CDC 8090 computer

AFP Performance Benefits. Comparisons between the performance of the Advanced Flexible Processor and other current super computers have been made on the image processing Change Detection Algorithm. The Advanced Flexible Processor has been determined to be approximately 2,000 times faster than a CDC 6600 on the Change Detection Algorithm, and to provide approximately 100 times the capability of the CDC 7600 computer. The Advanced Flexible Processor is found to perform 20 times faster than its predecessor, the Flexible Processor. 

For both structures atomic scattering factors for neutral F, Xe, and As given by Doyle and Turner and the values of the dispersion corrections, for Xe and As, of Cromer and Liberman were used. Calculations were performed on our CDC 6600 and CDC 7600 computers. ... 

In contrast to gas-phase classical trajectory calculations, the forces in this system vary rapidly with distance. As a consequence, no computer time advantage is gained by using a high-order predictor-corrector integrator. A low-order predictor-corrector is most efficient computationally. One impact point on a clean metal system with 240 atoms typically takes 120 timesteps, integrates for 2 X 10 seconds and takes about 30 seconds on a CDC 7600 computer. The computer time is approximately proportional to where N is the number of atoms in the system. 

The program storage requirements will depend somewhat on the computer and FORTRAN compiler involved. The execution times can be corrected approximately to those for other computer systems by use of factors based upon bench-mark programs representative of floating point manipulations. For example, execution times on a CDC 6600 would be less by a factor of roughly 4 than those given in the tcible and on a CDC 7600 less by a factor of roughly 24. 

Least-squares computations were performed with a local version of ORFLS (37), with the X-RAY system (33), or with the CRYM system (39). Molecular plots were produced with ORTEP (40). Calculations for the neutron structures were carried out on CDC 7600 and CDC 6600 computers at Brookhaven National Laboratory, making use of programs described by Berman et al. (41). 

Further comments on the size and extent of this bismuth cross-section calculational effort should be made. Table 5 summarizes the number of target states that we will need to consider (the 21 states include both ground and isomeric states), the number of separate reaction excitation functions that must be included, as well as estimates of the number of computer runs and the CDC 7600 CPU computer time that will be required. In our calculations, we typically use energy-bin sizes of 10 to 250 keV, depending on the reaction type and the energy ranges of concern. 

The main characteristics of the CRAY-1 computer cure shown in Table I (see also reference (2 ). The scalar operations are seen to be approximately twice that of the CDC 7600 and IBM 360/195. 

The maximum vector capability occurs for matrix multiplication, for which the measured time on the CRAY-1 is twenty times faster than the best hand coded routines on the CDC 7600 or IBM 360/195. The maximum rate is circa. 135 Mflops (Millions of floating-point operations per second) for matrices that have dimensions which are a multiple of 64, the vector register size. The rate of computation for matrix multiplication is shown in figure 1 as a function of matrix size. 

Several general lessons may be learned from this study. The kernel of the integrals code actually operates at approximately 30 times faster than the CDC 7600/ so that the non-kernel code, which takes about 10% of the computer time on a conventional machine occupies 60% of the time in our present CRAY-1 program. The implication is that work to vectorise the non-kernel components of the calculation might now be profitable. 

The electronic computer is undeniably an essential component in the tool bag of the modern theoretical chemist and, with ever improved accessibilty to more powerful computing, it is tempting to feel a sense of euphoria about current computer capabilities. At Los Alamos, we have a truly impressive resource of large computers — at present we have a choice of two 1-million word CRAY machines and four CDC 7600 machines. However, even with this powerful a computing environment, the main objective of this talk is to ask whether or not this current euphoria is really justified. Have we yet reached the stage where we can, with current computers, address problems which are traditionally thought of as chemistry The answer is, in many cases, no. 

The branch for the case when the squared pair separation is outside the table will inhibit vectorization. The last element of the table has been changed to zero and all occurrence outside the table are truncated to LMAX. The rest of the code, which is not executed on the VAX or CDC 7600, is executed here. It is often necessary on a vector machine to increase the total number of floating point operations to achieve vector rather than scalar processing. The MFLOP rates reported here are computed on the basis of the original number of floating point operations. The extra ones added to achieve vectorization are not included. 

Both closed and open-shell systems can be calculated. The programs can handle several hundred basis functions in a CDC 6600 computer and more in a CDC 7600. In addition, we plan to explore further new and novel methods for subsequent calculation on large molecules the size of block regions of DNA and for interaction of reagents with helical DNA by molecular partitioning. 

All of the structures tackled have been refined by least squares methods and, with few exceptions, by full-matrix least squares methods. The total computing investment over the past three years amounts to approximately 300 hours of central-processor time on a CDC-6400. When the necessary calculations have exceeded the capacity of the CDC-6400 (about 250 variables), we have turned to a remote hookup with the CDC-7600 at Lawrence Berkeley Laboratory. 

In 1958, computer scientistsjohn Cocke and Daniel Slotnick of IBM described one of the first uses of parallel computing in a memo about numerical analysis. A number of early computer systems supported parallel computing, including the IBM MVS series (1964-1995), which used threadlike tasks the GE Multics system (1969), a symmetric multiprocessor the ILLIAC IV (1964-1985), the most famous array processor and the Control Data Corporation (CDC) 7600 (1971-1983), a supercomputer that used several types of parallelism. 

The coupled, first-order Hamiltonian equations of motion for the various systems studied were integrated numerically on either a CDC 7600 or a DEC VAX 11/780 digital computer using a variable step-size, fifth-order Adams-Moulton predictor-corrector integration technique As a test of accuracy, rate constants were computed for... 

Table III shows the results achieved for the actual Monte Carlo inner loops (level 0) detailed in Table I. The results for these inner loops show the AP 190L executing at 0.6 times the speed of the CDC 7600, or at 2.5 times the speed of the IBM 370/168. Table IV compares the AP 190L timings for the level 1 outer loop with those for the CDC 7600, IBM 370/168, and PRIME 400 computers. The execution time, T, of the level 1 loop is a non-linear function of the number of particles considered. It is given by the equation...

---