User Details
- User Since
- Jul 26 2016, 7:17 AM (309 w, 6 d)
Wed, Jun 29
Tue, Jun 28
LIT tests updated
Fri, Jun 24
LIT tests changed. Description updated.
Tue, Jun 21
debug output fixed
Apr 1 2022
LGTM if we do not want to change the COPY processing in the SIInstrInfo::isOperandLegal
Mar 30 2022
Mar 22 2022
Mar 21 2022
test updated
Mar 19 2022
test case for SCC multiple defs added. Unnecessary compiler options removed from the test command line.
Mar 18 2022
formatting
IsSALU check chamged to query operand register class.
MIR test were made auto-generated
SCC clobbering case added. MIR test simplified.
Mar 12 2022
Mar 10 2022
Feb 14 2022
LGTM
Looks good but I'd like to see the selection-only LIT test:
uniform bitreverse i32,
divergent bitreverse i32,
uniform bitreverse i64,
divergent bitreverse i64
with -stop-after=amdgpu-isel
The purpose of the selection-only tests is to control the divergence-driven selection not broken.
Otherwise, it could be broken but full-stack tests are still matching because of the moveToVALU hackery.
Test corrected. Added complexity for the AddNoCarry case.
Feb 11 2022
Feb 10 2022
One more test attributes corrected
Test file attributes corrected
Feb 9 2022
Odd comments and copy-paste typo corrected
Feb 8 2022
Jan 26 2022
Jan 25 2022
FIXME v_perm_b32 added
removed accidentally added files
Added detailed comment explainingthe new target hook.
Memory access pattern check changed to match exactly the address operand.
Minor fixes.
Jan 24 2022
Added comment to common target hook declaration. Condition changed.
Removed constant folding heuristic, prooved useless.
Jan 21 2022
Bug fixed: Memory access DAG pattern check must ensure that "base + offset" pattern has MemSDNode users
Initial DAG
DAG after the transformation and constant folding
This can be selected to v_perm_b32
Jan 20 2022
Initial DAG
DAG after the transformation and constant folding
This can be selected to v_perm_b32
condition was made more readable
Jan 17 2022
DAG combiner hook added to control divergence-driven peephole optimizatoins.
Jan 13 2022
In general, I don't like the idea of making the DAGCombiner::reassociateOpsCommutative take into account the divergence.
Jan 11 2022
I think it is worth trying to change this generic combine to give up if x is uniform and y is divergent.
Jan 10 2022
Jan 7 2022
Added postprocessing of the selected machine IR. This makes it on par with the existing selection mechanism.
Jan 6 2022
odd COPY_TO_REGCLASS removed. Test updated.
Dec 26 2021
test file attributes corrected
Dec 24 2021
This looks like a regression in xnor.ll :
LIT test file attributes corrected
Dec 23 2021
test attributes corrected
Dec 22 2021
Dec 20 2021
test corrected