llvm dev - Feb 2011 - [LLVMdev] Use of movupd instead of movapd for x86

Hi all,


Is there a way to force llc to generate movupd instruction instead of movapd for
x86 target ?
I know that movapd is more performant, but I would like to measure degradation
when alignment constraints are not met.

Best Regards
Seb
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20110225/8d401a39/attachment.html>

Sebastien DELDON-GNB <sebastien.deldon at st.com> writes:
> Hi all,
>
> Is there a way to force llc to generate movupd instruction instead of
movapd for x86 target ?
>
> I know that movapd is more performant, but I would like to measure
degradation when alignment constraints are not met.
On modern processors a movupd on aligned data is going to be
indistinguishable in performance from a movapd.

                               -Dave

On Feb 25, 2011, at 12:54 AM, Sebastien DELDON-GNB wrote:
> Hi all,
>  
>  
> Is there a way to force llc to generate movupd instruction instead of
movapd for x86 target ?
> I know that movapd is more performant, but I would like to measure
degradation when alignment constraints are not met.
>  
You can hack loads and stores to have alignment of 1 in the IR, or hack LLC
itself.

-Chris

-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20110225/c3be42cd/attachment.html>

Understood for the aligned case, I want to measure performance degradation for
unaligned case.
I mean unaligned case versus aligned. I know this is stupid, but I want to try
to pass a <4 x float>* as parameter of a routine and at the call site I
want to pass a misaligned pointer. Since LLVM is generating movapd instruction
it will raise an exception (SEGFAULT), I just want to know if there is a way to
enforce
generation of movupd instruction instead of movapd.

Seb
> -----Original Message-----
> From: David A. Greene [mailto:greened at obbligato.org]
> Sent: Friday, February 25, 2011 5:13 PM
> To: Sebastien DELDON-GNB
> Cc: llvmdev at cs.uiuc.edu
> Subject: Re: [LLVMdev] Use of movupd instead of movapd for x86
> 
> Sebastien DELDON-GNB <sebastien.deldon at st.com> writes:
> 
> > Hi all,
> >
> > Is there a way to force llc to generate movupd instruction instead of
> movapd for x86 target ?
> >
> > I know that movapd is more performant, but I would like to measure
> degradation when alignment constraints are not met.
> 
> On modern processors a movupd on aligned data is going to be
> indistinguishable in performance from a movapd.
> 
>                                -Dave