Displaying 6 results from an estimated 6 matches for "mult_4xf32".
2012 Oct 05
2
[LLVMdev] LLVM Loop Vectorizer
...ty out of TLI.
>>
>
> Possibly, though I think TargetData should still be able to get you
> what you want.
TargetData does not have enough information for vectorization. For example, we need to ask the target if it has efficient "cos4" implementation or the cost of 'mult_4xf32'. We need lots of target specific information for deciding when to vectorize and which vectorization optimizations to apply.
>
>>
>> Currently TLI is only available in LLC. I suggest that we merge LLC and OPT
>> into a single tool that will drive both IR-level passes a...
2012 Oct 05
0
[LLVMdev] LLVM Loop Vectorizer
Nadav,
>> Possibly, though I think TargetData should still be able to get you
>> what you want.
>
>
> TargetData does not have enough information for vectorization. For example, we need to ask the target if it has efficient "cos4" implementation or the cost of 'mult_4xf32'. We need lots of target specific information for deciding when to vectorize and which vectorization optimizations to apply.
>
Sure. I was mostly going with the idea of "insert some Targetish
structure here".
>> TargetData is pretty useful during opt if it's available,...
2012 Oct 05
2
[LLVMdev] LLVM Loop Vectorizer
...Possibly, though I think TargetData should still be able to get you
>>> what you want.
>>
>>
>> TargetData does not have enough information for vectorization. For example, we need to ask the target if it has efficient "cos4" implementation or the cost of 'mult_4xf32'. We need lots of target specific information for deciding when to vectorize and which vectorization optimizations to apply.
>>
>
> Sure. I was mostly going with the idea of "insert some Targetish
> structure here".
>
>>> TargetData is pretty useful durin...
2012 Oct 05
0
[LLVMdev] LLVM Loop Vectorizer
...rgetData should still be able to get you
> >>> what you want.
> >>
> >>
> >> TargetData does not have enough information for vectorization. For
> example, we need to ask the target if it has efficient "cos4"
> implementation or the cost of 'mult_4xf32'. We need lots of target
> specific information for deciding when to vectorize and which
> vectorization optimizations to apply.
> >>
> >
> > Sure. I was mostly going with the idea of "insert some Targetish
> > structure here".
> >
> >>&...
2012 Oct 05
0
[LLVMdev] LLVM Loop Vectorizer
> Regarding TLI. So, DAGCombine, CodeGenPrepare, LoopReduce all use the TLI
> interface which can answer questions such as "is this operation supported ?"
> or "is this type legal". This is a subset of what we need in a vectorized.
> We can discuss other requirements that the vectorizer may have after we
> finish with the first phase. I suspect that we may
2012 Oct 05
6
[LLVMdev] LLVM Loop Vectorizer
On Oct 5, 2012, at 12:08 AM, Nick Lewycky <nicholas at mxc.ca> wrote:
> I absolutely think that we should have something like TargetData (now DataLayout) but for the vector types and operations. However, I'm not familiar with "Target Lowering Interface". Could you explain?
I agree. Once we make the codegen accessible to the IR-level passes we need to start talking about