[fpc-devel] Same 64bit assembly code compiles under windows but not in linux (fpc 260)

[luiz americo pereira camara]

Hi,

I'm porting some Delphi assembly code.

It worked fine with fpc 2.6.0 i386-64bit windows compiler

When i tried the same code with fpc 2.6.0 i386-64bit for linux it failed to
compile with the following error:

Error: Asm: 16 or 32 Bit references not supported

at the line
         // Load XMM5 with the bias value.
        MOVD        XMM5, [Bias]  //Bias = Integer

Is it a know issue or a limitation of linux version?

There's a workaround to this issue?

The complete procedure:

{$ASMMODE INTEL}

procedure AlphaBlendLineConstant(Source, Destination: Pointer; Count:
Integer; ConstantAlpha, Bias: Integer);

asm

{$ifdef CPU64}
// RCX contains Source
// RDX contains Destination
// R8D contains Count
// R9D contains ConstantAlpha
// Bias is on the stack

        //.NOFRAME

        // Load XMM3 with the constant alpha value (replicate it for every
component).
        // Expand it to word size.
        MOVD        XMM3, R9D  // ConstantAlpha
        PUNPCKLWD   XMM3, XMM3
        PUNPCKLDQ   XMM3, XMM3

        // Load XMM5 with the bias value.
        MOVD        XMM5, [Bias]
        PUNPCKLWD   XMM5, XMM5
        PUNPCKLDQ   XMM5, XMM5

        // Load XMM4 with 128 to allow for saturated biasing.
        MOV         R10D, 128
        MOVD        XMM4, R10D
        PUNPCKLWD   XMM4, XMM4
        PUNPCKLDQ   XMM4, XMM4

@1:     // The pixel loop calculates an entire pixel in one run.
        // Note: The pixel byte values are expanded into the higher bytes
of a word due
        //       to the way unpacking works. We compensate for this with an
extra shift.
        MOVD        XMM1, DWORD PTR [RCX]   // data is unaligned
        MOVD        XMM2, DWORD PTR [RDX]   // data is unaligned
        PXOR        XMM0, XMM0    // clear source pixel register for
unpacking
        PUNPCKLBW   XMM0, XMM1{[RCX]}    // unpack source pixel byte values
into words
        PSRLW       XMM0, 8       // move higher bytes to lower bytes
        PXOR        XMM1, XMM1    // clear target pixel register for
unpacking
        PUNPCKLBW   XMM1, XMM2{[RDX]}    // unpack target pixel byte values
into words
        MOVQ        XMM2, XMM1    // make a copy of the shifted values, we
need them again
        PSRLW       XMM1, 8       // move higher bytes to lower bytes

        // calculation is: target = (alpha * (source - target) + 256 *
target) / 256
        PSUBW       XMM0, XMM1    // source - target
        PMULLW      XMM0, XMM3    // alpha * (source - target)
        PADDW       XMM0, XMM2    // add target (in shifted form)
        PSRLW       XMM0, 8       // divide by 256

        // Bias is accounted for by conversion of range 0..255 to -128..127,
        // doing a saturated add and convert back to 0..255.
        PSUBW     XMM0, XMM4
        PADDSW    XMM0, XMM5
        PADDW     XMM0, XMM4
        PACKUSWB  XMM0, XMM0      // convert words to bytes with saturation
        MOVD      DWORD PTR [RDX], XMM0     // store the result
@3:
        ADD       RCX, 4
        ADD       RDX, 4
        DEC       R8D
        JNZ       @1

{$endif}

end;
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.freepascal.org/pipermail/fpc-devel/attachments/20121002/c32607a5/attachment.html>