asked on

What is the defference between movd and movss?

Dear all,

movd is to move 32-bit interger to xmm register.
movss is to to 32-bit floating float instead.

however, would:

movd xmm0, DWORD PTR[eax]
movss xmm0, DWORD PTR[eax]

be the same? Or this there a difference in speed?

Thank you.

dimitry

These are same commands according to Intel spec:
MOVD instruction when destination operand is XMM register:
DEST[31-0] ←SRC;
DEST[127-32] ←000000000000000000000000H;

MOVSS instruction when source operand is memory location and destination operand is XMM register:
DEST[31-0] ←SRC;
DEST[127-32] ←000000000000000000000000H;

However they have different C/C++ Intel Compiler Intrinsics...
Despite I think there is no speed difference, I would suggest to use movss as special SSE command.

ASKER CERTIFIED SOLUTION

dimitry

membership

This solution is only available to members.

To access this solution, you must be a member of Experts Exchange.

Start Free Trial

srini_vc

no- movd moves 64 bit data not 32 bit
movss is not there in 80x86 instruction set. movs is there but it's used for moving string. i thought, i'm correct?

byte (MOVB 8 bits),
word (MOVW 16 bits),
longword (MOVL 32 bits),
quadword (MOVQ 64 bits),
octaword (MOVQ 128 bits),
single precision floating (MOVF 32 bits),
double precision floating (MOVD 64 bits),
G floating (MOVG 64 bits), or
H floating (MOVH 128 bits)

mbizup

No comment has been added to this question in more than 21 days, so it is now classified as abandoned.

I will leave the following recommendation for this question in the Cleanup topic area:
Accept: dimitry {http:#12547124}

Any objections should be posted here in the next 4 days. After that time, the question will be closed.

mbizup
EE Cleanup Volunteer