Intel ARCHITECTURE IA-32 - Manual (Page 414)

IA-32 Intel® Architecture Optimization
8-6
Use 32-Bit Versions of CVTSI2SS and CVTSI2SD When
Possible
The CVTSI2SS and CVTSI2SD instructions convert a signed integer in
a general-purpose register or memory location to a single-precision or
double-precision floating-point value. The signed integer can be either
32-bits or 64-bits.
The 32-bit version will result in traces delivered out of the trace cache;
the 64-bit version will result in a microcode flow from the microcode
ROM and takes longer to execute. In most cases, the 32-bit versions of
CVTSI2SS and CVTSI2SD is sufficient.
Assembly/Compiler Coding rule
Use the 32-bit versions of CTVSI2SS and CVTSI2SD when possible.
Using Software Prefetch
Intel recommends that software developers follow the recommendations
in Chapter 2 and Chapter 6 when considering the choice of organizing
data access patterns to take advantage of the hardware prefetcher
(versus using software prefetch).
Assembly/Compiler Coding Rule
If software prefetch instructions are necessary, use the prefetch instructions
provided by SSE.