shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity

[mlir][xevm] Fix dialect descriptions formatting (#147729)

Browse Source 
Fixes markdown formatting of xevm dialect docs.
This commit is contained in:
Adam Siemieniuk 2025-07-10 19:36:58 +02:00 committed by GitHub
parent 582cfb142c
commit 8ad384ba7f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 54 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

108
mlir/include/mlir/Dialect/LLVMIR/XeVMOps.td
View File

@ -201,25 +201,25 @@ def XeVM_BlockLoad2dOp
let description = [{
The `xevm.blockload2d` operation loads a two dimensional matrix tile
from a base matrix residing in global memory. The parameters are:
$ptr - the base address of the base matrix containing the tile to load
$base_width - the width of the base matrix in number of bytes.
$base_height - the number of rows in the base matrix
$base_pitch - the physical stride between the first columns of the current
row and the subsequent row in number of bytes.
$x, $y, $tile_width, $tile_height - the starting offsets and shape of
the tile to load in number of elements.
$elem_size_in_bits - the size in bits of the matrix element type
* `ptr` - the base address of the base matrix containing the tile to load
* `base_width` - the width of the base matrix in number of bytes.
* `base_height` - the number of rows in the base matrix
* `base_pitch` - the physical stride between the first columns of the current
row and the subsequent row in number of bytes.
* `x`, `y`, `tile_width`, `tile_height` - the starting offsets and shape of
the tile to load in number of elements.
* `elem_size_in_bits` - the size in bits of the matrix element type
- 32 for f32, tf32
- 16 for f16, int16, bf16
- 8 for int8
$v_blocks - number of consecutive tiles in innermost dimension direction to load
$transpose - transpose the tile in registers (useful for 32 bit element type)
$pack_register - pack element types narrower than register bit width.
* `v_blocks` - number of consecutive tiles in innermost dimension direction to load
* `transpose` - transpose the tile in registers (useful for 32 bit element type)
* `pack_register` - pack element types narrower than register bit width.
[M, N] => [M/factor, N, factor] where factor is register_size_in_bits / elem_size_in_bits
$cache_control - an enumerator that sets the cache behaviour
* `cache_control` - an enumerator that sets the cache behaviour
Notes:
- the $transpose and $pack_register parameters are mutual exclusive
- the `transpose` and `pack_register` parameters are mutual exclusive
- transposing the tile loaded is used for A matrix in backward path or used for the B matrix operand
(D = C + A * B), where A has row-major layout and B should have column-major layout in memory.
- if the tile loaded contains out of bound elements of the matrix, they are filled with 0.
@ -262,19 +262,19 @@ def XeVM_BlockStore2dOp
let description = [{
The `xevm.blockstore2d` operation stores a two dimensional tile into a
larger matrix residing in global memory. The parameters are:
$ptr - the base address of the target matrix where to store the tile
$base_width - the width of the base matrix in number of bytes.
$base_height - the number of rows in the base matrix
$base_pitch - the physical stride between the first columns of the current
row and the subsequent row in number of bytes.
$x, $y, $tile_width, $tile_height - the starting offsets and shape of the tile to store
* `ptr` - the base address of the target matrix where to store the tile
* `base_width` - the width of the base matrix in number of bytes.
* `base_height` - the number of rows in the base matrix
* `base_pitch` - the physical stride between the first columns of the current
row and the subsequent row in number of bytes.
* `x`, `y`, `tile_width`, `tile_height` - the starting offsets and shape of the tile to store
in number of elements.
$elem_size_in_bits - the size in bits of the matrix element
* `elem_size_in_bits` - the size in bits of the matrix element
- 32 for f32, tf32
- 16 for f16, int16, bf16
- 8 for int8
$cache_control - an enumerator that sets the cache behaviour
$stored_val - the tile to store
* `cache_control` - an enumerator that sets the cache behaviour
* `stored_val` - the tile to store
Example:
```mlir
@ -351,10 +351,10 @@ def XeVM_MemfenceOp
This operation ensures that all prior memory accesses of this
work-item to `addrspace` are visible to all other work-items in `scope`.
Parameters description:
$scope - specify the memory scope at which all other work-items should observe
memory operations prior to the fence.
$addrspace - specify the address space of work-item's memory accesses
to be affected by the fence.
* `scope` - specify the memory scope at which all other work-items should observe
memory operations prior to the fence.
* `addrspace` - specify the address space of work-item's memory accesses
to be affected by the fence.
}];
let assemblyFormat = [{prop-dict attr-dict}];
@ -370,9 +370,9 @@ def XeVM_PrefetchOp
let summary = "Prefetch data into a cache subsystem.";
let description = [{
Work-item issues a prefetch from global memory to cache:
$ptr - LLVM pointer with address space. Address space must be 1 (global)
or 4 (generic)
$cache_control - specify caching options
* `ptr` - LLVM pointer with address space. Address space must be 1 (global)
or 4 (generic)
* `cache_control` - specify caching options
}];
let assemblyFormat = [{
operands prop-dict attr-dict `:` `(` type(operands) `)`
@ -395,19 +395,19 @@ def XeVM_BlockPrefetch2dOp
let description = [{
The `xevm.blockprefetch2d` operation prefetches a two dimensional tile
from a larger base matrix residing in global memory. The parameters are:
$ptr - the base address of the base matrix containing the tile to prefetch
$base_width - the width of the base matrix in number of bytes.
$base_height - the number of rows in the base matrix
$base_pitch - the physical stride between the first columns of the current
row and the subsequent row in number of bytes.
$x, $y, $tile_width, $tile_height - the starting offsets and shape of tile
to prefetch in number of elements.
$elem_size_in_bits - the size in bits of the matrix element
- 32 for f32, bf32
- 16 for f16, int16, bf16
- 8 for int8, int4, int2
$v_blocks - number of tiles in innermost dimension direction to prefetch
$cache_control - an enumerator that sets the cache behaviour
* `ptr` - the base address of the base matrix containing the tile to prefetch
* `base_width` - the width of the base matrix in number of bytes.
* `base_height` - the number of rows in the base matrix
* `base_pitch` - the physical stride between the first columns of the current
row and the subsequent row in number of bytes.
* `x`, `y`, `tile_width`, `tile_height` - the starting offsets and shape of tile
to prefetch in number of elements.
* `elem_size_in_bits` - the size in bits of the matrix element
- 32 for f32, bf32
- 16 for f16, int16, bf16
- 8 for int8, int4, int2
* `v_blocks` - number of tiles in innermost dimension direction to prefetch
* `cache_control` - an enumerator that sets the cache behaviour
Example:
```mlir
@ -452,9 +452,9 @@ def XeVM_ElemTypeAttr : I32EnumAttr<"ElemType", "XeVM element type",
def XeVM_MMAShapeAttr : XeVM_Attr<"MMAShape", "mma_shape"> {
let description = [{
MMA operation is represented as D=AxB+C, where
A has the shape MxK.
B has the shape KxN.
D and C have the shape MxN.
- A has the shape MxK.
- B has the shape KxN.
- D and C have the shape MxN.
This attribute encodes the shape of all matrices that participate in MMA.
}];
let parameters = (ins "int":$m, "int":$n, "int":$k);
@ -484,17 +484,17 @@ def XeVM_MMAOp
D = C + A x B
where the A, B, C input matrices and the result D have shapes:
D : MxN
C : MxN
A : MxK
B : KxN
- D : MxN
- C : MxN
- A : MxK
- B : KxN
Parameters:
`a` - vector of matrix A elements.
`b` - vector of matrix B elements.
`c` - (optional) vector of matrix C elements.
`shape` - the shape of the matrices, specified as `M`, `N`, and `K` values.
`types` - the data types of the matrices, specified as `D`, `A`, `B`, and optionally `C`.
* `a` - vector of matrix A elements.
* `b` - vector of matrix B elements.
* `c` - (optional) vector of matrix C elements.
* `shape` - the shape of the matrices, specified as `M`, `N`, and `K` values.
* `types` - the data types of the matrices, specified as `D`, `A`, `B`, and optionally `C`.
Example:
```mlir