We currently have problems with the way that low overhead loops are
specified, with LR being spilled between the t2LoopDec and the t2LoopEnd
forcing the entire loop to be reverted late in the backend. As they will
eventually become a single instruction, this patch introduces a
t2LoopEndDec which is the combination of the two, combined before
registry allocation to make sure this does not fail.
Unfortunately this instruction is a terminator that produces a value
(and also branches - it only produces the value around the branching
edge). So this needs some adjustment to phi elimination and the register
allocator to make sure that we do not spill this LR def around the loop
(needing to put a spill after the terminator). We treat the loop very
carefully, making sure that there is nothing else like calls that would
break it's ability to use LR. For that, this adds a
isUnspillableTerminator to opt in the new behaviour.
There is a chance that this could cause problems, and so I have added an
escape option incase. But I have not seen any problems in the testing
that I've tried, and not reverting Low overhead loops is important for
our performance. If this does work then we can hopefully do the same for
t2WhileLoopStart and t2DoLoopStart instructions.
This patch also contains the code needed to convert or revert the
t2LoopEndDec in the backend (which just needs a subs; bne) and the code
pre-ra to create them.
Differential Revision: https://reviews.llvm.org/D91358
When llvm-rc loads an external file, it looks for it relative to
a number of include directories and the current working directory.
If the path is considered absolute, llvm-rc tries to open the
filename as such, and doesn't try to open it relative to other
paths.
On Windows, a path name like "\dir\file" isn't considered absolute
as it lacks the drive name, but by appending it on top of the search
dirs, it's not found.
LLVM's sys::path::append just appends such a path (same with a properly
absolute posix path) after the paths it's supposed to be relative to.
This fix doesn't handle the case if the resource script and the
external file are on a different drive than the current working
directory; to fix that, we'd have to make LLVM's sys::path::append
handle appending fully absolute and partially absolute paths (ones
lacking a drive prefix but containing a root directory), or switch
to C++17's std::filesystem.
Differential Revision: https://reviews.llvm.org/D92558
Current interface of AddressMap assumes that relocations exist.
That is correct for not-linked object file but is not correct
for linked executable. This patch changes interface in such way
that AddressMap could be used not only with not-linked object files:
hasValidRelocationAt()
replaced with:
hasLiveMemoryLocation()
hasLiveAddressRange()
Differential Revision: https://reviews.llvm.org/D87723
Both ds_read_b128 and ds_read2_b64 are valid for 128bit 16-byte aligned
loads but the one that will be selected is determined either by the order in
tablegen or by the AddedComplexity attribute. Currently ds_read_b128 has
priority.
While ds_read2_b64 has lower alignment requirements, we cannot always
restrict ds_read_b128 to 16-byte alignment because of unaligned-access-mode
option. This was causing ds_read_b128 to be selected for 8-byte aligned
loads regardles of chosen access mode.
To resolve this we use two patterns for selecting ds_read_b128. One
requires alignment of 16-byte and the other requires
unaligned-access-mode option.
Same goes for ds_write2_b64 and ds_write_b128.
Differential Revision: https://reviews.llvm.org/D92767
The phi created in a low overhead loop gets created with a default
register class it seems. There are then copied inserted between the low
overhead loop pseudo instructions (which produce/consume GPRlr
instructions) and the phi holding the induction. This patch removes
those as a step towards attempting to make t2LoopDec and t2LoopEnd a
single instruction, and appears useful in it's own right as shown in the
tests.
Differential Revision: https://reviews.llvm.org/D91267
This patch implements amx programming model that discussed in llvm-dev
(http://lists.llvm.org/pipermail/llvm-dev/2020-August/144302.html).
Thank Hal for the good suggestion in the RA. The fast RA is not in the patch yet.
This patch implemeted 7 components.
1. The c interface to end user.
2. The AMX intrinsics in LLVM IR.
3. Transform load/store <256 x i32> to AMX intrinsics or split the
type into two <128 x i32>.
4. The Lowering from AMX intrinsics to AMX pseudo instruction.
5. Insert psuedo ldtilecfg and build the def-use between ldtilecfg to amx
intruction.
6. The register allocation for tile register.
7. Morph AMX pseudo instruction to AMX real instruction.
Change-Id: I935e1080916ffcb72af54c2c83faa8b2e97d5cb0
Differential Revision: https://reviews.llvm.org/D87981
llvm::Linker::linkModules() is a static member, so there is no need
to pass reference to llvm::Linker instance to loadArFile() function.
Reviewed By: tra
Differential Revision: https://reviews.llvm.org/D92918
There is an explicit option for the lexer to support this, but we crash
when `-preserve-comments` is enabled because it checks for
`getTok().getString().empty()` to detect the case. This doesn't
work currently because the lexer reports this case as a string of length
1, containing a null byte.
Change the lexer to instead report this case via an empty string, as the
null terminator isn't logically a part of the textual input, and the
check for `.empty()` seems natural and obvious in the calling code.
Reviewed By: niravd
Differential Revision: https://reviews.llvm.org/D92681
Rather than creating a series of associated calls and ensuring that
everything is lined up, use a table driven approach that ensures that
they two always stay in sync.
Avoids spurious newlines showing up in the output when emitting assembly
via MC.
Reviewed By: MaskRay, arsenm
Differential Revision: https://reviews.llvm.org/D92690
Pretty sure we meant to be checking signed 32 immediates here
rather than unsigned 32 bit. I suspect I messed this up because
in MathExtras.h we have isIntN and isUIntN so isIntN differs in
signedness depending on whether you're using APInt or plain integers.
This fixes a case where we didn't fold a constant created
by shrinkAndImmediate. Since shrinkAndImmediate doesn't topologically
sort constants it creates, we can fail to convert the Constant
to a TargetConstant. This leads to very strange behavior later.
Fixes PR48458.
-DENABLE_EXPERIMENTAL_NEW_PASS_MANAGER=on configured LLD and LLVMgold.so
will use the new pass manager by default. Add an option to
use the legacy pass manager. This will also be used by the Clang driver
when -fno-new-pass-manager (D92915) / -fno-experimental-new-pass-manager is set.
Reviewed By: aeubanks, tejohnson
Differential Revision: https://reviews.llvm.org/D92916
Revert part of https://reviews.llvm.org/D92084 to make it simpler to
start consuming the EndOfStatement token within AMDGPU's
ParseInstruction in a future patch. This also brings us back to what
every other target currently does.
A future change to move the position back to the end of the statement
would likely need to audit all of the AMDGPUOperand SMLoc ranges, and
determine the SMLoc for the last character of the last operand.
Reviewed By: dp
Differential Revision: https://reviews.llvm.org/D92960
Add builtins required to implement vcmla and rotated variants from
the ACLE
Reviewed By: t.p.northover
Differential Revision: https://reviews.llvm.org/D92929
Regenerated using:
./llvm/utils/update_llc_test_checks.py -u llvm/test/CodeGen/RISCV/*.ll
This has added comments to spill-related instructions and added @plt to
some symbols.
Differential Revision: https://reviews.llvm.org/D92841
*************
* The problem
*************
See motivation examples in compiler-rt/test/dfsan/pair.cpp. The current
DFSan always uses a 16bit shadow value for a variable with any type by
combining all shadow values of all bytes of the variable. So it cannot
distinguish two fields of a struct: each field's shadow value equals the
combined shadow value of all fields. This introduces an overtaint issue.
Consider a parsing function
std::pair<char*, int> get_token(char* p);
where p points to a buffer to parse, the returned pair includes the next
token and the pointer to the position in the buffer after the token.
If the token is tainted, then both the returned pointer and int ar
tainted. If the parser keeps on using get_token for the rest parsing,
all the following outputs are tainted because of the tainted pointer.
The CL is the first change to address the issue.
**************************
* The proposed improvement
**************************
Eventually all fields and indices have their own shadow values in
variables and memory.
For example, variables with type {i1, i3}, [2 x i1], {[2 x i4], i8},
[2 x {i1, i1}] have shadow values with type {i16, i16}, [2 x i16],
{[2 x i16], i16}, [2 x {i16, i16}] correspondingly; variables with
primary type still have shadow values i16.
***************************
* An potential implementation plan
***************************
The idea is to adopt the change incrementially.
1) This CL
Support field-level accuracy at variables/args/ret in TLS mode,
load/store/alloca still use combined shadow values.
After the alloca promotion and SSA construction phases (>=-O1), we
assume alloca and memory operations are reduced. So if struct
variables do not relate to memory, their tracking is accurate at
field level.
2) Support field-level accuracy at alloca
3) Support field-level accuracy at load/store
These two should make O0 and real memory access work.
4) Support vector if necessary.
5) Support Args mode if necessary.
6) Support passing more accurate shadow values via custom functions if
necessary.
***************
* About this CL.
***************
The CL did the following
1) extended TLS arg/ret to work with aggregate types. This is similar
to what MSan does.
2) implemented how to map between an original type/value/zero-const to
its shadow type/value/zero-const.
3) extended (insert|extract)value to use field/index-level progagation.
4) for other instructions, propagation rules are combining inputs by or.
The CL converts between aggragate and primary shadow values at the
cases.
5) Custom function interfaces also need such a conversion because
all existing custom functions use i16. It is unclear whether custome
functions need more accurate shadow propagation yet.
6) Added test cases for aggregate type related cases.
Reviewed-by: morehouse
Differential Revision: https://reviews.llvm.org/D92261
This method previously always recursively checked both the left-hand
side and right-hand side of binary operations for splatted (broadcast)
vector values to determine if the parent DAG node is a splat.
Like several other SelectionDAG methods, limit the recursion depth to
MaxRecursionDepth (6). This prevents stack overflow.
See also https://issuetracker.google.com/173785481
Patch by Nicolas Capens. Thanks!
Differential Revision: https://reviews.llvm.org/D92421
To support llorg builds this patch provides the following changes:
1) Added cmake variable ITTAPI_GIT_REPOSITORY to control the location of ITTAPI repository.
Default value of ITTAPI_GIT_REPOSITORY is github location: https://github.com/intel/ittapi.git
Also, the separate cmake variable ITTAPI_GIT_TAG was added for repo tag.
2) Added cmake variable ITTAPI_SOURCE_DIR to control the place where the repo will be cloned.
Default value of ITTAPI_SOURCE_DIR is build area: PROJECT_BINARY_DIR
Reviewed By: etyurin, bader
Patch by ekovanov.
Differential Revision: https://reviews.llvm.org/D91935
This was accidentally reverted by a later change.
LSR currently only runs in the codegen pass manager.
There are a couple issues with LSR and the NPM.
1) Lots of tests assume that LCSSA isn't run before LSR. This breaks a
bunch of tests' expected output. This is fixable with some time put in.
2) LSR doesn't preserve LCSSA. See
llvm/test/Analysis/MemorySSA/update-remove-deadblocks.ll. LSR's use of
SCEVExpander is the only use of SCEVExpander where the PreserveLCSSA option is
off. Turning it on causes some code sinking out of loops to fail due to
SCEVExpander's inability to handle the newly created trivial PHI nodes in the
broken critical edge (I was looking at
llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll).
I also tried simply just calling formLCSSA() at the end of LSR, but the extra
PHI nodes cause regressions in codegen tests.
We'll delay figuring these issues out until later.
This causes the number of check-llvm failures with -enable-new-pm true
by default to go from 60 to 29.
Reviewed By: asbirlea
Differential Revision: https://reviews.llvm.org/D92796
Explicitly opt-out llvm/test/Transforms/Attributor.
Verified by flipping the default value of allow-unused-prefixes and
observing that none of the failures were under llvm/test/Transforms.
Differential Revision: https://reviews.llvm.org/D92404
This is an enhancement to load vectorization that is motivated by
a pattern in https://llvm.org/PR16739.
Unfortunately, it's still not enough to make a difference there.
We will have to handle multi-use cases in some better way to avoid
creating multiple overlapping loads.
Differential Revision: https://reviews.llvm.org/D92858
The non-strict variants are already handled because they are canonicalized
to strict variants by swapping hands in both the select and icmp,
and the fold simply considers that strictness is irrelevant here.
But that isn't actually true for the last pattern, as PR48390 reports.
