RESHAPE() fails inappropriately at runtime if the source array
is larger than the result -- which is perfectly valid -- because
of an obviously reversed comparison of their numbers of elements
is activating the runtime asserts meant for the opposite case
(source smaller than result).
Differential Revision: https://reviews.llvm.org/D114474
Relative to the previous landing attempt, this makes
insertValueToMap() resilient against the value already being
present in the map -- previously I only checked this for the
createSimpleAffineAddRec() case, but the same issue can also
occur for the general createNodeForPHI(). In both cases, the
addrec may be constructed and added to the map in a recursive
query trying to create said addrec. In this case, this happens
due to the invalidation when the BE count is computed, which
ends up clearing out the symbolic name as well.
-----
This adds validation for consistency of ValueExprMap and
ExprValueMap, and fixes identified issues:
* Addrec construction directly wrote to ValueExprMap in a few places,
without updating ExprValueMap. Add a helper to ensures they stay
consistent. The adjustment in forgetSymbolicName() explicitly
drops the old value from the map, so that we don't rely on it
being overwritten.
* forgetMemoizedResultsImpl() was dropping the SCEV from
ExprValueMap, but not dropping the corresponding entries from
ValueExprMap.
Differential Revision: https://reviews.llvm.org/D113349
This allows --power10-stubs= and --[no-]power10-stubs to override each other
(they are position dependent in GNU ld).
Also improve --help messages and the manpage.
Note: GNU ld's default "auto" mode uses heuristics to decide whether Power10
instructions are used. Arguably it is a design mistake of R_PPC64_REL24_NOTOC
(acked by the relevant folks on a libc-alpha discussion). We don't implement
"auto", so the default --power10-stubs is the same as "yes".
We check whether the maximum index of dimensional identifier present
in the result expressions is less than dimCount (number of dimensional
identifiers) argument passed in the AffineMap::get() and the maximum index
of symbolic identifier present in the result expressions is less than
symbolCount (number of symbolic identifiers) argument passed in AffineMap::get().
Reviewed By: nicolasvasilache, bondhugula
Differential Revision: https://reviews.llvm.org/D114238
Initially we were passing wrong numSymbols argument while calling
AffineMap::get() for creaating affine map with linearized result
expressions. The main problems was the number of symbols of the newly
to be created map may be different from that of the source map, as
new symbolic identifiers may be introduced while creating strided layout
linearized expressions.
Reviewed By: nicolasvasilache, bondhugula
Differential Revision: https://reviews.llvm.org/D114240
The canonical term is "extract" (GNU ld documentation, Solaris's `-z *extract`
options). Avoid inventing a term and match --why-extract. (ld64 prefers "load"
but the word is overloaded too much)
Mostly MFC, except for --help messages and the header row in
--print-archive-stats output.
This changes the op to produce `AnyVectorOfAnyRank` following mostly the code for 1-D vectors.
Depends On D114598
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D114550
This changes the op to produce `AnyVectorOfAnyRank` and implements this by just
inserting the element (skipping the shuffle that we do for the 1-D case).
Depends On D114549
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D114598
Previously, when adding a constraint to a Simplex that is already marked
as having no solutions (marked empty), the Simplex would be marked empty again,
and a second UnmarkEmpty entry would be pushed to the undo log. When rolling
back, Simplex should be unmarked empty only after rolling back past the
creation of the first constraint that made it empty.
Reviewed By: Groverkss
Differential Revision: https://reviews.llvm.org/D114613
Previously, the pivot function would only update the non-redundant rows when
pivoting. This is incorrect because in some cases, when rolling back past a
`detectRedundant` call, the basis being used could be different from that which
was used at the time of returning from the `detectRedundant` call. Therefore,
it is important to update the redundant rows as well during pivots. This could
also be triggered by pivots that occur when testing successive constraints for
being redundant in `detectRedundant` after some initial constraints are marked redundant.
Reviewed By: Groverkss
Differential Revision: https://reviews.llvm.org/D114614
Renamed the option for llvm-cov and changed variable names to use more
inclusive terms. Also changed the binary for the test.
Reviewed By: alanphipps
Differential Revision: https://reviews.llvm.org/D112816
Instead of silently swallowing errors that happen during Lit configuration
(for example trying to obtain compiler macros but compiling fails), raise
an exception with some amount of helpful information.
This should avoid the possibility of silently configuring Lit in a bogus
way, and also provides more helpful information when things fail.
Note that this requires a bit more finesse around how we handle some
failing configuration checks that we would previously return None for.
Differential Revision: https://reviews.llvm.org/D114010
-Wformat-nonliteral was turned on in https://reviews.llvm.org/D112927,
however we forgot to apply some __format__ attributes in Linux specific
code paths, which led to warnings when building on Linux. This patch
addresses that oversight.
Differential Revision: https://reviews.llvm.org/D113876
This reverts commit fac3f20de5.
I found this has broken how we detect the last memory region in
GetMemoryRegions/"memory region" command.
When you're debugging an AArch64 system with pointer authentication,
the ABI plugin will remove the top bit from the end address of the last
user mapped area.
(lldb)
[0x0000fffffffdf000-0x0001000000000000) rw- [stack]
ABI plugin removes anything above the 48th bit (48 bit virtual addresses
by default on AArch64, leaving an address of 0.
(lldb)
[0x0000000000000000-0x0000000000400000) ---
You get back a mapping for 0 and get into an infinite loop.
When a symbol comes from the non self-contained header, we recursively uplift
the file we consider used to the first includer that has a header guard. We
need to do this while we still have FileIDs because every time a non
self-contained header is included, it gets a new FileID but is later
deduplicated by HeaderID and it's not possible to understand where it was
included from.
Based on D114370.
Reviewed By: sammccall
Differential Revision: https://reviews.llvm.org/D114623
Compiler has an analysis for perfect diamond matching but it does not
support nodes with main/alternate opcodes. The problem is that the
scalars themselves are different and might not match directly with other
nodes, but operands and main/alternate opcodes might match and compiler
might reuse some previously emitted vector instructions. Need to include
this analysis in the cost model and actual vector instructions emission
process.
Differential Revision: https://reviews.llvm.org/D114101
std::invoke_result takes function object type and arguments separately
(unlike std::result_of) so, std::invoke_result_t<F()> usage is
incorrect.
On the other hand, we don't need std::invoke() semantics here at all. So
just simplifying the code without extra dependency and use trailing
return type as the fix.
Reviewed By: MikeDvorskiy
Differential Revision: https://reviews.llvm.org/D114624
Certain commands like 'memory write', 'register read' etc all use
the OptionGroupFormat options but the help usage text for those
options is not customized to those commands.
One such example is:
(lldb) help memory read
-s <byte-size> ( --size <byte-size> )
The size in bytes to use when displaying with the selected format.
(lldb) help memory write
-s <byte-size> ( --size <byte-size> )
The size in bytes to use when displaying with the selected format.
This patch allows such commands to overwrite the help text for the options
in the OptionGroupFormat group as needed and fixes help text of memory write.
llvm.org/pr49018.
Reviewed By: DavidSpickett
Differential Revision: https://reviews.llvm.org/D114448
Accum is guaranteed to be defined outside L (via Loop::isLoopInvariant
checks above). I think that should guarantee that the more powerful
ScalarEvolution::isLoopInvariant also determines that the value is loop
invariant.
Reviewed By: nikic
Differential Revision: https://reviews.llvm.org/D114634
There is special logic for InsertSliceOp to check if a memcpy is needed. This change extracts that piece of code and makes it a PostAnalysisStep.
The purpose of this change is to untangle `bufferize` from BufferizationAliasInfo. (Not fully there yet.)
Differential Revision: https://reviews.llvm.org/D114513
This is a small diff that splits out the debug output for PDL bytecode. When running bytecode with debug output on, it is useful to know the line numbers where the PDLIntepr operations are performed. Usually, these are in a single MLIR file, so it's sufficient to print out the line number rather than the entire location (which tends to be quite verbose). This debug output is gated by `LLVM_DEBUG` rather than `#ifndef NDEBUG` to make it easier to test.
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D114061
This is commit 4 of 4 for the multi-root matching in PDL, discussed in https://llvm.discourse.group/t/rfc-multi-root-pdl-patterns-for-kernel-matching/4148 (topic flagged for review).
This PR integrates the various components (root ordering algorithm, nondeterministic execution of PDL bytecode) to implement multi-root PDL matching. The main idea is for the pattern to specify mulitple candidate roots. The PDL-to-PDLInterp lowering selects one of these roots and "hangs" the pattern from this root, traversing the edges downwards (from operation to its operands) when possible and upwards (from values to its uses) when needed. The root is selected by invoking the optimal matching multiple times, once for each candidate root, and the connectors are determined form the optimal matching. The costs in the directed graph are equal to the number of upward edges that need to be traversed when connecting the given two candidate roots. It can be shown that, for this choice of the cost function, "hanging" the pattern an inner node is no better than from the optimal root.
The following three main additions were implemented as a part of this PR:
1. OperationPos predicate has been extended to allow tracing the operation accepting a value (the opposite of operation defining a value).
2. Predicate checking if two values are not equal - this is useful to ensure that we do not traverse the edge back downwards after we traversed it upwards.
3. Function for for building the cost graph among the candidate roots.
4. Updated buildPredicateList, building the predicates optimal branching has been determined.
Testing: unit tests (an integration test to follow once the stack of commits has landed)
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D108550
This is commit 3 of 4 for the multi-root matching in PDL, discussed in https://llvm.discourse.group/t/rfc-multi-root-pdl-patterns-for-kernel-matching/4148 (topic flagged for review).
We form a graph over the specified roots, provided in `pdl.rewrite`, where two roots are connected by a directed edge if the target root can be connected (via a chain of operations) in the underlying pattern to the source root. We place a restriction that the path connecting the two candidate roots must only contain the nodes in the subgraphs underneath these two roots. The cost of an edge is the smallest number of upward traversals (edges) required to go from the source to the target root, and the connector is a `Value` in the intersection of the two subtrees rooted at the source and target root that results in that smallest number of such upward traversals. Optimal root ordering is then formulated as the problem of finding a spanning arborescence (i.e., a directed spanning tree) of minimal weight.
In order to determine the spanning arborescence (directed spanning tree) of minimum weight, we use the [Edmonds' algorithm](https://en.wikipedia.org/wiki/Edmonds%27_algorithm). The worst-case computational complexity of this algorithm is O(_N_^3) for a single root, where _N_ is the number of specified roots. The `pdl`-to-`pdl_interp` lowering calls this algorithm as a subroutine _N_ times (once for each candidate root), so the overall complexity of root ordering is O(_N_^4). If needed, this complexity could be reduced to O(_N_^3) with a more efficient algorithm. However, note that the underlying implementation is very efficient, and _N_ in our instances tends to be very small (<10). Therefore, we believe that the proposed (asymptotically suboptimal) implementation will suffice for now.
Testing: a unit test of the algorithm
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D108549
This is commit 2 of 4 for the multi-root matching in PDL, discussed in https://llvm.discourse.group/t/rfc-multi-root-pdl-patterns-for-kernel-matching/4148 (topic flagged for review).
This commit implements the features needed for the execution of the new operations pdl_interp.get_accepting_ops, pdl_interp.choose_op:
1. The implementation of the generation and execution of the two ops.
2. The addition of Stack of bytecode positions within the ByteCodeExecutor. This is needed because in pdl_interp.choose_op, we iterate over the values returned by pdl_interp.get_accepting_ops until we reach finalize. When we reach finalize, we need to return back to the position marked in the stack.
3. The functionality to extend the lifetime of values that cross the nondeterministic choice. The existing bytecode generator allocates the values to memory positions by representing the liveness of values as a collection of disjoint intervals over the matcher positions. This is akin to register allocation, and substantially reduces the footprint of the bytecode executor. However, because with iterative operation pdl_interp.choose_op, execution "returns" back, so any values whose original liveness cross the nondeterminstic choice must have their lifetime executed until finalize.
Testing: pdl-bytecode.mlir test
Reviewed By: rriddle, Mogball
Differential Revision: https://reviews.llvm.org/D108547
We can not swap multiplicand and multiplier because the sve intrinsics
are predicated. Imagine lanes in vectors having the following values:
pg = 0
multiplicand = 1 (from dup)
multiplier = 2
The resulting value should be 1, but if we swap multiplicand and multiplier it will become 2,
which is incorrect.
Differential Revision: https://reviews.llvm.org/D114577
This is commit 1 of 4 for the multi-root matching in PDL, discussed in https://llvm.discourse.group/t/rfc-multi-root-pdl-patterns-for-kernel-matching/4148 (topic flagged for review).
These operations are:
* pdl.get_accepting_ops: Returns a list of operations accepting the given value or a range of values at the specified position. Thus if there are two operations `%op1 = "foo"(%val)` and `%op2 = "bar"(%val)` accepting a value at position 0, `%ops = pdl_interp.get_accepting_ops of %val : !pdl.value at 0` will return both of them. This allows us to traverse upwards from a value to operations accepting the value.
* pdl.choose_op: Iteratively chooses one operation from a range of operations. Therefore, writing `%op = pdl_interp.choose_op from %ops` in the example above will select either `%op1`or `%op2`.
Testing: Added the corresponding test cases to mlir/test/Dialect/PDLInterp/ops.mlir.
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D108543
When unwind step reaches the end of the stack that means the force unwind should notify the stop function.
This is not an error, it could mean just the thread is cleaned up completely.
Reviewed By: #libunwind, mstorsjo
Differential Revision: https://reviews.llvm.org/D109856
Attempt to further document the intended cache policies requested
by different combinations of GLC, SLC and DLC bits.
GFX10 non-temporal stores are updated to set GLC.
Reviewed By: t-tye
Differential Revision: https://reviews.llvm.org/D114351
This change folds a basic funnel shift idiom:
- (or (shl x, amt), (lshr y, sub(bw, amt))) -> fshl(x, y, amt)
- (or (shl x, sub(bw, amt)), (lshr y, amt)) -> fshr(x, y, amt)
This also helps in folding to rotate shift if x and y are equal since we
already have a funnel shift to rotate combine.
Differential Revision: https://reviews.llvm.org/D114499
In VPRecipeBuilder::handleReplication if we believe the instruction
is predicated we then proceed to create new VP region blocks even
when the load is uniform and only predicated due to tail-folding.
I have updated isPredicatedInst to avoid treating a uniform load as
predicated when tail-folding, which means we can do a single scalar
load and a vector splat of the value.
Tests added here:
Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll
Differential Revision: https://reviews.llvm.org/D112552
The filesystem used during dependency scanning does two things: it caches file entries and minimizes source file contents. We use the term "ignored file" in a couple of places, but it's not clear what exactly that means. This commit clears up the semantics, explicitly spelling out this relates to minimization.
Nikita Popov