llvm dev - Sep 2014 - [LLVMdev] Preserving NSW/NUW bits

David/All,
Just a quick question about NSW/NUW bits, if you've got a second.  I
noticed you've been doing a little work on this as of late.

I have a bit of code that looks like the following:

  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %2 = add i64 %indvars.iv.next, -1
  %tmp = trunc i64 %2 to i32
  %cmp = icmp slt i32 %tmp, %0
  br i1 %cmp, label %for.body, label %for.end.loopexit

I'm trying to fold the 2nd add instruction into the compare by changing
the condition from from 'slt' to 'sle':

  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %tmp = trunc i64 %indvars.iv.next to i32
  %cmp = icmp sle i32 %tmp, %0
  br i1 %cmp, label %for.body, label %for.end.loopexit

However, AFAICT the NSW bits must be set.  In what cases can we propagate
the NSW bit from the first add to the second, if any?  If a case exists,
can this be handled by the WillNotOverflowSignedAdd function?

 Chad

So, the trunc makes this transform a bit questionable because you have to
reason about bits in the middle of your value.

Consider the following input values:
%indvars.iv = 0x........7fffffff
%0 = 0x8......1

Consider the following values in the 'before' case:
%2 = 0x........7fffffff
%indvars.iv.next = 0x........80000000
%tmp = 0x7fffffff
%cmp = false

This results in the following values in the 'after' case:
%indvars.iv.next = 0x........80000000
%tmp = 0x80000000
%cmp = true

Regardless of whether or not you propagate nsw/nuw, the transform is
currently unsound.

The transform is sound if %indvars.iv has a sufficiently large number of
signbits.
e.x.
%indvars.iv = sext i31 %invdars.actual to i64

If this precondition holds, any existing nsw or nuw flags should still hold.



On Tue, Sep 2, 2014 at 3:22 PM, Chad Rosier <mcrosier at codeaurora.org>
wrote:
> David/All,
> Just a quick question about NSW/NUW bits, if you've got a second.  I
> noticed you've been doing a little work on this as of late.
>
> I have a bit of code that looks like the following:
>
>   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
>   %2 = add i64 %indvars.iv.next, -1
>   %tmp = trunc i64 %2 to i32
>   %cmp = icmp slt i32 %tmp, %0
>   br i1 %cmp, label %for.body, label %for.end.loopexit
>
> I'm trying to fold the 2nd add instruction into the compare by changing
> the condition from from 'slt' to 'sle':
>
>   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
>   %tmp = trunc i64 %indvars.iv.next to i32
>   %cmp = icmp sle i32 %tmp, %0
>   br i1 %cmp, label %for.body, label %for.end.loopexit
>
> However, AFAICT the NSW bits must be set.  In what cases can we propagate
> the NSW bit from the first add to the second, if any?  If a case exists,
> can this be handled by the WillNotOverflowSignedAdd function?
>
>  Chad
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20140902/594b29b9/attachment.html>

On Tue, Sep 2, 2014 at 4:16 PM, David Majnemer <david.majnemer at
gmail.com>
wrote:
> So, the trunc makes this transform a bit questionable because you have to
> reason about bits in the middle of your value.
>
> Consider the following input values:
> %indvars.iv = 0x........7fffffff
> %0 = 0x8......1
>
> Consider the following values in the 'before' case:
> %2 = 0x........7fffffff
> %indvars.iv.next = 0x........80000000
> %tmp = 0x7fffffff
> %cmp = false
>
> This results in the following values in the 'after' case:
> %indvars.iv.next = 0x........80000000
> %tmp = 0x80000000
> %cmp = true
>
> Regardless of whether or not you propagate nsw/nuw, the transform is
> currently unsound.
>
> The transform is sound if %indvars.iv has a sufficiently large number of
> signbits.
> e.x.
> %indvars.iv = sext i31 %invdars.actual to i64
>
> If this precondition holds, any existing nsw or nuw flags should still
> hold.
>
Some other interesting things spring to mind.
If either (%indvars.iv & (1 << 31)) == 1 or if (%indvars.iv & (1
<< 31)) =(%indvars.iv & (1 << 30)), then the transform is safe;
I'm not immediately
sure about nuw or nsw.

>
>
>
> On Tue, Sep 2, 2014 at 3:22 PM, Chad Rosier <mcrosier at
codeaurora.org>
> wrote:
>
>> David/All,
>> Just a quick question about NSW/NUW bits, if you've got a second. 
I
>> noticed you've been doing a little work on this as of late.
>>
>> I have a bit of code that looks like the following:
>>
>>   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
>>   %2 = add i64 %indvars.iv.next, -1
>>   %tmp = trunc i64 %2 to i32
>>   %cmp = icmp slt i32 %tmp, %0
>>   br i1 %cmp, label %for.body, label %for.end.loopexit
>>
>> I'm trying to fold the 2nd add instruction into the compare by
changing
>> the condition from from 'slt' to 'sle':
>>
>>   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
>>   %tmp = trunc i64 %indvars.iv.next to i32
>>   %cmp = icmp sle i32 %tmp, %0
>>   br i1 %cmp, label %for.body, label %for.end.loopexit
>>
>> However, AFAICT the NSW bits must be set.  In what cases can we
propagate
>> the NSW bit from the first add to the second, if any?  If a case
exists,
>> can this be handled by the WillNotOverflowSignedAdd function?
>>
>>  Chad
>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20140902/7ec69e2d/attachment.html>