2.08 and Incompatible Battle Reports

[AStott]

Eh... why bother with all the complicated methods of ensuring the calls happen in the right order. Instead, change:
if penetration+2d6 < MR+2d6

To:
if penetration < MR+2d6-2d6

Since both of the random calls are on the same side of the equation, the defined precendence order will ensure they are called in a consistent manner.

[Arryn]

Originally posted by AStott:
Eh... why bother with all the complicated methods of ensuring the calls happen in the right order. Instead, change:
if penetration+2d6 < MR+2d6

To:
if penetration < MR+2d6-2d6

Since both of the random calls are on the same side of the equation, the defined precendence order will ensure they are called in a consistent manner.

The problem comes in that the compiler's optimization will substitute the same call to the random number function for both die rolls. It won't make the two rand() calls the coders intend. What it does is make one call and plug the same value into both places. The optimizer does not know that in this circumstance, two calls to the same function do not return the same value.

[Peter Ebbesen]

Originally posted by Arryn:
The problem comes in that the compiler's optimization will substitute the same call to the random number function for both die rolls. It won't make the two rand() calls the coders intend. What it does is make one call and plug the same value into both places. The optimizer does not know that in this circumstance, two calls to the same function do not return the same value.

That would be an exceedingly poorly written optimizer. I certainly did not understand that as the original problem. I am certain that any decent compiler would make the two rand calls.

As I understood it, the real problem was that in the expression "a < b" the order of evaluation of "a" and "b" is undefined [Ansi-C, and its derivatives, with a few exceptions only specifies the order of evaluation for operators, not for sub-expressions]. Either side "a" or "b" can be evaluated first.

Given that the seed is the same, assume the RNG will return R1 and R2 over the next two calls in that order. Then the inequality:

(penetration+2d6 < MR+2d6)

can legally be compiled such that the evaluation is either of the following:
penetration+R1 < MR+R2 (left hand side evaluated first)
penetration+R2 < MR+R1 (right hand side evaluated first)

- Which may or may not give different return values.

Changing the inequality as AStott suggested, to
penetration < MR+2d6-2d6
would not necessarily solve the problem either, as the order of evaluation of the two 2d6 function calls is not defined either. (The order of the addition and subtraction is, but not the order of evaluation of the sub-expressions)

If you are in doubt, split such expressions over multiple commands independently evaluated. A bad optimizer may still hurt you, but at least you won't be bitten by the "undefined evaluation order", which is nobody's fault but your own. Or, to quote Kernigham & Ritchie:

The moral is that writing code that depends on order of evaluation is a bad programming practice in any language. Naturally, it is necessary to know what things to avoid, but if you don't know how they are done on various machines, you won't be tempted to take advantage of a particular implementation.

[ February 25, 2004, 23:23: Message edited by: Peter Ebbesen ]

[Arryn]

A cogent, well-stated reply, Peter. The quote by K&R was what I tried to allude to in an earlier posting.

BTW, it's not so much that the opitimizer may be "bad" than that it may be using "overly aggressive" choices. I remember the Borland compiler dev team in the early 90s having many headaches over just how far they should go. In those days, Borland and MS kept trying to out-do each other via how powerful their optimizations were. After a few cycles of this we started seeing cases of too much optimization.

A careful review of what all the default optimization switches do should be undertaken by anyone that's serious about code-writing, especially cross-platform code, to avoid potential pitfalls. Hell, one should also look at the linker's switches too.

[alexti]

Originally posted by Arryn:
The problem comes in that the compiler's optimization will substitute the same call to the random number function for both die rolls. It won't make the two rand() calls the coders intend. What it does is make one call and plug the same value into both places. The optimizer does not know that in this circumstance, two calls to the same function do not return the same value.

Consider the following:

code:

---

  void print_blank_line { printf("\n"); }

  

  void print_2blank_lines()

  {

    print_blank_line();

    print_blank_line();

  }

---

Do you think compiler/optimizer will call print_blank_line just once? The similar situation will happen in the following:

code:

---

  std::vector<int> x;



  void foo()

  {

    x.push_back(1);

    x.push_back(1);

  }

---

Will push_back be called only once (parameters are the same)?

If any compiler does make one call instead of 2 in these cases, you're not likely to build anything usable with it. So it's safe to assume that any common compiler doesn't have this problem.

[alexti]

Originally posted by Taqwus:
*scratches head*
'volatile' may also help. The MSDN C++ Language Reference states, "Objects declared as volatile are not used in optimizations because their value can change at any time"

Volatile won't help here, the idea behind volatile is that if you need to read/write into the some variables of one process from another process (after passing address by some IPC means), compiler/optimizer won't know that you plan to use the variable in such a way and may put it into the register. So volatile is just used to prevent it from happening.

[Arryn]

Alexti, your examples are not the same. In the first example: 1) they have void returns and invoke I/O, which the optimizer treats differently. 2) the statements are on separate lines, and IIRC there are various scoping rules to what the compiler will attempt to "consolidate" when it goes to generate machine code.

For the second example: it depends on the switches used. I have seen (though not recently) compilers that would, indeed, consolidate those two statements when you viewed generated assembler code.

However, the most obvious thing you said that bears careful review is the statement "... it's safe to assume ...". It's never safe to assume anything. That's the first step towards making mistakes ...

We've flown the Space Shuttle in cold weather before, and it's only a few degrees colder now, the Challenger should be okay.

It's only a 2-pound chunk of foam. How can that damage reinforced carbon fiber? It probably shattered into dust on impact with the Columbia's wing.

The list of assumptions people make that lead to bad results has a long and inglorious history.