IBM Blue Research Articles

Advances in Rosetta protein structure prediction on massively parallel systems

One of the key challenges in computational biology is prediction of three-dimensional protein structures from amino-acid sequences. For most proteins, the state lies at the bottom of a free-energy landscape. Protein structure prediction involves varying the degrees of freedom of the protein in a constrained manner until it approaches its native state. In the Rosetta protein structure prediction protocols, a large number of independent folding trajectories are simulated, and several lowest-energy results are likely to be close to the native state. The availability of hundred-teraflop, and shortly, petaflop, computing resources is revolutionizing the approaches available for protein structure prediction. Here, we discuss issues involved in utilizing such machines efficiently with the Rosetta code, including an overview of recent results of the Critical Assessment of Techniques for Protein Structure Prediction 7 (CASP7) in which the computationally demanding structure-refinement process was run on 16 racks of the IBM Blue Gene/L™ system at the IBM T. J. Watson Research Center. We highlight recent advances in high-performance computing and discuss future development paths that make use of the next-generation petascale (>1012 floating-point operations per second) machines.

Architecture of Qbox: A scalable first-principles molecular dynamics code

We describe the architecture of Qbox, a parallel, scalable first-principles molecular dynamics (FPMD) code. Qbox is a C++/Message Passing Interface implementation of FPMD based on the plane-wave, pseudopotential method for electronic structure calculations. It is built upon well-optimized parallel numerical libraries, such as Basic Linear Algebra Communication Subprograms (BLACS) and Scalable Linear Algebra Package (ScaLAPACK), and also features an Extensible Markup Language (XML) interface built on the Apache Xerces-C library. We describe various choices made in the design of Qbox that led to excellent scalability on large parallel computers. In particular, we discuss the case of the IBM Blue Gene/L™ platform on which Qbox was run using up to 65,536 nodes. Future design challenges for upcoming petascale computers are also discussed. Examples of applications of Qbox to a variety of first-principles simulations of solids, liquids, and nanostructures are briefly described.

High performance computing environment for multidimensional image analysis

BackgroundThe processing of images acquired through microscopy is a challenging task due to the large size of datasets (several gigabytes) and the fast turnaround time required. If the throughput of the image processing stage is significantly increased, it can have a major impact in microscopy applications.ResultsWe present a high performance computing (HPC) solution to this problem. This involves decomposing the spatial 3D image into segments that are assigned to unique processors, and matched to the 3D torus architecture of the IBM Blue Gene/L machine. Communication between segments is restricted to the nearest neighbors. When running on a 2 Ghz Intel CPU, the task of 3D median filtering on a typical 256 megabyte dataset takes two and a half hours, whereas by using 1024 nodes of Blue Gene, this task can be performed in 18.8 seconds, a 478× speedup.ConclusionOur parallel solution dramatically improves the performance of image processing, feature extraction and 3D reconstruction tasks. This increased throughput permits biologists to conduct unprecedented large scale experiments with massive datasets.

Dynamic Binary Instrumentation and Data Aggregation on Large Scale Systems

Dynamic binary instrumentation for performance analysis on large scale architectures such as the IBM Blue Gene/L system (BG/L) poses unique challenges. Their unprecedented scale and often limited OS support require new mechanisms to organize binary instrumentation, to interact with the target application, and to collect the resulting data. We describe the design and current status of a new implementation of the Dynamic Probe Class Library (DPCL) API for large scale systems. DPCL provides an easy to use layer for dynamic instrumentation on parallel MPI applications based on the DynInst dynamic instrumentation library for sequential platforms. Our work includes modifying DynInst to control instrumentation from remote I/O nodes and porting DPCL's communication for performance data collection to use MRNet, a tree-based overlay network that (TBON) supports scalable multicast and data reduction. We describe extensions to the DPCL API that support instrumentation of task subsets and aggregation of collected performance data.

Free Energy Landscape Analysis System Based on Parallel Molecular Dynamics Simulation

We created a Free Energy Landscape Analysis System based on a parallelized molecular dynamics (MD) simulation adapted for the IBM Blue Gene/L supercomputer. We begin with an outline of our Free Energy Landscape Analysis system. Next we discuss how Parallel MD was tuned for Blue Gene/L. We then show the results for some test targets run on Blue Gene/L, including their efficiency. Finally, we mention some future directions for extension of this project.

Scalable dynamic binary instrumentation for Blue Gene/L

Dynamic binary instrumentation for performance analysis on new, large scale architectures such as the IBM Blue Gene/L system (BG/L) poses new challenges. Their scale---with potentially hundreds of thousands of compute nodes---requires new, more scalable mechanisms to deploy and to organize binary instrumentation and to collect the resulting data gathered by the inserted probes. Further, many of these new machines don't support full operating systems on the compute nodes; rather, they rely on light-weight custom compute kernels that do not support daemon-based implementations.We describe the design and current status of a new implementation of the DPCL (Dynamic Probe Class Library) API for BG/L. DPCL provides an easy to use layer for dynamic instrumentation on parallel MPI applications based on the DynInst dynamic instrumentation mechanism for sequential platforms. Our work includes modifying DynInst to control instrumentation from remote I/O nodes and porting DPCL's communication to use MRNet, a scalable data reduction network for collecting performance data. We describe extensions to the DPCL API that support instrumentation of task subsets and aggregation of collected performance data. Overall, our implementation provides a scalable infrastructure that provides efficient binary instrumentation on BG/L.

Early performance data on the Blue Matter molecular simulation framework

Blue Matter is the application framework being developed in conjunction with the scientific portion of the IBM Blue Gene® project. We describe the parallel decomposition currently being used to target the Blue Gene/L machine and discuss the application-based trace tools used to analyze the performance of the application. We also present the results of early performance studies, including a comparison of the performance of the Ewald and the particle-particle particle-mesh (P3ME) methods, compare the measured performance of some key collective operations with the limitations imposed by the hardware, and discuss some future directions for research.

Early analysis tools for system-on-a-chip design

The paper describes the need for early analysis tools to enable developers of today's system-on-a-chip (SoC) designs to take advantage of pre-designed components, such as those found in the IBM Blue Logic® Library, and rapidly explore high-level design alternatives to meet their system requirements. We report on a new approach for developing high-level performance models for these SoC designs and outline how this performance analysis capability can be integrated into an overall environment for efficient SoC design.

Embedded DRAM design and architecture for the IBM 0.11-µm ASIC offering

This paper presents an overview of the macro design, architecture, and built-in self-test (BIST) implementation as part of the IBM third-generation embedded dynamic random-access memory (DRAM) for the IBM Blue Logic® 0.11-µm application-specific integrated circuit (ASIC) design system (CU-11). Issues associated with embedding DRAM in an ASIC design are identified and addressed, including fundamental DRAM core function, user interface, test, and diagnosis. Macro operation and organization are detailed and contrasted with traditional DRAM designs. The use of BIST, a key enabler for embedded DRAM, is discussed while highlighting innovations required by the embedded DRAM.

Integrating the MPEG-2 subsystem for digital television

An MPEG-2 subsystem consisting of the transport demultiplexor, audio decoder, and video decoder is described, along with the supporting processor and memory subsystem. This subsystem is directly applicable to set-top box designs used in a digital television broadcast environment. The advantages of an integrated MPEG-2 subsystem consisting of cores from the IBM Blue Logic library are discussed. The integrated architecture supports a shared memory address space implemented using the PowerPC® local bus (PLB) standard high-speed bus. The resulting memory-management improvements for on-screen display (OSD), decoder rate buffers, audio and video clip data, and transport system data are illustrated. The real-time memory bandwidth and latency requirements for processing an MPEG-2 stream also have an impact on the architecture of the subsystem. Additional enhancements are provided for channel changes, time-base changes, error handling, and enhanced processing in the transport by adding more specialized buses. Programming effort is reduced because the software has less responsibility managing data movement through the system and because the same programming method is used to control all of the MPEG-2 functions.

Design considerations for the ALDC cores

The IBM adaptive lossless data compression (ALDC) family of products uses a derivative of Lempel-Ziv encoding to compress data. Several variables affect the compression performance of the ALDC algorithm: data content, history size, and data extent. As ALDC compression is integrated into different applications, restrictions are placed upon these variables that affect the overall compression performance of the system. More complex applications require further support for higher-order data structures such as variable-length segments, error recovery, and expansion. The IBM Blue Logic ALDC and embedded lossless data compression (ELDC) cores have been developed to work in these application environments. These cores and the issues associated with integrating data compression into a system are discussed.