Explore chapters and articles related to this topic
Math Unit Architecture and Instruction Set
Published in Julio Sanchez, Maria P. Canton, Software Solutions for Engineers and Scientists, 2018
Julio Sanchez, Maria P. Canton
In Table 7.5 notice that if no explicit operand is present in the mnemonic, the math unit operates as a pure stack machine. In this case the source operand is assumed to be in ST and the destination in ST(1). After performing the calculation the result is stored in ST(1) and the stack is popped, effectively replacing both operands with the result. Perhaps a more reasonable way of implementing a classical stack operation is to use an operand in the form ST(1),ST and the pop mnemonic form of the opcode (see Table 7.5). For example, in the instruction FADDP ST(1), ST
Computer Architecture — an Introduction
Published in K. S. Fu, Ichikawa Tadao, Special Computer Architectures for Pattern Processing, 1982
C. V. Ramamoorthy, Benjamin W. Wah
A microprogram computer can also be used to interpret high level languages. As early as 1953, investigations were made on the influence of programming techniques on the design of computers.18 Subsequently, computers have been designed for specific high level languages such as ALGOL 60, FORTRAN, EULER, PL/1, APL, and SNOBOL. The technique of using microprogramming to execute high level languages consists of translating the high level language program into an intermediate interpretive language or Directly Executable Language (DEL)17 program that can be executed directly using microprogram. The compiler for doing this translation can be written in the DEL or it can be implemented directly using microprogram such as the experiment of Weber in the compilation of EULER.51 The high level language may coincide with the DEL, in which case no compilation is necessary, and the high level language can be executed directly. An example of this is the microprogrammed FORTRAN computer designed by Melbourne and Pugmire.25 Since the performance of the system depends on the design of the DEL, it is important that the interpretation of the DEL be as efficient as possible and the DEL be designed to facilitate easy translation. The DEL should allow efficient code generation and require a minimal amount of space for DEL program representation. Further, the limitation on the resources in the host computer should not affect the characteristics of the DEL. Due to the efficiency reasons, it is sometimes difficult to design a universal DEL at a level higher than the machine language level. Riegel et al.38 observed the need to provide specific interpretative languages for various high level languages. The Burroughs B1700 computer actually provides a series of interpretative S languages, operated under the control of microprograms in a writeable control store, one each for FORTRAN, BASIC, RPG, and COBOL. Besides using a microprogrammed interpreter, it is also possible to provide direct execution of high level languages via the use of a stack or via direct hardwiring. The stack machine is discussed in Section III. Direct hardwiring, which is quite inflexible, is represented by the effort of Bashkow in the implementation of the FORTRAN machine.5
Qualification of NSTX-U Inner TF Bundle Using Hi-Fidelity Models
Published in Fusion Science and Technology, 2021
Yuhu Zhai, Thomas Willard, Charles Neumeyer, Stefan Gerhardt, Peter Titus, Mark Pauley, Steve Raftopoulos, Robert Ellis, Richard Hawryluk
The National Spherical Torus eXperiment (NSTX) is a low-aspect-ratio spherical torus optimized for plasma confinement in a machine of its compact size.1 The NSTX Upgrade (NSTX-U) is an essential science facility for U.S. fusion innovation as it provides access to new physics that may answer critical fusion science questions. A central core of NSTX-U is the center stack upgrade that expands the NSTX operational space and physics exploration for next-step spherical tokamak facilities. With a new central magnet assembled in a new center stack machine core and a second neutral beam for heating, NSTX-U will generate up to two times higher magnetic field, plasma current, and heating power, which is equivalent to four times of the heat flux and five times of the plasma pulse length.2Figure 1 presents the NSTX-U machine core, inner toroidal field (TF) bundle, and second neutral beam.