Page MenuHomePhabricator
Feed Advanced Search

Dec 25 2016

gareevroman updated the diff for D28090: [Polly] Specify the default values of the cache parameters.

Hi Roman,

Dec 25 2016, 1:58 AM

Dec 23 2016

gareevroman retitled D28090: [Polly] Specify the default values of the cache parameters from to [Polly] Specify the default values of the cache parameters.
Dec 23 2016, 11:39 PM

Dec 21 2016

gareevroman updated the diff for D28020: [Polly] Align newly created arrays to the first level cache line boundary.

Update according to the comments.

Dec 21 2016, 4:41 AM
gareevroman updated the diff for D28019: [Polly] Change the determination of parameters of macro-kernel.

Update according to the comments.

Dec 21 2016, 4:36 AM
gareevroman added a comment to D28021: [Polly] Update the documentation on how the packing transformation is implemented.

Why is the _access_ relation mapping to a 9 dimensional space. You talk about a _schedule_ here, right?

Dec 21 2016, 3:17 AM
gareevroman retitled D28021: [Polly] Update the documentation on how the packing transformation is implemented from to [Polly] Update the documentation on how the packing transformation is implemented.
Dec 21 2016, 3:16 AM
gareevroman retitled D28020: [Polly] Align newly created arrays to the first level cache line boundary from to [Polly] Align newly created arrays to the first level cache line boundary.
Dec 21 2016, 3:13 AM
gareevroman retitled D28019: [Polly] Change the determination of parameters of macro-kernel from to [Polly] Change the determination of parameters of macro-kernel.
Dec 21 2016, 3:09 AM

Dec 19 2016

gareevroman added a comment to D27878: [Polly] Use three-dimensional arrays to store packed operands of the matrix multiplication.

Could you add some more information to the commit message:

Dec 19 2016, 3:42 AM
gareevroman updated D27878: [Polly] Use three-dimensional arrays to store packed operands of the matrix multiplication.
Dec 19 2016, 3:41 AM
gareevroman updated the diff for D27878: [Polly] Use three-dimensional arrays to store packed operands of the matrix multiplication.

Hi Michael,

Dec 19 2016, 1:25 AM

Dec 17 2016

gareevroman added a comment to D27878: [Polly] Use three-dimensional arrays to store packed operands of the matrix multiplication.

For example, getAddressFunction() can return the following map . Subsequently, Memory::applyScheduleToAccessRelation tries to apply the schedule to its domain.

Dec 17 2016, 8:20 AM
gareevroman retitled D27878: [Polly] Use three-dimensional arrays to store packed operands of the matrix multiplication from to [Polly] Compute the lexicographic minimum in Memory::applyScheduleToAccessRelation, when the schedule is applied.
Dec 17 2016, 8:04 AM

Dec 15 2016

gareevroman updated the diff for D25653: [Polly] Change the loop order of micro and macro kernels.

Hi Roman,

Dec 15 2016, 3:41 AM

Oct 18 2016

gareevroman updated the diff for D25653: [Polly] Change the loop order of micro and macro kernels.

Hi Roman,

the general direction looks fine to me. Two questions:

Oct 18 2016, 8:09 AM
gareevroman added a comment to D25655: [Polly] Restrict ranges of extension maps.

Hi Michael,

Oct 18 2016, 7:59 AM

Oct 16 2016

gareevroman retitled D25655: [Polly] Restrict ranges of extension maps from to [Polly] Restrict ranges of extension maps.
Oct 16 2016, 6:11 AM
gareevroman updated D25653: [Polly] Change the loop order of micro and macro kernels.
Oct 16 2016, 1:02 AM
gareevroman retitled D25653: [Polly] Change the loop order of micro and macro kernels from to [Polly] Change the loop order of micro and macro kernels.
Oct 16 2016, 12:59 AM

Sep 13 2016

gareevroman added a comment to D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.

Hi Tobias,

Sep 13 2016, 7:14 AM
gareevroman updated the diff for D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.

A new version updated according to the comments.

Sep 13 2016, 7:12 AM

Sep 12 2016

gareevroman added a comment to D23991: [Polly] Store the size of the outermost dimension in case of newly created arrays that require memory allocation..

I think that the first dimensions is always nullptr, and all others are never nullptr. This is what your code is written for, but we can be more general, where nullptr could be at any position.

Sep 12 2016, 10:18 AM
gareevroman added a comment to D23991: [Polly] Store the size of the outermost dimension in case of newly created arrays that require memory allocation..

Hi Michael,

Sep 12 2016, 6:49 AM
gareevroman updated the diff for D23991: [Polly] Store the size of the outermost dimension in case of newly created arrays that require memory allocation..

A new version updated according to the comments.

Sep 12 2016, 6:48 AM

Aug 31 2016

gareevroman added a comment to D23991: [Polly] Store the size of the outermost dimension in case of newly created arrays that require memory allocation..

Hi Michael,

Aug 31 2016, 12:54 AM
gareevroman updated the diff for D23991: [Polly] Store the size of the outermost dimension in case of newly created arrays that require memory allocation..

A new version updated according to the comments.

Aug 31 2016, 12:54 AM

Aug 30 2016

gareevroman added a comment to D23991: [Polly] Store the size of the outermost dimension in case of newly created arrays that require memory allocation..

Hi Michael,

Aug 30 2016, 5:16 AM
gareevroman updated the diff for D23991: [Polly] Store the size of the outermost dimension in case of newly created arrays that require memory allocation..

A new version updated according to the comments.

Aug 30 2016, 5:16 AM

Aug 29 2016

gareevroman retitled D23991: [Polly] Store the size of the outermost dimension in case of newly created arrays that require memory allocation. from to [Polly] Store the size of the outermost dimension in case of newly created arrays that require memory allocation..
Aug 29 2016, 6:59 AM

Aug 27 2016

gareevroman updated the diff for D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.

Fix misprints.

Aug 27 2016, 2:46 AM
gareevroman updated the diff for D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.

Hi Roman,

thanks for this update:

Aug 27 2016, 1:02 AM

Aug 26 2016

gareevroman added inline comments to D23916: [Polly] Check validity of new access relations. NFC..
Aug 26 2016, 6:54 AM · Restricted Project
gareevroman added a comment to D23916: [Polly] Check validity of new access relations. NFC..

Hi Michael,

Aug 26 2016, 6:53 AM · Restricted Project

Aug 21 2016

gareevroman added inline comments to D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.
Aug 21 2016, 11:04 AM
gareevroman updated the diff for D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.

This is a new version of the patch updated according to the comments.

Aug 21 2016, 11:04 AM
gareevroman retitled D23759: [GSoC 2016] [Polly] [WIP] Simplify AccFuncMap to vector<> AccessFunctions from to [GSoC 2016] [Polly] [WIP] Simplify AccFuncMap to vector<> AccessFunctions.
Aug 21 2016, 3:47 AM

Aug 20 2016

gareevroman added inline comments to D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.
Aug 20 2016, 1:21 AM
gareevroman retitled D23740: [GSoC 2016] [Polly] [WIP] Add a flag to dump SCoP optimized with the IslScheduleOptimizer pass from to [GSoC 2016] [Polly] [WIP] Add a flag to dump SCoP optimized with the IslScheduleOptimizer pass.
Aug 20 2016, 1:19 AM
gareevroman added a comment to D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.

Hi Tobias,

Aug 20 2016, 1:03 AM

Aug 16 2016

gareevroman added inline comments to D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.
Aug 16 2016, 10:18 AM
gareevroman updated the diff for D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.

Hi Michael,

Aug 16 2016, 10:11 AM

Aug 15 2016

gareevroman updated the diff for D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

Hi Tobias,

Aug 15 2016, 3:08 AM

Aug 13 2016

gareevroman added inline comments to D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.
Aug 13 2016, 4:16 AM
gareevroman updated the diff for D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

A new version of the patch updated according to the comments.

Aug 13 2016, 4:15 AM

Aug 11 2016

gareevroman added a comment to D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

Hi Tobias,

Aug 11 2016, 8:34 AM

Aug 9 2016

gareevroman added a comment to D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.

Hi Michael,

Aug 9 2016, 6:54 AM

Aug 8 2016

gareevroman updated the diff for D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

In this version the issue related to wrong access function of B type matrices is fixed and redundant functions are removed.

Aug 8 2016, 5:58 AM
gareevroman added a comment to D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.

In this draft of the patch copy statements are represented as Scop statements whose values of BB and R fields are equal to nullptr. These statements have only two memory accesses. The first one represents reading from an array that should be packed. The second one represents writing to a created array. What do you think about it?

Aug 8 2016, 5:55 AM
gareevroman retitled D23260: [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation from to [GSoC 2016] [Polly] [WIP] Perform copying to created arrays according to the packing transformation.
Aug 8 2016, 5:54 AM

Aug 1 2016

gareevroman added a comment to D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

As far as I understand, it is more intuitive to remap all accesses to the array to a new array using, for example, the following function:

Aug 1 2016, 11:43 AM
gareevroman updated the diff for D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

A new version of the patch updated according to the comments.

Aug 1 2016, 11:41 AM

Jul 30 2016

gareevroman added a comment to D22828: [GSoC 2016][Polly][WIP] Extend the jscop interface to allow the user to declare new arrays and to reference these arrays from access expressions.

I get the following error:

"error: ‘polly::PollyIRBuilder’ has no member named ‘GetCurrentBlock’"

If I'm not mistaken, IRBuilder doesn't have methods that return basic
blocks.

Jul 30 2016, 2:35 AM
gareevroman added inline comments to D22828: [GSoC 2016][Polly][WIP] Extend the jscop interface to allow the user to declare new arrays and to reference these arrays from access expressions.
Jul 30 2016, 1:45 AM

Jul 29 2016

gareevroman updated the diff for D22828: [GSoC 2016][Polly][WIP] Extend the jscop interface to allow the user to declare new arrays and to reference these arrays from access expressions.

I would make this a plain pointer and use a unique_ptr to track ownership in ScopArrayInfoSet

Jul 29 2016, 9:37 AM
gareevroman added inline comments to D22828: [GSoC 2016][Polly][WIP] Extend the jscop interface to allow the user to declare new arrays and to reference these arrays from access expressions.
Jul 29 2016, 4:20 AM

Jul 28 2016

gareevroman added inline comments to D22828: [GSoC 2016][Polly][WIP] Extend the jscop interface to allow the user to declare new arrays and to reference these arrays from access expressions.
Jul 28 2016, 2:31 PM
gareevroman updated the diff for D22828: [GSoC 2016][Polly][WIP] Extend the jscop interface to allow the user to declare new arrays and to reference these arrays from access expressions.

Hi Tobias,

Jul 28 2016, 2:31 PM

Jul 27 2016

gareevroman added inline comments to D22828: [GSoC 2016][Polly][WIP] Extend the jscop interface to allow the user to declare new arrays and to reference these arrays from access expressions.
Jul 27 2016, 11:39 AM
gareevroman updated the diff for D22828: [GSoC 2016][Polly][WIP] Extend the jscop interface to allow the user to declare new arrays and to reference these arrays from access expressions.

Thanks for the comments! I've tried to address them in this version of the patch.

Jul 27 2016, 11:37 AM

Jul 26 2016

gareevroman added a comment to D22828: [GSoC 2016][Polly][WIP] Extend the jscop interface to allow the user to declare new arrays and to reference these arrays from access expressions.

This is a draft of the path. I think that it has at least the following drawbacks:

Jul 26 2016, 12:00 PM
gareevroman retitled D22828: [GSoC 2016][Polly][WIP] Extend the jscop interface to allow the user to declare new arrays and to reference these arrays from access expressions from to [GSoC 2016][Polly][WIP] Extend the jscop interface to allow the user to declare new arrays and to reference these arrays from access expressions.
Jul 26 2016, 11:59 AM

Jul 25 2016

gareevroman added a comment to D21491: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel.

@grosser, @Meinersbur, @mreisinger, thank you for the comments! I've tried to address them in r276616 and r276627.

Jul 25 2016, 2:53 AM

Jul 20 2016

gareevroman added inline comments to D21491: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel.
Jul 20 2016, 2:56 AM

Jul 18 2016

gareevroman added a comment to D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

Also, AFAIU only one of the two matrices A and B needs to be transposed. Consequently, I would expect that only one of them has to be mapped. You seem to want to map two arrays - MemRef_6 and MemRef_7. Why is this necessary?

Jul 18 2016, 7:47 AM

Jul 17 2016

gareevroman added a comment to D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

Hi Roman,

I may not yet fully unserstand this issue, but don't you transform all accesses to the matrix. Assume you don't transpose a submatrix but the full matrix A would applying the mapping A[x0][x1] -> A2[x1][x0] on all accesses what you want to do. The same should hold when you are working with submatrixes, except that the mapping function is slightly more complicated.

Yes, I think this is true.

I guess I figured out. Thanks.

It is not possible that, for example, A[i][j] and A[i][k] of the following access relations S1[i, j, k]->A[i][j] and S2[i, j, k]->A[i, k], which may correspond to the following code, have the same identifier. Consequently, we'll be able to remap only one of these two accesses, if we apply A[i][j] -> New[x][y][z], using the interface. Is it right?

Not sure what you mean by the same identifier. It still seems you want to apply the mapping only to a subset of the memory references by somehow identifying the ones on which you want to apply the mapping through the identifiers in their access function. Is this true?

Jul 17 2016, 5:23 AM
gareevroman added a comment to D21003: Fix mentor name.

@vivekvpandya, no worries. I just tried to understand the issue.

Jul 17 2016, 5:07 AM
gareevroman added a comment to D21003: Fix mentor name.

OK. I'll commit it. @vivekvpandya, @mreisinger do you have a commit access? Sorry, I don't know whether you have it. Usually authors commit their patches.

Jul 17 2016, 4:53 AM

Jul 16 2016

gareevroman added a comment to D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

Hi Roman,

I may not yet fully unserstand this issue, but don't you transform all accesses to the matrix. Assume you don't transpose a submatrix but the full matrix A would applying the mapping A[x0][x1] -> A2[x1][x0] on all accesses what you want to do. The same should hold when you are working with submatrixes, except that the mapping function is slightly more complicated.

Jul 16 2016, 2:33 AM
gareevroman added inline comments to D21491: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel.
Jul 16 2016, 12:28 AM

Jul 15 2016

gareevroman added a comment to D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

Hi Michael,

Jul 15 2016, 11:09 PM
gareevroman added a comment to D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.
  1. I am not sure I like the interface to replace memory accesses. It seems this interface takes a specific memory access relation and replaces all accesses that have this specific relation the new access relation. I understand that this might work, but wonder if another interface might not be more intuitive. One could e.g. provide a relation

A[i][j] -> New[x][y][z] which is applied to all accesses to remap all accesses to A to a new array. Would such an interface work for your transformation?

Jul 15 2016, 11:07 PM

Jul 14 2016

gareevroman added a comment to D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.
  1. I am not sure I like the interface to replace memory accesses. It seems this interface takes a specific memory access relation and replaces all accesses that have this specific relation the new access relation. I understand that this might work, but wonder if another interface might not be more intuitive. One could e.g. provide a relation

A[i][j] -> New[x][y][z] which is applied to all accesses to remap all accesses to A to a new array. Would such an interface work for your transformation?

Yes, I think that an ability to remap specific memory accesses to A is unnecessary for the transformation and such an interfaces would work fine for it.

Jul 14 2016, 6:23 AM
gareevroman added a comment to D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

Hi Roman,

thanks for your work. Even though this is still WIP, here already some first commtents:

Jul 14 2016, 2:53 AM

Jul 13 2016

gareevroman updated the diff for D21491: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel.

The test case was missed.

Jul 13 2016, 12:29 PM
gareevroman added inline comments to D21491: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel.
Jul 13 2016, 12:24 PM
gareevroman updated the diff for D21491: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel.

Hi Tobias,

Jul 13 2016, 12:21 PM

Jul 11 2016

gareevroman updated the diff for D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

Fix wrong comments and names of variables.

Jul 11 2016, 3:16 AM

Jul 9 2016

gareevroman updated the diff for D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

Fix incomplete comments.

Jul 9 2016, 8:50 AM
gareevroman updated D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.
Jul 9 2016, 6:59 AM
gareevroman added a comment to D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation.

This is a draft of the third patch to apply the BLIS matmul optimization pattern on matmul kernels. It should probably be split to separate modification of the existent code (creation of macro kernel, determination its parameters http://reviews.llvm.org/D21491) and replacement of access relations.

Jul 9 2016, 6:58 AM
gareevroman retitled D22187: [GSoC 2016] [Polly] [WIP] Perform replacement of access relations and creation of new arrays according to the packing transformation from to [GSoC 2016] [Polly] [WIP] Perform replacement of access relations according to the packing transformation.
Jul 9 2016, 6:58 AM

Jul 5 2016

gareevroman added a comment to D21283: Add weekly report blog url to SummerOfCode/2016.html.

Has this patch been committed?

Jul 5 2016, 11:00 PM

Jun 24 2016

gareevroman added inline comments to D21491: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel.
Jun 24 2016, 4:53 AM
gareevroman updated the diff for D21491: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel.

Changed according to the comments.

Jun 24 2016, 4:51 AM

Jun 21 2016

gareevroman added a comment to D21491: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel.

Thanks for the patch and meaningful comments.

Jun 21 2016, 12:13 AM

Jun 18 2016

gareevroman added a comment to D21491: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel.

This is a draft of the second patch to apply the BLIS matmul optimization pattern on matmul kernels. I'm not sure how it is better to implement interchanging of loops using schedule trees. That's why I would be very grateful for your comments, feedback and ideas.

Jun 18 2016, 10:40 AM
gareevroman retitled D21491: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel from to [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and interchangings to get a macro-kernel.
Jun 18 2016, 10:40 AM

Jun 13 2016

gareevroman added a comment to D21140: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and unrollings to get a micro-kernel.

Hi Tobias,

Jun 13 2016, 10:33 AM
gareevroman accepted D21283: Add weekly report blog url to SummerOfCode/2016.html.
Jun 13 2016, 5:08 AM

Jun 12 2016

gareevroman updated the diff for D21140: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and unrollings to get a micro-kernel.

Hi Tobias,

Jun 12 2016, 10:42 AM

Jun 8 2016

gareevroman added a comment to D21140: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and unrollings to get a micro-kernel.

I haven't yet found out how to get throughput of vector instructions per clock cycle and latency of instructions That's why these values are passed as command line parameters. Maybe TargetTransformInfo::getArithmeticInstrCost can be used for this purpose. However, I haven't found an algorithm that is used by target architectures to compute a cost in TargetTransformInfoImpl.

Jun 8 2016, 8:53 AM
gareevroman retitled D21140: [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and unrollings to get a micro-kernel from to [GSoC 2016] [Polly] [WIP] Apply all necessary tilings and unrollings to get a micro-kernel.
Jun 8 2016, 8:53 AM

Jun 3 2016

gareevroman added a comment to D20969: The second fix of "determination of statements that contain matrix multiplication".

Thank you for the comment!

Jun 3 2016, 10:27 AM
gareevroman retitled D20969: The second fix of "determination of statements that contain matrix multiplication" from to The second fix of "determination of statements that contain matrix multiplication".
Jun 3 2016, 9:22 AM

May 31 2016

gareevroman retitled D20806: [GSoC 2016][Polly][FIX] Determination of statements that contain matrix multiplication from to [GSoC 2016][Polly][FIX] Determination of statements that contain matrix multiplication.
May 31 2016, 3:10 AM

May 28 2016

gareevroman updated the diff for D20575: [GSoC 2016][Polly] Determination of statements that contain matrix multiplication.

-instnamer was used.

May 28 2016, 9:02 AM
gareevroman updated the diff for D20575: [GSoC 2016][Polly] Determination of statements that contain matrix multiplication.

Thank you for the explanation! This version of a patch adds positive and negative test cases. I’ve also fixed issues related to the isInputDimUsed and the debug output of the optimizeBand.

May 28 2016, 8:05 AM

May 27 2016

gareevroman updated the diff for D20575: [GSoC 2016][Polly] Determination of statements that contain matrix multiplication.

Hello Tobias,

May 27 2016, 10:39 AM

May 24 2016

gareevroman added a comment to D20575: [GSoC 2016][Polly] Determination of statements that contain matrix multiplication.

This is a first draft, which contains determination of the following class of statements:

May 24 2016, 9:59 AM
gareevroman retitled D20575: [GSoC 2016][Polly] Determination of statements that contain matrix multiplication from to [GSoC 2016][Polly][WIP] Determination of statements that contain matrix multiplication.
May 24 2016, 9:59 AM