If we assume `llvm.amdgcn.s.barrier` is aligned we may remove it and
cause OpenMP GPU applications on the AMD GPU to be stuck or wrongly
synchronized.
Reported by Carlo Bertolli.
This is a follow up to 4f3f4d6722
("sanitizer_common: fix __sanitizer_get_module_and_offset_for_pc signature mismatch")
which fixes a similar problem for msan build.
I am getting the following error compiling a unit test for code that
uses sanitizer_common headers and googletest transitively includes
sanitizer interface headers:
In file included from third_party/gwp_sanitizers/singlestep_test.cpp:3:
In file included from sanitizer_common/sanitizer_common.h:19:
sanitizer_interface_internal.h:41:5: error: typedef redefinition with different types
('struct __sanitizer_sandbox_arguments' vs 'struct __sanitizer_sandbox_arguments')
} __sanitizer_sandbox_arguments;
common_interface_defs.h:39:3: note: previous definition is here
} __sanitizer_sandbox_arguments;
Reviewed By: melver
Differential Revision: https://reviews.llvm.org/D119546
This lets us avoid redundant implication work in the constructor of SCEVUnionPredicate which simplifies an upcoming change. If we're actually building a predicate via PSE, that goes through addPredicate which does include the implication check.
This ports the aarch64 combines for HADD and RHADD over to DAG combine,
so that they can be used in more architectures (notably MVE in a
followup patch). They are renamed to AVGFLOOR and AVGCEIL in the
process, to avoid confusion with instructions such as X86 hadd. The code
was also rewritten slightly to remove the AArch64 idiosyncrasies.
The general pattern for a AVGFLOORS is
%xe = sext i8 %x to i32
%ye = sext i8 %y to i32
%a = add i32 %xe, %ye
%r = lshr i32 %a, 1
%t = trunc i32 %r to i8
An AVGFLOORU is equivalent with zext. Because of the truncate
lshr==ashr, as the top bits are not demanded. An AVGCEIL also includes
an extra rounding, so includes an extra add of 1.
Differential Revision: https://reviews.llvm.org/D106237
```
always_inline foo() { }
bar () {
noinline foo();
}
```
We should prefer call site attribute over attribute on decl. This is fix for AlwaysInliner, similar fix is needed for normal Inliner (follow up).
Related to https://reviews.llvm.org/D119061
Reviewed By: aeubanks
Differential Revision: https://reviews.llvm.org/D119553
If a cast is needed when replacing uses with newly created values, the
cast must be inserted after the instruction that defines the new value.
Fixes: SWDEV-321215
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D119524
This is an alternative to D118667 that instead of fixing the store
to match phase 1, it tries to detect the mismatch with the expected
value at the end of the block. This inserts a vsetvli after the vse
to satisfy the requirement of the other basic block.
We still have serious design issues in the pass, that is going to
require some rethinking.
Differential Revision: https://reviews.llvm.org/D119518
We're missing a vsetvli before a vse after a redsum in this test.
This appears to be because the vmv.s.x has a VL of 1, but did not
trigger a vsetvli because it is a scalar move op and any non-zero
VL would work. So it looked at it the predecessors and decided it was
that they all had a non-zero vl. Then the redsum was visited, it
also took the VL from the predecessors since the vmv.s.x and the 4
was found compatible.
Finally we visit the vse and it looks at the BBLocalInfo and sees
that is compatible because it contains a VL of 1 from the vmv.s.x,
the first instruction in the block. BBLocalInfo was not updated
when the vredsum was visited because BBLocalInfo was valid and no
vsetvli was generated.
I think fundamentally the vmv.s.x optimization has the same first
phase and third phase not matching problem that D118667 was trying
to fix for stores.
Differential Revision: https://reviews.llvm.org/D119516
This patch refactors all the existing M68k arithmetic instructions
to use the new VarLenCodeEmitterGen infrastructure.
This patch is tested by the existing MC test cases.
Note that one of the codegen tests needed to be updated because the
ordering of two equivalent instructions were switched.
Differential Revision: https://reviews.llvm.org/D115234
Full write up:
https://gist.github.com/mshockwave/66e98d099256deefc062633909bb7b5b
The existing CodeEmitterGen infrastructure is unable to generate encoder
function for ISAs with variable-length instructions. This patch
introduces a new infrastructure to support variable-length instruction
encoding, including a new TableGen syntax for writing instruction
encoding directives and a new TableGen backend component,
VarLenCodeEmitterGen, built on top of CodeEmitterGen.
Differential Revision: https://reviews.llvm.org/D115128
`ranges_swap_ranges.h` includes `<type_traits>` but does not use anything from
it. So, remove the include.
Differential Revision: https://reviews.llvm.org/D119491
Use a subtarget feature instead of a command line argument to reduce
global state.
We want to enable flat scratch for graphics in some cases and this
doesn't work well with command line options.
Differential Revision: https://reviews.llvm.org/D119425
The module flag to indicate use of hostcall is insufficient to catch
all cases where hostcall might be in use by a kernel. This is now
replaced by a function attribute that gets propagated to top-level
kernel functions via their respective call-graph.
If the attribute "amdgpu-no-hostcall-ptr" is absent on a kernel, the
default behaviour is to emit kernel metadata indicating that the
kernel uses the hostcall buffer pointer passed as an implicit
argument.
The attribute may be placed explicitly by the user, or inferred by the
AMDGPU attributor by examining the call-graph. The attribute is
inferred only if the function is not being sanitized, and the
implictarg_ptr does not result in a load of any byte in the hostcall
pointer argument.
Reviewed By: jdoerfert, arsenm, kpyzhov
Differential Revision: https://reviews.llvm.org/D119216
Add a new llvm.fptrunc.round intrinsic to precisely control
the rounding mode when converting from f32 to f16.
Differential Revision: https://reviews.llvm.org/D110579
When generating nested CS profile with all calling contexts of a function duplicated into a base profile under `--generate-merged-base-profiles`, do not recount callee samples when computing profile summary. This fixes the profile summary mismatch between flat cs profile and nested cs profile, for both extbinary and text format.
Reviewed By: wenlei
Differential Revision: https://reviews.llvm.org/D119494
The XPLINK return `b 2(7)` has size 4 bytes, while the Linux return
`br 7` only has size 2 bytes. Thus a new alias is required to have correct
instruction byte count. It also fixes the conditional return code.
Reviewed By: uweigand
Differential Revision: https://reviews.llvm.org/D119437
Replace the *_EXTEND node with the raw operands, this will make it easier to use combineToExtendBoolVectorInReg for any boolvec extension combine.
Cleanup prep for Issue #53760
This avoids using an libc++ internal macro in our tests. This version
doesn't depend on the internal macro but redefines it.
Reviewed By: #libc, ldionne
Differential Revision: https://reviews.llvm.org/D119460
Dexter saves various files to a new results directory each time it is run
(including when it's run by lit tests) and there isn't a way to opt-out. This
patch reconfigures the behaviour to be opt-in by removing the default
`--results-directory` location. Now results are only saved if
`--results-directory` is specified.
Reviewed By: jmorse
Differential Revision: https://reviews.llvm.org/D119545
If we had some source value we could infer an address space from that
went through a ptrtoint/inttoptr pair, this would fail since bitcast
can't change the address space.
Fixes issue 53665.
... to use hyphens instead of underscores, making it consistent with
our other substitutions like %no-arg-lld and %lld-watchos.
Reviewed By: keith
Differential Revision: https://reviews.llvm.org/D119513