Displaying 9 results from an estimated 9 matches for "uglygep_sum".
Did you mean:
uglygep14_sum
2012 Oct 17
4
[LLVMdev] Redundant Add Operation in Code Generation?
..., %tmp45*
%scevgep15 = getelementptr i8* %extIn_013, i32 %uglygep14_sum
%scevgep1516 = bitcast i8* %scevgep15 to i16*
%tmp79 = load i16* %scevgep1516, align 2
%conv93.i.i = sext i16 %tmp79 to i32
*%uglygep.sum = add i32 %lsr_iv8, %tmp45*
%scevgep11 = getelementptr i8* %sysBits_010, i32 %uglygep_sum
You can see here that "add i32 %lsr_iv8, %tmp45" is done multiple times,
appearing that there are two redundant add operations that are not needed
yet are generated?
Thanks.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/piperma...
2012 Oct 17
0
[LLVMdev] Redundant Add Operation in Code Generation?
...= getelementptr i8* %extIn_013, i32 %uglygep14_sum
> %scevgep1516 = bitcast i8* %scevgep15 to i16*
> %tmp79 = load i16* %scevgep1516, align 2
> %conv93.i.i = sext i16 %tmp79 to i32
> %uglygep.sum = add i32 %lsr_iv8, %tmp45
> %scevgep11 = getelementptr i8* %sysBits_010, i32 %uglygep_sum
>
> You can see here that "add i32 %lsr_iv8, %tmp45" is done multiple times,
> appearing that there are two redundant add operations that are not needed
> yet are generated?
CodeGenPrepare manipulates GEPs in a way that can expose redundancy
where it wasn't obvious before...
2012 Oct 19
3
[LLVMdev] Redundant Add Operation in Code Generation?
...getelementptr i8* %extIn_013, i32 %uglygep14_sum
> %scevgep1516 = bitcast i8* %scevgep15 to i16*
> %tmp79 = load i16* %scevgep1516, align 2
> %conv93.i.i = sext i16 %tmp79 to i32
> *%uglygep.sum = add i32 %lsr_iv8, %tmp45*
> %scevgep11 = getelementptr i8* %sysBits_010, i32 %uglygep_sum
>
> You can see here that "add i32 %lsr_iv8, %tmp45" is done multiple times,
> appearing that there are two redundant add operations that are not needed
> yet are generated?
>
>
> That's LSR, as you can see from the variable names ;) It might think that
> load(...
2012 Oct 19
0
[LLVMdev] Redundant Add Operation in Code Generation?
...= getelementptr i8* %extIn_013, i32 %uglygep14_sum
> %scevgep1516 = bitcast i8* %scevgep15 to i16*
> %tmp79 = load i16* %scevgep1516, align 2
> %conv93.i.i = sext i16 %tmp79 to i32
> %uglygep.sum = add i32 %lsr_iv8, %tmp45
> %scevgep11 = getelementptr i8* %sysBits_010, i32 %uglygep_sum
>
> You can see here that "add i32 %lsr_iv8, %tmp45" is done multiple times, appearing that there are two redundant add operations that are not needed yet are generated?
That's LSR, as you can see from the variable names ;) It might think that load(Base + Index) is a legal add...
2012 Oct 19
2
[LLVMdev] Redundant Add Operation in Code Generation?
...xtIn_013, i32 %uglygep14_sum
>> %scevgep1516 = bitcast i8* %scevgep15 to i16*
>> %tmp79 = load i16* %scevgep1516, align 2
>> %conv93.i.i = sext i16 %tmp79 to i32
>> *%uglygep.sum = add i32 %lsr_iv8, %tmp45*
>> %scevgep11 = getelementptr i8* %sysBits_010, i32 %uglygep_sum
>>
>> You can see here that "add i32 %lsr_iv8, %tmp45" is done multiple times,
>> appearing that there are two redundant add operations that are not needed
>> yet are generated?
>>
>>
>> That's LSR, as you can see from the variable names ;) It...
2012 Oct 17
2
[LLVMdev] Redundant Add Operation in Code Generation?
...n_013, i32 %uglygep14_sum
> > %scevgep1516 = bitcast i8* %scevgep15 to i16*
> > %tmp79 = load i16* %scevgep1516, align 2
> > %conv93.i.i = sext i16 %tmp79 to i32
> > %uglygep.sum = add i32 %lsr_iv8, %tmp45
> > %scevgep11 = getelementptr i8* %sysBits_010, i32 %uglygep_sum
> >
> > You can see here that "add i32 %lsr_iv8, %tmp45" is done multiple times,
> > appearing that there are two redundant add operations that are not needed
> > yet are generated?
>
> CodeGenPrepare manipulates GEPs in a way that can expose redundancy
>...
2012 Oct 19
0
[LLVMdev] Redundant Add Operation in Code Generation?
...%extIn_013, i32 %uglygep14_sum
>> %scevgep1516 = bitcast i8* %scevgep15 to i16*
>> %tmp79 = load i16* %scevgep1516, align 2
>> %conv93.i.i = sext i16 %tmp79 to i32
>> %uglygep.sum = add i32 %lsr_iv8, %tmp45
>> %scevgep11 = getelementptr i8* %sysBits_010, i32 %uglygep_sum
>>
>> You can see here that "add i32 %lsr_iv8, %tmp45" is done multiple times, appearing that there are two redundant add operations that are not needed yet are generated?
>
> That's LSR, as you can see from the variable names ;) It might think that load(Base + Ind...
2012 Oct 19
0
[LLVMdev] Redundant Add Operation in Code Generation?
...ygep14_sum
>>> %scevgep1516 = bitcast i8* %scevgep15 to i16*
>>> %tmp79 = load i16* %scevgep1516, align 2
>>> %conv93.i.i = sext i16 %tmp79 to i32
>>> %uglygep.sum = add i32 %lsr_iv8, %tmp45
>>> %scevgep11 = getelementptr i8* %sysBits_010, i32 %uglygep_sum
>>>
>>> You can see here that "add i32 %lsr_iv8, %tmp45" is done multiple times, appearing that there are two redundant add operations that are not needed yet are generated?
>>
>> That's LSR, as you can see from the variable names ;) It might think that...
2012 Oct 17
0
[LLVMdev] Redundant Add Operation in Code Generation?
...4_sum
>> > %scevgep1516 = bitcast i8* %scevgep15 to i16*
>> > %tmp79 = load i16* %scevgep1516, align 2
>> > %conv93.i.i = sext i16 %tmp79 to i32
>> > %uglygep.sum = add i32 %lsr_iv8, %tmp45
>> > %scevgep11 = getelementptr i8* %sysBits_010, i32 %uglygep_sum
>> >
>> > You can see here that "add i32 %lsr_iv8, %tmp45" is done multiple times,
>> > appearing that there are two redundant add operations that are not
>> needed
>> > yet are generated?
>>
>> CodeGenPrepare manipulates GEPs in a way...