Optimal mullps/addps instructions order for 3 SSE units for Intel Core 2 Duo and How to install Phalcon on android

flag Questions

It's known that Intel Core 2 Duo has 3 SSE units. These 3 units allows 3 SSE instructions to be run paralelly (1), for example:

It's known also, that each SSE unit consists of 2 modules: one for addition (substraction), and one for multiplication (division). The latter allows to run mullps-addps instruction sequences parallelly (2), for example:

Which way of instruction ordering should I prefer, A or B?

More specifically:

  • Is it possible to distribute 3 mulps to 3 SSE multiplication units (1), and at the same time (2) to distribute addps to their respective SSE addition units, resulting in total 6 instructions per schedule cycle?

  • If I run N mullps first, and N addps then - which N is optimal?

Remarks

by 'scheduled' I mean throughput rate.
solved
Jun 25/15 at 07:23 9 Answers 15 Views 1

About the Author

I'm creating a website that provides a service to people that allows them to access their documents and desktops remotely, and obviously, they should be the only ones that can access their information, but how do I go about doing that?

Answers ( 11 )

    0
    Jul 7/15 at 03:56

    Which way of instruction ordering should I prefer, A or B?

    0
    Jul 7/15 at 03:55

    It's known also, that each SSE unit consists of 2 modules: one for addition (substraction), and one for multiplication (division). The latter allows to run mullps-addps instruction sequences parallelly (2), for example:

    0
    Jul 7/15 at 03:54

    Which way of instruction ordering should I prefer, A or B?

    0
    Jul 7/15 at 03:53

    Which way of instruction ordering should I prefer, A or B?

    0
    Jul 7/15 at 03:53

    Which way of instruction ordering should I prefer, A or B?

    0
    Jul 7/15 at 03:52

    Which way of instruction ordering should I prefer, A or B?

    0
    Jul 7/15 at 03:49

    Which way of instruction ordering should I prefer, A or B?

    0
    Jul 7/15 at 03:36

    It's known also, that each SSE unit consists of 2 modules: one for addition (substraction), and one for multiplication (division). The latter allows to run mullps-addps instruction sequences parallelly (2), for example:

    0
    Jul 7/15 at 03:36

    It's known also, that each SSE unit consists of 2 modules: one for addition (substraction), and one for multiplication (division). The latter allows to run mullps-addps instruction sequences parallelly (2), for example:

    0
    Jul 6/15 at 02:00

    Is it possible to distribute 3 mulps to 3 SSE multiplication units (1), and at the same time (2) to distribute addps to their respective SSE addition units, resulting in total 6 instructions per schedule cycle?

    0
    Jun 27/15 at 02:00

    Which way of instruction ordering should I prefer, A or B?

    More specifically:

Leave a reply

 Prev question

Next question