Supercomputer performance

In addition to steady gains in the performance of a single chip, the speeds of the fastest parallel computers have shown tremendous growth. The TOP500 

---

Supercomputers are found in many government research laboratories, intelligence agencies, universities, and a small number of industrial companies. In the United States, the National Science Foundation (NSF) has provided supercomputers to several prominent universities for both academic and industrial users. These centers provide state-of-the-art, supercomputer-tuned appHcations for a wide variety of disciplines, together with staffs who are very knowledgeable in optimization for supercomputer performance. 

Furthermore, hardware like multiprocessor workstations, which provide near-supercomputer performance within the UPSM programming model, are becoming available from several vendors (see chapter appendix). These machines are capable of exploiting the shared-memory parallelism that is already represented in code libraries such as LAPACK. Another important positive sign is that issues of scalable library construction have become more visible—for example, as an IEEE-sponsored workshop. " Such efforts, combined with the availability of software like ScaLAPACK as seed code, may well serve to crystallize the development of common data layout and program structure conventions. 

Nelson, M., Humphrey, W., Gursoy, A., Dalke, A., Kale, L., Skeel, R.D., Schul-ten, K. NAMD - A parallel, object-oriented molecular dynamics program. Int. J. Supercomputing Applications and High Performance Computing 10 (1996) 251-268. 

K. Schulten. NAMD—a parallel, object-oriented molecular dynamics program. Inti. J. Supercomput. Applies. High Performance Computing, 10 251-268, 1996. 

Quantum mechanics gives a mathematical description of the behavior of electrons that has never been found to be wrong. However, the quantum mechanical equations have never been solved exactly for any chemical system other than the hydrogen atom. Thus, the entire held of computational chemistry is built around approximate solutions. Some of these solutions are very crude and others are expected to be more accurate than any experiment that has yet been conducted. There are several implications of this situation. First, computational chemists require a knowledge of each approximation being used and how accurate the results are expected to be. Second, obtaining very accurate results requires extremely powerful computers. Third, if the equations can be solved analytically, much of the work now done on supercomputers could be performed faster and more accurately on a PC. 

A common acronym is MFLOPS, millions of floating-point operations per second. Because most scientific computations are limited by the speed at which floating point operations can be performed, this is a common measure of peak computing speed. Supercomputers of 1991 offered peak speeds of 1000 MFLOPS (1 GFLOP) and higher. 

The memory subsystem on most supercomputers is organized to support maximum performance on loops of stride one, or when the elements of an array are accessed sequentially with no gaps. In general, the stride is defined by... 

Many of the faster work stations can provide throughput similar to that observed on a crowded, shared supercomputer, especially for codes that do not benefit greatly from vectorization. The availabihty of such machines for less than 50,000 (much less for academic users) has once again changed concepts of what is computationally feasible. Many more people can perform computations that a few years ago were the sole domain of those with access to large-scale computing faciUties, and this trend is expected to continue. 

These codes have stressed the current supercomputer, whether it was the CDC 6600 in the 1970s, the Grays in the 1980s, or the massively parallel computers of the 1990s. Multimillion cell calculations are routinely performed at Sandia National Laboratories with the CTH [1], [2] code, yet... 

One Important aspect of the supercomputer revolution that must be emphasized Is the hope that not only will It allow bigger calculations by existing methods, but also that It will actually stimulate the development of new approaches. A recent example of work along these lines Involves the solution of the Hartree-Fock equations by numerical Integration In momentum space rather than by expansion In a basis set In coordinate space (2.). Such calculations require too many fioatlng point operations and too much memory to be performed In a reasonable way on minicomputers, but once they are begun on supercomputers they open up several new lines of thinking. 

All calculations were performed on the Cray-2 computers at the Minnesota Supercomputer Center. In some cases the two-electron Integrals could be kept in the 256 megaword central memory of the Cray-2, and in these cases an "in-core" integral and SCF code(53) was used. The largest in-core calculations possible in... 

---