论文标题
Gamorra：用于基于栅格化的图形管道体系结构的API级工作负载模型
GAMORRA: An API-Level Workload Model for Rasterization-based Graphics Pipeline Architecture
论文作者
论文摘要
需要构架渲染时间估计或动态频率缩放的应用程序的性能，依赖于这些应用程序中使用的工作负载模型的准确性。现有模型在其核心模型中缺乏足够的准确性。因此，它们需要更改目标应用程序或硬件以产生准确的结果。本文为基于栅格的图形应用程序编程接口（API）管道（名为Gamorra）引入了数学工作负载模型，该模型名为Gamorra，该管道基于管道的每个阶段的负载和复杂性。首先，Gamorra根据管道的每个阶段的操作复杂性和输入数据大小对管道的每个阶段进行建模。然后，将计算出的阶段工作负载作为解释变量馈送到多线性回归（MLR）模型。还提出了一个混合离线/在线培训计划来培训模型。还设计了一组基准测试套件，以根据目标系统的性能调整模型参数。实验是在Direct3d 11和两个不同的渲染平台上进行的，将Gamorra与自回归（AR）模型，框架复杂度模型（FCM）和基于频率（FRQ）模型进行了比较。该实验表明，FCM的平均范围为1.27 ms帧渲染时间估计误差（9.45％），而FCM平均误差（13.23％），这是三种选择的方法中最好的方法。但是，与FCM相比，时间复杂性增加了0.54 ms（4.58％）的成本。此外，与FCM相比，Gammora将频率低估提高了1.1％。
The performance of applications that require frame rendering time estimation or dynamic frequency scaling, rely on the accuracy of the workload model that is utilized within these applications. Existing models lack sufficient accuracy in their core model. Hence, they require changes to the target application or the hardware to produce accurate results. This paper introduces a mathematical workload model for a rasterization-based graphics Application Programming Interface (API) pipeline, named GAMORRA, which works based on the load and complexity of each stage of the pipeline. Firstly, GAMORRA models each stage of the pipeline based on their operation complexity and the input data size. Then, the calculated workloads of the stages are fed to a Multiple Linear Regression (MLR) model as explanatory variables. A hybrid offline/online training scheme is proposed as well to train the model. A suite of benchmarks is also designed to tune the model parameters based on the performance of the target system. The experiments were performed on Direct3D 11 and on two different rendering platforms comparing GAMORRA to an AutoRegressive (AR) model, a Frame Complexity Model (FCM) and a frequency-based (FRQ) model. The experiments show an average of 1.27 ms frame rendering time estimation error (9.45%) compared to an average of 1.87 ms error (13.23%) for FCM which is the best method among the three chosen methods. However, this comes at the cost of 0.54 ms (4.58%) increase in time complexity compared to FCM. Furthermore, GAMMORA improves frametime underestimations by 1.1% compared to FCM.
