| 
|
QuoteRef: engbJ5_1999
topics >
all references >
ThesaHelp:
ACM references a-e
ThesaHelp:
references e-f
Topic:
performance testing
Topic:
embedded systems
Topic:
program statistics
Topic:
intermediate representation of code
Topic:
functional side effects
Topic:
global declarations and variables
Topic:
local vs. global
Reference
Engblom, J., "Why SpecInt95 should not be used to benchmark embedded systems tools", Proceedings of the ACM SIGPLAN 1999 Workshop on Languages, Compilers, and Tools for Embedded Systems (LCTES'99), Atlanta GA, May 1999, pp. 96-103. Google
97 ;;Quote: compared standalone embedded systems written in C with the SpecInt95 benchmark (go, lisp, jpeg, etc.)
97 ;;Quote: compared intermediate code instead of C code; captures the essential properties of a program
98 ;;Quote: embedded programs use unsigned 8/16-bit data; SpecInt95 programs use signed and unsigned 32-bit data
98+;;Quote: embedded programs use logic and arithmetic instructions; SpecInt95 programs use 5x as many arithmetic instructions
98+;;Quote: 35% of embedded functions are void f(void); i.e., for side effects
99 ;;Quote: most data (by amount) is global for SpecInt95 and embedded programs
ThesaHelp: ACM references a-e (259 items)
ThesaHelp: references e-f (168 items)
Topic: performance testing (8 items)
Topic: embedded systems (26 items)
Topic: program statistics (27 items)
Topic: intermediate representation of code (29 items)
Topic: functional side effects (11 items)
Topic: global declarations and variables (33 items)
Topic: local vs. global (29 items)