Meinersbur (Michael Kruse)
User

Projects

User does not belong to any projects.

User Details

User Since
Jun 17 2015, 7:07 AM (165 w, 5 d)

Recent Activity

Today

Meinersbur added inline comments to D50209: cmake: Explicitely specify benchmark data.
Mon, Aug 20, 5:29 PM
Meinersbur added inline comments to D50209: cmake: Explicitely specify benchmark data.
Mon, Aug 20, 4:23 PM
Meinersbur accepted D50209: cmake: Explicitely specify benchmark data.

I am ok with committing this, but maybe we should have someone else's opinion as well?

Mon, Aug 20, 10:38 AM
Meinersbur added inline comments to D49281: [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes..
Mon, Aug 20, 10:16 AM
Meinersbur added inline comments to D50698: [UnJ] Ensure unroll_and_jam metadata is removed once consumed..
Mon, Aug 20, 9:39 AM

Fri, Aug 17

Meinersbur added inline comments to D49281: [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes..
Fri, Aug 17, 4:24 PM
Meinersbur updated the diff for D49281: [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes..
  • Report unroll-and-jam as not applied even if unroll is present as well.
    • rename followup_cyclic/followup_noncyclic to followup_sequential/followup_coincident
    • Move hasUnrollAndJamTransformation in LoopUnrollAndJamPass to different place
    • Remove some unrelated whitespace changes made by clang-format
    • Extract followup attribute names into constant
Fri, Aug 17, 4:23 PM
Meinersbur committed rL340072: [AST] Adapt Polly to AnalysisSetTracker changes. NFC..
[AST] Adapt Polly to AnalysisSetTracker changes. NFC.
Fri, Aug 17, 12:32 PM

Thu, Aug 16

Meinersbur added a comment to D50805: Don't warn on returning the address of a label from a statement expression.

If you added a new option -Wret-addr-label as suggested above (for a total patch of +2 lines), then is it accurate to say:

  • if -Wret-addr-label was enabled by default, we know of at least one codebase that would pass -Wno-ret-addr-label to their build
  • if -Wret-addr-label was disabled by default, we don't know of any codebases that would voluntarily enable it And if nobody would enable it voluntarily... might as well eliminate it, right?
Thu, Aug 16, 8:47 AM · Restricted Project

Tue, Aug 14

Meinersbur added inline comments to D50075: [UnJ] Improve explicit loop count checks.
Tue, Aug 14, 3:56 PM
Meinersbur added inline comments to D49281: [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes..
Tue, Aug 14, 3:46 PM
Meinersbur added a comment to D49281: [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes..

I am thinking about adding a LoopMetadataTacker (sort of a combination of LoopVectorizeHints and AssumptionTracker) analysis pass which would centralize the interpretation of that metadata and avoid the linear search through the metadata list when looking up a specific attribute.

Tue, Aug 14, 3:44 PM
Meinersbur added inline comments to D50698: [UnJ] Ensure unroll_and_jam metadata is removed once consumed..
Tue, Aug 14, 3:04 PM

Mon, Aug 13

Meinersbur added inline comments to D50214: Add inherited attributes before parsed attributes..
Mon, Aug 13, 2:11 PM
Meinersbur added a reviewer for D50642: [IslExprBuilder] Allow 64-bit ints in hasLargeInts(): grosser.
Mon, Aug 13, 11:35 AM
Meinersbur added a comment to D50642: [IslExprBuilder] Allow 64-bit ints in hasLargeInts().

To add some details: The original failure was external/skia/src/gpu/GrTestUtils.cpp of the aosp buildbot. It expects a library function __muloti4 which was lowered from the intrinsic llvm.smul.with.overflow.i128. The next smaller llvm.smul.with.overflow.i64 should be able to handle 64 bit values (not just 64 bits).

Mon, Aug 13, 9:56 AM
Meinersbur accepted D50529: [test-suite] Add Bilateral Filter kernel using benchmark library.
Mon, Aug 13, 9:17 AM

Fri, Aug 10

Meinersbur added a comment to D49281: [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes..

The added paragraph looks good to me on the implementation side specification. Looking forward to see the programmers (i.e., compiler users, not compiler writers) side pragma description, but that will not gate my review of this patch. There is a difference between specification forcing one behavior versus implementation choice ends up in the same behavior. I wanted the former, not the latter.

Fri, Aug 10, 7:43 PM
Meinersbur committed rL339484: [DepInfo] Use isl++ in Dependences::isValidSchedule. NFC..
[DepInfo] Use isl++ in Dependences::isValidSchedule. NFC.
Fri, Aug 10, 3:34 PM

Thu, Aug 9

Meinersbur added a comment to D49281: [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes..

I'd like to see us explicitly saying that any subsequent explicit transformation metadata will be ignored for the given loop ---- if that's what we'll agree on, or be explicit about something else we'll agree on in the terms that can be clearly explainable to the programmers. "Compiler will skip all remaining transformations after the first failed transform" is pretty straightforward to the programmers. If anyone is proposing other behaviors, I'd like to also see how to explain those behaviors to the programmers.

Thu, Aug 9, 8:43 PM
Meinersbur updated the diff for D49281: [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes..
  • Explicitly document followup of not applied transformations to be ignored
  • Unroll/UnrollAndJam: Interpret enable/count/full as forced
  • Unroll/UnrollAndJam: Add tests for disable_nonforced combined with enable/count/full
  • Reduce size of unroll-pragmas_transform.ll
Thu, Aug 9, 8:42 PM
Meinersbur added a comment to D50529: [test-suite] Add Bilateral Filter kernel using benchmark library.

Should the total execution time of benchmarks be around second or less?
Maybe reduce the number of tested parameters to reduce the total runtime?

Thu, Aug 9, 3:22 PM
Meinersbur accepted D50063: [UnJ] Pull code out into a separate function NFC.

Ah, sorry, I now see HasConsistentIterationCounts has been suggested in that other ticket. Oh well, as I said, I was bike shedding names (but still think 'invariant' is better :-)) Anyway, please ignore if you disagree.

Thu, Aug 9, 2:41 PM
Meinersbur accepted D50075: [UnJ] Improve explicit loop count checks.

There are other pragma tests in pragma.ll, which check combinations of unroll and unroll_and_jam pragmas. The current behaviour if there is both unroll metadata and unroll_and_jam metadata isn't currently very refined. I would expect, at least in the default pipeline, for the unroll metadata to be handled first in one of the early unroll passes.

Thu, Aug 9, 2:27 PM
Meinersbur accepted D49883: [test-suite] Added Image Processing Kernels Using Benchmark Library: Dilate Kernel.

LGTM

Thu, Aug 9, 11:59 AM
Meinersbur added a comment to D50322: Bitcode tests failure because of the change in r338787.

Could you close the review if it's not needed anymore?

Thu, Aug 9, 8:54 AM

Tue, Aug 7

Meinersbur edited reviewers for D50425: The fix for c++11 flag issue was fixed in svn r339154 but for one Blur benchmark., added: proton; removed: proton0001.
Tue, Aug 7, 10:34 PM
Meinersbur closed D50379: New ImageProcessing tests were failing becuase c++ flags are used in c flags..

Seems that @proton already fixed this as part of rL339154. Closing this review. In any case, I want to thank you for opening it!

Tue, Aug 7, 12:31 PM
Meinersbur added a comment to D50322: Bitcode tests failure because of the change in r338787.

Looks like an obvious change, but r338787 is by @MatzeB I'd wait for his ok.

Tue, Aug 7, 9:36 AM
Meinersbur added inline comments to D50055: Update the coding standard about NFC changes and whitespace.
Tue, Aug 7, 8:31 AM
Meinersbur added a comment to D50379: New ImageProcessing tests were failing becuase c++ flags are used in c flags..

@santosh Do you need someone to commit?

Tue, Aug 7, 8:30 AM
Meinersbur accepted D50379: New ImageProcessing tests were failing becuase c++ flags are used in c flags..

Thank you. LGTM.

Tue, Aug 7, 8:28 AM

Mon, Aug 6

Meinersbur accepted D50345: [test-suite] Add Interpolation kernels Using Benchmark Library.

LGTM

Mon, Aug 6, 7:15 PM
Meinersbur accepted D48046: [test-suite] Backprop kernel from Rodinia Benchmark.

LGTM

Mon, Aug 6, 12:23 PM
Meinersbur added a comment to D49281: [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes..

What I'm not seeing from this RFC/patch is that, if the programmer specifies transformation behavior A -> B -> C, what happens if transformation A does not kick-in? Should we just warn that "A did not happen" and stop processing the request B and C?

Mon, Aug 6, 12:10 PM
Meinersbur accepted D49341: [test-suite] Added Image Processing Kernels Using Benchmark Library: Blur Algorithms.

LGTM

Mon, Aug 6, 8:32 AM

Sat, Aug 4

Meinersbur added inline comments to D50055: Update the coding standard about NFC changes and whitespace.
Sat, Aug 4, 7:48 PM

Fri, Aug 3

Meinersbur added a comment to D50214: Add inherited attributes before parsed attributes..

For this patch the goal is to have the attributes in the AST in an order that is less surprising to consumers (including out-of-tree). If we change it now, new/revised code/diagnostics will be written to match this order.

Fri, Aug 3, 8:07 PM
Meinersbur added a comment to D49281: [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes..

Some extra tests for nonforced + a pragma would be good to see.

Fri, Aug 3, 7:47 PM
Meinersbur added inline comments to D49341: [test-suite] Added Image Processing Kernels Using Benchmark Library: Blur Algorithms.
Fri, Aug 3, 11:32 AM
Meinersbur accepted D49886: [test-suite] Add pathfinder kernel from Rodinia Benchmark.

LGTM

Fri, Aug 3, 9:15 AM

Thu, Aug 2

Meinersbur committed rL338810: [CodeGen] Emit parallel_loop_access for each loop in the loop stack..
[CodeGen] Emit parallel_loop_access for each loop in the loop stack.
Thu, Aug 2, 9:43 PM
Meinersbur committed rC338810: [CodeGen] Emit parallel_loop_access for each loop in the loop stack..
[CodeGen] Emit parallel_loop_access for each loop in the loop stack.
Thu, Aug 2, 9:43 PM
Meinersbur closed D48808: [CodeGen] Emit parallel_loop_access for each loop in the loop stack..
Thu, Aug 2, 9:43 PM
Meinersbur added a comment to D48348: [ADT] Add zip_longest iterators..

Getting the size may require iterating the sequence in advance, which I tried to avoid in D48100.

Yeah, it's a tradeoff there, to be sure. Not sure if anyone else has thoughts on the design tradeoffs here - would hope other folks might chime in.

Thu, Aug 2, 8:55 PM
Meinersbur added a comment to D48100: Append new attributes to the end of an AttributeList..

I have two approaches to tackle the wrong marker order: D50215 and D50216. IMHO both are too invasive to be justified for the small issue.

Thu, Aug 2, 8:04 PM
Meinersbur added a dependency for D50216: Pass IsInherited when merging attribute lists [RFC]: D50214: Add inherited attributes before parsed attributes..
Thu, Aug 2, 8:01 PM
Meinersbur added a dependent revision for D50214: Add inherited attributes before parsed attributes.: D50216: Pass IsInherited when merging attribute lists [RFC].
Thu, Aug 2, 8:01 PM
Meinersbur created D50216: Pass IsInherited when merging attribute lists [RFC].
Thu, Aug 2, 8:00 PM
Meinersbur created D50215: Change attribute merge order [RFC].
Thu, Aug 2, 7:37 PM
Meinersbur created D50214: Add inherited attributes before parsed attributes..
Thu, Aug 2, 7:23 PM
Meinersbur committed rL338800: Append new attributes to the end of an AttributeList..
Append new attributes to the end of an AttributeList.
Thu, Aug 2, 6:22 PM
Meinersbur committed rC338800: Append new attributes to the end of an AttributeList..
Append new attributes to the end of an AttributeList.
Thu, Aug 2, 6:22 PM
Meinersbur closed D48100: Append new attributes to the end of an AttributeList..
Thu, Aug 2, 6:21 PM
Meinersbur closed D48100: Append new attributes to the end of an AttributeList..
Thu, Aug 2, 6:21 PM
Meinersbur added a comment to D50209: cmake: Explicitely specify benchmark data.

Some notes:

  • I is only for the benchmarks shipping with the test-suite yet. The things in External will need some additional changes (they will keep working as is, just won't consistenly have their data in the builddir)
  • The copying grows the builddir from ~900MB to 1GB for me. If this is a concern then we could add a mode that creates symlinks when the test-suite is running locally; however I wasn't convinced yet it is worth having two modes just for 100MB savings in the builddir.
Thu, Aug 2, 6:19 PM

Wed, Aug 1

Meinersbur added a comment to D49950: [Polly][JSONExporter] Replace bundled Jsoncpp with LLVM's JSON.h. NFC..
if (!ParseResult) {
  ParseResult.takeError();
  errs() << "JSCoP file could not be parsed\n";
  return false;
}
json::Object &jscop = *ParseResult.get().getAsObject();

What are you doing with the result of takeError()?

Wed, Aug 1, 5:15 PM · Restricted Project
Meinersbur committed rL338659: [JSONExporter] Print instead of ignoring parser error..
[JSONExporter] Print instead of ignoring parser error.
Wed, Aug 1, 5:11 PM
Meinersbur committed rL338646: [ScopBuilder] Set domain to empty instead of NULL..
[ScopBuilder] Set domain to empty instead of NULL.
Wed, Aug 1, 3:28 PM
Meinersbur added a comment to D49024: [Polly] [WIP] Introduce ShapeInfo into polly for sizes and strides..

Suppose we are considering a 3-dimensional array named arr (Consider C language for now).
Does the offset/padding solution suggested in the previous comment model the situation where each dimension of the array has its range from 0 to some dimension size value and while accessing the array, we use some arithmetic along with the respective dimension index ( arr[i+1][2*j-1][3*k] for instance)?

Wed, Aug 1, 2:50 PM
Meinersbur updated the diff for D48100: Append new attributes to the end of an AttributeList..
  • Remove TODOs about the attribute order
Wed, Aug 1, 2:27 PM
Meinersbur added inline comments to D48100: Append new attributes to the end of an AttributeList..
Wed, Aug 1, 2:24 PM
Meinersbur added a comment to D49886: [test-suite] Add pathfinder kernel from Rodinia Benchmark.

Can you add the Rodinia/Makefile file? It was present in the first revision r338163 but after it was reverted in r338166, the subsequent revisions didn't add it back and it's been causing buildbot failures ever since.

Wed, Aug 1, 1:07 PM
Meinersbur added a comment to D48100: Append new attributes to the end of an AttributeList..

I am unsure how to proceed. Commit since already accepted? Wait for reconfirmation? Open new differential?

Wed, Aug 1, 1:01 PM
Meinersbur added reviewers for D48100: Append new attributes to the end of an AttributeList.: dlj, sammccall, dmgreen.
Wed, Aug 1, 1:00 PM
Meinersbur updated the diff for D48100: Append new attributes to the end of an AttributeList..

Rebase after de-listifying in r336945

Wed, Aug 1, 12:57 PM
Meinersbur reopened D48100: Append new attributes to the end of an AttributeList..

Reopen after revert (and to be able to update the diff)

Wed, Aug 1, 12:57 PM

Tue, Jul 31

Meinersbur added a comment to D49024: [Polly] [WIP] Introduce ShapeInfo into polly for sizes and strides..

As mentioned in the last phone call, I think we should not use 'Stride' as an alternative to row-major indexing. The primary reason is that there are no unique coordinates for a single memory location which means we cannot accurately compute dependencies. Indeed, the delinearization stuff is all about ensuring that there is no unpredictable aliasing.

Tue, Jul 31, 7:21 PM
Meinersbur added inline comments to D49341: [test-suite] Added Image Processing Kernels Using Benchmark Library: Blur Algorithms.
Tue, Jul 31, 6:23 PM
Meinersbur committed rL338466: [JSONExporter] Try to appease buildbot. NFC..
[JSONExporter] Try to appease buildbot. NFC.
Tue, Jul 31, 5:50 PM
Meinersbur committed rL338462: [Polly-ACC] Fix compilation after r338450. NFC..
[Polly-ACC] Fix compilation after r338450. NFC.
Tue, Jul 31, 5:28 PM
Meinersbur committed rL338461: [JSONExporter] Replace bundled Jsoncpp with llvm/Support/JSON.h. NFC..
[JSONExporter] Replace bundled Jsoncpp with llvm/Support/JSON.h. NFC.
Tue, Jul 31, 5:15 PM
Meinersbur closed D49950: [Polly][JSONExporter] Replace bundled Jsoncpp with LLVM's JSON.h. NFC..
Tue, Jul 31, 5:15 PM · Restricted Project
Meinersbur updated the diff for D49950: [Polly][JSONExporter] Replace bundled Jsoncpp with LLVM's JSON.h. NFC..
  • Remove appendToArray helper function
  • Replace some get("")->getAsXYZ by getXYZ("")
Tue, Jul 31, 5:12 PM · Restricted Project
Meinersbur committed rL338451: [CodeGen] Convert IslNodeBuilder::getNumberOfIterations to isl++. NFC..
[CodeGen] Convert IslNodeBuilder::getNumberOfIterations to isl++. NFC.
Tue, Jul 31, 4:02 PM
Meinersbur committed rL338450: [CodeGen] Convert IslNodeBuilder::createForSequential to isl++. NFC..
[CodeGen] Convert IslNodeBuilder::createForSequential to isl++. NFC.
Tue, Jul 31, 3:43 PM
Meinersbur committed rL338449: [CodeGen] Convert IslNodeBuilder::getUpperBound to isl++. NFC..
[CodeGen] Convert IslNodeBuilder::getUpperBound to isl++. NFC.
Tue, Jul 31, 3:43 PM
Meinersbur accepted D47267: [UnrollAndJam] Add unroll_and_jam pragma handling.

LGTM

Tue, Jul 31, 10:13 AM
Meinersbur accepted D50062: [UnJ] Add debug messages at to why loops are not unrolled. NFC.

LGTM.

Tue, Jul 31, 9:49 AM
Meinersbur added a comment to D50075: [UnJ] Improve explicit loop count checks.

I find the summary confusing. Can we say that simple unrolling will be prioritized over llvm.loop.unroll_and_jam.count metadata and -unroll-and-jam-count= cmdline options?

Tue, Jul 31, 9:39 AM
Meinersbur added a comment to D48271: [llvm-readobj] Fix printing format.

Has this been recommitted yet?

Tue, Jul 31, 9:13 AM

Mon, Jul 30

Meinersbur added a comment to D49872: [Polly][ScopDetect] Add option -polly-allow-nonaffine-read and enable by default..

Cannot commit this as it miscompiles a few test-suite tests (as does -polly-allow-nonaffine):

FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pabsw_239.test (64 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_packssdw_217.test (67 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_packusdw_296.test (73 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_paddsw_102.test (97 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_paddusw_104.test (104 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_paddw_92.test (110 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pavgw_127.test (119 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pavgw_128.test (120 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pcmpeqw_113.test (146 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pcmpgtw_114.test (160 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pmaxsw_129.test (174 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pmaxuw_283.test (186 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pminsw_130.test (194 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pminuw_284.test (206 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pmulhuw_110.test (210 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pmulhuw_134.test (212 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pmulhuw_133.test (213 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pmulhuw_135.test (214 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pmulhw_106.test (227 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pmulhw_107.test (228 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pmulhw_109.test (230 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pmulhw_108.test (231 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_pmullw_94.test (248 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_psubsw_103.test (265 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_psubusw_105.test (273 of 1340)
FAIL: test-suite :: Bitcode/simd_ops/simd_ops_test_op_psubw_93.test (281 of 1340)
NOEXE: test-suite :: External/SPEC/CFP2017rate/526.blender_r/526.blender_r.test (532 of 1340)
FAIL: test-suite :: External/SPEC/CINT2006/401.bzip2/401.bzip2.test (554 of 1340)
FAIL: test-suite :: External/SPEC/CINT2006/458.sjeng/458.sjeng.test (563 of 1340)
FAIL: test-suite :: External/SPEC/CINT2017rate/502.gcc_r/502.gcc_r.test (569 of 1340)
FAIL: test-suite :: External/SPEC/CINT2017speed/602.gcc_s/602.gcc_s.test (578 of 1340)
FAIL: test-suite :: MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt.test (741 of 1340)
FAIL: test-suite :: MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl.test (742 of 1340)
FAIL: test-suite :: Polybench/Polybench-boost/linear-algebra/kernels/3mm/Pboost_3mm.test (1021 of 1340)
Mon, Jul 30, 7:58 PM · Restricted Project

Sat, Jul 28

Meinersbur added a comment to D49503: [test-suite] Add Image Processing Kernels Using Benchmark Library: Dither Algorithms.

Did you check the execution time?

Sat, Jul 28, 5:51 PM
Meinersbur accepted D49948: [test-suite] Add Image Processing Kernels Using Benchmark Library: Anisotropic diffusion.

LGTM

Sat, Jul 28, 5:51 PM
Meinersbur added a comment to D49950: [Polly][JSONExporter] Replace bundled Jsoncpp with LLVM's JSON.h. NFC..

Usage of JSON.h looks pretty good, thanks for doing this migration!

Sat, Jul 28, 5:45 PM · Restricted Project

Fri, Jul 27

Meinersbur updated the diff for D49950: [Polly][JSONExporter] Replace bundled Jsoncpp with LLVM's JSON.h. NFC..
  • Rebase
Fri, Jul 27, 6:14 PM · Restricted Project
Meinersbur created D49950: [Polly][JSONExporter] Replace bundled Jsoncpp with LLVM's JSON.h. NFC..
Fri, Jul 27, 6:05 PM · Restricted Project
Meinersbur added a comment to D49948: [test-suite] Add Image Processing Kernels Using Benchmark Library: Anisotropic diffusion.

Wow, that's 10x fast with Polly!

Fri, Jul 27, 4:58 PM
Meinersbur accepted D49503: [test-suite] Add Image Processing Kernels Using Benchmark Library: Dither Algorithms.

What is the execution time of this?

Fri, Jul 27, 4:52 PM
Meinersbur retitled D49503: [test-suite] Add Image Processing Kernels Using Benchmark Library: Dither Algorithms from [test-suite] Added Image Processing Kernels Using Benchmark Library: Dither Algorithms to [test-suite] Add Image Processing Kernels Using Benchmark Library: Dither Algorithms.
Fri, Jul 27, 4:48 PM
Meinersbur accepted D49339: [test-suite] Added Image Processing Kernels Using Benchmark Library: utilities functions.

Can be committed just before the first dependent patch being committed.

Fri, Jul 27, 4:47 PM
Meinersbur added inline comments to D49503: [test-suite] Add Image Processing Kernels Using Benchmark Library: Dither Algorithms.
Fri, Jul 27, 2:22 PM
Meinersbur added a comment to D48348: [ADT] Add zip_longest iterators..

ping. Any other opinions on this?

Fri, Jul 27, 2:01 PM
Meinersbur added a comment to D49872: [Polly][ScopDetect] Add option -polly-allow-nonaffine-read and enable by default..

Does this still allow disproving data dependences?

Fri, Jul 27, 9:02 AM · Restricted Project

Thu, Jul 26

Meinersbur accepted D49894: [test-suite] Added hotspot kernel from Rodinia Benchmark.

Otherwise LGTM

Thu, Jul 26, 8:08 PM
Meinersbur accepted D49891: [test-suite] Added srad kernel from Rodinia Benchmark.

Title: Added -> Add

Thu, Jul 26, 8:07 PM
Meinersbur added a comment to D49896: [test-suite] Added common files requred by kernels of Rodinia Benchmark.

Typo in title: requred

Thu, Jul 26, 8:00 PM
Meinersbur added inline comments to D49883: [test-suite] Added Image Processing Kernels Using Benchmark Library: Dilate Kernel.
Thu, Jul 26, 7:58 PM
Meinersbur added inline comments to D49503: [test-suite] Add Image Processing Kernels Using Benchmark Library: Dither Algorithms.
Thu, Jul 26, 7:51 PM
Meinersbur updated the diff for D49281: [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes..
Thu, Jul 26, 7:32 PM