Why we must align memory address to get high performance ? - Intel Community

Intel® Integrated Performance Primitives

Deliberate problems developing high-performance vision, signal, security, and storage applications.

Why we must align memory address to get high performance ?

555 Views

When using IPP function or writing MMX/SSE codes , it is important to

align data address with 16 or 32 bytes to meet cache , and what is the

reason ?

Link Copied

1 Reply

555 Views

Hi,

the reason is performance. Please consult with:

Regards,

Vladimir

Copy link

Community support is provided Monday to Friday. Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.