Using Butterfly-Patterned Partial Sums to Optimize GPU Memory Accesses for Drawing from Discrete Distributions
نویسندگان
چکیده
We describe a technique for drawing values from discrete distributions, such as sampling from the random variables of a mixture model, that avoids computing a complete table of partial sums of the relative probabilities. A table of alternate (“butterfly-patterned”) form is faster to compute, making better use of coalesced memory accesses. From this table, complete partial sums are computed on the fly during a binary search. Measurements using an NVIDIA Titan Black GPU show that for a sufficiently large number of clusters or topics (K > 200), this technique alone more than doubles the speed of a latent Dirichlet allocation (LDA) application already highly tuned for GPU execution.
منابع مشابه
Parallelization of Rich Models for Steganalysis of Digital Images using a CUDA-based Approach
There are several different methods to make an efficient strategy for steganalysis of digital images. A very powerful method in this area is rich model consisting of a large number of diverse sub-models in both spatial and transform domain that should be utilized. However, the extraction of a various types of features from an image is so time consuming in some steps, especially for training pha...
متن کاملPaper Title
Prefix sums are an important parallel primitive, especially in massively-parallel programs. This paper discusses two orthogonal generalizations thereof, which we call higher-order and tuple-based prefix sums. Moreover, it describes and evaluates SAM, a GPU-friendly algorithm for computing prefix sums and other scans that directly supports higher orders and tuple values. Its templated CUDA imple...
متن کاملOffline Permutation Algorithms on the Discrete Memory Machine with Performance Evaluation on the GPU
The Discrete Memory Machine (DMM) is a theoretical parallel computing model that captures the essence of the shared memory access of GPUs. The bank conflicts should be avoided for maximizing the bandwidth of the shared memory access. Offline permutation of an array is a task to copy all elements in array a into array b along a permutation given in advance. The main contribution of this paper is...
متن کاملGPUDrano: Detecting Uncoalesced Accesses in GPU Programs
Graphics Processing Units (GPUs) have become widespread and popular over the past decade. Fully utilizing the parallel compute and memory resources that GPUs present remains a significant challenge, however. In this paper, we describe GPUDrano: a scalable static analysis that detects uncoalesced global memory accesses in CUDA programs. Uncoalesced global memory accesses arise when a GPU program...
متن کاملAn initial investigation of the performance of GPU-based swept time-space decomposition
Simulations of physical phenomena are essential to the expedient design of precision components in aerospace and other high-tech industries. These phenomena are often described by mathematical models involving partial differential equations (PDEs) without exact solutions. Modern design problems require simulations with a level of resolution that is difficult to achieve in a reasonable amount of...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1505.03851 شماره
صفحات -
تاریخ انتشار 2015