| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Fixed setting predicates for compressed instructions.
Some instructions were being generated with C extension
enabled only, without proper checks for the other
required extensions like F, D and 32 and 64-bit target checks.
Affected instructions:
C_FLD, C_FLW, C_LD, C_FSD, C_FSW, C_SD,
C_JAL, C_ADDIW, C_SUBW, C_ADDW,
C_FLDSP, C_FLWSP, C_LDSP, C_FSDSP, C_FSWSP, C_SDSP
Reviewers: asb, shiva0217
Reviewed By: asb
Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, sabuasal, niosHD, llvm-commits
Differential Revision: https://reviews.llvm.org/D42132
llvm-svn: 322876
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
There's some abstraction overhead in the underlying
mechanisms that were being used, and it was leading to an
abundance of small but not-free copies being made. This
showed up on a profile. Eliminating this and going back to
a low-level byte-based implementation speeds up lld with
/DEBUG between 10 and 15%.
Differential Revision: https://reviews.llvm.org/D42148
llvm-svn: 322871
|
| |
|
|
|
|
|
|
| |
Committed r322867 too soon.
Differential Revision: https://reviews.llvm.org/D42239
llvm-svn: 322868
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
r322086 removed the trailing information describing reg classes for each
register.
This patch adds printing reg classes next to every register when
individual operands/instructions/basic blocks are printed. In the case
of dumping MIR or printing a full function, by default don't print it.
Differential Revision: https://reviews.llvm.org/D42239
llvm-svn: 322867
|
| |
|
|
| |
llvm-svn: 322855
|
| |
|
|
|
|
|
| |
* Handle more cases where the MI is not attached yet
* Add similar asserts like in MIRPrinter::print
llvm-svn: 322848
|
| |
|
|
|
|
| |
Found by msan.
llvm-svn: 322847
|
| |
|
|
| |
llvm-svn: 322843
|
| |
|
|
| |
llvm-svn: 322839
|
| |
|
|
|
|
|
|
|
| |
Follow-up to r322120 which can cause assertions for AArch64 because
v1f64 and v1i64 are legal types.
Differential Revision: https://reviews.llvm.org/D42097
llvm-svn: 322823
|
| |
|
|
|
|
|
|
| |
consistency with loads.
Previously we used 64 for vXi64 stores and 32 for everything else. This change uses 64 for everything just like do for loads.
llvm-svn: 322820
|
| |
|
|
|
|
|
|
| |
integer vector loads.
These patterns were just looking for a vXi64 bitcasted to vXi32, but there is no advantage to using vmovdqa32 over vmovdqa64.
llvm-svn: 322819
|
| |
|
|
|
|
|
|
|
| |
LTO sets dso_local as an optimization, so don't clear it.
This avoid clearing it from undefined hidden symbols, which would then
fail the verifier.
llvm-svn: 322814
|
| |
|
|
|
|
|
|
|
|
| |
elemnt is a bitcast from a vector type into a concat_vector
For example, a build_vector of i64 bitcasted from v2i32 can be turned into a concat_vectors of the v2i32 vectors with a bitcast to a vXi64 type
Differential Revision: https://reviews.llvm.org/D42090
llvm-svn: 322811
|
| |
|
|
|
|
|
|
|
|
|
|
| |
This is similar to r322317, but for visibility. It is not as neat
because we have to special case extern_weak.
The idea is the same as the previous change, make the transition to
explicit dso_local easier for the frontends. With this they only have
to add dso_local to symbols where we need some external information to
decide if it is dso_local (like it being part of an ELF executable).
llvm-svn: 322806
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Right now, it is not possible to run MachineCSE in the middle of the
GlobalISel pipeline. Being able to run generic optimizations between the
core passes of GlobalISel was one of the goals of the new ISel framework.
This is the first attempt to do it.
The problem is that MachineCSE pass assumes all register operands have a
register class, which, in GlobalISel context, won't be true until after the
InstructionSelect pass. The reason for this behaviour is that before
replacing one virtual register with another, MachineCSE pass (and most of
the other optimization machine passes) must check if the virtual registers'
constraints have a (sufficiently large) intersection, and constrain the
resulting register appropriately if such intersection exists.
GlobalISel extends the representation of such constraints from just a
register class to a triple (low-level type, register bank, register
class).
This commit adds MachineRegisterInfo::constrainRegAttrs method that extends
MachineRegisterInfo::constrainRegClass to such a triple.
The idea is that going forward we should use:
- RegisterBankInfo::constrainGenericRegister within GlobalISel's
InstructionSelect pass
- MachineRegisterInfo::constrainRegClass within SelectionDAG ISel
- MachineRegisterInfo::constrainRegAttrs everywhere else regardless
the target and instruction selector it uses.
Patch by Roman Tereshin. Thanks!
llvm-svn: 322805
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Remove the tight coupling between llvm/CodeGenRuntimeLibcalls.def and
the table of supported singatures for wasm. This will allow adding new libcalls
without changing wasm's signature table.
Also, some cleanup:
Use ManagedStatics instead of const tables to avoid memory/binary bloat.
Use a StringMap instead of a linear search for name lookup.
Differential Revision: https://reviews.llvm.org/D35592
llvm-svn: 322802
|
| |
|
|
|
|
| |
Do not run GlobalISel if `-fast-isel=0 -global-isel=false`.
llvm-svn: 322800
|
| |
|
|
|
|
|
|
|
|
| |
Before, it wasn't possible to get backtraces inside outlined functions. This
commit adds DISubprograms to the IR functions created by the outliner which
makes this possible. Also attached a test that ensures that the produced
debug information is correct. This is useful to users that want to debug
outlined code.
llvm-svn: 322789
|
| |
|
|
|
|
|
|
|
|
|
| |
Every known PE COFF target emits /EXPORT: linker flags into a .drective
section. The AsmPrinter should handle this.
While we're at it, use global_values() and emit each export flag with
its own .ascii directive. This should make the .s file output more
readable.
llvm-svn: 322788
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
-hwasan-mapping-offset defines the non-zero shadow base address.
-hwasan-kernel disables calls to __hwasan_init in module constructors.
Unlike ASan, -hwasan-kernel does not force callback instrumentation.
This is controlled separately with -hwasan-instrument-with-calls.
Reviewers: kcc
Subscribers: srhines, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D42141
llvm-svn: 322785
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
This patch adds a new target option in order to control GlobalISel.
This will allow the users to enable/disable GlobalISel prior to the
backend by calling `TargetMachine::setGlobalISel(bool Enable)`.
No test case as there is already a test to check GlobalISel
command line options.
See: CodeGen/AArch64/GlobalISel/gisel-commandline-option.ll.
Reviewers: qcolombet, aemerson, ab, dsanders
Reviewed By: qcolombet
Subscribers: rovka, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D42137
llvm-svn: 322773
|
| |
|
|
|
|
| |
compiler_rt doesn't provide them (yet), but libgcc does. PR34076.
llvm-svn: 322772
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
The class wraps a uint64_t and an enum to represent the type of profile
count (real and synthetic) with some helper methods.
Reviewers: davidxl
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41883
llvm-svn: 322771
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
The code wasn't zero-extending correctly, so the comparison could
spuriously fail.
Adds some AArch64 tests to cover this case.
Inspired by D41791.
Differential Revision: https://reviews.llvm.org/D41798
llvm-svn: 322767
|
| |
|
|
|
|
| |
Fix confusing typo in comment.
llvm-svn: 322765
|
| |
|
|
|
|
| |
Failing build bots. Revert the commit now.
llvm-svn: 322748
|
| |
|
|
| |
llvm-svn: 322747
|
| |
|
|
|
|
| |
https://reviews.llvm.org/D42149
llvm-svn: 322743
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Get rid of DEBUG_FUNCTION_NAME symbols. When we actually debug
data, maybe we'll want somewhere to put it... but having a symbol
that just stores the name of another symbol seems odd.
It means you have multiple Symbols with the same name, one
containing the actual function and another containing the name!
Store the names in a vector on the WasmObjectFile when reading
them in. Also stash them on the WasmFunctions themselves.
The names are //not// "symbol names" or aliases or anything,
they're just the name that a debugger should show against the
function body itself. NB. The WasmObjectFile stores them so that
they can be exported in the YAML losslessly, and hence the tests
can be precise.
Enforce that the CODE section has been read in before reading
the "names" section. Requires minor adjustment to some tests.
Patch by Nicholas Wilson!
Differential Revision: https://reviews.llvm.org/D42075
llvm-svn: 322741
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Trying to link
__attribute__((weak, visibility("hidden"))) extern int foo;
int *main(void) {
return &foo;
}
on OS X fails with
ld: 32-bit RIP relative reference out of range (-4294971318 max is +/-2GB): from _main (0x100000FAB) to _foo@0x00001000 (0x00000000) in '_main' from test.o for architecture x86_64
The problem being that 0 cannot be computed as a fixed difference from
%rip. Exactly the same issue exists on ELF and we can use the same
solution.
llvm-svn: 322739
|
| |
|
|
|
|
|
|
| |
This extends my previous patches to also optimize overflow-checked multiplies during SelectionDAG.
Differential revision: https://reviews.llvm.org/D40922
llvm-svn: 322738
|
| |
|
|
|
|
|
|
| |
The ARM backend contains code that tries to optimize compares by replacing them with an existing instruction that sets the flags the same way. This allows it to replace a "cmp" with a "adds", generalizing the code that replaces "cmp" with "sub". It also heuristically disables sinking of instructions that could potentially be used to replace compares (currently only if they're next to each other).
Differential revision: https://reviews.llvm.org/D38378
llvm-svn: 322737
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
list/set
Summary:
Discovered while working on a patch to move alignment in
@llvm.memcpy/move/set from an arg into parameter attributes.
The current implementations of AttributeSet::removeAttribute() and
AttributeList::removeAttribute crash when attempting to remove the
alignment attribute. Currently, these implementations add the
to-be-removed attributes to an AttrBuilder and then remove
the builder from the list/set. Alignment is special in that it
must be added to a builder with an integer value for the alignment;
attempts to add alignment to a builder without a value is an error.
This change fixes the removeAttribute implementations for AttributeSet and
AttributeList to make them able to remove the alignment, and other similar,
attributes.
Reviewers: rnk, chandlerc, pete, javed.absar, reames
Reviewed By: rnk
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41951
llvm-svn: 322735
|
| |
|
|
|
|
| |
Most are just replaced with instrs lists, but a few regexps have been further generalized to match more instructions with a single pattern.
llvm-svn: 322734
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
elements and use a 64-bit broadcast
If we are splatting pairs of 32-bit elements, we can use a 64-bit broadcast to get the job done.
We could probably could probably do this with other sizes too, for example four 16-bit elements. Or we could broadcast pairs of 16-bit elements using a 32-bit element broadcast. But I've left that as a future improvement.
I've also restricted this to AVX2 only because we can only broadcast loads under AVX.
Differential Revision: https://reviews.llvm.org/D42086
llvm-svn: 322730
|
| |
|
|
|
|
|
|
|
|
|
|
| |
introduce bitcasts to i64 in 32-bit mode
We legalize selects of masks with scalar conditions using a bitcast to an integer type. But if we are in 32-bit mode we can't convert v64i1 to i64. So instead split the v64i1 to v32i1 and concat it back together. Each half will then be legalized by bitcasting to i32 which is fine.
The test case is a little indirect. If we have the v64i1 select in IR it will get legalized by legalize vector ops which has a run of type legalization after it. That type legalization run is able to fix this i64 bitcast. So in order to avoid that we need a build_vector of a splat which legalize vector ops will ignore. Legalize DAG will then turn that into a select via LowerBUILD_VECTORvXi1. And the select will get legalized. In this case there is no type legalizer run to cleanup the bitcast.
This fixes pr35972.
llvm-svn: 322724
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
candidates with coldcc attribute.
This patch adds support for the coldcc calling convention for Power.
This changes the set of non-volatile registers. It includes a pass to stress
test the implementation by marking all static directly called functions with
the coldcc attribute through the option -enable-coldcc-stress-test. It also
includes an option, -ppc-enable-coldcc, to add the coldcc attribute to
functions which are cold at all call sites based on BlockFrequencyInfo when
the containing function does not call any non cold functions.
Differential Revision: https://reviews.llvm.org/D38413
llvm-svn: 322721
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary: Added VS and VC, required for disassembling.
Reviewers: petecoup
Reviewed By: petecoup
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D42172
llvm-svn: 322718
|
| |
|
|
|
|
|
|
| |
BRCTH is capable of a long branch which needs to be recognized during branch
relaxation. This is done by checking for ExtraRelaxSize == 0.
Review: Ulrich Weigand
llvm-svn: 322688
|
| |
|
|
|
|
|
|
| |
This assert typically happens if an unstructured CFG is passed
to the pass. This can happen if the pass is run independently
without the structurizer.
llvm-svn: 322685
|
| |
|
|
| |
llvm-svn: 322667
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Loading a vector of 4 half-precision FP sometimes results in an LD1
of 2 single-precision FP + a reversal. This results in an incorrect
byte swap due to the conversion from little endian to big endian.
In order to generate the correct byte swap, it is easier to
generate the correct LD1 of 4 half-precision FP, thus avoiding the
subsequent reversal.
Reviewers: craig.topper, jmolloy, olista01
Reviewed By: olista01
Subscribers: efriedma, samparker, SjoerdMeijer, rogfer01, aemerson, rengolin, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D41863
llvm-svn: 322663
|
| |
|
|
|
|
|
|
|
| |
I was comparing the demanded-bits implementations between InstCombine
and TargetLowering as part of investigating questions in D42088 and
noticed that this was wrong in IR. We were losing all of the prior
known bits when we got back to the 'zext'.
llvm-svn: 322662
|
| |
|
|
|
|
|
|
|
|
| |
When the compressed instruction set is enabled, the 16-bit c.nop can be
generated if necessary.
Differential Revision: https://reviews.llvm.org/D41221
Patch by Shiva Chen.
llvm-svn: 322658
|
| |
|
|
| |
llvm-svn: 322657
|
| |
|
|
|
|
|
|
|
|
|
|
| |
added llvm.amdgcn.atomic.{add|min|max}.f32 intrinsics
to allow generate ds_{add|min|max}[_rtn]_f32 instructions
needed for OpenCL float atomics in LDS
Reviewed by: arsenm
Differential Revision: https://reviews.llvm.org/D37985
llvm-svn: 322656
|
| |
|
|
|
|
|
|
|
| |
See bug 35771: https://bugs.llvm.org/show_bug.cgi?id=35771
Differential Revision: https://reviews.llvm.org/D42058
Reviewers: vpykhtin, artem.tamazov, arsenm
llvm-svn: 322655
|
| |
|
|
|
|
|
|
|
|
|
| |
Mark G_FPEXT and G_FPTRUNC as legal or libcall, depending on hardware
support, but only for conversions between float and double.
Also add the necessary boilerplate so that the LegalizerHelper can
introduce the required libcalls. This also works only for float and
double, but isn't too difficult to extend when the need arises.
llvm-svn: 322651
|
| |
|
|
|
|
| |
Differential Revision: https://reviews.llvm.org/D41565
llvm-svn: 322650
|