Make it a static function RISCVISelLowering, the only place it
is used.
I think I'm going to make this return a fractional LMULs in some
cases so I'm sorting out where it should live before I start
making changes.
We can have RISCVISelDAGToDAG.cpp call the VT only version by
finding the RISCVTargetLowering object via the Subtarget.
Make the static versions just global static functions in
RISCVISelLowering that can be called by static functions in that
file.
We were taking a reference to a value in `loadedDylibs`, which in turn
called `make<DylibFile>()`, which could then recursively call
`loadDylibs`, which would then potentially resize `loadedDylibs` and
invalidate that reference.
Fixes PR50101.
Reviewed By: #lld-macho, oontvoo
Differential Revision: https://reviews.llvm.org/D101175
I was a bit confused by the comment because I thought that "Tests
that..." was describing the tests contained within the same file.
Reviewed By: #lld-macho, thakis
Differential Revision: https://reviews.llvm.org/D101160
While doing speculative execution opt, it conservatively drops all insn's debug info in the merged `ThenBB`(see the loop at line 2384) including the dangling probe. The missing debug info of the dangling probe will cause the wrong inference computation.
So we should avoid dropping the debug info from pseudo probe, this change try to fix this by moving the to-be dangling probe to the merging target BB before the debug info is dropped.
Reviewed By: hoy, wenlei
Differential Revision: https://reviews.llvm.org/D101195
Instead of conditionally overwriting a nullptr and then branching on its
nullness, just branch directly on the original condition. Then we can
make both pointers (non-null) references instead.
Adds new intrinsics for instructions that are in the final SIMD spec but did not
previously have intrinsics. Also updates the names of existing intrinsics to
reflect the final names of the underlying instructions in the spec. Keeps the
old names as deprecated functions to ease the transition to the new names.
Differential Revision: https://reviews.llvm.org/D101112
There are some interfaces in altivec.h that are not compatible
between Clang and XL (although Clang is compatible with GCC).
Currently, we have found 3 but there may be others.
Clang/GCC signatures:
vector double vec_ctf(vector signed long long)
vector double vec_ctf(vector unsigned long long)
vector signed long long vec_cts(vector double)
vector unsigned long long vec_ctu(vector double)
XL signatures:
vector float vec_ctf(vector signed long long)
vector float vec_ctf(vector unsigned long long)
vector signed int vec_cts(vector double)
vector unsigned int vec_ctu(vector double)
This patch provides the XL behaviour under the __XL_COMPAT_ALTIVEC__
macro for users that rely on XL behaviour.
Differential revision: https://reviews.llvm.org/D101130
Includes tests and implementation for both integer and floating point values.
Both nearest neighbor and bilinear interpolation is included.
Differential Revision: https://reviews.llvm.org/D101009
If no range is given, return the translation unit AST.
This is useful for tooling operations that require e.g. the full path to
a node.
Reviewed By: sammccall
Differential Revision: https://reviews.llvm.org/D101057
I went through the callers of `readFile()` and `addFile()` in Driver.cpp
and checked that the options that use them all get rewritten in the
--reproduce response file. -(un)exported_symbols_list and -bundle_loader
weren't, so add them.
Also spruce up the test for reproduce a bit and actually try linking
with the exptracted repro archive.
Motivated by the response file in PR50098 complaining abou the
-exported_symbols_list path being wrong :)
Differential Revision: https://reviews.llvm.org/D101182
Pseudo probe distribution factor is used to scale down profile samples to avoid misleading the counts inference due to the usage of "maximum" in `getBlockWeight`. For callsites, the scaling down can come from code duplication prior to the sample profile loader (prelink or postlink), or due to the indirect call promotion in sample loader inliner. This patch fixes an issue in sample loader ICP where the leftover indirect callsite scaling down causes the loss of non-promoted call target samples unexpectedly. While the scaling down is to favor BFI/BPI with accurate an callsite count, it doesn't fit in the current distribution factor that represents code duplication changes. Ideally, we would need two factors, one is for code duplication, the other is for ICP. However this seems over complicated. I'm going to trade one usage (callsite counts) for the other (call target counts).
Seeing perf win on one benchmark (mcf) of SPEC2017 with others unchanged.
Reviewed By: wenlei
Differential Revision: https://reviews.llvm.org/D100993
Now that page aliasing for x64 has landed, we don't need to worry about
passing tagged pointers to libc, and thus D98875 removed it.
Unfortunately, we still test on aarch64 devices that don't have the
kernel tagged address ABI (https://reviews.llvm.org/D98875#2649269).
All the memory that we pass to the kernel in these tests is from global
variables. Instead of having architecture-specific untagging mechanisms
for this memory, let's just not tag the globals.
Reviewed By: eugenis, morehouse
Differential Revision: https://reviews.llvm.org/D101121
As discussed in https://llvm.org/PR50096 , we could
convert the 'not' into a 'sub' and see the same
fold. That's because we already have another demanded
bits optimization for 'sub'.
We could add a related transform for
odd-number-of-type-bits, but that seems unlikely
to be practical.
https://alive2.llvm.org/ce/z/TWJZXr
This patch does a few cleanup things:
1. The non-standalone scudo has a problem where GWP-ASan allocations
may not meet alignment requirements where Scudo was requested to have
alignment >= 16. Use the new GWP-ASan API to fix this.
2. The standalone variant loses some debugging information inside of
GWP-ASan because we ask GWP-ASan to allocate an aligned size in the
frontend. This means reports end up with 'UaF on a 16-byte allocation'
for a 1-byte allocation with 16-byte alignment. Also use the new API to
fix this.
3. Add post-alloc hooks for GWP-ASan intercepted allocations, and add
stats tracking for GWP-ASan allocations.
4. Add a small test that checks the alignment of the frontend
allocator, so that it can be used under GWP-ASan torture mode.
5. Add GWP-ASan torture mode as a testing configuration to catch these
regressions.
Depends on D94830, D95889.
Reviewed By: cryptoad
Differential Revision: https://reviews.llvm.org/D95884
Mishandling of variadic arguments in a function call caused a crash
(runtime assert fail) in bugprone-infinite-loop tidy checker. Fix
is to limit argument matching to the lesser of the number of variadic
params in the prototype or the number of actual args in the call.
Reviewed By: aaron.ballman
Differential Revision: https://reviews.llvm.org/D101108
There is already code in InlineCost.cpp to identify and ignore ephemeral
values (llvm.assume intrinsics and other side-effect free instructions
only feeding the assumes). However, because llvm.type.test intrinsics
were not marked speculatable, they and any instructions specifically
feeding the type test (typically a bitcast) were being counted towards
the instruction cost when inlining. This was causing profile matching
issues in some cases when enabling -fwhole-program-vtables for whole
program devirtualization.
According to the language reference, the speculatable attribute means:
"the function does not have any effects besides calculating its result
and does not have undefined behavior". I see no reason why type tests
cannot be marked with this attribute.
There are 2 test changes:
llvm/test/Transforms/Inline/ephemeral.ll: I added a type test intrinsic
here to verify the fix. Also, I found the test was not actually testing
what it originally intended. Many of the existing instructions were
optimized away by -Oz, and the cost of inlining was negative due to the
benefit of removing the call. So I changed the test to simply invoke the
inline pass and check the number of instructions computed by InlineCost.
I also fixed an instruction that was not actually used anywhere.
llvm/test/Transforms/SimplifyCFG/no-md-sink.ll needed to be made more
robust to code changes that reordered the metadata.
Differential Revision: https://reviews.llvm.org/D101180
This nasty patch rewrites the tuple constructors to match those defined
by the Standard. We were previously providing several extensions in those
constructors - those extensions are removed by this patch.
The issue with those extensions is that we've had numerous bugs filed
against us over the years for problems essentially caused by them. As a
result, people are unable to use tuple in ways that are blessed by the
Standard, all that for the perceived benefit of providing them extensions
that they never asked for.
Since this is an API break, I communicated it in the release notes.
I do not foresee major issues with this break because I don't think the
extensions are too widely relied upon, but we can ship it and see if we
get complaints before the next LLVM release - that will give us some
amount of information regarding how much use these extensions have.
Differential Revision: https://reviews.llvm.org/D96523
As this is a test that actually gets to operating the debugger, it
needs to be limited to scenarios where the debugger is available.
(We'll file this in the set of things Dexter doesn't handle gracefully..)
Theses instructions are allowed to write v0 when they are masked.
We'll still never use v0 because of the earlyclobber constraint so
this doesn't really help anything. It just makes the definitions
correct.
While I was there remove an unused multiclass I noticed.
Reviewed By: HsiangKai
Differential Revision: https://reviews.llvm.org/D101118
From a cache perspective it's better to store the header immediately
after loading it. If we delay this operation until after we've
retagged it's more likely that our header will have been evicted from
the cache and we'll need to fetch it again in order to perform the
compare-exchange operation.
For similar reasons, store the deallocation stack before retagging
instead of afterwards.
Differential Revision: https://reviews.llvm.org/D101137
This patch adds a new iterator to traverse through VPRegionBlocks and a
GraphTraits specialization using the iterator to traverse through
VPRegionBlocks.
Because there is already a GraphTraits specialization for VPBlockBase *
and co, a new VPBlockRecursiveTraversalWrapper helper is introduced.
This allows us to provide a new GraphTraits specialization for that
type. Users can use the new recursive traversal by using this wrapper.
The graph trait visits both the entry block of a region, as well as all
its successors. Exit blocks of a region implicitly have their parent
region's successors. This ensures all blocks in a region are visited
before any blocks in a successor region when doing a reverse post-order
traversal of the graph.
Reviewed By: a.elovikov
Differential Revision: https://reviews.llvm.org/D100175
When an object is allocated in a non-default address space we do not
need to check for a constructor if it is not initialized and has a
trivial constructor (which we won't call then).
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D100929
The values of registers in inactive lanes needs to be saved during
function calls.
Save all registers used for whole wave mode, similar to how it is done
for VGPRs that are used for SGPR spilling.
Differential Revision: https://reviews.llvm.org/D99429
Reapply with fixed tests on window.
These are added for compatibility with XLC. They are similar to
vec_cts and vec_ctu except that the result is a doubleword vector
regardless of the parameter type.
Using `cmake` >=3.20 results in many warnings about this new policy. This change silences the warnings by explicitly declaring use of the "OLD" behavior.
This policy currently affects only one place: the `tablegen()` function in `TableGen.cmake`.
Differential Revision: https://reviews.llvm.org/D101083
In this patch, I provide a detailed explanation for each argument
constraint. This explanation is added in an extra 'note' tag, which is
displayed alongside the warning.
Since these new notes describe clearly the constraint, there is no need
to provide the number of the argument (e.g. 'Arg3') within the warning.
However, I decided to keep the name of the constraint in the warning (but
this could be a subject of discussion) in order to be able to identify
the different kind of constraint violations easily in a bug database
(e.g. CodeChecker).
Differential Revision: https://reviews.llvm.org/D101060
Avoid string allocation in particular, but also avoid attempting to
impose any particular ordering based on formatted results.
Differential Revision: https://reviews.llvm.org/D101054
This patch updates the final test that can be shared between the old and
the new Flang drivers and that has not been ported yet. %f18 (always
expanded as `f18`) is replaced with %flang_fc1 (expanded as either `f18`
or `flang-new -fc1`, depending on `FLANG_BUILD_NEW_DRIVER`).
This test should've been updated in https://reviews.llvm.org/D100309,
but I missed it then. That's because this test contains non-ascii
characters and `grep -I %f18` (as well as other grep-like tools) skips
it because it's interpreted as a data/binary file. In fact, it's just a
text file with non-ascii chars.
Since this is an obvious omission from D100309 (reviewed, accepted and
merged), I'm sending this without a review to reduce the noise on
Phabricator.
Craig Topper