Depends On D115263
By aligning block size to inner loop iterations parallel_compute_fn LLVM can later unroll and vectorize some of the inner loops with small number of trip counts. Up to 2x speedup in multiple benchmarks.
Reviewed By: bkramer
Differential Revision: https://reviews.llvm.org/D115436
With complex recursive structure of async dispatch function LLVM can't always propagate constants to the parallel_compute_fn and it often prevents optimizations like loop unrolling and vectorization. We help LLVM by pushing known constants into the parallel_compute_fn explicitly.
Reviewed By: bkramer
Differential Revision: https://reviews.llvm.org/D115263
The new form of printing attribute in the declarative assembly is eliding the `#dialect.mnemonic` prefix to only keep the `<....>` part.
Differential Revision: https://reviews.llvm.org/D113873
Precursor: https://reviews.llvm.org/D110200
Removed redundant ops from the standard dialect that were moved to the
`arith` or `math` dialects.
Renamed all instances of operations in the codebase and in tests.
Reviewed By: rriddle, jpienaar
Differential Revision: https://reviews.llvm.org/D110797
Previously only await inside the async function (coroutine after lowering to async runtime) would check the error state
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D109229
Currently TFRT does not support top-level coroutines, so this functionality will allow to have a single blocking await at the top level until TFRT implements the necessary functionality.
Reviewed By: ezhulenev
Differential Revision: https://reviews.llvm.org/D106730
Interop parallelism requires needs awaiting on results. Blocking awaits are bad for performance. TFRT supports lightweight resumption on threads, and coroutines are an abstraction than can be used to lower the kernels onto TFRT threads.
Reviewed By: ezhulenev
Differential Revision: https://reviews.llvm.org/D106508
Depends On D104999
Automatic reference counting based on the liveness analysis can add a lot of reference counting overhead at runtime. If the IR is known to be constrained to few particular "shapes", it's much more efficient to provide a custom reference counting policy that will specify where it is required to update the async value reference count.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D105037
Depends On D104998
Function calls "transfer ownership" to the callee and it puts additional constraints on the reference counting optimization pass
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D104999
Depends On D104850
Add a test that verifies that canonicalization removes all async overheads if it is statically known that the scf.parallel operation will be computed using a single block.
Reviewed By: herhut
Differential Revision: https://reviews.llvm.org/D104891
Depends On D104780
Recursive work splitting instead of sequential async tasks submission gives ~20%-30% speedup in microbenchmarks.
Algorithm outline:
1. Collapse scf.parallel dimensions into a single dimension
2. Compute the block size for the parallel operations from the 1d problem size
3. Launch parallel tasks
4. Each parallel task reconstructs its own bounds in the original multi-dimensional iteration space
5. Each parallel task computes the original parallel operation body using scf.for loop nest
Reviewed By: herhut
Differential Revision: https://reviews.llvm.org/D104850
Specify the `!async.group` size (the number of tokens that will be added to it) at construction time. `async.await_all` operation can potentially race with `async.execute` operations that keep updating the group, for this reason it is required to know upfront how many tokens will be added to the group.
Reviewed By: ftynse, herhut
Differential Revision: https://reviews.llvm.org/D104780
Depends On D103109
If any of the tokens/values added to the `!async.group` switches to the error state, than the group itself switches to the error state.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D103203
Depends On D103102
Not yet implemented:
1. Error handling after synchronous await
2. Error handling for async groups
Will be addressed in the followup PRs
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D103109
Support reference counted values implicitly passed (live) only to some of the successors.
Example: if branched to ^bb2 token will leak, unless `drop_ref` operation is properly created
```
^entry:
%token = async.runtime.create : !async.token
cond_br %cond, ^bb1, ^bb2
^bb1:
async.runtime.await %token
async.runtime.drop_ref %token
br ^bb2
^bb2:
return
```
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D103102
Depends On D95311
Previous automatic-ref-counting pass worked with high level async operations (e.g. async.execute), however async values reference counting is a runtime implementation detail.
New pass mostly relies on the save liveness analysis to place drop_ref operations, and does better verification of CFG with different liveIn sets in block successors.
This is almost NFC change. No new reference counting ideas, just a cleanup of the previous version.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D95390
This commit introduced a cyclic dependency:
Memref dialect depends on Standard because it used ConstantIndexOp.
Std depends on the MemRef dialect in its EDSC/Intrinsics.h
Working on a fix.
This reverts commit 8aa6c3765b.
Create the memref dialect and move several dialect-specific ops without
dependencies to other ops from std dialect to this dialect.
Moved ops:
AllocOp -> MemRef_AllocOp
AllocaOp -> MemRef_AllocaOp
DeallocOp -> MemRef_DeallocOp
MemRefCastOp -> MemRef_CastOp
GetGlobalMemRefOp -> MemRef_GetGlobalOp
GlobalMemRefOp -> MemRef_GlobalOp
PrefetchOp -> MemRef_PrefetchOp
ReshapeOp -> MemRef_ReshapeOp
StoreOp -> MemRef_StoreOp
TransposeOp -> MemRef_TransposeOp
ViewOp -> MemRef_ViewOp
The roadmap to split the memref dialect from std is discussed here:
https://llvm.discourse.group/t/rfc-split-the-memref-dialect-from-std/2667
Differential Revision: https://reviews.llvm.org/D96425
Depends On D95000
Move async.execute outlining and async -> async.runtime lowering into the separate Async transformation pass
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D95311
[NFC] No new functionality, mostly a cleanup and one more abstraction level between Async and LLVM IR.
Instead of lowering from Async to LLVM coroutines and Async Runtime API in one shot, do it progressively via async.coro and async.runtime operations.
1. Lower from async to async.runtime/coro (e.g. async.execute to function with coro setup and runtime calls)
2. Lower from async.runtime/coro to LLVM intrinsics and runtime API calls
Intermediate coro/runtime operations will allow to run transformations on a higher level IR and do not try to match IR based on the LLVM::CallOp properties.
Although async.coro is very close to LLVM coroutines, it is not exactly the same API, instead it is optimized for usability in async lowering, and misses a lot of details that are present in @llvm.coro intrinsic.
Reviewed By: ftynse
Differential Revision: https://reviews.llvm.org/D94923
Depends On D89963
**Automatic reference counting algorithm outline:**
1. `ReturnLike` operations forward the reference counted values without
modifying the reference count.
2. Use liveness analysis to find blocks in the CFG where the lifetime of
reference counted values ends, and insert `drop_ref` operations after
the last use of the value.
3. Insert `add_ref` before the `async.execute` operation capturing the
value, and pairing `drop_ref` before the async body region terminator,
to release the captured reference counted value when execution
completes.
4. If the reference counted value is passed only to some of the block
successors, insert `drop_ref` operations in the beginning of the blocks
that do not have reference coutned value uses.
Reviewed By: silvas
Differential Revision: https://reviews.llvm.org/D90716
Depends On D89958
1. Adds `async.group`/`async.awaitall` to group together multiple async tokens/values
2. Rewrite scf.parallel operation into multiple concurrent async.execute operations over non overlapping subranges of the original loop.
Example:
```
scf.for (%i, %j) = (%lbi, %lbj) to (%ubi, %ubj) step (%si, %sj) {
"do_some_compute"(%i, %j): () -> ()
}
```
Converted to:
```
%c0 = constant 0 : index
%c1 = constant 1 : index
// Compute blocks sizes for each induction variable.
%num_blocks_i = ... : index
%num_blocks_j = ... : index
%block_size_i = ... : index
%block_size_j = ... : index
// Create an async group to track async execute ops.
%group = async.create_group
scf.for %bi = %c0 to %num_blocks_i step %c1 {
%block_start_i = ... : index
%block_end_i = ... : index
scf.for %bj = %c0 t0 %num_blocks_j step %c1 {
%block_start_j = ... : index
%block_end_j = ... : index
// Execute the body of original parallel operation for the current
// block.
%token = async.execute {
scf.for %i = %block_start_i to %block_end_i step %si {
scf.for %j = %block_start_j to %block_end_j step %sj {
"do_some_compute"(%i, %j): () -> ()
}
}
}
// Add produced async token to the group.
async.add_to_group %token, %group
}
}
// Await completion of all async.execute operations.
async.await_all %group
```
In this example outer loop launches inner block level loops as separate async
execute operations which will be executed concurrently.
At the end it waits for the completiom of all async execute operations.
Reviewed By: ftynse, mehdi_amini
Differential Revision: https://reviews.llvm.org/D89963
Async execute operation can take async arguments as dependencies.
Change `async.execute` custom parser/printer format to use `%value as %unwrapped: !async.value<!type>` sytax.
Reviewed By: mehdi_amini, herhut
Differential Revision: https://reviews.llvm.org/D88601
bakhtiyar