Parallel Computer Centre
FMP autotasking translation phase, ie invokes Fortran multitasking translator to translate Autotasking directives for input to cft77 compiler.
CFT77 actual compiler ie compiles Fortran source code into relocatable object code which can loaded by segldr into an executable file.
SEGLDR segment loader which converts relocatable object code into an executable binary file.
options - specify the invocation of one or more components
cf77 -Z invokes the preprocessor and the mid processor in the following ways:
-Zp - invokes both fpp and fmp
-Zc - bypasses both fpp and fmp (this is the default option)
-Zv - all phases except fmp
-Zu - all phases except fpp
Example sequence of events invoked by the following command:
cf77 -Zp prog.f
fpp prog.f > prog.m
fmp prog.m > prog.j
cft77 prog.j
rm prog.m prog.j
segldr prog.o
rm prog.o
Whole system cf77 command
cf77 -Zp -Wd"fpp options" -Wu"fmp options" -Wf"cft77 options" prog.f
cf77 -Zp -o prog compiling system options
-Wd"-ei" dependency analyser options
-Wu"-x" translator options
-Wf"-em" compiler options
-Wl"-i dirs" loader options
file.f file1.f input filenames
Files within the compiling system
*.f = source
*.l = listing
*.s = CAL ie Cray Assembly Language
*.o = compiled code
*.m = code containing Autotasking/microtasking directives
*.j = Fortran code previously processed by fmp
*.a = library files
*.F = code to be processed by Generic preprocessor GPP
FPP and FMP are two phases which can significantly improve a programs performance. CFT recognises many parallel constructs automatically and compiles them for multitasking without requiring additional user input ie autotasking. Autotasking cannot do any harm in that it merely decides if the program may be broken down into separate tasks.
This operates in two modes either explicit or automatic. When a program unit calls a subprogram the called subprogram is incorporated (within the resulting binary program) into the calling program unit where the call occurred. This eliminates the calling overhead and allows vectorization of loops which would otherwise be prevented from vectorizing due to the external call. A problem with inlining is that it may cause an unacceptable increase in the size of the program.
CROSS-COMPILING
This is compiling a program on one system to execute on another. The target system is specified by cpu and hdw arguments either on the complier line (using -C) or directly to the operating system (using the TARGET environment variable).
The various categories of compiler directives are, vectorization control, scalar optimization control, listable output control, localised use of features specified by command line options and storage specifications.
FPP and FMP generate directives used by the compiler beginning with CDIR@ whereas the user may use CDIR$, in columns 1 to 5, leaving 6 blank and then columns 7 to 72 are used for the directives.
A directive in the source program applies only to the program unit in which it appears whereas it may also be specified on the command line and thus apply to the entire compilation. Generally the CDIR$ directives for features override the command-line option for the same feature.
Unwinding makes several copies of the body of a loop resulting in straight code which is then vectorizable.
Unrolling creates a new version of the loop at the scheduling level not in the source but does not remove the original. The new copy consists of n copies of the loops computations ie n iterations. This reduces loop overhead and improves scheduling and register assignment in the new unrolled loop.