Displaying 8 results from an estimated 8 matches for "add_u8s".
Did you mean:
add_fs
2013 Nov 15
0
[LLVMdev] Limit loop vectorizer to SSE
Nadav,
I believe aligned accesses to unaligned pointers is precisely the issue.
Consider the function `add_u8S` before[1] and after[2] the loop vectorizer
pass. There is no alignment assumption associated with %kernel_data prior
to vectorization. I can't tell if it's the loop vectorizer or the codegen
at fault, but the alignment assumption seems to sneak in somewhere.
v/r,
Josh
[1] http://pastebin...
2013 Nov 15
4
[LLVMdev] Limit loop vectorizer to SSE
...rDataTy);
unsigned VectorElementSize = DL->getTypeStoreSize(DataTy)/VF;
Should fix this.
On Nov 15, 2013, at 3:49 PM, Joshua Klontz <josh.klontz at gmail.com> wrote:
> Nadav,
>
> I believe aligned accesses to unaligned pointers is precisely the issue. Consider the function `add_u8S` before[1] and after[2] the loop vectorizer pass. There is no alignment assumption associated with %kernel_data prior to vectorization. I can't tell if it's the loop vectorizer or the codegen at fault, but the alignment assumption seems to sneak in somewhere.
>
> v/r,
> Josh
>...
2013 Nov 15
2
[LLVMdev] Limit loop vectorizer to SSE
A fix for this is in r194876.
Thanks for reporting this!
On Nov 15, 2013, at 3:49 PM, Joshua Klontz <josh.klontz at gmail.com> wrote:
> Nadav,
>
> I believe aligned accesses to unaligned pointers is precisely the issue. Consider the function `add_u8S` before[1] and after[2] the loop vectorizer pass. There is no alignment assumption associated with %kernel_data prior to vectorization. I can't tell if it's the loop vectorizer or the codegen at fault, but the alignment assumption seems to sneak in somewhere.
>
> v/r,
> Josh
>...
2013 Nov 15
6
[LLVMdev] Limit loop vectorizer to SSE
On Nov 15, 2013, at 12:36 PM, Renato Golin <renato.golin at linaro.org> wrote:
> On 15 November 2013 20:24, Joshua Klontz <josh.klontz at gmail.com> wrote:
> Agreed, is there a pass that will insert a runtime alignment check? Also, what's the easiest way to get at TargetTransformInfo::getRegisterBitWidth() so I don't have to hard code 32? Thanks!
>
> I think
2013 Nov 15
0
[LLVMdev] Limit loop vectorizer to SSE
...eStoreSize(DataTy)/VF;
>
> Should fix this.
>
> On Nov 15, 2013, at 3:49 PM, Joshua Klontz <josh.klontz at gmail.com>
> wrote:
>
> > Nadav,
> >
> > I believe aligned accesses to unaligned pointers is precisely the
> > issue. Consider the function `add_u8S` before[1] and after[2] the
> > loop vectorizer pass. There is no alignment assumption associated
> > with %kernel_data prior to vectorization. I can't tell if it's the
> > loop vectorizer or the codegen at fault, but the alignment
> > assumption seems to sneak in so...
2013 Nov 15
2
[LLVMdev] Limit loop vectorizer to SSE
...;> Should fix this.
>>
>> On Nov 15, 2013, at 3:49 PM, Joshua Klontz <josh.klontz at gmail.com>
>> wrote:
>>
>>> Nadav,
>>>
>>> I believe aligned accesses to unaligned pointers is precisely the
>>> issue. Consider the function `add_u8S` before[1] and after[2] the
>>> loop vectorizer pass. There is no alignment assumption associated
>>> with %kernel_data prior to vectorization. I can't tell if it's the
>>> loop vectorizer or the codegen at fault, but the alignment
>>> assumption seems to...
2013 Nov 16
0
[LLVMdev] Limit loop vectorizer to SSE
...A fix for this is in r194876.
>
> Thanks for reporting this!
>
>
> On Nov 15, 2013, at 3:49 PM, Joshua Klontz <josh.klontz at gmail.com> wrote:
>
>> Nadav,
>>
>> I believe aligned accesses to unaligned pointers is precisely the issue. Consider the function `add_u8S` before[1] and after[2] the loop vectorizer pass. There is no alignment assumption associated with %kernel_data prior to vectorization. I can't tell if it's the loop vectorizer or the codegen at fault, but the alignment assumption seems to sneak in somewhere.
>>
>> v/r,
>>...
2013 Nov 16
1
[LLVMdev] Limit loop vectorizer to SSE
...gt;> Thanks for reporting this!
>>
>>
>> On Nov 15, 2013, at 3:49 PM, Joshua Klontz <josh.klontz at gmail.com> wrote:
>>
>>> Nadav,
>>>
>>> I believe aligned accesses to unaligned pointers is precisely the issue. Consider the function `add_u8S` before[1] and after[2] the loop vectorizer pass. There is no alignment assumption associated with %kernel_data prior to vectorization. I can't tell if it's the loop vectorizer or the codegen at fault, but the alignment assumption seems to sneak in somewhere.
>>>
>>> v/r,...