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 13 of 13 for “"Dynamic parallelism"”.

  1. Techniques for optimizing dynamic parallelism on graphics processing units

    Dynamic parallelism is a feature of general purpose graphics processing units (GPUs) whereby threads running on a GPU can spawn other threads without CPU intervention. This feature is useful for programming applications with nested parallelism where threads executing in parallel may each identify …

    uiuc Repository record for Techniques for optimizing dynamic parallelism on graphics processing units (opens in a new tab)

  2. Acceleration and optimization of dynamic parallelism for irregular applications on GPUs

    … supports time-varying, nested, fine-grained dynamic parallelism occurring in the irregular data intensive applications. These dynamically formed pockets of structured parallelism can utilize the recently introduced device-side nested kernel launch capabilities on GPUs. However, the low …

    gatech Repository record for Acceleration and optimization of dynamic parallelism for irregular applications on GPUs (opens in a new tab)

  3. Compiler-assisted workload consolidation to efficiently exploit dynamic parallelism for recursive applications

    … for those application which express a flat data parallelism, a simple data parallelism that is known at compiling time and can be easily distributed to different GPU blocks and threads. However, for those applications that contain nested data parallelism, which is not known a priori and can only …

    missouri Repository record for Compiler-assisted workload consolidation to efficiently exploit dynamic parallelism for recursive applications (opens in a new tab)

  4. Techniques for enabling GPU code generation of low-level optimizations and dynamic parallelism from high-level abstractions

    … (on global and shared memories), and GPU dynamic parallelism to be easily generated. A practical implementation of these transformations is built on Tangram, a high-level kernel synthesis framework. The performance of the automatically generated low-level instructions is compared against …

    uiuc Repository record for Techniques for enabling GPU code generation of low-level optimizations and dynamic parallelism from high-level abstractions (opens in a new tab)

  5. Dynamically parallel CAMSHIFT: GPU accelerated object tracking in digital video

    … CAMSHIFT algorithm is widely used for tracking dynamically sized and positioned objects in real-time applications. In spite of its extensive study on the platform of sequential CPU, its research on massively parallel Graphical Processing Unit (GPU) platform is quite limited. In this work, we …

    eastern-wash Repository record for Dynamically parallel CAMSHIFT: GPU accelerated object tracking in digital video (opens in a new tab)

  6. Protecting File Transfers Against Silent Data Corruption with Robust End-to-End Integrity Verification

    … file content on the disk. Finally, we present dynamic parallelism to adjust the number of transfer and checksum threads to overcome performance bottlenecks. The results show that dynamic parallelism lead to more than 5x increase in RIVA's speed.

    unr Repository record for Protecting File Transfers Against Silent Data Corruption with Robust End-to-End Integrity Verification (opens in a new tab)

  7. Accelerating Spatial Query Operations

    … time complexity. The second algorithm uses dynamic parallelism to remove synchronization and scales to utilize available GPU hardware (single GPU). Experiments on both synthetic and real world data sets are performed. The results show improvement in execution time with respect to recent …

    siu-theses Repository record for Accelerating Spatial Query Operations (opens in a new tab)

  8. Haptic Interaction with 3D oriented point clouds on the GPU

    … for haptic applications. Also, the use of dynamic parallelism as a technique to scale the number of threads needed from the accelerator according to the interaction requirements is studied allowing the editing of data sets of up to one million points at interactive haptic frame rates.

    east-anglia Download PDF for Haptic Interaction with 3D oriented point clouds on the GPU (opens in a new tab)

  9. Integrating stream parallelism and task parallelism in a dataflow programming model

    … multicore computing becomes the norm, exploiting parallelism in applications becomes a requirement for all software. Many applications exhibit different kinds of parallelism, but most parallel programming languages are biased towards a specific paradigm, of which two common ones are task and …

    rice Repository record for Integrating stream parallelism and task parallelism in a dataflow programming model (opens in a new tab)

  10. Relational Joins on GPUs for In-Memory Database Query Processing

    … file and shared memory, native atomic operation, dynamic parallelism, and CUDA Streams. Lastly, we explore how join processing would benefit from the adaptation of multiple GPUs. We identify the low rate and complex patterns of data transfer among the CPU and GPUs as the main challenges in …

    usf Repository record for Relational Joins on GPUs for In-Memory Database Query Processing (opens in a new tab)

  11. Point Based Approximate Color Bleeding with Cuda

    … work which could include the use of CUDA’s Dynamic Parallelism and a stack free implementation which could increase the speedups seen by our algorithm.

    calpoly Repository record for Point Based Approximate Color Bleeding with Cuda (opens in a new tab)

  12. Efficient OpenMP runtime support for general - purpose and embedded multi - core platforms

    … expression and management of irregular and dynamic parallelism. Recently, another significant addition to OpenMP was the introduction of device directives that target systems consisting of general-purpose hosts and accelerator devices that may execute portions of a unified application code. …

    greece Repository record for Efficient OpenMP runtime support for general - purpose and embedded multi - core platforms (opens in a new tab)

  13. Architectural Frameworks for Automated Design and Optimization of Hardware Accelerators

    … framework uses a computation model that supports dynamic parallelism in addition to static parallelism, and includes a flexible architecture that supports dynamic scheduling to enable mapping a wide range of parallel applications to hardware accelerators and achieve good performance. In addition, …

    cornell Repository record for Architectural Frameworks for Automated Design and Optimization of Hardware Accelerators (opens in a new tab)