| Age | Commit message (Collapse) | Author |
|---|
|
vector.splat has been deprecated (user: please use the very similar vector.broadcast instead)
with the last PR landing about 6 weeks ago.
The discourse discussion is at
https://discourse.llvm.org/t/rfc-mlir-vector-deprecate-then-remove-vector-splat/87143/1
The last PR was #152230
This PR completely removes vector.splat. In addition to removing vector.splat from VectorOps.td, it
- Updates the few remaining places where vector::SplatOp is created (now vector::BroadcastOp is created)
- Removes temporary patterns where vector.splat is replaced by vector.broadcast
The only place 'vector.splat' appears is now the files
https://github.com/llvm/llvm-project/blob/main/mlir/utils/tree-sitter-mlir/test/corpus/op.txt
and
https://github.com/llvm/llvm-project/blob/main/mlir/utils/tree-sitter-mlir/dialect/vector.js
---------
Signed-off-by: James Newling <james.newling@gmail.com>
|
|
(#161670)
Use the `Base` type alias from
https://github.com/llvm/llvm-project/pull/158433.
|
|
This patch updates the following ops to use `source` (instead of
`vector`) as the name for their source argument:
* `vector.extract`
* `vector.scalable.extract`
* `vector.extract_strided_slice`
This change ensures naming consistency with the "builders" for these Ops
that already use the name `source` rather than `vector`. It also
addresses part of:
* https://github.com/llvm/llvm-project/issues/131602
Specifically, it ensures that we use `source` and `dest` for read and
write operations, respectively (as opposed to `vector` and `dest`).
|
|
VectorTransforms.cpp (NFC)
|
|
In FoldArithToVectorOuterProduct pattern, static cast to vector type
causes assertion when a scalar type was encountered. It seems the author
meant to have a dyn_cast instead.
This NFC patch handles it by using dyn_cast.
|
|
This is part of vector.splat deprecation
Reference: https://discourse.llvm.org/t/rfc-mlir-vector-deprecate-then-remove-vector-splat/87143/5
Instead of creating vector::SplatOp, create vector::BroadcastOp
|
|
This patch extends the operation that rewrites elementwise operations
whose inputs are all broadcast from the same shape to handle
mixed-types, such as when the result and input types don't match, or
when the inputs have multiple types.
PR #150867 failed to check for the possibility of type mismatches when
rewriting splat constants. In order to fix that issue, we add support
for mixed-type operations more generally.
|
|
(#150867)
There is a pattern that rewrites
elementwise_op(broadcast(x1 : T to U), broadcast(x2 : T to U), ...) to
broadcast(elementwise_op(x1, x2, ...) : T to U).
This pattern did not, however, account for the case where a broadcast
constant is represented as a SplatElementsAttr, which can safely be
reshaped or scalarized but is not a `vector.broadcast` or `vector.splat`
operation.
This patch fixes this oversight, prenting premature broadcasting.
This did result in the need to update some linalg dialect tests, which
now feature a less-broadcast computation and/or more constant folding.
|
|
See https://github.com/llvm/llvm-project/pull/147168 for more info.
|
|
See https://github.com/llvm/llvm-project/pull/147168 for more info.
|
|
Propagating vector.extract when a dynamic position is present can cause
dominance issues and needs better handling. For now, disable propagation
if there is a dynamic position present.
|
|
`populateVectorTransferCollapseInnerMostContiguousDimsPatterns` (#145228)
Renames `populateVectorTransferCollapseInnerMostContiguousDimsPatterns`
as `populateDropInnerMostUnitDimsXferOpPatterns` + updates the
corresponding comments.
This addresses a TODO and makes the difference between these two
`populate*` methods clearer:
* `populateDropUnitDimWithShapeCastPatterns`,
* `populateDropInnerMostUnitDimsXferOpPatterns`.
|
|
This patch updates `CombineContractBroadcastMask` to inherit from
`MaskableOpRewritePattern`, enabling it to handle masked
`vector.contract` operations. The pattern rewrites:
```mlir
%a = vector.broadcast %a_bc
%res vector.contract %a_bc, %b, ...
```
into:
```mlir
// Move the broadcast into vector.contract (by updating the indexing
// maps)
%res vector.contract %a, %b, ...
```
The main challenge is supporting cases where the pattern drops a leading
unit dimension. For example:
```mlir
func.func @contract_broadcast_unit_dim_reduction_masked(
%arg0 : vector<8x4xi32>,
%arg1 : vector<8x4xi32>,
%arg2 : vector<8x8xi32>,
%mask: vector<1x8x8x4xi1>) -> vector<8x8xi32> {
%0 = vector.broadcast %arg0 : vector<8x4xi32> to vector<1x8x4xi32>
%1 = vector.broadcast %arg1 : vector<8x4xi32> to vector<1x8x4xi32>
%result = vector.mask %mask {
vector.contract {
indexing_maps = [#map0, #map1, #map2],
iterator_types = ["reduction", "parallel", "parallel", "reduction"],
kind = #vector.kind<add>
} %0, %1, %arg2 : vector<1x8x4xi32>, vector<1x8x4xi32> into vector<8x8xi32>
} : vector<1x8x8x4xi1> -> vector<8x8xi32>
return %result : vector<8x8xi32>
}
```
Here, the leading unit dimension is dropped. To handle this, the mask is
cast to the correct shape using a `vector.shape_cast`:
```mlir
func.func @contract_broadcast_unit_dim_reduction_masked(
%arg0: vector<8x4xi32>,
%arg1: vector<8x4xi32>,
%arg2: vector<8x8xi32>,
%arg3: vector<1x8x8x4xi1>) -> vector<8x8xi32> {
%mask_sc = vector.shape_cast %arg3 : vector<1x8x8x4xi1> to vector<8x8x4xi1>
%res = vector.mask %mask_sc {
vector.contract {
indexing_maps = [#map, #map1, #map2],
iterator_types = ["parallel", "parallel", "reduction"],
kind = #vector.kind<add>
} %arg0, %arg1, %mask_sc : vector<8x4xi32>, vector<8x4xi32> into vector<8x8xi32>
} : vector<8x8x4xi1> -> vector<8x8xi32>
return %res : vector<8x8xi32>
}
```
While this isn't ideal - since it introduces a `vector.shape_cast` that
must be cleaned up later - it reflects the best we can do once the input
reaches `CombineContractBroadcastMask`. A more robust solution may
involve simplifying the input earlier. I am leaving that as a TODO for
myself to explore this further. Posting this now to unblock downstream
work.
LIMITATIONS
Currently, this pattern assumes:
* Only leading dimensions are dropped in the mask.
* All dropped dimensions must be unit-sized.
|
|
isZeroInteger. (#139340)
The revision adds isOneInteger helper, and simplifies the existing code
with the two methods. It removes some lambda, which makes code cleaner.
For downstream users, you can update the code with the below script.
```bash
sed -i "s/isZeroIndex/isZeroInteger/g" **/*.h
sed -i "s/isZeroIndex/isZeroInteger/g" **/*.cpp
```
---------
Signed-off-by: hanhanW <hanhan0912@gmail.com>
|
|
[mlir][vector] Standardize base Naming Across Vector Ops (NFC)
This change standardizes the naming convention for the argument
representing the value to read from or write to in Vector ops that
interface with Tensors or MemRefs. Specifically, it ensures that all
such ops use the name `base` (i.e., the base address or location to
which offsets are applied).
Updated operations:
* `vector.transfer_read`,
* `vector.transfer_write`.
For reference, these ops already use `base`:
* `vector.load`, `vector.store`, `vector.scatter`, `vector.gather`,
`vector.expandload`, `vector.compressstore`, `vector.maskedstore`,
`vector.maskedload`.
This is a non-functional change (NFC) and does not alter the semantics of these
operations. However, it does require users of the XFer ops to switch from
`op.getSource()` to `op.getBase()`.
To ease the transition, this PR temporarily adds a `getSource()` interface
method for compatibility. This is intended for downstream use only and should
not be relied on upstream. The method will be removed prior to the LLVM 21
release.
Implements #131602
|
|
```
vector.load %arg0[%arg1] : memref<?xf32>, vector<4xf32>
vector.extract %0[1] : f32 from vector<4xf32>
```
Gets converted to:
```
%c1 = arith.constant 1 : index
%0 = arith.addi %arg1, %c1 overflow<nsw> : index
%1 = memref.load %arg0[%0] : memref<?xf32>
```
```
%0 = vector.splat %arg2 : vector<1xf32>
vector.store %0, %arg0[%arg1] : memref<?xf32>, vector<1xf32>
```
Gets converted to:
```
memref.store %arg2, %arg0[%arg1] : memref<?xf32>
```
|
|
This PR removes one OpRewritePattern `shape_cast(shape_cast(x)) -> x`
that is already handled by `ShapeCastOp::fold`.
Note that this might affect downstream users who indirectly call
`populateShapeCastFoldingPatterns(RewritePatternSet &patterns,
PatternBenefit)` and then use `patterns` with a `GreedyRewriteConfig
config` that has `config.fold = false`. (only user I've checked is IREE,
that never uses config.fold = false).
|
|
(#134206)
This change standardises the naming convention for the argument
representing the value to store in various vector operations.
Specifically, it ensures that all vector ops storing a value—whether
into memory, a tensor, or another vector — use `valueToStore` for the
corresponding argument name.
Updated operations:
* `vector.transfer_write`, `vector.insert`, `vector.scalable_insert`,
`vector.insert_strided_slice`.
For reference, here are operations that currently use `valueToStore`:
* `vector.store` `vector.scatter`, `vector.compressstore`,
`vector.maskedstore`.
This change is non-functional (NFC) and does not affect the
functionality of these operations.
Implements #131602
|
|
Propagate `Extract(Elementwise(...))` -> `Elemetwise(Extract...)`.
Currenly limited to the case when extract is the single use of
elementwise to avoid introducing additional elementwise ops.
|
|
functions (#120024)
Avoids the need for cast, and matches the extra build functions, which
take a `MemRefType`
|
|
|
|
`BreakDownVectorBitCast` leverages
* `vector.extract_strided_slices` + `vector.insert_strided_slices`
As these Ops do not support extracting scalable sub-vectors (i.e.
extracting/inserting a fraction of a scalable dim), it's best to bail
out.
|
|
(#123714)
In the LLVM style guide, we prefer not using braced initializer lists to
call a constructor. Also, we prefer using an equal before the open curly
brace if we use a braced initializer list when initializing a variable.
See
https://llvm.org/docs/CodingStandards.html#do-not-use-braced-initializer-lists-to-call-a-constructor
for more details.
The style guide does not explain the reason well. There is an article
from abseil, which mentions few benefits. E.g., we can avoid the most
vexing parse, etc. See https://abseil.io/tips/88 for more details.
Signed-off-by: hanhanW <hanhan0912@gmail.com>
|
|
Turn free-standing `MemRefType`-related helper functions in
`BuiltinTypes.h` into member functions.
|
|
Note that PointerUnion::{is,get} have been soft deprecated in
PointerUnion.h:
// FIXME: Replace the uses of is(), get() and dyn_cast() with
// isa<T>, cast<T> and the llvm::dyn_cast<T>
I'm not touching PointerUnion::dyn_cast for now because it's a bit
complicated; we could blindly migrate it to dyn_cast_if_present, but
we should probably use dyn_cast when the operand is known to be
non-null.
|
|
(#116518)
Previously the patch was not expecting to handle non-static index, when
the index is a non constant value it will crash.
This patch is to make sure it return gracefully instead of crashing.
|
|
Adds a new Transform Dialect Op that collects patters for dropping unit
dims from various Ops:
* `transform.apply_patterns.vector.drop_unit_dims_with_shape_cast`.
It excludes patterns for vector.transfer Ops - these are collected
under:
* `apply_patterns.vector.rank_reducing_subview_patterns`,
and use ShapeCastOp _and_ SubviewOp to reduce the rank (and to eliminate
unit dims).
This new TD Ops allows us to test the "ShapeCast folder" pattern in
isolation. I've extracted the only test that I could find for that
folder from "vector-transforms.mlir" and moved it to a dedicated file:
"shape-cast-folder.mlir". I also added a test case with scalable
vectors.
Changes in VectorTransforms.cpp are not needed (added a comment with
a TODO + ordered the patterns alphabetically). I am Including them here
to avoid a separate PR.
|
|
This adds a pattern for dropping unit dims from the iter_args of scf.for
ops using vector.shape_cast. This composes with the other patterns for
dropping unit dims from elementwise ops and transposes.
|
|
Group all patterns that re-order vector.transpose and vector.broadcast
Ops (*) under `populateSinkVectorOpsPatterns`. These patterns are
normally used to "sink" redundant Vector Ops, hence grouping together.
Example:
```mlir
%at = vector.transpose %a, [1, 0]: vector<4x2xf32> to vector<2x4xf32>
%bt = vector.transpose %b, [1, 0]: vector<4x2xf32> to vector<2x4xf32>
%r = arith.addf %at, %bt : vector<2x4xf32>
```
would get converted to:
```mlir
%0 = arith.addf %a, %b : vector<4x2xf32>
%r = vector.transpose %0, [1, 0] : vector<2x4xf32>
```
This patch also moves all tests for these patterns so that all of them
are:
* run under one test-flag: `test-vector-sink-patterns`,
* located in one file: "vector-sink.mlir".
To facilitate this change:
* `-test-sink-vector-broadcast` is renamed as
`test-vector-sink-patterns`,
* "sink-vector-broadcast.mlir" is renamed as "vector-sink.mlir",
* tests for `ReorderCastOpsOnBroadcast` and
`ReorderElementwiseOpsOnTranspose` patterns are moved from
"vector-reduce-to-contract.mlir" to "vector-sink.mlir",
* `ReorderElementwiseOpsOnTranspose` patterns are removed from
`populateVectorReductionToContractPatterns` and added to (newly
created) `populateSinkVectorOpsPatterns`,
* `ReorderCastOpsOnBroadcast` patterns are removed from
`populateVectorReductionToContractPatterns` - these are already
present in `populateSinkVectorOpsPatterns`.
This should allow us better layering and more straightforward testing.
For the latter, the goal is to be able to easily identify which pattern
a particular test is exercising (especially when it's a specific
pattern).
NOTES FOR DOWNSTREAM USERS
In order to preserve the current functionality, please make sure to add
* `populateSinkVectorOpsPatterns`,
wherever you are using `populateVectorReductionToContractPatterns`.
Also, rename `populateSinkVectorBroadcastPatterns` as
`populateSinkVectorOpsPatterns`.
(*) I didn't notice any other re-order patterns.
|
|
(#102286)
Adds tests for scalable vectors in:
* sink-vector-broadcast.mlir
This test file excercises patterns grouped under
`populateSinkVectorBroadcastPatterns`, which includes:
* `ReorderElementwiseOpsOnBroadcast`,
* `ReorderCastOpsOnBroadcast`.
Right now there are only tests for the former. However, I've noticed
that "vector-reduce-to-contract.mlir" contains tests for the latter and
I've left a few TODOs to group these tests back together in one file.
Additionally, added some helpful `notifyMatchFailure` messages in
`ReorderElementwiseOpsOnBroadcast`.
|
|
https://github.com/llvm/llvm-project/commit/da8778e499d8049ac68c2e152941a38ff2bc9fb2
breaks the lowering of vector.transpose that all the dimensions are unit
dimensions. The revision fixes the issue and adds a test.
---------
Signed-off-by: hanhanW <hanhan0912@gmail.com>
|
|
This accidentally returned `failure()` (rather than `success()`) when it
applied.
|
|
Example:
BEFORE:
```mlir
%transpose = vector.transpose %vector, [3, 0, 1, 2]
: vector<1x1x4x[4]xf32> to vector<[4]x1x1x4xf32>
```
AFTER:
```mlir
%dropDims = vector.shape_cast %vector
: vector<1x1x4x[4]xf32> to vector<4x[4]xf32>
%transpose = vector.transpose %0, [1, 0]
: vector<4x[4]xf32> to vector<[4]x4xf32>
%restoreDims = vector.shape_cast %transpose
: vector<[4]x4xf32> to vector<[4]x1x1x4xf32>
```
|
|
Since the `in_bounds` attribute is mandatory, there's no need for logic
like this (`readOp.getInBounds()` is guaranteed to return a non-empty
ArrayRef):
```cpp
ArrayAttr inBoundsAttr = readOp.getInBounds()
? rewriter.getArrayAttr( readOp.getInBoundsAttr().getValue().drop_back(dimsToDrop))
: ArrayAttr();
```
Instead, we can do this:
```cpp
ArrayAttr inBoundsAttr = rewriter.getArrayAttr(
readOp.getInBoundsAttr().getValue().drop_back(dimsToDrop));
```
This is a small follow-up for #97049 - this change should've been
included there.
|
|
trailing dimensions. (#98455)
Generalizes DropUnitDimFromElementwiseOps to support inner unit
dimensions.
This change stems from improving lowering of contractionOps for Arm SME.
Where we end up with inner unit dimensions on MulOp, BroadcastOp and
TransposeOp, preventing the generation of outerproducts.
discussed
[here](https://discourse.llvm.org/t/on-improving-arm-sme-lowering-resilience-in-mlir/78543/17?u=nujaa).
Fix after : https://github.com/llvm/llvm-project/pull/97652 showed an
unhandled edge case when all dimensions are one. The generated target
VectorType would be `vector<f32>` which is apparently not supported by
the mulf.
In case all dimensions are dropped, the target vectorType is
vector<1xf32>
---------
Co-authored-by: Benjamin Maxwell <macdue@dueutil.tech>
|
|
Restrict `DropInnerMostUnitDimsTransfer{Read|Write}` so that it fails
when one of the indices to be dropped could be != 0 and "out of bounds":
```mlir
func.func @negative_example(%arg0: memref<16x1xf32>, %arg1: vector<8x1xf32>, %idx_1: index, %idx_2: index) {
vector.transfer_write %arg1, %arg0[%idx_1, %idx_2] {in_bounds = [true, false]} : vector<8x1xf32>, memref<16x1xf32>
return
}
```
This is an edge case that could represent an out-of-bounds access,
though that will depend on the actual value of %i. Importantly, without
this change it would be transformed as follows:
```mlir
func.func @negative_example(%arg0: memref<16x1xf32>, %arg1: vector<8x1xf32>, %arg2: index, %arg3: index) {
%subview = memref.subview %arg0[0, 0] [16, 1] [1, 1] : memref<16x1xf32> to memref<16xf32, strided<[1]>>
%0 = vector.shape_cast %arg1 : vector<8x1xf32> to vector<8xf32>
vector.transfer_write %0, %subview[%arg2] {in_bounds = [true]} : vector<8xf32>, memref<16xf32, strided<[1]>>
return
}
```
This is incorrect - `%idx_2` is ignored and the "out of bounds" flags is
not propagated. Hence the extra restriction to avoid such cases.
NOTE: This is a follow-up for: #94904
|
|
leading / trailing dimensions." (#97652)
Reverts llvm/llvm-project#92934 because it breaks some lowering. To
repro: `mlir-opt -test-vector-transfer-flatten-patterns ~/repro.mlir`
```mlir
func.func @unit_dim_folding(%arg0: vector<1x1xf32>) -> vector<1x1xf32> {
%cst = arith.constant dense<0.000000e+00> : vector<1x1xf32>
%0 = arith.mulf %arg0, %cst : vector<1x1xf32>
return %0 : vector<1x1xf32>
}
```
|
|
This patch is part of a project to move the Presburger library into
LLVM.
|
|
Many state of the art models and quantization operations are now
directly working on vector.contract on integers.
This commit enables generalizes ext-contraction folding S.T we can emit
more performant vector.contracts on codegen pipelines.
Signed-off-by: Stanley Winata <stanley.winata@amd.com>
|
|
1D multi-reduction are lowered to arith which can prevent some
optimisations. I propose `ElementwiseToOuterproduct` matching a series of
ops to generate `vector.outerproduct`.
As part of some `ElementwiseToVectorOpsPatterns`, it could allow to fuse
other elementwiseOps to vector dialect.
Originally discussed
https://discourse.llvm.org/t/on-improving-arm-sme-lowering-resilience-in-mlir/78543/24.
quote @MacDue
```
%lhsBcast = vector.broadcast %lhsCast : vector<[4]xf32> to vector<[4]x[4]xf32>
%lhsT = vector.transpose %lhsBcast, [1, 0] : vector<[4]x[4]xf32> to vector<[4]x[4]xf32>
%rhsBcast = vector.broadcast %rhs : vector<[4]xf32> to vector<[4]x[4]xf32>
%mul = arith.mulf %lhsT, %rhsBcast : vector<[4]x[4]xf32>
```
Can be rewritten as:
```
%mul = vector.outerproduct $lhs, $rhs : vector<[4]xf32>, vector<[4]xf32>
```
---------
Co-authored-by: Han-Chung Wang <hanhan0912@gmail.com>
|
|
The main goal of this PR (and subsequent PRs), is to add more tests with
scalable vectors to:
* vector-transfer-collapse-inner-most-dims.mlir
There's quite a few cases to consider, hence this is split into multiple
PRs. In this PR, the very first test for `vector.transfer_write` is
complemented with all the possible combinations:
* scalable (rather than fixed) unit trailing dim,
* dynamic (rather than static) trailing dim in the source memref.
To this end, the following tests:
* `@leading_scalable_dimension_transfer_write`
`@trailing_scalable_one_dim_transfer_write`
are replaced with:
* `@drop_two_inner_most_dim_scalable_inner_dim` and
`@negative_scalable_unit_dim`,
respectively. In addition:
* "_for_transfer_write" is removed from function names (to reduce
noise).
In addition, to maintain consistency between the tests for `xfer_read`
and `xfer_write`, 2 negative tests for `xfer_read` are also renamed.
This is to follow the suggestion made during the review of this PR.
Extra comments in "VectorTransforms.cpp" are added to better
document the limitations related to scalable vectors and which tests
added here excercise.
This is a follow-up for: #94490 and #94604
NOTE: This PR is limited to tests for `vector.transfer_write`.
|
|
trailing dimensions. (#92934)
Generalizes `DropUnitDimFromElementwiseOps` to support inner unit
dimensions.
This change stems from improving lowering of contractionOps for Arm SME.
Where we end up with inner unit dimensions on MulOp, BroadcastOp and
TransposeOp, preventing the generation of outerproducts.
discussed
[here](https://discourse.llvm.org/t/on-improving-arm-sme-lowering-resilience-in-mlir/78543/17?u=nujaa).
---------
Co-authored-by: Benjamin Maxwell <macdue@dueutil.tech>
|
|
Restrict `DropInnerMostUnitDimsTransferRead` so that it fails when one
of the indices to be dropped could be != 0, e.g.
```mlir
func.func @negative_example(%A: memref<16x1xf32>, %i:index, %j:index) -> (vector<8x1xf32>) {
%f0 = arith.constant 0.0 : f32
%1 = vector.transfer_read %A[%i, %j], %f0 : memref<16x1xf32>, vector<8x1xf32>
return %1 : vector<8x1xf32>
}
```
This is an edge case that could represent an out-of-bounds access,
though that will depend on the actual value of `%j`. Importantly,
_without this change_ it would be transformed as follows:
```mlir
func.func @negative_example(%arg0: memref<16x1xf32>, %arg1: index, %arg2: index) -> vector<8x1xf32> {
%cst = arith.constant 0.000000e+00 : f32
%subview = memref.subview %arg0[0, 0] [16, 1] [1, 1] : memref<16x1xf32> to memref<16xf32, strided<[1]>>
%0 = vector.transfer_read %subview[%arg1], %cst : memref<16xf32, strided<[1]>>, vector<8xf32>
%1 = vector.shape_cast %0 : vector<8xf32> to vector<8x1xf32>
return %1 : vector<8x1xf32>
}
```
This is incorrect - `%arg2` is ignored. Hence the extra restriction to
avoid such cases.
NOTE: This PR is limited to tests for `vector.transfer_read`.
|
|
patterns (#92402)
Previously, these rewrites would drop scalable dimensions and treated
`[1]` (scalable one dim) as a unit dimension. This patch propagates
scalable dimensions and ensures `[1]` is not treated as a unit
dimension.
|
|
An `arith.select` may have a scalar condition and true/false vector values.
|
|
(#84395)
Fixes https://github.com/openxla/iree/issues/16475
|
|
This PR is adds support for `vector.insert` to the patterns that bubble up and down `vector.bitcat` ops across `vector.extract/extract_slice/insert_slice` ops.
|
|
shapes." (#80712) (#81778)
This reverts commit b4c7152eb4f7971c111e3e2f60b55892def58d5d.
Downstream regression due to another issue that this PR exposes. We have identified the work-items to fix the new issue here: https://github.com/openxla/iree/issues/16406
Co-authored-by: Han-Chung Wang <hanchung@google.com>
|
|
Fix obvious bug in AffineMap::replace for the case of zero result maps.
Extend/complete inferExprsFromList to work with empty expression lists.
|
|
This is part of
https://github.com/llvm/llvm-project/commit/66347e516e22f9159b86024071fb92f364ac4418
The regression in downstream projects is about transfer_read patterns,
which needs more investigation. Add the support for transfer_write for
now.
|
