The logic of vector on boolean was missed. This patch adds the logic and test on
it.
Reviewed By: mravishankar
Differential Revision: https://reviews.llvm.org/D91403
Adapt the declarations of `svpattern` and `svprfop` to the most recent
one defined in section "5. Enum declarations" of the SVE ACLE
specifications [1].
The signature of the intrinsics using these enums have been changed
accordingly.
A test has been added to make sure that `svpattern` and `svprfop` are
not typedefs.
[1] https://developer.arm.com/documentation/100987/latest, version
00bet6
Reviewed By: joechrisellis
Differential Revision: https://reviews.llvm.org/D91333
Original commit message: "
Move the test compiler setup in a common place. NFCI
This patch reduces the copy paste in the unittest/CodeGen folder by moving the
common compiler setup phase in a header file.
Differential revision: https://reviews.llvm.org/D91061
"
This patch includes a fix for the memory leaks pointed out by @vitalybuka
This patch fixes the function isWideningInstruction for scalable vectors.
Now the cost model can check the widening pattern for SVE.
Differential Revision: https://reviews.llvm.org/D91260
In `GetGlobalSizeFromDescriptor` we use `dladdr` to get info on the the
current address. `dladdr` returns 0 if it failed.
During testing on Linux this returned 0 to indicate failure, and
populated the `info` structure with a NULL pointer which was
dereferenced later.
This patch checks for `dladdr` returning 0, and in that case returns 0
from `GetGlobalSizeFromDescriptor` to indicate failure of identifying
the address.
This occurs when `GetModuleNameAndOffsetForPC` succeeds for some address
not in a dynamically loaded library. One example is when the found
"module" is '[stack]' having come from parsing /proc/self/maps.
Differential Revision: https://reviews.llvm.org/D91344
Create a helper GetOffsetRegSetData() method to get pointer
to the regset data accounting for the necessary offset. Establish
the offsets in the constructor and store them in the structure. This
avoids having to add new Get*Offset() methods and combines some common
code.
Differential Revision: https://reviews.llvm.org/D91411
Eliminate the remaining swith-case code for register getters,
and migrate YMM registers to regset-oriented model. Since these
registers are recombined from XMM and YMM_Hi128 XSAVE blocks, while LLDB
gdb-server protocol transmits YMM registers whole, the offset-based
model will not work here. Nevertheless, some improvement was possible.
Replace generic 'XSaveRegSet' along with sub-sets for XSAVE components
with 'YMMRegSet' (and more regsets in the future as further components
are implemented). Create a helper GetYMMSplitReg() method that obtains
pointers to the appropriate XMM and YMM_Hi128 blocks to reduce code
duplication.
Differential Revision: https://reviews.llvm.org/D91293
Use offset-based method to access x86 debug registers. This also
involves adding a test for the correctness of these offsets, and making
GetDR() method of NativeRegisterContextWatchpoint_x86 public to avoid
duplicate code.
Differential Revision: https://reviews.llvm.org/D91268
Use offset-based method to access base x87 FPU registers, using offsets
relative to the position of 'struct FPR', as determined by the location
of first register in it (fctrl). Change m_fpr to use a fixed-size array
matching FXSAVE size (512 bytes). Add unit tests for verifying
RegisterInfo offsets and sizes against the FXSAVE layout.
Differential Revision: https://reviews.llvm.org/D91248
Read and write registers from m_gpr using offsets from RegisterInfo
rather than explicit switch-case. This eliminates a lot of redundant
code, and avoids mistakes such as type mismatches seen recently (wrt
segment registers). The same logic will be extended to other register
sets in the future.
Make m_gpr an uint8_t std::array to ease accesses. Ideally, we could
avoid including <machine/reg.h> entirely in the future and instead
get the correct GPR size from Utility/RegisterContextFreeBSD_* somehow.
While at it, modify register set logic to use an explicit enum with
llvm::Optional<>, making the code cleaner and at the same time enabling
compiler warnings for unhandled sets.
Since now we're fully relying on 'struct GPR' defined
in Utility/RegisterContextFreeBSD_* being entirely in sync with
the system structure, add unit tests to verify the field offsets
and sizes.
Differential Revision: https://reviews.llvm.org/D91216
scf.parallel is currently not a good fit for tiling on tensors.
Instead provide a path to parallelism directly through scf.for.
For now, this transformation ignores the distribution scheme and always does a block-cyclic mapping (where block is the tile size).
Differential revision: https://reviews.llvm.org/D90475
This patch updates Clang's IRGen to add !annotation nodes with an
"auto-init" annotation to all stores for auto-initialization.
As discussed in 'RFC: Combining Annotation Metadata and Remarks'
(http://lists.llvm.org/pipermail/llvm-dev/2020-November/146393.html)
this allows using optimization remarks to track down where auto-init
code was inserted (and not removed by optimizations).
There are a few cases in the tests where !annotation gets dropped by
optimizations. Those optimizations will be updated in subsequent
patches.
This patch is based on a patch by Francis Visoiu Mistrih.
Reviewed By: thegameg, paquette
Differential Revision: https://reviews.llvm.org/D91417
Widen the IV to the widest available and legal integer type, which makes this
transformations always safe so that we can skip overflow checks.
Motivation is to let this pass trigger on 64-bit targets too, and this is the
last patch in a serie to achieve this: D90402 moves pass LoopFlatten to just
before IndVarSimplify so that IVs are not already widened, D90421 factors out
widening from IndVarSimplify into Utils/SimplifyIndVar so that we can also use
it in LoopFlatten.
Differential Revision: https://reviews.llvm.org/D90640
This patch adds the SchedMachineModel for Cortex-M7. It
also adds test cases for the scheduling information.
Details of the pipeline and descriptions are in comments
in file ARMScheduleM7.td included in this patch.
Differential Revision: https://reviews.llvm.org/D91355
This introduces the new `ARCHER_OPTIONS` flag `ignore_serial=0|1` to disable
analysis and logging of memory accesses in the sequential part of the OpenMP
application.
In the sequential part of an OpenMP program no data race is possible, unless
there is non-OpenMP concurrency (such as pthreads, MPI, ...). For the latter
reason, this is not active by default.
Besides reducing the runtime overhead for the sequential part of the program,
this reduces the memory overhead for sequential initialization. In combination
with `flush_shadow=1` this can allow analysis of applications, which run close
to the limit of available memory, but only access smaller parts of shared
memory during each OpenMP parallel region.
A problem for this approach is that Archer only gets active, when the OpenMP
runtime gets initialized, which might be after serial initialization of the
application. In such case, it helps to call for example `omp_get_max_threads()`
at the beginning of main.
Differential Revision: https://reviews.llvm.org/D90473
Similar to the X86 and AMDGPU targets, this uses a macro to cut down on
repetitive and error-prone code when converting RISCVISD node names to
strings in getTargetNodeName.
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D91414
This enables automatically parsing and generating CC1 arguments for options where two flags control the same field, e.g. -fexperimental-new-pass-manager and -fno-experimental new pass manager.
Reviewed By: Bigcheese, dexonsmith
Original patch by Daniel Grumberg.
Differential Revision: https://reviews.llvm.org/D83071
Patch by Elena Kovanova. Thanks Elena!
Problem:
LLVM already has a feature to profile the JIT-compiled code with VTune. This is
done using Intel JIT Profiling API (https://github.com/intel/ittapi). Function
information is captured by VTune as soon as the function is JIT-compiled. We
tried to use the same approach to report the function information generated by
the MCJIT engine – read parsing the debug information for in-memory ELF module
and report it using JIT API. As the results, we figured out that it did not work
properly for the following cases: inline functions, the functions located in
multiple source files, the functions having several bodies (address ranges).
Solution:
To overcome limitations described above, we have introduced new APIs as a part
of Intel ITT APIs to report the entire in-memory ELF module to be further
processed as regular ELF binaries with debug information.
This patch
1. Switches LLVM to open source version of Intel ITT/JIT APIs
(https://github.com/intel/ittapi) to keep it always up to date.
2. Adds support of profiling the code generated by MCJIT engine using Intel
VTune profiler
Another separate patch will get rid of obsolete Intel ITT APIs stuff, having
LLVM already switched to https://github.com/intel/ittapi.
Differential Revision: https://reviews.llvm.org/D86435
The VE backend represents vector instructions with an explicit 'i32'
vector length operand. In the VE ISA, the vector length is always read
from the VL hardware register. The LVLGen pass inserts 'lvl'
instructions as necessary to set VL to the right value before each
vector instruction.
Reviewed By: kaz7
Differential Revision: https://reviews.llvm.org/D91416
This patch teaches the jump threading pass to call BPI->eraseBlock
when it folds a conditional branch.
Without this patch, BranchProbabilityInfo could end up with stale edge
probabilities for the basic block containing the conditional branch --
one edge probability with less than 1.0 and the other for a removed
edge.
This patch is one of the steps before we can safely re-apply D91017.
Differential Revision: https://reviews.llvm.org/D91511
We unconditionally marked i64 as Custom, but did not install a
handler in ReplaceNodeResults when i64 isn't legal type. This
leads to ReplaceNodeResults asserting.
We have two options to fix this. Only mark i64 as Custom on
64-bit targets and let it expand to two i32 bitreverses which
each need a VPPERM. Or the other option is to add the Custom
handling to ReplaceNodeResults. This is what I went with.
In the last change to IRCE the BPI is ignored if BFI is present, however
BFI and BPI have a different thresholds. Specifically BPI approach checks only
latch exit probability so it is expected if the loop has only one exit block (latch)
the behavior with BFI and BPI should be the same,
BPI approach by default uses threshold 10, so it considers the loop with estimated
number of iterations less then 10 should not be considered for IRCE optimization.
BFI approach uses the default value 3 and this is inconsistent.
The CL modifies the code to use the same threshold for both approaches..
The test is updated due to it has two side-exits (except latch) and each of them has a
probability 1/16, so BFI estimates the number of runtime iteration is about to 7
(1/16 + 1/16 + some for latch) and test fails.
Reviewers: mkazantsev, ebrevnov
Reviewed By: mkazantsev
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D91230
I had manually removed unused prefixes from CodeGen/X86 directory for more than 100 tests.
I checked the change history for each of them at the beginning, and then I mainly focused on the format since I found all of the unused prefixes were result from either insensible copy or residuum after functional update.
I think it's OK to remove the remaining X86 tests by script now. I wrote a rough script which works for me in most tests. I put it in llvm/utils temporarily for review and hope it may help other components owners.
The tests in this patch are all generated by the tool and checked by update tool for the autogenerated tests. I skimmed them and checked about 30 tests and didn't find any unexpected changes.
Reviewed By: mtrofin, MaskRay
Differential Revision: https://reviews.llvm.org/D91496
parameters.
It appears that LLVM isn't able to generate a DW_AT_const_value for a
constant of class type, but if it could, we'd match GCC's debug info in
this case, and in the interim we no longer crash.
Hanhan Wang