31 Dec
2017
31 Dec
'17
6:56 p.m.
On Dec 31, 2017, at 12:20 AM, Rudi Blom
<rudi.j.blom(a)gmail.com> wrote:
.With the
Compaq C compiler and HP-UX ANSI C I mostly get pages of warning and a
few errors. By the time I 'corrected' what I think is relevant some
nasty coredumps tend to disappear :-)
I had to chuckle when we read these two lines. As Paul I’m sure also remembers and
mentioned about the 32/64 bit issues, when we released Alpha there we very few to zero
tools available to help find errors in ISV or customer created C code that was caused by
assumptions of size. As you point out with the new ‘Gem’ compilers a great deal of work
was spent by Paul and his brothers and sisters in the compiler group putting in just those
messages. For C++ it was worse than C because the language was so new at the time few
tools for it existed. So one of our engineers, Judy Ward, lead the effort to make the C++
front end be extremely useful and offered extremely good errors and warnings (she also had
worked on the C FE before that).
When people complained about the compiler before no so “noisy” my response was “Listen to
Judy’s advise. She’s seeing something you are not and she knows more about C and C++ that
all of the rest of us.”
We discovered a curious thing. The ISVs reported way fewer bugs after the Alpha port
because Judy’s messages forced them to clean up long standing issues that were silently
causing problem on other systems. I’ve always said Alpha C and C++ compilers was the
greatest gift to the Sparc ISVs there was.
Like you to this day, except for possibly Gimple’s Flexilint product, the old DEC
compilers are still the best tools I have ever used to clean up code.
I’ve reminded and thanked Judy for this many times when I seen her. That was a labor of
love by some folks that really cared to make a great product as useful as it could be.
Clem