search for: d38676

>I think we need to get that story right for both cases up front. Renato, I kicked off this secondary discussion, borrowing the opportunity from Michael's RFC, but to the point of reviewing https://reviews.llvm.org/D38676, I'd like the review to proceed separately from this bigger (and most likely longer) discussion. We intentionally made the interfaces similar such that whatever the outcome of this discussion would be, the changes we have to make later, if any, is small and mechanical. We just need to agree tha...

.... https://reviews.llvm.org/D28975 by Gil Rapaport. (Introducing VPlan to model the vectorized code and drive its transformation)      Has been broken down to a series of smaller patches and went in. The last (re)commit of the series is      https://reviews.llvm.org/rL311849 https://reviews.llvm.org/D38676 by Gil Rapaport. (Modeling masking in VPlan, introducing VPInstructions)      This is also being broken down to a series of smaller patches to facilitate the review.      Committed as https://reviews.llvm.org/rL318645   Where We Are: ------------- With the first patch, we introduced the concept of...

On 10/14/2017 05:28 PM, Daniel Berlin via llvm-dev wrote: > > > On Sat, Oct 14, 2017 at 2:54 PM, Michael Kruse <llvmdev at meinersbur.de > <mailto:llvmdev at meinersbur.de>> wrote: > > 2017-10-14 5:03 GMT+02:00 Daniel Berlin <dberlin at dberlin.org > <mailto:dberlin at dberlin.org>>: > > FWIW: We hit a subset of this issue with

...dramatically changed since > ~2yrs ago, it's unlikely that you'll get overwhelming support on "copy the entire function" before the decision to transform is taken. So, if this part is optional, you may want to state that. > > Having said that, in https://reviews.llvm.org/D38676, we are > introducing concepts like VPValue, VPUser, and VPInstruction, in order > to manipulate and interact with things that didn't come from the IR of > the original loop (nest). As such, I can see why you think "a playground copy of IR" is beneficial. Even before readi...

...ty mindset has dramatically changed since ~2yrs ago, it's unlikely that you'll get overwhelming support on "copy the entire function" before the decision to transform is taken. So, if this part is optional, you may want to state that. Having said that, in https://reviews.llvm.org/D38676, we are introducing concepts like VPValue, VPUser, and VPInstruction, in order to manipulate and interact with things that didn't come from the IR of the original loop (nest). As such, I can see why you think "a playground copy of IR" is beneficial. Even before reading your RFC, I was...

.... > > >> Add support for SLP style vectorization to Vplan >> ------------------------------------------------------------------------ >> Introduce 2 new recipes VPSLPMemoryRecipe and VPSLPInstructionRecipe. > > We introduced VPInstructions to model masking in patch D38676. They are necessary to properly model the def-use/use-def chains in the VPlan representation, and we believe you will need to represent def-use/use-def chains for newly inserted operations, shuffles, and inserts/extracts. As such, VPInstructions would be a more proper representation than the Recipe...

.... https://reviews.llvm.org/D28975 by Gil Rapaport. (Introducing VPlan to model the vectorized code and drive its transformation)      Has been broken down to a series of smaller patches and went in. The last (re)commit of the series is      https://reviews.llvm.org/rL311849 https://reviews.llvm.org/D38676 by Gil Rapaport. (Modeling masking in VPlan, introducing VPInstructions)      This is also broken down to a series of smaller patches to facilitate the review.      Committed as https://reviews.llvm.org/rL318645   With the first patch, we introduced the concept of VPlan to LV and started explicitly...

...seems to fit into that category. > Add support for SLP style vectorization to Vplan > ------------------------------------------------------------------------ > Introduce 2 new recipes VPSLPMemoryRecipe and VPSLPInstructionRecipe. We introduced VPInstructions to model masking in patch D38676. They are necessary to properly model the def-use/use-def chains in the VPlan representation, and we believe you will need to represent def-use/use-def chains for newly inserted operations, shuffles, and inserts/extracts. As such, VPInstructions would be a more proper representation than the Recipe...

...ce ~2yrs ago, it's unlikely that you'll get overwhelming > support on "copy the entire function" before the decision > > to transform is taken. So, if this part is optional, you may want to > state that. > > > > Having said that, in https://reviews.llvm.org/D38676, we are > introducing concepts like VPValue, VPUser, and VPInstruction, > > in order to manipulate and interact with things that didn't come from > the IR of the original loop (nest). As such, I can see > > why you think "a playground copy of IR" is beneficial. Even...

...8975 by Gil Rapaport. (Introducing VPlan to > model the vectorized code and drive its transformation) >      Has been broken down to a series of smaller patches and went in. > The last (re)commit of the series is >      https://reviews.llvm.org/rL311849 > https://reviews.llvm.org/D38676 by Gil Rapaport. (Modeling masking in > VPlan, introducing VPInstructions) >      This is also broken down to a series of smaller patches to facilitate the review. >      Committed as https://reviews.llvm.org/rL318645 > > With the first patch, we introduced the concept of VPlan...

.... (Introducing VPlan to >> model the vectorized code and drive its transformation) >>      Has been broken down to a series of smaller patches and went in. >> The last (re)commit of the series is >>      https://reviews.llvm.org/rL311849 >> https://reviews.llvm.org/D38676 by Gil Rapaport. (Modeling masking in >> VPlan, introducing VPInstructions) >>      This is also broken down to a series of smaller patches to facilitate the review. >>      Committed as https://reviews.llvm.org/rL318645 >> >> With the first patch, we introduce...

Hello, We would like to propose making LoopVectorize aware of SLP operations, to improve the generated code for loops operating on struct fields or doing complex math. At the moment, LoopVectorize uses interleaving to vectorize loops that operate on values loaded/stored from consecutive addresses: vector loads/stores are generated to combine consecutive loads/stores and then shufflevector

...to >>> model the vectorized code and drive its transformation) >>>        Has been broken down to a series of smaller patches and went in. >>> The last (re)commit of the series is >>>        https://reviews.llvm.org/rL311849 >>> https://reviews.llvm.org/D38676 by Gil Rapaport. (Modeling masking in >>> VPlan, introducing VPInstructions) >>>        This is also broken down to a series of smaller patches to >>> facilitate the review. >>>        Committed as https://reviews.llvm.org/rL318645 >>>    With the first...