Reduced instruction set for computing

The mid-range workstations offer 10 to 15 MIPS performance, with numeric processing at 1 to 2 MFLOPS, drawing rates of 200,000 to 400,0(X) v/s and 20,000 p/s. Their higher performance arises from so-call RISC architecture (Reduced Instruction Set CPU), which allow the computer to perform fewer tasks per CPU instruction. They also utilize faster, proprietary graphics display processors and larger display memory, which allows more colors and multiple windows. These units cost between 30,000 and 70,000, and they probably make up the bulk of recent CAMD woikstation purchases. They are suitable for solid model display and manipulation of small molecules, and wireframe and dot-surface display of macromolecules. Molecular mechanics and dynamics calcinations on small molecules and ensembles can be run in batch mode on these machines, and the results can be displayed and manipulated interactively. 

Reduced instruction set computer (RISC) A design style where instructions are implemented for only the most frequently executed operations addressing modes are limited to registers and special load/store modes to memory. 

In RISC (reduced instruction set computer) research, an efficient technique has been proposed to enhance the utilization of both function units and buses. Fig 3 shows the timing diagram of such an architecture. Data transfer operations (read or write) and function unit operations are performed in parallel during each control step. Therefore, the clock period is reduced to rr ax top, U + ))- However, this gain in speed is not free. Note that for each operation its three micro-operations are performed across three consecutive control steps. In order to hold the operands across the step boundary, a latch is needed in every input/output port of every function unit. 

The requirement for a simple instruction set was primarily motivated by the desire to observe the primitive operations of neural algorithms. Initial experimentation with various instruction sets indicated that the use of a reduced instruction set numbering around 8-12 instructions can satisfy most of the computational requirements of neural models. 

The first two rows of Table 1 make readily apparent the poor suitability of both ST0-3G and 3-21G for H-bonds the intermolecular R(00) distance is some 0.2 A too short. The 6-31G(d) set (also known as 6-31G" ) contains a better representation of the inner shells as well as polarization functions on O. The SCF distance of 2.971 A computed with this basis set is a substantial improvement over those from the smaller basis sets, STO-3G and 3-21G. Further improvements in the basis set make relatively minor changes in this distance. For example, addition of p-functions to H elongates the bond by 0.009 A, whereas augmentation of O by -f- functions (a diffuse sp-shell) reduces the distance by 0.007 A. It is instructive to note that the latter two effects are not additive. That is, one might naively expect a net bond elongation of 0.002 A to result from incorporation of both H p-functions and O -F functions by addition of the two latter effects. However, the 6-31 -F G(d,p) R (OO) distance reported in Table 1 is 2.988 A, 0.017 A longer than the 6-31G(d) value. 

---