Original patch by @rogfer01.
All ordered comparisons except ONE are supported natively, and all
unordered comparisons except UNE are expanded into sequences involving
explicit NaN checks and mask arithmetic.
Additionally, we expand GT,OGT,GE,OGE to their swapped-operand versions, and
pattern-match those back to the "original", swapping operands once more. This
way we catch both operations and both "vf" and "fv" forms with fewer patterns.
Also add support for floating-point splat_vector, with an optimization for
splatting fpimm0.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Fraser Cormack <fraser@codeplay.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94242
Lowering of async dialect uses a fixed type converter and therefore does not support lowering non-standard types.
This revision adds a structural conversion so that non-standard types in `!async.value`s can be lowered to LLVM before lowering the async dialect itself.
Reviewed By: ezhulenev
Differential Revision: https://reviews.llvm.org/D94404
On z/OS, the error message "EDC5111I Permission denied." is not matched correctly in lit tests. This patch updates the check expression to match successfully.
Reviewed By: fanbo-meng
Differential Revision: https://reviews.llvm.org/D94432
Change [x86] Fix tile register spill issue was causing problems for our build
using gcc-5.4.1
The problem was caused by this line:
for (const MachineInstr &MI : make_range(MIS.begin(), MI))
where MI was previously defined as a MachineBasicBlock iterator.
Differential Revision: https://reviews.llvm.org/D94415
Summary:
Introduce a new mode of operation for -print-changed that only reports
after a pass changes the IR with all of the other messages suppressed (ie,
no initial IR and no messages about ignored, filtered or non-modifying
passes).
The option processing for -print-changed is changed to take an optional
string indicating options for print-changed. Initially, the only option
supported is quiet (as described above). This new quiet mode is specified
with -print-changed=quiet while -print-changed will continue to function
in the same way. It is intended that there will be more options in the
future.
Author: Jamie Schmeiser <schmeise@ca.ibm.com>
Reviewed By: aeubanks (Arthur Eubanks)
Differential Revision: https://reviews.llvm.org/D92589
Please see D93747 for more context which tries to make linkage names of internal
linkage functions to be the uniqueified names. This causes a problem with gdb
because breaking using the demangled function name will not work if the new
uniqueified name cannot be demangled. The problem is the generated suffix which
is a mix of integers and letters which do not demangle. The demangler accepts
either all numbers or all letters. This patch simply converts the hash to decimal.
There is no loss of uniqueness by doing this as the precision is maintained.
The symbol names get longer by a few characters though.
Differential Revision: https://reviews.llvm.org/D94154
Remove duplicated function to check for required clauses on a directive. This was
still there from the merging of OpenACC and OpenMP common semantic checks and it can now be
removed so we use only one function.
Reviewed By: sameeranjoshi
Differential Revision: https://reviews.llvm.org/D93575
This wasn't possible before because there was no support for affine expressions
as maps. Now that this support is available, provide the mechanism for
constructing maps with a layout and inspecting it.
Rework the `get` method on MemRefType in Python to avoid needing an explicit
memory space or layout map. Remove the `get_num_maps`, it is too low-level,
using the length of the now-avaiable pseudo-list of layout maps is more
pythonic.
Depends On D94297
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D94302
Now that the bindings for AffineExpr have been added, add more bindings for
constructing and inspecting AffineMap that consists of AffineExprs.
Depends On D94225
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D94297
This adds the Python bindings for AffineExpr and a couple of utility functions
to the C API. AffineExpr is a top-level context-owned object and is modeled
similarly to attributes and types. It is required, e.g., to build layout maps
of the built-in memref type.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D94225
VOP3 and VOP DPP subroutines to generate input
operands and asm strings were essentially copy
pasted several times. They are deduplicated to
reduce the maintenance burden and allow faster
development.
Reviewed By: dp
Differential Revision: https://reviews.llvm.org/D94102
Change-Id: I76225eed3c33239d9573351e0c8a0abfad0146ea
The result cannot be widened, unfortunately, because widening vNi1
would depend on the context in which it appears (i.e. the type alone
is not sufficient to tell if it needs to be widened).
Introduce a function attribute 'enforce_tcb' that prevents the function
from calling other functions without the same attribute. This allows
isolating code that's considered to be somehow privileged so that it could not
use its privileges to exhibit arbitrary behavior.
Introduce an on-by-default warning '-Wtcb-enforcement' that warns
about violations of the above rule.
Introduce a function attribute 'enforce_tcb_leaf' that suppresses
the new warning within the function it is attached to. Such leaf functions
may implement common functionality between the trusted and the untrusted code
but they require extra careful audit with respect to their capabilities.
Fixes after a revert in 419ef38a50293c58078f830517f5e305068dbee6:
Fix a test.
Add workaround for GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67274).
Attribute the patch appropriately!
Differential Revision: https://reviews.llvm.org/D91898
Now that we flush the local value map for every instruction, we don't
need any extra flushes for specific cases. Also, LastFlushPoint is
not used for anything. Follow-ups to #c161665 (D91734).
This reapplies #3fd39d3.
Differential Revision: https://reviews.llvm.org/D92338
Fixes PR48681: after LTO, lto.tmp may reference a libcall symbol not in an IR
symbol table of any bitcode file. If such a symbol is defined in an archive
matched by a --exclude-libs, we don't correctly localize the symbol.
Add another `excludeLibs` after `compileBitcodeFiles` to localize such libcall
symbols. Unfortunately we have keep the existing one for D43126.
Using VER_NDX_LOCAL is an implementation detail of `--exclude-libs`, it does not
necessarily tie to the "localize" behavior. `local:` patterns in a version
script can be omitted.
The `symbol ... has undefined version ...` error should not be exempted.
Ideally we should error as GNU ld does. https://issuetracker.google.com/issues/73020933
Reviewed By: psmith
Differential Revision: https://reviews.llvm.org/D94280
When fusing tensor_reshape ops with generic/indexed_Generic op, new
linalg.init_tensor operations were created for the `outs` of the fused
op. While correct (technically) it is better to just reshape the
original `outs` operands and rely on canonicalization of init_tensor
-> tensor_reshape to achieve the same effect.
Differential Revision: https://reviews.llvm.org/D93774
This allow more accurate modeling of the side effects and allow dead code
elimination to remove dead transfer ops.
Differential Revision: https://reviews.llvm.org/D94318
If vpermf128/vpermi128 is acting on 2 similar 'inlane' ops, then try to perform the vpermf128 first which will allow us to merge the ops.
This will help us fix one of the regressions in D56387
Local values are constants or addresses that can't be folded into
the instruction that uses them. FastISel materializes these in a
"local value" area that always dominates the current insertion
point, to try to avoid materializing these values more than once
(per block).
https://reviews.llvm.org/D43093 added code to sink these local
value instructions to their first use, which has two beneficial
effects. One, it is likely to avoid some unnecessary spills and
reloads; two, it allows us to attach the debug location of the
user to the local value instruction. The latter effect can
improve the debugging experience for debuggers with a "set next
statement" feature, such as the Visual Studio debugger and PS4
debugger, because instructions to set up constants for a given
statement will be associated with the appropriate source line.
There are also some constants (primarily addresses) that could be
produced by no-op casts or GEP instructions; the main difference
from "local value" instructions is that these are values from
separate IR instructions, and therefore could have multiple users
across multiple basic blocks. D43093 avoided sinking these, even
though they were emitted to the same "local value" area as the
other instructions. The patch comment for D43093 states:
Local values may also be used by no-op casts, which adds the
register to the RegFixups table. Without reversing the RegFixups
map direction, we don't have enough information to sink these
instructions.
This patch undoes most of D43093, and instead flushes the local
value map after(*) every IR instruction, using that instruction's
debug location. This avoids sometimes incorrect locations used
previously, and emits instructions in a more natural order.
In addition, constants materialized due to PHI instructions are
not assigned a debug location immediately; instead, when the
local value map is flushed, if the first local value instruction
has no debug location, it is given the same location as the
first non-local-value-map instruction. This prevents PHIs
from introducing unattributed instructions, which would either
be implicitly attributed to the location for the preceding IR
instruction, or given line 0 if they are at the beginning of
a machine basic block. Neither of those consequences is good
for debugging.
This does mean materialized values are not re-used across IR
instruction boundaries; however, only about 5% of those values
were reused in an experimental self-build of clang.
(*) Actually, just prior to the next instruction. It seems like
it would be cleaner the other way, but I was having trouble
getting that to work.
This reapplies commits cf1c774d and dc35368c, and adds the
modification to PHI handling, which should avoid problems
with debugging under gdb.
Differential Revision: https://reviews.llvm.org/D91734
There were a number of tests needing updates for D91734, and I added a
bunch of LABEL directives to help track down where those had to go.
These directives are an improvement independent of the functional
patch, so I'm committing them as their own separate patch.
This can lead to issues if files in the tmp directory we don't care about / control are found.
This was partially addressed in D94321, but this is a more permanent fix.
Fixes https://github.com/clangd/clangd/issues/354
Reviewed By: adamcz, sammccall
Differential Revision: https://reviews.llvm.org/D94359
The existing implementation of parallel region merging applies only to
consecutive parallel regions that have speculatable sequential
instructions in-between. This patch lifts this limitation to expand
merging with any sequential instructions in-between, except calls to
unmergable OpenMP runtime functions. In-between sequential instructions
in the merged region are sequentialized in a "master" region and any
output values are broadcasted to the following parallel regions and the
sequential region continuation of the merged region.
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D90909
This patch unifies the way recipes and VPValues are printed after the
transition to VPDef.
VPSlotTracker has been updated to iterate over all recipes and all
their defined values to number those. There is no need to number
values in Value2VPValue.
It also updates a few places that only used slot numbers for
VPInstruction. All recipes now can produce numbered VPValues.
Introduce a function attribute 'enforce_tcb' that prevents the function
from calling other functions without the same attribute. This allows
isolating code that's considered to be somehow privileged so that it could not
use its privileges to exhibit arbitrary behavior.
Introduce an on-by-default warning '-Wtcb-enforcement' that warns
about violations of the above rule.
Introduce a function attribute 'enforce_tcb_leaf' that suppresses
the new warning within the function it is attached to. Such leaf functions
may implement common functionality between the trusted and the untrusted code
but they require extra careful audit with respect to their capabilities.
Differential Revision: https://reviews.llvm.org/D91898
Linalg ops are perfect loop nests. When materializing the concrete
loop nest, the default order specified by the Linalg op's iterators
may not be the best for further CodeGen: targets frequently need
to plan the loop order in order to gain better data access. And
different targets can have different preferences. So there should
exist a way to control the order.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D91795
With this, now we can specify a list of attributes on named ops
generated from the spec. The format is defined as
```
attr-id ::= bare-id (`?`)?
attr-typedef ::= type (`[` `]`)?
attr-def ::= attr-id `:` attr-typedef
tc-attr-def ::= `attr` `(` attr-def-list `)`
tc-def ::= `def` bare-id
`(`tensor-def-list`)` `->` `(` tensor-def-list`)`
(tc-attr-def)?
```
For example,
```
ods_def<SomeCppOp>
def some_op(...) -> (...)
attr(
f32_attr: f32,
i32_attr: i32,
array_attr : f32[],
optional_attr? : f32
)
```
where `?` means optional attribute and `[]` means array type.
Reviewed By: hanchung, nicolasvasilache
Differential Revision: https://reviews.llvm.org/D94240
The following frontend driver invocation will generate 2 output files
in the same directory as the input files:
```
flang-new -fc1 input-1.f input-2.f
```
This is the desired behaviour. However, when testing we need to make
sure that we don't pollute the source directory. To this end, copy test
input files into a temporary directory.
Differential Revision: https://reviews.llvm.org/D94243
Do not cache gpu.async.token type so that the pass can be created before the GPU dialect is registered.
Reviewed By: ftynse
Differential Revision: https://reviews.llvm.org/D94397
This adds uses for locals introduced for new debug messages for the load store optimizer. Those locals are only used on debug statements and otherwise create unused variable warnings.
Differential Revision: https://reviews.llvm.org/D94398
These are often generated when building a vector from the reduction sums of independent vectors.
I've implemented some typical patterns from various v4f32/v4i32 based off current codegen emitted from the vectorizers, although these tests are more about tweaking some hadd style backend folds to handle whatever the vectorizers/vectorcombine throws at us...
This test seems to be broken there (which is not totally surprising as
this functionality was never used on windows). Disable the test while I
investigate.
It has multiple issues fixed by this patch:
1) It shouldn't test how llvm-readelf/yaml2obj works.
2) It should use "-NEXT" prefix for check lines.
3) It can use YAML macros, that allows to use a single YAML.
4) It should probably test the case when a group member is a null section.
Differential revision: https://reviews.llvm.org/D93753
As was mentioned in comments here:
https://reviews.llvm.org/D92636#inline-864967
we are not consistent and sometimes index things from 0, but sometimes
from 1 in warnings.
This patch fixes 2 places: messages reported for
program headers and messages reported for relocations.
Differential revision: https://reviews.llvm.org/D93805
VLST return values are coerced to VLATs in the function epilog for
consistency with the VLAT ABI. Previously, this coercion was done
through memory. It is preferable to use the
llvm.experimental.vector.insert intrinsic to avoid going through memory
here.
Reviewed By: c-rhodes
Differential Revision: https://reviews.llvm.org/D94290
Fraser Cormack