| Issue |
61397
|
| Summary |
[CodeGen] Machine Late Instructions Cleanup Pass spends significant time at clearKillsForDef.
|
| Labels |
backend:AMDGPU,
slow-compile
|
| Assignees |
vpykhtin,
JonPsson
|
| Reporter |
vpykhtin
|
The attached testcase for AMDGPU target shows significant time spent in the _Machine Late Instructions Cleanup Pass_. Vtune profiler shows _clearKillsForDef_ function as the main reason.
\> llc -mtriple=amdgcn-hsa-amdhsa -mcpu=gfx90a -time-passes -no-stack-slot-sharing long-compile-time-func.bc
```
Total Execution Time: 670.4078 seconds (670.7149 wall clock)
---User Time--- --System Time-- --User+System-- ---Wall Time--- --- Name ---
289.2998 ( 43.7%) 0.1439 ( 1.8%) 289.4437 ( 43.2%) 289.5775 ( 43.2%) Structurize control flow
124.9852 ( 18.9%) 0.0000 ( 0.0%) 124.9852 ( 18.6%) 125.0289 ( 18.6%) Machine Late Instructions Cleanup Pass
45.2408 ( 6.8%) 0.0000 ( 0.0%) 45.2408 ( 6.7%) 45.2740 ( 6.8%) SI Form memory clauses
38.0358 ( 5.7%) 0.0240 ( 0.3%) 38.0598 ( 5.7%) 38.0767 ( 5.7%) Simple Register Coalescing
...
```
[long-compile-time-func.zip](https://github.com/llvm/llvm-project/files/10965409/long-compile-time-func.zip)
![]()
_______________________________________________
llvm-bugs mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
