Profile hidden Markov models (profile HMMs) and probabilistic inference methods have made important contributions to the theory of sequence database homology search. However, practical use of profile HMM methods has been hindered by the computational expense of existing software implementations. Here I describe an acceleration heuristic for profile HMMs, the "multiple segment Viterbi" (MSV) algorithm. The MSV algorithm computes an optimal sum of multiple ungapped local alignment segments using a striped vector-parallel approach previously described for fast Smith/Waterman alignment. MSV scores follow the same statistical distribution as gapped optimal local alignment scores, allowing rapid evaluation of significance of an MSV score and thus facilitating its use as a heuristic filter. I also describe a 20-fold acceleration of the standard profile HMM Forward/Backward algorithms using a method I call "sparse rescaling". These methods are assembled in a pipeline in which high-scoring MSV hits are passed on for reanalysis with the full HMM Forward/Backward algorithm. This accelerated pipeline is implemented in the freely available HMMER3 software package. Performance benchmarks show that the use of the heuristic MSV filter sacrifices negligible sensitivity compared to unaccelerated profile HMM searches. HMMER3 is substantially more sensitive and 100- to 1000-fold faster than HMMER2. HMMER3 is now about as fast as BLAST for protein searches.

/pdf/accelerated-profile-hmm-searches-5f0frwnmca.pdf

Accelerated Profile HMM Searches

The advent of multicore CPUs and manycore GPUs means that mainstream processor chips are now parallel systems. Furthermore, their parallelism continues to scale with Moore's law. The challenge is to develop mainstream application software that transparently scales its parallelism to leverage the increasing number of processor cores, much as 3D graphics applications transparently scale their parallelism to manycore GPUs with widely varying numbers of cores.

/pdf/scalable-parallel-programming-with-cuda-fx7qj9io5g.pdf

Scalable parallel programming with CUDA

The rapid increase in the performance of graphics hardware, coupled with recent improvements in its programmability, have made graphics hardware a compelling platform for computationally demanding tasks in a wide variety of application domains. In this report, we describe, summarize, and analyze the latest research in mapping general-purpose computation to graphics hardware. We begin with the technical motivations that underlie general-purpose computation on graphics processors (GPGPU) and describe the hardware and software developments that have led to the recent interest in this field. We then aim the main body of this report at two separate audiences. First, we describe the techniques used in mapping general-purpose computation to graphics hardware. We believe these techniques will be generally useful for researchers who plan to develop the next generation of GPGPU algorithms and techniques. Second, we survey and categorize the latest developments in general-purpose application development on graphics hardware. This survey should be of particular interest to researchers who are interested in using the latest GPGPU applications in their systems of interest.

/pdf/a-survey-of-general-purpose-computation-on-graphics-hardware-2phx1q9xxr.pdf

A Survey of General-Purpose Computation on Graphics Hardware

We present an implementation of generalized Born implicit solvent all-atom classical molecular dynamics (MD) within the AMBER program package that runs entirely on CUDA enabled NVIDIA graphics processing units (GPUs). We discuss the algorithms that are used to exploit the processing power of the GPUs and show the performance that can be achieved in comparison to simulations on conventional CPU clusters. The implementation supports three different precision models in which the contributions to the forces are calculated in single precision floating point arithmetic but accumulated in double precision (SPDP), or everything is computed in single precision (SPSP) or double precision (DPDP). In addition to performance, we have focused on understanding the implications of the different precision models on the outcome of implicit solvent MD simulations. We show results for a range of tests including the accuracy of single point force evaluations and energy conservation as well as structural properties pertainining to protein dynamics. The numerical noise due to rounding errors within the SPSP precision model is sufficiently large to lead to an accumulation of errors which can result in unphysical trajectories for long time scale simulations. We recommend the use of the mixed-precision SPDP model since the numerical results obtained are comparable with those of the full double precision DPDP model and the reference double precision CPU implementation but at significantly reduced computational cost. Our implementation provides performance for GB simulations on a single desktop that is on par with, and in some cases exceeds, that of traditional supercomputers.

/pdf/routine-microsecond-molecular-dynamics-simulations-with-41c2fb6wpv.pdf

Routine Microsecond Molecular Dynamics Simulations with AMBER on GPUs. 1. Generalized Born

The graphics processing unit (GPU) has become an integral part of today's mainstream computing systems. Over the past six years, there has been a marked increase in the performance and capabilities of GPUs. The modern GPU is not only a powerful graphics engine but also a highly parallel programmable processor featuring peak arithmetic and memory bandwidth that substantially outpaces its CPU counterpart. The GPU's rapid increase in both programmability and capability has spawned a research community that has successfully mapped a broad range of computationally demanding, complex problems to the GPU. This effort in general-purpose computing on the GPU, also known as GPU computing, has positioned the GPU as a compelling alternative to traditional microprocessors in high-performance computer systems of the future. We describe the background, hardware, and programming model for GPU computing, summarize the state of the art in tools and techniques, and present four GPU computing successes in game physics and computational biophysics that deliver order-of-magnitude performance gains over optimized CPU applications.

GPU Computing

In this paper, we present Brook for GPUs, a system for general-purpose computation on programmable graphics hardware. Brook extends C to include simple data-parallel constructs, enabling the use of the GPU as a streaming co-processor. We present a compiler and runtime system that abstracts and virtualizes many aspects of graphics hardware. In addition, we present an analysis of the effectiveness of the GPU as a compute engine compared to the CPU, to determine when the GPU can outperform the CPU for a particular algorithm. We evaluate our system with five applications, the SAXPY and SGEMV BLAS operators, image segmentation, FFT, and ray tracing. For these applications, we demonstrate that our Brook implementations perform comparably to hand-written GPU code and up to seven times faster than their CPU counterparts.

/pdf/brook-for-gpus-stream-computing-on-graphics-hardware-49gy5u8zyg.pdf

Brook for GPUs: stream computing on graphics hardware

We present Sequoia, a programming language designed to facilitate the development of memory hierarchy aware parallel programs that remain portable across modern machines featuring different memory hierarchy configurations. Sequoia abstractly exposes hierarchical memory in the programming model and provides language mechanisms to describe communication vertically through the machine and to localize computation to particular memory locations within it. We have implemented a complete programming system, including a compiler and runtime systems for Cell processor-based blade systems and distributed memory clusters, and demonstrate efficient performance running Sequoia programs on both of these platforms.

/pdf/sequoia-programming-the-memory-hierarchy-2juw2c1av5.pdf

Sequoia: programming the memory hierarchy

Over the past few years, the powerful computation rates and high memory bandwidth of GPUs have attracted efforts to run raytracing on GPUs. Our work extends Foley et al.'s GPU k-d tree research. We port their kd-restart algorithm from multi-pass, using CPU load balancing, to single pass, using current GPUs' branching and looping abilities. We introduce three optimizations: a packetized formulation, a technique for restarting partially down the tree instead of at the root, and a small, fixed-size stack that is checked before resorting to restart. Our optimized implementation achieves 15 - 18 million primary rays per second and 16 - 27 million shadow rays per second on our test scenes.Our system also takes advantage of GPUs' strengths at rasterization and shading to offer a mode where rasterization replaces eye ray scene intersection, and primary hits and local shading are produced with standard Direct3D code. For 1024x1024 renderings of our scenes with shadows and Phong shading, we achieve 12-18 frames per second. Finally, we investigate the efficiency of our implementation relative to the computational resources of our GPUs and also compare it against conventional CPUs and the Cell processor, which both have been shown to raytrace well.

Interactive k-d tree GPU raytracing

The proliferation of biological sequence data has motivated the need for an extremely fast probabilistic sequence search. One method for performing this search involves evaluating the Viterbi probability of a hidden Markov model (HMM) of a desired sequence family for each sequence in a protein database. However, one of the difficulties with current implementations is the time required to search large databases. Many current and upcoming architectures offering large amounts of compute power are designed with data-parallel execution and streaming in mind. We present a streaming algorithm for evaluating an HMMs Viterbi probability and refine it for the specific HMM used in biological sequence search. We implement our streaming algorithm in the Brook language, allowing us to execute the algorithm on graphics processors. We demonstrate that this streaming algorithm on graphics processors can outperform available CPU implementations. We also demonstrate this implementation running on a 16 node graphics cluster.

/pdf/clawhmmer-a-streaming-hmmer-search-implementatio-1v3ugnbw2o.pdf

ClawHMMER: A Streaming HMMer-Search Implementatio

Light fields can be used to represent an object's appearance with a high degree of realism. However, unlike their geometric counterparts, these image-based representations lack user control for manipulating them. We present a system that allows a user to interactively manipulate, composite and render multiple light fields. LightShop is a modular system consisting of three parts: 1) a set of functions that allow a user to model a scene containing multiple light fields, 2) a ray-shading language that describes how an image should be constructed from a set of light fields, and 3) a real-time light field rendering system in OpenGL that can plug into existing 3D engines as a GLSL shader.We show applications in digital photography and we demonstrate how to integrate light fields into a modern space-flight game using LightShop.

Daniel Reiter Horn

Papers

Brook for GPUs: stream computing on graphics hardware

Sequoia: programming the memory hierarchy

Interactive k-d tree GPU raytracing

ClawHMMER: A Streaming HMMer-Search Implementatio

LightShop: interactive light field manipulation and rendering