|
This format definitely has an advantage in that if you suspect displayModesMatch of doing something wrong, or otherwise just want to know what it is doing, you only need to set one breakpoint.
I guess both approaches have their merits.
But before we just go ahead and assume that this way is better than that way, let's see how C++ would have done this task. I found the results quite surprising.
To simplify, I used the following code snippet:
bool test1(int dim1, int dim2, int depth1, int depth2, int refresh1, int refresh2)
{
bool isEqDim = (dim1 == dim2);
bool isEqDepth = (depth1 == depth2);
bool isEqRefresh = (refresh1 == refresh2);
return isEqDim && isEqDepth && isEqRefresh;
}
bool test2(int dim1, int dim2, int depth1, int depth2, int refresh1, int refresh2)
{
if (dim1 != dim2)
return false;
if (depth1 != depth2)
return false;
if (refresh1 != refresh2)
return false;
return true;
}
void trialrig()
{
int dim1, dim2, depth1, depth2, refresh1, refresh2;
scanf("%i", &dim1);
scanf("%i", &dim2);
scanf("%i", &depth1);
scanf("%i", &depth2);
scanf("%i", &refresh1);
scanf("%i", &refresh2);
bool b1_1 = test1(dim1, dim2, depth1, depth2, refresh1, refresh2);
bool b2_1 = test2(dim1, dim2, depth1, depth2, refresh1, refresh2);
if (b1_1)
printf("b1 is true\n");
if (b2_1)
printf("b2 is true\n");
}
The scanf's were important, because if they're not there, my compiler just optimized both the test functions out of existence.
During compiling, some of these were inlined, so I have to compensate somewhat. So for simplicity, assume that both code blocks below are prefixed with these instructions:
mov eax, DWORD PTR _dim1$[esp+88]
mov ecx, DWORD PTR _dim2$[esp+88]
mov esi, DWORD PTR _depth1$[esp+88]
mov edi, DWORD PTR _depth2$[esp+88]
mov ebx, DWORD PTR _refresh1$[esp+88]
mov ebp, DWORD PTR _refresh2$[esp+88]
In release build, it produced the following for one of the two functions (excluding the preamble above):
cmp eax, ecx
jne SHORT $LN7@test12
cmp esi, edi
jne SHORT $LN7@test12
cmp ebx, ebp
jne SHORT $LN7@test12
mov dl, 1
jmp SHORT $LN8@test12
$LN7@test12:
xor dl, dl
$LN8@test12:
And the following code for the other function:
cmp eax, ecx
je SHORT $LN11@test12
xor bl, bl
jmp SHORT $LN9@test12
$LN11@test12:
cmp esi, edi
je SHORT $LN10@test12
xor bl, bl
jmp SHORT $LN9@test12
$LN10@test12:
cmp ebx, ebp
sete dl
$LN9@test12:
Now just to drive the point home, I'm not going to tell you which of those two code blocks were produced by which function, because as you can see, they're quite similar.
Now, for the first snippet, starting at the cmp, the longest path of execution is 8 instructions, and the shortest path of execution is 3 instructions. For the second snippet, the longest path of execution is 6 instructions, and the shortest path is 4 instructions.
So to summarize, one approach takes 3-8 instructions, whereas the other takes 4-6 instructions.
So if this code was in a real tight loop somewhere, which approach is actually faster depends really on what you expect the outcome to be.
Never assume that you know how the compiler/bytecode interpreter is going to optimize things, and never optimize things without profiling your code to see where the real bottle necks lie.
|
|
|
|
|
Wow this information is interesting. Thx for the effort. I could be wrong but i can't see the solution with 1 statement anywhere among your tests functions. I presume that using that solution would be even faster.
|
|
|
|
|
It's all in the first block of code. test1() vs. test2().
The examples are a bit contrived, and might not look like the original question anymore. For one thing, I just assume that you magically know the result of "getWidth()", etc. Basically, I try to pit the concept of declaring boolean variables versus returning false early against each other.
|
|
|
|
|
i could be saying dumb sh*t here but would it be faster to not use the variables and simply return the whole thing?
|
|
|
|
|
It's hard for me to tell what the answer would be inside a Java interpreter. I suspect that the difference will be small.
I doubt that declaring local variables vs. not declaring will actually make a difference in C/C++. Local variables get assigned machine registers, and they may actually not require stack locations at all.
In fact, with a decent optimizing compiler, the following snippets will compile to the same code:
void fx(int x)
{
doSomethingWithX(x);
}
and
void fx(int x)
{
int descriptionForX = x;
doSomethingWithX(descriptionForX);
}
The reason is that the 'descriptionForX' variable will be coalesced so that it uses the same register as x, and will subsequently be removed by the compiler.
|
|
|
|
|
That sounds reasonable to me. Your knowledge seems impressive. Nevertheless I think it is strange to return a boolean from the result of any if structure. It just seems strange to me.
Just one remark on the variable/nonvariable matter. I don't know about C/C++ but in java when you combine boolean expressions using the && operator, automatically when 1 value is false the other expression are skipped. That's why i would assume that it has the same advantage of being able to skip part of the calculations. I would think when using the variables, that advantage would be partially lost because you'd split up the calculations, this enlarging the calculations i'd think.
This is just theory i'm not sure of this
sorry if i'm not clear i'm having trouble expressing myself in english
|
|
|
|
|
All-in-all, I agree with you. I like tidying up the code as well...multiple return statements and complicated ifs do make code less clear. IMHO, however, I'd probably move these into their own methods within a class (let's name it DisplayModeAnalyzer). I would especially do this if these same conditions are used elsewhere in the code...then it could read something like:
public boolean displayModesMatch( DisplayMode mode1,
DisplayMode mode2 )
{
DisplayModeAnalyzer analyzer = new DisplayModeAnalyzer( mode1, mode2 );
boolean result = true;
if( analyzer.dimensionsNotEqual() )
result = false;
else if( analyzer.depthNotEqual() )
result = false;
else if( analyzer.refreshRateNotEqual() )
result = false;
return result;
}
Breaking it into methods like this increases the amount of code (unless you use these conditions elsewhere) but makes the intent a bit clearer when you scan the code (similar to what you were doing). The DisplayModeAnalyzer class, coded for the above, would also be highly unit-testable.
Note, as I think others said...those tests against the constants are very important. I actually like the clarity of your code better than the original, but not the logic...it breaks a fundamental rule of refactoring...NEVER change the logic on existing code. The reason for those constant tests is so that if it's Multi-depth, then even if the depths are equal, that condition would return false. Same for the refresh rate.
Kevin
|
|
|
|
|
if( analyzer.dimensionsNotEqual() )
result = false;
look at what ur writing here...
i'm not trying to insult you, but that just seems illogical to me.
<br />
analyzer.dimensionsNotEqual()<br />
this method returns a boolean value, this enabling you to simply write:
<br />
result = analyzer.dimensionsNotEqual();<br />
this was what bothered me the most when i posted the code. The fact that someone tests for a boolean value within a if structure, and then depending on the outcome returns true or false, that seems so strange to me.
if the above explanation isn't clear enough i'll explain a bit more below why this is so strange to me.
the contents00 if(boolean){contents00}else{contents01} are executed when the boolean value is true.
when the boolean is false the contents01 are executed.
When the only command within the contents00 or contents01 is a command to put a certain value within a boolean variable, you really are testing for no reason.
simply take the boolean value within the if structure, remove the if structure and directly put that value within that variable.
I believe when you write stuf like if(boolean00){boolean immaboolean = boolean00} it is called 'False selection' not sure how people call it in english though.
Hope i'm making my point clear here 
|
|
|
|
|
Ah, I see, so your main point was simply that using boolean conditions in ifs and then returning boolean is nonsensical. That's fair enough, so long as the operations aren't expensive and/or aren't frequent. Sometimes, as others pointed out, you do need to exit early for performance (i.e. if checking refresh rate is expensive and called frequently, then you would definitely not want to do it your way). Personally, though, I was more focused on the advantages of breaking things into methods than on the ifs.
So, more on my point of breaking it into methods, but also taking into consideration your main point...methods can meet your criteria...but additionally, meet the performance criteria of many of the other posters, e.g.
public boolean displayModesMatch( DisplayMode mode1,
DisplayMode mode2 )
{
DisplayModeAnalyzer analyzer = new DisplayModeAnalyzer( mode1, mode2 );
return analyzer.dimensionsEqual() && analyzer.depthEqual()
&& analyzer.refreshRateEqual();
}
By breaking it into methods and doing it this way it's still very readable, it meets your conditions of not having ifs to surround boolean returns, and it also satisfies the point that others had about checking all the conditions at the beginning of the method can reduce performance. If the dimensions are not equal, it will return false immediately without checking depth or refresh rate...thus slightly less expensive than checking all the conditions at the beginning of the method.
Thus, this has the same fail-early/"good performance" of the original "coding horror" you posted, while at the same time having the simplicity of your solution.
Kevin
|
|
|
|
|
the code you wrote evaluates every possible scenario and then returns a value.. The original code disqualifies the rest of the code and returns rather than proceeding. What if isEqualDepth takes 3 seconds to run.. every method call would take 3 seconds even when they obviously didnt match after the first if
Running every if and returning a combined boolean makes sense for validation but the logic doesnt translate to this situation at all..
DrewG MCSD .Net
|
|
|
|
|
Are you talking about the variables code or the 1 statement code?
When you are talking about the variables code you are right (but like 9999999... people already stated that, and that solution was but a compromise for greater readability)
If you are talking about the 1 statement code you are wrong.
|
|
|
|
|
lordofawesome wrote: boolean isEqualDimention = (mode1.getWidth() == mode2.getWidth() && mode1.getHeight() == mode2.getHeight());
boolean isEqualDepth = (mode1.getBitDepth() == mode2.getBitDepth());
boolean isEqualRefreshRate = (mode1.getRefreshRate() == mode2.getRefreshRate());
return (isEqualDimention && isEqualDepth && isEqualRefreshRate);
Actually (as a firmware developer), I found the original code quite reasonable.
The function was exited as quickly as possible, with as few calculations as possible.
The quoted code above performs ALL the calculations before exiting the function, doing a lot of (possibly) unnecessary work.
|
|
|
|
|
Pls read other posts, i'm getting tired of getting the same remark over and over again :p
|
|
|
|
|
CDP1802 wrote: It sure does its job, wich itself is not really complicated. So why don't you just post your more fitting version?
How about creating a function to check if any two of the three parameters are equal? Calling that function with a parameter from each display mode along with the "matches anything" constant would perform three 'equals' tests.
|
|
|
|
|
So what's wrong with that? I think it's the tidiest piece of code I have ever seen in Coding Horrors.
Phil
The opinions expressed in this post are not necessarily those of the author, especially if you find them impolite, inaccurate or inflammatory.
|
|
|
|
|
I must be missing something obvious. What's your point?
|
|
|
|
|
I think this is a code horror because all this could be done with 1 statement, this is the most performant way to do this AND with proper indenting the readability isn't compromised.
|
|
|
|
|
Ideally, yes, but there are exceptions... this isn't one of them.
|
|
|
|
|
lordofawesome wrote: I think this is a code horror because all this could be done with 1 statement, this is the most performant way to do this AND with proper indenting the readability isn't compromised.
I would like to see that one liner, that could be as quickly and easily understood as the original.
Assuming that DisplayMode has only the elements that are being tested in this routine (height, width, depth, etc.), I think would be a mistake, and error prone should DisplayMode not now or in the future, contain only those elements.
Flip the And/Or logic, swap != and == and remove the If's and you can do it in one return statement, but it wouldn't be as simple or quick to grasp.
Gary
|
|
|
|
|
public boolean displayModesMatch(DisplayMode mode1,
DisplayMode mode2)
{
return (mode1.getWidth() == mode2.getWidth() &&
mode1.getHeight() == mode2.getHeight()) &&
(mode1.getBitDepth() == DisplayMode.BIT_DEPTH_MULTI ||
mode2.getBitDepth() == DisplayMode.BIT_DEPTH_MULTI ||
mode1.getBitDepth() == mode2.getBitDepth()) &&
(mode1.getRefreshRate() ==
DisplayMode.REFRESH_RATE_UNKNOWN ||
mode2.getRefreshRate() ==
DisplayMode.REFRESH_RATE_UNKNOWN ||
mode1.getRefreshRate() == mode2.getRefreshRate());
}
Better? I don't think so.
Faster? Maybe.
Gary
|
|
|
|
|
How about this one?
return
mode1.getBitDepth() != DisplayMode.BIT_DEPTH_MULTI &&
mode2.getBitDepth() != DisplayMode.BIT_DEPTH_MULTI &&
mode1.getRefreshRate() != DisplayMode.REFRESH_RATE_UNKNOWN &&
mode2.getRefreshRate() != DisplayMode.REFRESH_RATE_UNKNOWN &&
mode1.getBitDepth() == mode2.getBitDepth() &&
mode1.getRefreshRate() == mode2.getRefreshRate();
I think this should be better and faster.
See you
|
|
|
|
|
_Erik_ wrote: How about this one?
return
mode1.getBitDepth() != DisplayMode.BIT_DEPTH_MULTI &&
mode2.getBitDepth() != DisplayMode.BIT_DEPTH_MULTI &&
mode1.getRefreshRate() != DisplayMode.REFRESH_RATE_UNKNOWN &&
mode2.getRefreshRate() != DisplayMode.REFRESH_RATE_UNKNOWN &&
mode1.getBitDepth() == mode2.getBitDepth() &&
mode1.getRefreshRate() == mode2.getRefreshRate();
I think this should be better and faster.
Faster. Absolutely NOT BETTER.
Only faster because you skip half the elements to test  .
You need to check all the conditions in the original code, including height and width  .
Also your test is just plain wrong.
The original...
if (mode1.getBitDepth() != DisplayMode.BIT_DEPTH_MULTI &&
mode2.getBitDepth() != DisplayMode.BIT_DEPTH_MULTI &&
mode1.getBitDepth() != mode2.getBitDepth())
{
return false;
}
Assume the case of mode1.getBitDepth() equals DisplayMode.BIT_DEPTH_MULTI.
The original code *might* return TRUE in this condition, depending on subsequent testing of RefreshRate.
Your code always returns FALSE under this condition.
![Rose | [Rose]](https://codeproject.global.ssl.fastly.net/script/Forums/Images/rose.gif)
Gary
|
|
|
|
|
Yes, you're right. I think I misunderstood the initial post. I thought it should return false if one of the modes was BIT_DEPTH_MULT or REFRESH_RATE_UNKNOWN. Instead, what I understand now is that bit depth matches if both are equal or one of them is BIT_DEPTH_MULTI, and refresh rate matches if both are equal or one of them is REFRESH_RATE_UNKNOWN. Am I right? I am sure you agree that looking at the original code does not help too much to figure out what it has to do, and that is exactly what we all are talking about here:
return mode1.getWidth() == mode2.getWidth() && mode1.getHeight() == mode2.getHeight() &&
(mode1.getBitDepth() == mode2.getBitDepth() ||
mode1.getBitDepth() == DisplayMode.BIT_DEPTH_MULTI ||
mode2.getBitDepth() == DisplayMode.BIT_DEPTH_MULTI)
&&
(mode1.getRefreshRate() == mode2.getRefreshRate() ||
mode1.getRefreshRate() == DisplayMode.REFRESH_RATE_UNKNOWN ||
mode2.getRefreshRate() == DisplayMode.REFRESH_RATE_UNKNOWN);
I think this would be much more readable, even without any comment explaining what it has to do.
Edit
That said, I think it would be still better to split this into three methods (sizeMatch, bitDepthMatch, refreshRateMatch), so displayModesMatch would still become much easier to read.
return sizeMatch(mode1, mode2) && bitDepthMatch(mode1, mode2) && refreshRateMatch(mode1, mode2);
You see, there are many ways to get the same result, and I think the given example here in the first post is a coding horror becouse it is one of the worst approaches.
See you.
modified on Monday, October 18, 2010 9:41 AM
|
|
|
|
|
Erik. A 2 vote? REALLY? Thanks buddy. I see you don't handle criticism very well.
The original code was very straight forward. Some developers don't like multiple returns. That does not make it a "horror".
Likely you did not read the comments in the code or analyze the code properly. I made this mistake upon first inspection, assuming I knew what it was doing, but did not.
Now, your latest example: Perform a routine, which performs 3 routines - that has to be the slowest rewrite that was presented in this thread. Loading and clearing the register stack 4 times. Wow! Too much overhead. Yes, clear, but doesn't belong in time-sensitive logic (if this is time-sensitive).
But I have to wonder how the bitdepth and refreshrate code would be written. You haven't gotten rid of the nuance, just move it and added some overhead. You'd have better comments?
In short, your final logic does the same as the original but is slower.
Gary
|
|
|
|
|
The 2 vote was another mistake of mine, sorry for that. I wanted to go to page 2 to see the original post, clicked the vote 2 instead, and forgot to make the correct vote to your post. I've just corrected it with the vote it really deserves, a 5.
I know my final logic does the same as the original but is slower. It is obvious. And it is much clearer, and this is also obvious. The sample I give just before does the same also, and is faster. Both of them improve the original in readability, and the first one also improves it in speed. If you had to manage a team of developers, some of them newcomers with very little experience, tell me, having the original code and the two samples I am giving, which one would you choose?
I would choose the last one, though I know it is slower, but I also know that the overhead is just negligible in this case, becouse this operation will not be used over and over again within de context of a long and complex batch process.
I don't mind to have several "return" in the same method... if it improves readability and/or performance. In the case presented here, it does not improve readablity neither performance, so that is the reason why I consider it a horror. Nobody is obligated to agree, I am just sharing my point of view.
Edit
Sorry again, I was forgetting the las part. The implementation for bitdepth and refreshrate is given just before, but like you wonder how they should be, I will give some extra clues:
return mode1.getWidth() == mode2.getWidth() && mode1.getHeight() == mode2.getHeight() &&
(mode1.getBitDepth() == mode2.getBitDepth() ||
mode1.getBitDepth() == DisplayMode.BIT_DEPTH_MULTI ||
mode2.getBitDepth() == DisplayMode.BIT_DEPTH_MULTI)
&&
(mode1.getRefreshRate() == mode2.getRefreshRate() ||
mode1.getRefreshRate() == DisplayMode.REFRESH_RATE_UNKNOWN ||
mode2.getRefreshRate() == DisplayMode.REFRESH_RATE_UNKNOWN);
Thank you
modified on Tuesday, October 19, 2010 9:28 AM
|
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
