Displaying 4 results from an estimated 4 matches for "getsizeasvectorelement".
2013 Jan 28
2
[LLVMdev] Floats as Doubles in Vectors
...nd of API to TTI that allows the default logic (# ==
> > vector-size/type-size) to be overridden. This could be something
> > specific to the problem at hand, such as: bool
> > areFloatsStoredAsDoublesInVectors(), or something more general.
> > Maybe something like: unsigned getSizeAsVectorElement(Type *T)
> > which would return the number of bytes that the specified type
> > actually takes up when used as a vector element.
>
> I prefer to fix the cost model. Do you see any problems with this
> approach ? I understand that it is more difficult to select the VF
> in...
2013 Jan 27
3
[LLVMdev] Floats as Doubles in Vectors
...y compile-time increase.
2. Add some kind of API to TTI that allows the default logic (# == vector-size/type-size) to be overridden. This could be something specific to the problem at hand, such as: bool areFloatsStoredAsDoublesInVectors(), or something more general. Maybe something like: unsigned getSizeAsVectorElement(Type *T) which would return the number of bytes that the specified type actually takes up when used as a vector element.
I'm certainly open to suggestions. I don't know if this situation applies to other targets as well.
Thanks again,
Hal
--
Hal Finkel
Postdoctoral Appointee
Leadership...
2013 Jan 28
0
[LLVMdev] Floats as Doubles in Vectors
...TTI that allows the default logic (# ==
>>> vector-size/type-size) to be overridden. This could be something
>>> specific to the problem at hand, such as: bool
>>> areFloatsStoredAsDoublesInVectors(), or something more general.
>>> Maybe something like: unsigned getSizeAsVectorElement(Type *T)
>>> which would return the number of bytes that the specified type
>>> actually takes up when used as a vector element.
>>
>> I prefer to fix the cost model. Do you see any problems with this
>> approach ? I understand that it is more difficult to sele...
2013 Jan 28
0
[LLVMdev] Floats as Doubles in Vectors
...or <8 x i8>.
> 2. Add some kind of API to TTI that allows the default logic (# == vector-size/type-size) to be overridden. This could be something specific to the problem at hand, such as: bool areFloatsStoredAsDoublesInVectors(), or something more general. Maybe something like: unsigned getSizeAsVectorElement(Type *T) which would return the number of bytes that the specified type actually takes up when used as a vector element.
I prefer to fix the cost model. Do you see any problems with this approach ? I understand that it is more difficult to select the VF in the BB vectorizer, but I suspect that ev...