C / C++ / MFC

30-Sep-09 12:57

I'm trying to replicate the recipient text control from Outlook which converts the text typed into objects that contain the formats CF_TEXT, CF_UNICODETEXT and MsOffice8Recipent. I've created an IDataObject with the CF_TEXT format but I can't work out how to get it into the RichEdit control as an object. There is a sample on MSDN for inserting bitmaps that uses OleCreateFromFile() to create the object but I can't work out which OleCreate function to use for my object. OleCreateStaticFromData() returns invalid clipboard format and OleCreateFromData() generates the following exception: 'Unhandled exception at 0x7730de64 (ntdll.dll) in acc3st.EXE: 0xC0000005: Access violation reading location 0x0023ffff'. Can anyone suggest what I'm doing wrong?

Richard MacCutchan30-Sep-09 13:34

Richard MacCutchan

30-Sep-09 13:34

I was going to comment on your question, but after checking the picture on your homepage, I think you are a wonderful and generous person, whose contribution to society is immeasurable!

Steve Thresher30-Sep-09 13:54

30-Sep-09 13:54

Would you care to elaborate on that most bizarre response?

Richard MacCutchan30-Sep-09 13:59

Richard MacCutchan

30-Sep-09 13:59

It's late, and the gun is scary! Sorry Steve, stupid English (feeble attempt at) humour!

Steve Thresher30-Sep-09 14:05

Re: RichEdit Controls / Embedded Objects but seriously

30-Sep-09 14:05

The picture was taken on while on my brothers stag week and it's the first and only time I've fired a real gun. I'd no idea it would elicit that kind of a response!

Richard MacCutchan30-Sep-09 23:26

Richard MacCutchan

30-Sep-09 23:26

The only one of these functions I ever used was OleLoadPicture() which I used to get a JPEG image loaded and displayed. This required the file to be read into memory first and then accessed via a LPSTREAM pointer.

You may find that OleLoadFromStream() offers similar capabilities. To be brutally frank I don't fully understand these functions, but I just did a lot of poking around until I got it to work.

Re: RichEdit Controls / Embedded Objects but seriously

Steve Thresher1-Oct-09 0:03

Re: RichEdit Controls / Embedded Objects but seriously

1-Oct-09 0:03

Thanks for the info. It sounds like I might be able to use the OleLoad() function to do what I want. Someone really ought to write a book on what's going on inside OLE Smile | :)

Gary R. Wheeler1-Oct-09 1:19

Gary R. Wheeler

1-Oct-09 1:19

They did. It's called The NecronomiCOM.

Software Zen: delete this;
Fold With Us![^]

float vs double - tricky performance issue [modified]

Dan Neely1-Oct-09 2:25

Dan Neely

1-Oct-09 2:25

Silly Hoplophobe. Roll eyes | :rolleyes:

The latest nation. Procrastination.

C^hris L^osinger30-Sep-09 10:50

30-Sep-09 10:50

(this is a long one, i apologize)

i'm working on an image filter. the basic operation is:

1. run across a row of pixels (one BYTE per component); perform a calculation and store the result in an array of floats. the output array is the same width as a pixel row.

2. run across the same row, but in the opposite direction; perform a similar (but not identical) calculation. store the results in a different array of floats.

3. sum each pair from the two float arrays and store the result in a temporary float image of the same dimensions as the input image, but rotate the output 90 degrees. in other words: output rows as columns in the temp image.

4. using the same basic method as 1 and 2, process the floating point temp image. sum the results and write them to an output 8-bit image.

so, again: there are two calculation loops and a summation loop per row. after all input rows are done, the process is repeated using the temp as input.

Loop over 8-bit Rows
   Loop over Column[y] left to right => tempRow1
   Loop over Column[y] right to left => tempRow2
   tempRow1 + tempRow2 => temp f.p. image row[y] // 90 deg rotation

Loop over temp f.p. Rows
   Loop over Column[y] left to right => tempRow1
   Loop over Column[y] right to left => tempRow2
   tempRow1 + tempRow2 => output 8-bit image row[y] // -90 deg rotation

just for reference, here's the first calculation loop:

// first four pixels are handled outside the loop.
// pCurPix is a pointer to the source image (BYTEs, variable number of channels).
// pTempPos is an array of floating point values
// the two factor arrays are floating points, too.
for (x=4;x < width;x++)
{
   pTempPos[x] =
     numerator_factors_positive[0] * pCurPix[0]   
   + numerator_factors_positive[1] * pCurPix[-iChannels]
   + numerator_factors_positive[2] * pCurPix[-2 * iChannels]
   + numerator_factors_positive[3] * pCurPix[-3 * iChannels]
   - denominator_factors_positive[1] * pTempPos[x - 1] 
   - denominator_factors_positive[2] * pTempPos[x - 2]
   - denominator_factors_positive[3] * pTempPos[x - 3] 
   - denominator_factors_positive[4] * pTempPos[x - 4];

   pCurPix+=uChannels;
}

that's the first loop. the third loop looks identical, except that pCurPix is a pointer to a floating point value in the third loop - it is a BYTE pointer here. the 2nd and 4th loops are very similar to that and are also identical to each other - again, except for the pCurPix data type.

also, i wrote this code as a template so i can switch the type of the floating point data from float to double, for testing (the "factor" arrays, the temp row buffers and the temp image).

a little more info:

one of the parameters ("sigma") to the function is used to set the values in those factors array. and the algorithm is constant complexity with respect to that parameter - sigma changes the values that pixels are multiplied by, not the number of times the calculations happen. the only thing that influences the amount of calculations performed is the size of the input image. in theory...

another parameter is the number of color channels in the input image (1=grayscale, 3=RGB, 4=RGBA, etc.)

and finally here's the problem! Laugh | :laugh:

:

when:
1. the class is using floats for the f.p. data type
2. the image is a single channel
3. the value of sigma is near 3...

the third loop (again, which looks exactly like what i've posted above) slows down to where it's literally ten times slower than all the other loops. as i move sigma away from three, the performance quickly goes to where it should : by 6, loop #3 is as fast as the rest, and they all stay the same speed as far as i can tell, for all other values of sigma: 50 is as fast as 6, and 70 is as fast as 6.

so it would seem the solution is to use doubles. but an array of doubles is 2x as big as an array floats. and, even worse, the float version of this is 2x faster than the double version ! Dead | X|

here are the overall timings for the float version (sigma 1st col, time for 50 reps, 2nd col):

0.10 0.44
0.60 0.56
1.10 0.76
1.60 0.80
2.10 1.29
2.60 1.48 -- spike, around 3.0
3.10 1.44
3.60 1.25
4.10 0.97
4.60 0.66
5.10 0.45
5.60 0.39
6.10 0.34
6.50 0.34

.. and then it stays at 0.34s until sigma = 93.5, when it totally blows up and does this:

93.00 0.34
93.10 0.36
93.20 0.34
93.30 0.34
93.40 0.34
93.50 27.22
93.60 27.38
93.70 27.19
93.80 0.34
93.90 0.36
94.00 0.36

these timings are on a Core2 2.4MHz. but i can duplicate the slowdown on a single-core Pentium D 2.8.

anybody have any idea what could be going on?

update: ok, 93.5 issue is when some of the array values go to infinity... i don't see anything like that at 3.0, though.

modified on Wednesday, September 30, 2009 4:59 PM

harold aptroot30-Sep-09 11:15

harold aptroot

30-Sep-09 11:15

Odd, according to the manual the speeds of fmul fadd and fsub are the same for all normal inputs, which is everything except denormals infinities and NANs.
Have you checked for denormals?

edit: it changes a little if you're using SSE, but not much, I would still check for denormals just in case

C^hris L^osinger30-Sep-09 11:19

30-Sep-09 11:19

yeah, i've been looking for that. it was blowing up at sigma = 93.5 because of a div by zero in the factors calculations (which put a bunch of #INFs and #INDs in the calcs). but everything looks reasonable in the sigma=3 range.

Re: float vs double - tricky performance issue [modified]

TimothyPMoore30-Sep-09 11:56

TimothyPMoore

30-Sep-09 11:56

Any chance you can show your code that includes your use of the sigma function parameter ? Does your code produce the correct values ?

C^hris L^osinger30-Sep-09 12:01

30-Sep-09 12:01

sure.

here's most of it:

void CalcIIRFactors (FloatType sigma)
{
   // constants from eq 38

   const FloatType b0 = (FloatType)-1.783;
   const FloatType b1 = (FloatType)-1.723;
   const FloatType w0 =  (FloatType)0.6318;
   const FloatType w1 =  (FloatType)1.997;

   const FloatType b0OverSigma = b0 / sigma;
   const FloatType b1OverSigma = b1 / sigma;
   const FloatType w0OverSigma = w0 / sigma;
   const FloatType w1OverSigma = w1 / sigma;

   const FloatType pi = (FloatType)acos(-1.0);
   const FloatType scale = sqrt (2 * pi) * sigma;
   const FloatType a0 = (FloatType)1.680 / scale;
   const FloatType a1 = (FloatType)3.735 / scale;
   const FloatType c0 = (FloatType)-0.6803 / scale;
   const FloatType c1 = (FloatType)-0.2598 / scale;

   // eq 21
   numerator_factors_positive [0] = a0 + c0;
   numerator_factors_positive [1] =
 (exp(b1OverSigma)*(c1*sin(w1OverSigma)-
 (c0+2*a0)*cos(w1OverSigma)) +
 exp(b0OverSigma)*(a1*sin(w0OverSigma) -
 (2*c0+a0)*cos (w0OverSigma)));

   numerator_factors_positive [2] =
 (2 * exp(b0OverSigma+b1OverSigma) *
 ((a0+c0)*cos(w1OverSigma)*cos(w0OverSigma) -
 a1*cos(w1OverSigma)*sin(w0OverSigma) -
 c1*cos(w0OverSigma)*sin(w1OverSigma)) +
 c0*exp(2*b0OverSigma) + a0*exp(2*b1OverSigma));

   numerator_factors_positive [3] =
 (exp(b1OverSigma+2*b0OverSigma) * (c1*sin(w1OverSigma) -
 c0*cos(w1OverSigma)) + exp(b0OverSigma+2*b1OverSigma) *
 (a1*sin(w0OverSigma) - a0*cos(w0OverSigma)));

   numerator_factors_positive [4] = 0.0;

   // eq 22
   denominator_factors_positive [0] = 0.0;
   denominator_factors_positive [1] =
 -2 * exp(b1OverSigma) * cos(w1OverSigma) -
 2 * exp(b0OverSigma) * cos (w0OverSigma);

   denominator_factors_positive [2] =
 4 * cos(w1OverSigma) * cos(w0OverSigma) *
 exp(b0OverSigma + b1OverSigma) +
 exp(2 * b1OverSigma) + exp(2 * b0OverSigma);

   denominator_factors_positive [3] =
 -2 * cos(w0OverSigma) * exp(b0OverSigma +
 2*b1OverSigma) -  2*cos(w1OverSigma) *
 exp(b1OverSigma + 2*b0OverSigma);

   denominator_factors_positive [4] = exp(2*b0OverSigma + 2*b1OverSigma);

   int i;

   // FACTORS = 5
   for (i = 0; i < FACTORS; i++)
   {
      denominator_factors_negative[i] = denominator_factors_positive[i];
   }

   numerator_factors_negative[0] = 0.0;

   for (i = 1; i < FACTORS; i++)
   {
      numerator_factors_negative[i] =
 numerator_factors_positive[i] -
 denominator_factors_positive[i] *
 numerator_factors_positive[0];
   }

there's a little more after this, but it's working on things that aren't used inside the offending loop. and, yes, the values are correct. - even when slow, it's giving good results.

also, testing with finer precision, it looks like the slowdown isn't centered at 3.0 exactly, rather, it's looking more like sigma = 2.7 is the key. e ?? OMG | :OMG:

i wish i could post the whole thing, but... well, it's proprietary.

modified on Wednesday, September 30, 2009 6:11 PM

TimothyPMoore30-Sep-09 13:02

TimothyPMoore

30-Sep-09 13:02

I understand about the proprietary requirements.

Your code produces normal values for the numerator/demonimator values over the range of sigma that I you mentioned in my experiments.

The only suggestion I have at this point is can you instrument your runtime statistics at a finer levels to see what portions of the your calculations could be responsible to efficiency reduction.

If you find the solution it would be nice if you could post a follow-up to the thread.

Good luck.

Rick York30-Sep-09 13:29

Rick York

30-Sep-09 13:29

Since performance is an issue you could probably achieve a speed improvement if you compute some more temporary variables like sin, cos, and exp of various expressions because several of those are recomputed more than once. For example, cos(w1OverSigma) is computed seven times in that function.

C^hris L^osinger30-Sep-09 13:38

30-Sep-09 13:38

the thing is, those are calculated ahead of the actual processing, and don't change. the actual work is pretty much 4x the loop i posted.