Handle the case when all inputs of phi are proven to be non zero.
Constants are checked in beginning of this method before check for depth of recursion,
so it is a partial case of non-constant phi.
Recursion depth is already handled by the function.
Reviewers: aqjune, nikic, efriedma
Reviewed By: nikic
Subscribers: dantrushin, hiraditya, jdoerfert, llvm-commits
Differential Revision: https://reviews.llvm.org/D88276
From preconditions it is known that either A dominates B or
B dominates A. If A does not dominate B, we do not really need
to check it. Assert should be enough. Should save some compile
time.
When removing exiting loop conditions, we only consider checks for
which we know the exact exit count. We could also eliminate checks for
which the condition is always true/false.
Differential Revision: https://reviews.llvm.org/D87344
Reviewed By: lebedev.ri, reames
Especially for templates we need to check at some point if the base
function matches the specialization we might call instead. Before this
lead to the replacement of `std::sqrt(int(2))` calls with one that
converts the argument to a `std::complex<int>`, clearly not the desired
behavior.
Reported as PR47655
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D88384
Summary:
========
Bugzilla Ticket No: Bug 46884 [https://bugs.llvm.org/show_bug.cgi?id=46884]
Flush op assembly syntax was ambiguous:
Consider the below test case:
flush operation is not having any arguments.
But the next statement token i.e "%2" is read as the argument for flush operation and then translator issues an error.
***************************************************************
$ cat -n flush.mlir
1 llvm.func @_QQmain(%arg0: !llvm.i32) {
2 %0 = llvm.mlir.constant(1 : i64) : !llvm.i64
3 %1 = llvm.alloca %0 x !llvm.i32 {in_type = i32, name = "a"} : (!llvm.i64) -> !llvm.ptr<i32>
4 omp.flush
5 %2 = llvm.load %1 : !llvm.ptr<i32>
6 llvm.return
7 }
$ mlir-translate -mlir-to-llvmir flush.mlir
flush.mlir:5:6: error: expected ':'
%2 = llvm.load %1 : !llvm.ptr<i32>
^
***************************************************************
Solution:
=========
Introduced begin ( `(` ) and end token ( `)` ) to determince the begin and end of variadic arguments.
The patch includes code changes and testcase modifications.
Reviewed By: Valentin Clement, Mehdi AMINI
Differential Revision: https://reviews.llvm.org/D88376
Commit 54d9f743c8 ("BPF: move AbstractMemberAccess and
PreserveDIType passes to EP_EarlyAsPossible") changed most
of CORE tests with opt run followed by llc and opt requires
the target triple specified in the IR.
There are few tests where little endian and big endian will
report different result and for little endian versions of
tests, "target triple = "bpf"" will produce wrong results
if the test executed in a big endian machine, e.g.
PowerPC big endian machine, since target "bpf" represents
host endian and will resolve to "bpfeb".
The builtbot reported such failures when build-and-run
on a PowerPC big endian machine.
To fix the issue, using "target triple = "bpfel"" instead.
Add a basic verifier for the data operation following the restriction from the standard.
Reviewed By: kiranchandramohan
Differential Revision: https://reviews.llvm.org/D88334
The OmpDialect is in practice optional during translation to LLVM IR: the code is tolerant
to have a "nullptr" when not present / needed.
The dependency still exists on the export to LLVMIR.
Reviewed By: ftynse
Differential Revision: https://reviews.llvm.org/D88351
When extending the subranges, the reaching-def may be an undefs. When
extending such kind of subrange, it will try to search for the reaching
def first. If the reaching def is an undef and we did not provide 'Undefs',
The findReachingDefs() will fail with message:
"Use of $noreg does not have a corresponding definition on every path:
LLVM ERROR: Use not jointly dominated by defs."
So we computeSubRangeUndefs() and pass the result to extendToIndices().
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D87744
Move abstractMemberAccess and PreserveDIType passes as early as
possible, right after clang code generation.
Currently, compiler may transform the above code
p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0);
p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2);
a = llvm.bpf.builtin.preserve_field_info(p2, EXIST);
if (a) {
p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0);
p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2);
bpf_probe_read(buf, buf_size, p2);
}
to
p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0);
p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2);
a = llvm.bpf.builtin.preserve_field_info(p2, EXIST);
if (a) {
bpf_probe_read(buf, buf_size, p2);
}
and eventually assembly code looks like
reloc_exist = 1;
reloc_member_offset = 10; //calculate member offset from base
p2 = base + reloc_member_offset;
if (reloc_exist) {
bpf_probe_read(bpf, buf_size, p2);
}
if during libbpf relocation resolution, reloc_exist is actually
resolved to 0 (not exist), reloc_member_offset relocation cannot
be resolved and will be patched with illegal instruction.
This will cause verifier failure.
This patch attempts to address this issue by do chaining
analysis and replace chains with special globals right
after clang code gen. This will remove the cse possibility
described in the above. The IR typically looks like
%6 = load @llvm.sk_buff:0:50$0:0:0:2:0
%7 = bitcast %struct.sk_buff* %2 to i8*
%8 = getelementptr i8, i8* %7, %6
for a particular address computation relocation.
But this transformation has another consequence, code sinking
may happen like below:
PHI = <possibly different @preserve_*_access_globals>
%7 = bitcast %struct.sk_buff* %2 to i8*
%8 = getelementptr i8, i8* %7, %6
For such cases, we will not able to generate relocations since
multiple relocations are merged into one.
This patch introduced a passthrough builtin
to prevent such optimization. Looks like inline assembly has more
impact for optimizaiton, e.g., inlining. Using passthrough has
less impact on optimizations.
A new IR pass is introduced at the beginning of target-dependent
IR optimization, which does:
- report fatal error if any reloc global in PHI nodes
- remove all bpf passthrough builtin functions
Changes for existing CORE tests:
- for clang tests, add "-Xclang -disable-llvm-passes" flags to
avoid builtin->reloc_global transformation so the test is still
able to check correctness for clang generated IR.
- for llvm CodeGen/BPF tests, add "opt -O2 <ir_file> | llvm-dis" command
before "llc" command since "opt" is needed to call newly-placed
builtin->reloc_global transformation. Add target triple in the IR
file since "opt" requires it.
- Since target triple is added in IR file, if a test may produce
different results for different endianness, two tests will be
created, one for bpfeb and another for bpfel, e.g., some tests
for relocation of lshift/rshift of bitfields.
- field-reloc-bitfield-1.ll has different relocations compared to
old codes. This is because for the structure in the test,
new code returns struct layout alignment 4 while old code
is 8. Align 8 is more precise and permits double load. With align 4,
the new mechanism uses 4-byte load, so generating different
relocations.
- test intrinsic-transforms.ll is removed. This is used to test
cse on intrinsics so we do not lose metadata. Now metadata is attached
to global and not instruction, it won't get lost with cse.
Differential Revision: https://reviews.llvm.org/D87153
Adding missing code that should have been part of "D85869: Utility to
vectorize loop nest using strategy."
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D88346
`atomic_compare_exchange_weak` is unused in Scudo, and its associated
test is actually wrong since the weak variant is allowed to fail
spuriously (thanks Roland).
This lead to flakes such as:
```
[ RUN ] ScudoAtomicTest.AtomicCompareExchangeTest
../../zircon/third_party/scudo/src/tests/atomic_test.cpp:98: Failure: Expected atomic_compare_exchange_weak(reinterpret_cast<T *>(&V), &OldVal, NewVal, memory_order_relaxed) is true.
Expected: true
Which is: 01
Actual : atomic_compare_exchange_weak(reinterpret_cast<T *>(&V), &OldVal, NewVal, memory_order_relaxed)
Which is: 00
../../zircon/third_party/scudo/src/tests/atomic_test.cpp💯 Failure: Expected atomic_compare_exchange_weak( reinterpret_cast<T *>(&V), &OldVal, NewVal, memory_order_relaxed) is false.
Expected: false
Which is: 00
Actual : atomic_compare_exchange_weak( reinterpret_cast<T *>(&V), &OldVal, NewVal, memory_order_relaxed)
Which is: 01
../../zircon/third_party/scudo/src/tests/atomic_test.cpp:101: Failure: Expected OldVal == NewVal.
Expected: NewVal
Which is: 24
Actual : OldVal
Which is: 42
[ FAILED ] ScudoAtomicTest.AtomicCompareExchangeTest (0 ms)
[----------] 2 tests from ScudoAtomicTest (1 ms total)
```
So I am removing this, if someone ever needs the weak variant, feel
free to add it back with a test that is not as terrible. This test was
initially ported from sanitizer_common, but their weak version calls
the strong version, so it works for them.
Differential Revision: https://reviews.llvm.org/D88443
Also have CMake fails if the user provides a TENSORFLOW_C_LIB_PATH but
we can't find TensorFlow at this path.
At the moment the CMake script tries to figure if TensorFlow is
available on the system and enables support for it. This is in general
not desirable to customize build features this way and instead it is
preferable to let the user opt-in explicitly into the features they want
to enable. This is in line with other optional external dependencies
like Z3.
There are a few reasons to this but amongst others:
- reproducibility: making features "magically" enabled based on whether
we find a package on the system or not makes it harder to handle bug
reports from users.
- user control: they can't have TensorFlow on the system and build LLVM
without TensorFlow right now. They also would suddenly distribute LLVM
with a different set of features unknowingly just because their build
machine environment would change subtly.
Right now this is motivated by a user reporting build failures on their system:
.../mesa-git/llvm-git/src/llvm-project/llvm/lib/Analysis/TFUtils.cpp:23:10: fatal error: tensorflow/c/c_api.h: No such file or directory
23 | #include "tensorflow/c/c_api.h"
| ^~~~~~
It looks like we detected TensorFlow at configure time but couldn't set all the paths correctly.
Differential Revision: https://reviews.llvm.org/D88371
For a call site which had both constant deopt operands and nonnull arguments, we were missing the opportunity to recognize the later by bailing early.
This is somewhat of a speculative fix. Months ago, I'd had a private report of performance and compile time regressions from the deopt operand folding. I never received a test case. However, the only possibility I see was that after that change CVP missed the nonnull fold, and we end up with a pass ordering/missed simplification issue. So, since it's a real issue, fix it and hope.
- use select-ops to make the lowering simpler
- change style of FileCheck variables names to be consistent
- change some variable names in the code to be more explicit
Differential Revision: https://reviews.llvm.org/D88258
This flag is the default in libtool on Darwin, and it's not supported
by llvm-libtool-darwin causing a build failure.
Differential Revision: https://reviews.llvm.org/D88449
We're technically not allowed by the Standard to call ::operator new in
constexpr functions like __libcpp_allocate. Clang doesn't seem to complain
about it, but GCC does.
We can do several optimizations for PDEP using computeKnownBits and SimplifyDemandedBits
-If the MSBs of the output aren't demanded, those MSBs of the mask input aren't demanded either. We need to keep the most significant demanded bit of the mask and any mask bits before it.
-The number of possible ones in the mask determines how many bits of the lsbs of the other operand are demanded. Any bits of the mask we don't demand by the previous rule should not be counted.
-The result will have zeros in any position that the mask is zero.
-Since non-mask input bits can only be output in the original position or a higher bit position, the result will have at least as many trailing zeroes as the non-mask input.
Differential Revision: https://reviews.llvm.org/D87883
This is a follow on to D85329 which disabled some llvm tools in the
runtimes build due to XCOFF64 limitations. This change disables them
in other external project builds as well, when no list of tools is
specified in the arguments.
Reviewed By: hubert.reinterpretcast, stevewan
Differential Revision: https://reviews.llvm.org/D88310
This isn't a real with the codegen, it's a previously known bug in clang which
causes non-deterministic failures due to garbage bits in undef registers being
used in saturating instructions.
I'm disabling the result checking for the test until this issue is resolved.
This reverts commit 6c8168324b.
Recently, restrictions on vector reductions were made more relaxed by
accepting any width signless integer and floating-point. This CL relaxes
the restriction even more by including unsigned and signed integers.
Reviewed By: bkramer
Differential Revision: https://reviews.llvm.org/D88442
Instead of expliciting emitting a setc in the inline asm instructions,
we can use flag output. This allows the backend to use the flag
directly if it is needed by a branch. Previously we needed a test
instruction to convert the register back to a flag.
If the flag can't be used directly, the backend will emit a setcc.
Differential Revision: https://reviews.llvm.org/D87888
Serguei Katkov