Ополин Дмитрий. Лабораторная работа 3. Backend. Вариант 1. #145
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
deademous
requested review from
aobolensk,
m-ly4 and
Kuznetsov-Artyom
as code owners
m-ly4
requested changes
May 17, 2025
Comment on lines
+60
to
+67
| BuildMI(MBB, it, dlDef, TII->get(scalarToAVX[opc1]), tmp) | ||
| .addReg(defMI->getOperand(1).getReg()) | ||
| .addReg(defMI->getOperand(2).getReg()); | ||
|
|
||
| BuildMI(MBB, it, dlUse, TII->get(scalarToAVX[opc2]), | ||
| useMI.getOperand(0).getReg()) | ||
| .addReg(tmp) | ||
| .addReg(useMI.getOperand(2).getReg()); |
There was a problem hiding this comment.
Technically, this is not a fusing. This is the same as tryUpgradeSingle, but for two dependent instructions.
Could you please select any Boolean algebra rule and apply for optimization here?
aobolensk
requested changes
May 17, 2025
Comment on lines
+3
to
+10
|
|
||
|
|
||
| # Source files | ||
| # test.cpp | ||
|
|
||
| # include <emmintrin.h> | ||
| # include <immintrin.h> | ||
|
|
There was a problem hiding this comment.
Suggested change
| # Source files | |
| # test.cpp | |
| # include <emmintrin.h> | |
| # include <immintrin.h> |
| class AVXLogicCombinerPass : public MachineFunctionPass { | ||
| const X86InstrInfo *TII = nullptr; | ||
| MachineRegisterInfo *RegInfo = nullptr; | ||
| DenseMap<unsigned, unsigned> scalarToAVX; |
There was a problem hiding this comment.
I guess you can use static const DenseMap<unsigned, unsigned> scalarToAVX = { ... }
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Outdated suggestions cannot be applied.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.
Этот LLVM Pass выполняет оптимизацию логических операций (AND, OR, XOR и их комбинаций) для архитектуры X86, заменяя скалярные SSE-инструкции на более эффективные векторные AVX-инструкции.