In the x86 assembly programming language, MOVDDUP is the name for a specific action performable by modern x86 processors with 3rd-generation Streaming SIMD Extensions (SSE3). This action involves copying a number to temporary space in the processor for use in other computations.
Specifically, MOVDDUP causes one, double-precision, floating-point source to be copied to both the lower half and upper half of an XMM register.
| Opcode | F2 0F 12 ''/r'' | |
|---|---|---|
| Assembly (Intel syntax) | MOVDDUP ''xmm1'', ''xmm2''/''m64'' | |
| Assembly (AT&T syntax) | MOVDDUP ''xmm2''/''m64'', ''xmm1'' | |
| intrinsic equivalent(s) | __m128d _mm_movedup_pd(__m128d a)__m128d _mm_load_pd1(const double * mem_addr) | |
| built-in(s) | v2df __builtin_ia32_movddup(v2df) |
The source operand can be either an XMM register (xmm2) or a memory address (m64). When the source operand is an XMM register, the lower half of the register is used in the operation. When the source operand is a memory address, it is assumed to be the address of an 8-byte region, the value at which is used in the operation.
The destination operand must be an XMM register (xmm1).