Microprocessors: from desktops to supercomputers.

Continuing improvements in integrated circuit technology and computer architecture have driven microprocessors to performance levels that rival those of supercomputers-at a fraction of the price. The use of sophisticated memory hierarchies enables microprocessor-based machines to have very large memories built from commodity dynamic random access memory while retaining the high bandwidth and low access time needed in a high-performance machine. Parallel processors composed of these high-performance microprocessors are becoming the supercomputing technology of choice for scientific and engineering applications. The challenges for these new supercomputers have been in developing multiprocessor architectures that are easy to program and that deliver high performance without extraordinary programming efforts by users. Recent progress in multiprocessor architecture has led to ways to meet these challenges.

Small shared-memory multiprocessors.

Multiprocessors built from today's microprocessors are economically attractive. Although we can use these multiprocessors for time-sharing applications, it would be preferable to use them as true parallel processors. One key to achieving efficient parallel processing is to match the communications capabilities of the multiprocessor to the communications needs of the problem. The other key is improved parallel programming systems. If these are achieved, then efficient parallel processing can be approached from both ends by providing more communications capability in the hardware and restructuring the problem to reduce the communications requirements.

Penicillin V and rifampin for the treatment of group A streptococcal pharyngitis: a randomized trial of 10 days penicillin vs 10 days penicillin with rifampin during the final 4 days of therapy.

To improve the bacteriologic and clinical cure rates of streptococcal pharyngitis, 79 children were randomly assigned to receive penicillin V alone for 10 days (39 patients) or penicillin for the same duration and rifampin during the last 4 days of penicillin therapy (40 patients). Eleven patients given penicillin had evidence of bacteriologic failure (including eight with relapse of clinical illness) on repeat cultures done 4 to 7 days after treatment, whereas there were no failures in children given combination therapy (P = 0.0015). All eight symptomatic children improved with penicillin-rifampin therapy and subsequent cultures were negative, whereas three asymptomatic children continued to harbor group A streptococci even after combination therapy. Antibody response by antistreptolysin O or antideoxyribonuclease B assay was seen in 50.6% of patients; the antibody responses in both groups were comparable. These results show that addition of rifampin to the penicillin regimen improves the clinical and bacteriologic cure rates in children with streptococcal pharyngitis.

A technique for estimating the position of the oxygen-hemoglobin dissociation curve.

A nomogram was constructed which allows estimation of the P(50) value from the Po(2) and per cent O(2) saturation of a single venous blood sample. There was excellent correlation between 50 estimated P(50) values obtained in 27 severely ill patients when compared with P(50) values determined from constructed OH-DC's (correlation coefficient 0.92). The mean of the differences between the estimated and determined P(50) values was 1.5 mm Hg with a standard deviation of +/-1.1, and the maximum difference was 4 mm Hg.