …

    byu Repository record for Reliability Techniques for Data Communication and Storage in FPGA-Based Circuits (opens in a new tab) Download PDF for Reliability Techniques for Data Communication and Storage in FPGA-Based Circuits (opens in a new tab)

  10. DSM64: A Distributed Shared Memory System in User-Space

    … release consistent software distributed shared memory (SDSM) system built entirely in user-space. The DSM64 system is capable of executing threaded applications implemented with pthreads on a cluster of networked machines without any modifications to the target application. The DSM64 system …

    calpoly Repository record for DSM64: A Distributed Shared Memory System in User-Space (opens in a new tab)

  11. Efficient Support for Speculative Tasking

    … called for signatures in hardware to accelerate memory disambiguation. To take full advantage of signatures, this thesis presents SoftBulk, a novel architecture that exposes signatures to software directly through the instruction set. Using SoftBulk, programs can collect information about their …

    uiuc Repository record for Efficient Support for Speculative Tasking (opens in a new tab)

  12. Characterizing the Performance Bottlenecks of Irregular GPU Kernels

    … applications with data-dependent, irregular memory access patterns and control flow. However, relatively little is known about the behavior of irregular GPU codes, and there has been minimal effort to quantify the ways in which they differ from regular general-purpose GPU applications. I …

    texas-state Repository record for Characterizing the Performance Bottlenecks of Irregular GPU Kernels (opens in a new tab)

  13. GPGPU-Based Fast Counting in Machine Learning Applications

    … provided by GPGPU parallelization, efficient memory access patterns and stream-based query execution strategies. We demonstrate performance and scalability of the resulting approach on random queries on embedded device based GPGPUs.

    buffalo Repository record for GPGPU-Based Fast Counting in Machine Learning Applications (opens in a new tab)

  14. Assessing performance and cost efficiency for parallel workloads on public clouds

    … general-purpose, compute-optimized, memory-optimized, and GPU-accelerated instances—further com plicating the selection process. Finally, HPC workloads exhibit diverse computational behaviors, such as varying degrees of parallelism, different memory access patterns, and distinct …

    brazil-ufrgs Repository record for Assessing performance and cost efficiency for parallel workloads on public clouds (opens in a new tab)

  15. Concurrent dynamic memory coalescing on goblin-core 64 architecture

    … work well in conjunction with applications that access memory in a linear fashion. However, applications that exhibit random or non-deterministic memory access patterns often induce a significant number of data cache misses, thus reducing the natural performance benefit from the data cache. In …

    ttu Repository record for Concurrent dynamic memory coalescing on goblin-core 64 architecture (opens in a new tab)

  16. Effective fault localization techniques for concurrent software

    … that locates single-variable concurrency bugs as memory-access patterns. Falcon uses dynamic pattern detection and statistical fault localization to report a ranked list of memory-access patterns for root causes of concurrency bugs. The overall Falcon approach is effective: in an empirical …

    gatech Repository record for Effective fault localization techniques for concurrent software (opens in a new tab)

  17. Enhancing Sparse Data Processing through Energy-Efficient Heterogeneous Architectures

    … overheads during indexing and irregular memory access patterns, limiting the performance and scalability of these applications. This research addresses these challenges by exploring innovative hardware solutions to improve the performance and energy efficiency of sparse linear algebra …

    unt Repository record for Enhancing Sparse Data Processing through Energy-Efficient Heterogeneous Architectures (opens in a new tab)

  18. Memory Access Characterization of Large Language Models in CPU Environment and Its Potential Impacts

    … increasingly valuable tool, the demand for their access has grown accordingly. Oftentimes, it is infeasible to run inference with larger models without an accelerator, which may be unavailable in environments that have constraints such as energy consumption, security, or cost. To increase the …

    tamu Repository record for Memory Access Characterization of Large Language Models in CPU Environment and Its Potential Impacts (opens in a new tab)

  19. An enhanced GPU architecture for not-so-regular parallelism with special implications for database search

    … intensity, regular control-flow and memory access patterns, and little to no communication among threads. However, not all parallel applications have these characteristics. Applications with a more balanced compute to memory ratio, divergent control flow, irregular memory accesses, …

    texas Repository record for An enhanced GPU architecture for not-so-regular parallelism with special implications for database search (opens in a new tab)

  20. Run-time optimization of adaptive irregular applications

    … match the characteristics of programs' dynamic memory access patterns and the appropriate optimization (parallelization) transformations. First, we present a general adaptive algorithm selection framework to automatically and adaptively select at run-time the best performing, functionally …

    tamu Repository record for Run-time optimization of adaptive irregular applications (opens in a new tab)

Page 1 of 7