Blue Gene/L advanced diagnostics environment

Abstract

This paper describes the Blue Genet/L advanced diagnostics environment (ADE) used throughout all aspects of the Blue Gene/L project, including design, logic verification, bringup, diagnostics, and manufacturing test. The Blue Gene/L ADE consists of a lightweight multithreaded coherence-managed kernel, runtime libraries, device drivers, system programming interfaces, compilers, and host-based development tools. It provides complete and flexible access to all features of the Blue Gene/L hardware. Prior to the existence of hardware, ADE was used on Very highspeed integrated circuit Hardware Description Language (VHDL) models, not only for logic verification, but also for performance measurements, code-path analysis, and evaluation of architectural tradeoffs. During early hardware bring-up, the ability to run in a cycle-reproducible manner on both hardware and VHDL proved invaluable in fault isolation and analysis. However, ADE is also capable of supporting high-performance applications and parallel test cases, thereby permitting us to stress the hardware to the limits of its capabilities. This paper also provides insights into systemlevel and device-level programming of Blue Gene/L to assist developers of high-performance applications to more fully exploit the performance of the machine.

Experiences with a Lightweight Supercomputer Kernel: Lessons Learned from Blue Gene's CNK

“…The CNK kernel low-core leverages aspects of the Blue Gene/L Advanced Diagnostic Environment [14]. Reproducibility enables debugging the hardware via logic scans, which are destructive to the chip state.…”

“…Traditional wisdom viewed such kernels as lacking significant function and providing an unfamiliar programming environment. Supporting this notion were previous generation kernels such as Catamount [19] (from Sandia, UNM, and Cray) for Cray supercomputers and IBM's CNK for Blue Gene/L [14], [23].…”

Blue Matter: Strong Scaling of Molecular Dynamics on Blue Gene/L

“…Even so, the realized performance on MPI does not yet reflect the full capabilities of the hardware. We have implemented the collective operations required by Blue Matter via the low-level System Programming Interface (SPI) of the Blue Gene/L Advanced Diagnostics Environment [21]. This is the environment used by the BG/L hardware team to test and validate hardware performance.…”

Blue Matter: Approaching the Limits of Concurrency for Classical Molecular Dynamics

“…The communication protocol designed for the k-space module on Blue Gene/L takes advantage of the hardware global collective network Giampapa et al 2005]. When the k-space module begins, it receives new position values from the integration module and for each, determines the list of target nodes owning relevant FFT mesh points.…”