[SYCL] Adjust for all Dims offset in accessor's device __init #6560
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
The optimization done for 1-dim accessor is suitable for all dimensions.
aelovikov-intel
force-pushed
the
accessor_init_offset
branch
from
7c97e36 to
de52645
Compare
|
@elizabethandrews , can you please look at the test's change? |
aelovikov-intel
force-pushed
the
accessor_init_offset
branch
from
f4c56cb to
77ee765
Compare
|
Failures on are unrelated and have been addressed already. |
|
@sergey-semenov , @elizabethandrews , gentle ping. |
sergey-semenov
previously approved these changes
Aug 16, 2022
There was a problem hiding this comment.
The header part looks good to me. @elizabethandrews Could you please take a look at the test?
elizabethandrews
approved these changes
Aug 17, 2022
sergey-semenov
approved these changes
Aug 17, 2022
|
OCL failures are known. |
|
@intel/dpcpp-esimd-reviewers , ping. |
v-klochkov
approved these changes
Aug 18, 2022
There was a problem hiding this comment.
Ok for ESIMD only part.
I still have some questions for general/sycl part of the changes, but relying on @sergey-semenov opinion for @intel/llvm-reviewers-runtime part of the changes.
Resolved via a call. |
|
@intel/llvm-gatekeepers , PR is ready. |
aelovikov-intel
added a commit
to aelovikov-intel/llvm-test-suite
that referenced
this pull request
Aug 23, 2022
Internally, we run the test suite with optimizations disabled and this test started to fail after intel/llvm#6560. Adust it to pass again.
againull
pushed a commit
to intel/llvm-test-suite
that referenced
this pull request
Aug 24, 2022
…O0 (#1174) Internally, we run the test suite with optimizations disabled and this test started to fail after intel/llvm#6560. Adust it to pass again.
aelovikov-intel
added a commit
to aelovikov-intel/llvm
that referenced
this pull request
Oct 3, 2022
The utility was introduced in intel#6560 because "#pragma unroll" doesn't always work and template-based solution is much more reliable. Original PR only changed the loops that resulted in immediate performance difference but other occurrences were missed. This PR updates remaining ones. Note that I've found them by looking into the LLVM IR produced by our device compiler and having the loop really unrolled improves readability of such dumps (and most likely codesize/perf, although not significantly).
pvchupin
pushed a commit
that referenced
this pull request
Oct 3, 2022
The utility was introduced in #6560 because "#pragma unroll" doesn't always work and template-based solution is much more reliable. Original PR only changed the loops that resulted in immediate performance difference but other occurrences were missed. This PR updates remaining ones. Note that I've found them by looking into the LLVM IR produced by our device compiler and having the loop really unrolled improves readability of such dumps (and most likely codesize/perf, although not significantly).
aelovikov-intel
added a commit
to aelovikov-intel/llvm
that referenced
this pull request
Mar 27, 2023
…O0 (intel/llvm-test-suite#1174) Internally, we run the test suite with optimizations disabled and this test started to fail after intel#6560. Adust it to pass again.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The optimization done for 1-dim accessor is suitable for all dimensions.
The test sycl/test/gdb/accessors-device.cpp had to be updated as its previous
implementation was fragile in capturing info it tried to verify.