Sorry if this is a common question

[savage]

what's the easiest way to get an absolute value of an sse register?
I'm thinking I could use AND 07FFFFFFFFF..... or something, but is there a better way?

[dsouza123]

Signed integers use twos complement encoding.
For switching signs
not reg  ; xor reg, -1
add 1

For example using a signed byte:
00000010 == 2
00000001 == 1
00000000 == 0
11111111 == -1
11111110 == -2

If you knew it was negative then the equivalent of this

xor reg, -1
add reg, 1

would give the positive version.


SSE code equivalent to this would do it no matter the sign of the integer.

mov reg, reg0
and reg,10000000  ; for byte sized signed integer
cmp reg, 0
je past
xor reg0, -1
add reg0, 1
past:

[redskull]

i don't know about SSE registers, but maybe something like this could be converted?  (for eax)

CDQ
XOR EAX, EDX
SUB EAX, EDX

[savage]

wow, yeah, guys, im asking about SSE =P

for regular registers i can just do

AND eax, 07FFF FFFFh

The problem is you can't use immediate values for sse instructions, so I was trying to avoid using a weird looking constant, it's not a big deal, I was just making sure there's not a faster way

[dsouza123]

AND eax, 07FFF FFFF wont give the correct absolute value.

The -1 will turn into 2147483647, surely not what you expected.

Redskull's code works correctly.

This code with tweaks may work, but it isn't tested .

Code Select Expand


.data
  number dq somenum, somenum
  minusone dq -1, -1
  zero dq 0, 0
  justhi dq  10..0b, 10..0b

.code
  movaps xmm1, minusone
  movaps xmm2, number
  movaps xmm3, xmm2
  andps xmm3, justhi
  comisd xmm3, justhi
  je past
  movaps xmm1, zero
past:
  xorps  xmm2, xmm1
  psubq  xmm2, xmm1


[Ossa]

dsouza123 is right, take a look at this: http://ossa.the-wot.co.uk/tutorial_asm1_tex.htm#1_6

It is something that I wrote a while back to explain 2's complement. Your code will only work for signed magnitude values, but Intel processors use 2's complement.

Ossa

[redskull]

Redskull's code works correctly.

Just for the record, i'm totally not claiming to have thought that code up; the original was a 16-bit version using CWD, taken from a book i can't remember long ago.  Again, sorry I can't help with SSE registers :'(

alan

[savage]

dsouza123 is right, take a look at this: http://ossa.the-wot.co.uk/tutorial_asm1_tex.htm#1_6

It is something that I wrote a while back to explain 2's complement. Your code will only work for signed magnitude values, but Intel processors use 2's complement.

Ossa

I feel stupid now, DUHHHHHHHHHHHHHHHHHHHHHH. 
Sorry guys, my neurons aren't exactly working this week.  :green2

[savage]

What about

   mov edx, eax
   sub eax, edx
   sub eax, edx

and

   movaps xmm1, xmm0
   subps xmm0, xmm1
   subps xmm0, xmm1

[Ossa]

   mov edx, eax
   sub eax, edx
   sub eax, edx

Therefore:

Code Select Expand

mov edx, eax    ; edx = eax = val
sub eax, edx    ; eax = 0, edx = val
sub eax, edx    ; eax = 0 - val = -val


I don't think that that's what you want to do.

Ossa

[savage]

I never said that.
You liar!   :cheekygreen:

I have a huge headache.  I think my brain is falling out of my ear. 

Why is it so hard to get the absolute value.  Arrrg

[Ossa]

This probably won't assemble (I haven't had time to check) but should work... there MUST be a better way though... I don't use MMX/SSE much, so I'm not the one to ask though:

Code Select Expand

mask1 dd  10000000h,  10000000h,  10000000h,  10000000h

movdqa   xmm2, xmm1
pand     xmm1, mask1
pcmpeqd  xmm1, mask1 ; xmm1 has all 1s for any dword that is negative

pxor     xmm3, xmm3
psubd    xmm3, xmm2 ; xmm3 = -xmm2

pand     xmm3, xmm1
pandn    xmm1, xmm2
por      xmm1, xmm3

[edit] Now that I finally looked at redskull's code, try this - I don't know of any sign extension instructions for SSE but I'll go have a look now:

Code Select Expand

mask1 dd  10000000h,  10000000h,  10000000h,  10000000h

movdqa   xmm2, xmm1
pand     xmm2, mask1
pcmpeqd  xmm2, mask1 ; xmm1 has all 1s for any dword that is negative

pxor     xmm1, xmm2
psubd    xmm1, xmm2

(for non-dowrd things, you just change the mask and the psubd instruction)

[/edit]

Ossa

[savage]

how does this look:

   movaps xmm1, xmm0
   cmpnltps xmm1, 0  ; obviously this shouldnt be immediate, but just an example
   andps xmm1, xmm0
   subps xmm0, xmm1
   subps xmm0, xmm1

[Ossa]

Wait - you're using FLOATS ??? well then, you first method WILL work and it is much the best.

[edit] The code that has been discussed so far is for integers, but you are using float SSE instructions there... which are you using? [/edit]

Ossa

[savage]

Well I'd like to have the best method for both.