mirror of
https://github.com/capstone-engine/llvm-capstone.git
synced 2024-11-23 13:50:11 +00:00
[mlir][docs] Fix a broken passes documentation (#77402)
- Add EmitC passes into Pass.md - Modify header level of the pass description to under the `LegalizeVectorStorage` pass
This commit is contained in:
parent
19870ed9c3
commit
d5985d4c70
@ -40,6 +40,10 @@ This document describes the available MLIR passes and their contracts.
|
||||
|
||||
[include "AsyncPasses.md"]
|
||||
|
||||
## 'emitc' Dialect Passes
|
||||
|
||||
[include "EmitCPasses.md"]
|
||||
|
||||
## 'func' Dialect Passes
|
||||
|
||||
[include "FuncPasses.md"]
|
||||
|
@ -21,7 +21,7 @@ def LegalizeVectorStorage
|
||||
|
||||
This pass currently addresses two issues.
|
||||
|
||||
## Loading and storing predicate types
|
||||
#### Loading and storing predicate types
|
||||
|
||||
It is only legal to load/store predicate types equal to (or greater than) a
|
||||
full predicate register, which in MLIR is `vector<[16]xi1>`. Smaller
|
||||
@ -49,7 +49,7 @@ def LegalizeVectorStorage
|
||||
%reload = arm_sve.convert_from_svbool %reload_svbool : vector<[4]xi1>
|
||||
```
|
||||
|
||||
## Relax alignments for SVE vector allocas
|
||||
#### Relax alignments for SVE vector allocas
|
||||
|
||||
The storage for SVE vector types only needs to have an alignment that
|
||||
matches the element type (for example 4 byte alignment for `f32`s). However,
|
||||
|
Loading…
Reference in New Issue
Block a user