With the recent refactorings, this class is no longer needed. We can use BufferizationOptions in all places were BufferizationState was used.
Differential Revision: https://reviews.llvm.org/D127653
Adding half float to types that can be represented by __attribute__((mode(xx))).
Original implementation authored by George Steed.
Differential Revision: https://reviews.llvm.org/D126479
This change changes the bufferization so that it utilizes the new TensorCopyInsertion pass. One-Shot Bufferize no longer calls the One-Shot Analysis. Instead, it relies on the TensorCopyInsertion pass to make the entire IR fully inplacable. The `bufferize` implementations of all ops are simplified; they no longer have to account for out-of-place bufferization decisions. These were already materialized in the IR in the form of `bufferization.alloc_tensor` ops during the TensorCopyInsertion pass.
Differential Revision: https://reviews.llvm.org/D127652
TTI::prefersVectorizedAddressing() try to vectorize the addresses that lead to loads.
For aarch64, only gather/scatter (supported by SVE) can deal with vectors of addresses.
This patch specializes the hook for AArch64, to return true only when we enable SVE.
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D124612
In addition to division by zero, signed division also traps for
SignedMin / -1. This was handled in isSafeToSpeculativelyExecute(),
but not in Constant::canTrap().
The 'emit_c_wrappers' option in the FuncToLLVM conversion requests C interface
wrappers to be emitted for every builtin function in the module. While this has
been useful to bootstrap the interface, it is problematic in the longer term as
it may unintentionally affect the functions that should retain their existing
interface, e.g., libm functions obtained by lowering math operations (see
D126964 for an example). Since D77314, we have a finer-grain control over
interface generation via an attribute that avoids the problem entirely. Remove
the 'emit_c_wrappers' option. Introduce the '-llvm-request-c-wrappers' pass
that can be run in any pipeline that needs blanket emission of functions to
annotate all builtin functions with the attribute before performing the usual
lowering that accounts for the attribute.
Reviewed By: chelini
Differential Revision: https://reviews.llvm.org/D127952
Let -fsanitize-memory-param-retval be used together with
-fsanitize=kernel-memory, so that it can be applied when building the
Linux kernel.
Also add clang/test/CodeGen/kmsan-param-retval.c to ensure that
-fsanitize-memory-param-retval eliminates shadow accesses for parameters
marked as undef.
Reviewed By: eugenis, vitalybuka
Differential Revision: https://reviews.llvm.org/D127860
From [class.copy.ctor]:
```
A non-template constructor for class X is a copy constructor if its first
parameter is of type X&, const X&, volatile X& or const volatile X&, and
either there are no other parameters or else all other parameters have
default arguments (9.3.4.7).
A copy/move constructor for class X is trivial if it is not user-provided and if:
- class X has no virtual functions (11.7.3) and no virtual base classes (11.7.2), and
- the constructor selected to copy/move each direct base class subobject is trivial, and
- or each non-static data member of X that is of class type (or array thereof),
the constructor selected to copy/move that member is trivial;
otherwise the copy/move constructor is non-trivial.
```
So `T(T&) = default`; should be trivial assuming that the previous
provisions are met.
This works in GCC, but not in Clang at the moment:
https://godbolt.org/z/fTGe71b6P
Reviewed By: royjacobson
Differential Revision: https://reviews.llvm.org/D127593
GNU ld has a hack that defaults to -X (--discard-locals) in the emulation file
`riscvelf.em`. The recommended way, as gcc/config/arm does, is to let the
compiler driver pass -X to ld.
(The motivation is likely to discard a plethora of `.L` symbols due to linker
relaxation.)
lld default to --discard-none. To make clang+lld match GNU ld's behavior, pass
-X to ld.
Note: GNU ld has a special rule to treat ld -r -s as ld -r -S -x. With -X, driver `-r -Wl,-s`
will behave as ld `-r -S -X`. This removes fewer symbols than `-r -S -x` but is safe.
Differential Revision: https://reviews.llvm.org/D127826
Add more feature to tableGen backend gen-dxil-operation.
It will generate getOpCodeProperty, getOpCodeClassName and getOpCodeName when build DirectX target.
Each of these functions has a table which generate based on DXIL operations.
These generated functions will replace the manually written functions which used for query DXIL operation information.
Reviewed By: bogner
Differential Revision: https://reviews.llvm.org/D125520
I realized we'd forgotten to cover this case (though our existing
behavior is indeed correct / matches ld64's).
Reviewed By: #lld-macho, thakis
Differential Revision: https://reviews.llvm.org/D128025
* Split ops into X_graph variants as discussed;
* Remove tokens from non-Graph region variants and rely on side-effect
modelling there while removing side-effect modelling from Graph
variants and relying on explicit ordering there;
* Make tokens required to be produced by Graph variants - but kept
explicit token type specification given previous discussion on this
potentially being configurable in future;
This results in duplicating some code. I considered adding helper
functions but decided against adding an abstraction there early given
size of duplication and creating accidental coupling.
Differential Revision: https://reviews.llvm.org/D127813
Where a constraint also has a def, emit the def only to avoid duplicate
output (and def has more complete info). Also move attributes and types
to the end rather than some on top and some at end.
Differential Revision: https://reviews.llvm.org/D127823
This is a first step towards allowing programs to pre-link against the ORC
runtime, which would allow us to move some code that is currently in the LLVM
OrcTarget library into the ORC runtime instead.
The C API header has limited utility as-is, but serves as a minimal first step
and provides clients with tools for interacting with wrapper functions.
Reviewed By: beanz
Differential Revision: https://reviews.llvm.org/D127324
This patch is the last prerequisite to switch the default behaviour to -fno-lax-vector-conversions in the future.
The first path ;D124093; fixed the altivec implicit castings.
Reviewed By: amyk
Differential Revision: https://reviews.llvm.org/D126540
Inspired by discussions on D127369, we probably can further improve LLVM's COFF
section name parsing. Hopefully, this makes the logic simpler and handles some
edge cases more elegantly.
Reviewed By: rnk
Differential Revision: https://reviews.llvm.org/D127902
Most tests have been updated to make use of vscale_range to reduce
the number of RUN lines. For the remaining RUN lines the check
prefixes have been updated to ensure the original expectation of
the manual CHECK lines is maintained after update_llc_test_checks
is run.
The sphinx-automodapi extension requires that the generated RST files
live next to the index file. This means that we generate them in the
source directory rather than the build directory. This patch ensures
these files are removed again when sphinx finishes its build.
The proper solution to this problem would be to move everything in the
doc folder from the source directory to the build directory before
generating the docs.
I believe that old RST files being kept around is the reason that the
Python API references on the website isn't getting updated. This patch
is meant as a speculative fix and a way to confirm that.
The semi-ring blocks were simply "inlined" by the sparse compiler but
without any filtering or patching. This revision improves the analysis
(rejecting blocks that use non-invariant computations from outside
their blocks, except for linalg.index) and also improves the codegen
by properly patching up index computations (previous version crashed).
With a regression test. Also updated the documentation now that the
example code is properly working.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D128000
Michał Górny