Summary:
Extend overlapping store elision to handle overwrites of stores by
larger stores.
Nontemporal tests have been modified to add memory dependencies to
prevent store elision.
Reviewers: craig.topper, rnk, t.p.northover
Subscribers: javed.absar, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D40969
llvm-svn: 321089
We try to prevent shuffle combining to value types that would stop the folding of masked operations, but by just returning early, we were failing to try different shuffle types.
The TODOs are all still relevant here to improve codegen but we're lacking test examples.
llvm-svn: 321085
As mentioned in D38318 and D40865, modern Intel processors prefer to combine multiple shuffles to a variable shuffle mask (PSHUFB/VPERMPS etc.) instead of having multiple stage 'fixed' shuffles which put more pressure on Port 5 (at the expense of extra shuffle mask loads).
This patch provides a FeatureFastVariableShuffle target flag for Haswell+ CPUs that prefers combining 2 or more fixed shuffles to a single variable shuffle (default is 3 shuffles).
The long term aim is to drive more of this from schedule data (probably via the MC) but we're not close to being ready for that yet.
Differential Revision: https://reviews.llvm.org/D41323
llvm-svn: 321074
Extension to D39729 which performed this for vXi16, with the same bit flipping to handle SMAX/SMIN/UMAX cases, vXi8 UMIN horizontal reductions can be performed.
This makes use of the fact that by performing a pair-wise i8 SHUFFLE/UMIN before PHMINPOSUW, we both get the UMIN of each pair but also zero-extend the upper bits ready for v8i16.
Differential Revision: https://reviews.llvm.org/D41294
llvm-svn: 321070
This instruction is encoded as zero, so we have handle that case when checking
for unimplemented opcodes when producing the encoding for an instruction.
llvm-svn: 321066
BWI supports shifting by word amounts. Even if VLX isn't support we can still widen to v32i16 and extract the lower half. For SKX its preferrable to not use 512-bit vector if we can.
llvm-svn: 321059
We need to handle IR for tests that want to do lowering (or just
-stop-after with IR as input). I've run this on one AArch64 test to
demonstrate what it looks like.
llvm-svn: 321048
I missed some prefixes and the fact that on AArch64 we use "bzero"
instead of "__bzero" as on X86 when doing my refactoring in r321035.
Improve tests for bzero.
llvm-svn: 321046
LR was undefined entering outlined functions that contain calls. This made the
machine verifier unhappy when expensive checks were enabled. This fixes that.
llvm-svn: 321014
LLVM IR function names which disable mangling start with '\01'
(https://www.llvm.org/docs/LangRef.html#identifiers).
When an identifier like "\01@abc@" gets dumped to MIR, it is quoted, but
only with single quotes.
http://www.yaml.org/spec/1.2/spec.html#id2770814:
"The allowed character range explicitly excludes the C0 control block
allowed), the surrogate block #xD800-#xDFFF, #xFFFE, and #xFFFF."
http://www.yaml.org/spec/1.2/spec.html#id2776092:
"All non-printable characters must be escaped.
[...]
Note that escape sequences are only interpreted in double-quoted scalars."
This patch adds support for printing escaped non-printable characters
between double quotes if needed.
Should also fix PR31743.
Differential Revision: https://reviews.llvm.org/D41290
llvm-svn: 320996
Fix an off by one error in the bounds checking for 'dinsu' and update
the ranges in the test comments so that they are accurate.
This version has the correct commit message.
Reviewers: atanasyan
Differential Revision: https://reviews.llvm.org/D41183
llvm-svn: 320991
Fix an off by one error in the bounds checking for 'dinsu' and update
the ranges in the test comments so that they are accurate.
Reviewers: atanasyan
https://reviews.llvm.org/D41183
llvm-svn: 320974
For Cylone, the instruction "movi.2d vD, #0" is executed incorrectly in some rare
circumstances. Work around the issue conservatively by avoiding the instruction entirely.
This patch changes CodeGen so that problematic instructions are never
generated, and the AsmParser so that an equivalent instruction is used (with a
warning).
llvm-svn: 320965
Search from AND nodes to find whether they can be propagated back to
loads, so that the AND and load can be combined into a narrow load.
We search through OR, XOR and other AND nodes and all bar one of the
leaves are required to be loads or constants. The exception node then
needs to be masked off meaning that the 'and' isn't removed, but the
loads(s) are narrowed still.
Differential Revision: https://reviews.llvm.org/D41177
llvm-svn: 320962
This is a follow up to the fmaddsub support added in r320950. Hopefully in the future we can fix lowering to handle this fmsubadd too.
llvm-svn: 320951
Summary:
We had no tests for this and we couldn't do the optimization because of a bad use count check. We need to know how many non-undef pieces of the build vector were filled in and ensure our use count is equal to that. But on the shuffle combine version we need the use count to be 2.
The missing coverage was noticed during the review of D40335.
Reviewers: RKSimon, zvi, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41133
llvm-svn: 320950
Assuming we can safely adjust the broadcast index for the new type to keep it suitably aligned, then peek through BITCASTs when looking for the broadcast source.
Fixes PR32007
llvm-svn: 320933
If the loop operand type is int8 then there will be no residual loop for the
unknown size expansion. Dont create the residual-size and bytes-copied values
when they are not needed.
llvm-svn: 320929
Previously we promoted to v8i64, but we don't need to go all the way to 512-bits. If we have VLX we can use the 256-bit instruction. And even if we don't have VLX we can widen v8i32 to v16i32 and drop the upper half.
llvm-svn: 320926
Summary:
Currently we don't handle v32i1/v64i1 insert_vector_elt correctly as we fail to look at the number of elements closely and assume it can only be v16i1 or v8i1.
We also can't type legalize v64i1 insert_vector_elt correctly on KNL due to the type not being byte addressable as required by the legalizing through memory accesses path requires.
For the first issue, the patch now tries to pick a 512-bit register with the correct number of elements and promotes to that.
For the second issue, we now extend the vector to a byte addressable type, do the stores to memory, load the two halves, and then truncate the halves back to the original type. Technically since we changed the type, we may not need two loads, but actually checking that is more work and for the v64i1 case we do need them.
Reviewers: RKSimon, delena, spatel, zvi
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D40942
llvm-svn: 320849
The original memcpy expansion inserted the loop basic block inbetween
the 2 new basic blocks created by splitting the original block the memcpy
call was in. This commit makes the new memcpy expansion do the same to keep the
layout of the IR matching between the old and new implementations.
Differential Review: https://reviews.llvm.org/D41197
llvm-svn: 320848
Work towards the unification of MIR and debug output by printing
`%stack.0` instead of `<fi#0>`, and `%fixed-stack.0` instead of
`<fi#-4>` (supposing there are 4 fixed stack objects).
Only debug syntax is affected.
Differential Revision: https://reviews.llvm.org/D41027
llvm-svn: 320827
The following CFI directives are suported by MC but not by MIR:
* .cfi_rel_offset
* .cfi_adjust_cfa_offset
* .cfi_escape
* .cfi_remember_state
* .cfi_restore_state
* .cfi_undefined
* .cfi_register
* .cfi_window_save
Add support for printing, parsing and update tests.
Differential Revision: https://reviews.llvm.org/D41230
llvm-svn: 320819
This patch switches the default for -riscv-no-aliases to false
and updates all affected MC and CodeGen tests. As recommended in
D41071, MC tests use the canonical instructions and the CodeGen
tests use the aliases.
Additionally, for the f and d instructions with rounding mode,
the tests for the aliased versions are moved and tightened such
that they can actually detect if alias emission is enabled.
(see D40902 for context)
Differential Revision: https://reviews.llvm.org/D41225
Patch by Mario Werner.
llvm-svn: 320797
This patch adds the necessary infrastructure to convert instructions that
take two register operands to those that take a register and immediate if
the necessary operand is produced by a load-immediate. Furthermore, it uses
this infrastructure to perform such conversions twice - first at MachineSSA
and then pre-emit.
There are a number of reasons we may end up with opportunities for this
transformation, including but not limited to:
- X-Form instructions chosen since the exact offset isn't available at ISEL time
- Atomic instructions with constant operands (we will add patterns for this
in the future)
- Tail duplication may duplicate code where one block contains this redundancy
- When emitting compare-free code in PPCDAGToDAGISel, we don't handle constant
comparands specially
Furthermore, this patch moves the initialization of PPCMIPeepholePass so that
it can be used for MIR tests.
llvm-svn: 320791
A couple places didn't use the same SDValue variables to connect everything all the way through.
I don't have a test case for a bug in insert into the lower bits of a non-zero, non-undef vector. Not sure the best way to create that. We don't create the case when lowering concat_vectors which is the main way to get insert_subvectors.
llvm-svn: 320790
The compare elimination peephole introduced in https://reviews.llvm.org/rL312514
causes a miscompile in AMDGPUInstrInfo.cpp which in turn causes some AMDGPU
test case failures in stage2 bootstrap testing. This miscompile didn't cause any
test case failures until https://reviews.llvm.org/rL320614, so it appeared as if
that patch caused these failures.
Disabling this transformation for now to bring the build bots back to green and
the author of the patch will investigate the miscompile.
llvm-svn: 320786
Add support for properly handling PIC code with no-PLT. This equates to
`-fpic -fno-plt -O0` with the clang frontend. External functions are
marked with nonlazybind, which must then be indirected through the GOT.
This allows code to be built without optimizations in PIC mode without
going through the PLT. Addresses PR35653!
llvm-svn: 320776
Summary:
- lowers @llvm.global_dtors by adding @llvm.global_ctors
functions which register the destructors with `__cxa_atexit`.
- impements @llvm.global_ctors with wasm start functions and linker metadata
See [here](https://github.com/WebAssembly/tool-conventions/issues/25) for more background.
Subscribers: jfb, dschuff, mgorny, jgravelle-google, aheejin, sunfish
Differential Revision: https://reviews.llvm.org/D41211
llvm-svn: 320774
This doesn't match the semantics of the extract_vector_elt operation. Nothing downstream knows the bits were zeroed so they still get masked or sign extended after the extrat anyway.
llvm-svn: 320723
MIPSR6 introduced several new jump instructions and deprecated
the use of the 'j' instruction. For microMIPS32R6, 'j' was removed
entirely and it only has non delay slot jumps.
This patch adds support for MIPSR6 by using some R6 instructions--
'bc' instead of 'j', 'jic $reg, 0' instead of 'jalr $zero, $reg'--
and modifies the sequences not to use delay slots for R6.
Reviewers: atanasyan
Reviewed By: atanasyan
Subscribers: dschuff, arichardson, llvm-commits
Differential Revision: https://reviews.llvm.org/D40786
llvm-svn: 320703
store operation on a truncated memory (load) of vXi1 is poorly supported by LLVM and most of the time end with an assertion.
This patch fixes this issue.
Differential Revision: https://reviews.llvm.org/D39547
Change-Id: Ida5523dd09c1ad384acc0a27e9e59273d28cbdc9
llvm-svn: 320691
Work towards the unification of MIR and debug output by printing
`@foo` instead of `<ga:@foo>`.
Also print target flags in the MIR format since most of them are used on
global address operands.
Only debug syntax is affected.
llvm-svn: 320682
Recommitting rL319773, which was reverted due to a recursive issue
causing timeouts. This happened because I failed to check whether
the discovered loads could be narrowed further. In the case of a tree
with one or more narrow loads, that could not be further narrowed, as
well as a node that would need masking, an AND could be introduced
which could then be visited and recombined again with the same load.
This could again create the masking load, with would be combined
again... We now check that the load can be narrowed so that this
process stops.
Original commit message:
Search from AND nodes to find whether they can be propagated back to
loads, so that the AND and load can be combined into a narrow load.
We search through OR, XOR and other AND nodes and all bar one of the
leaves are required to be loads or constants. The exception node then
needs to be masked off meaning that the 'and' isn't removed, but the
loads(s) are narrowed still.
Differential Revision: https://reviews.llvm.org/D41177
llvm-svn: 320679
A v32i1 CONCAT_VECTORS of v16i1 uses promotion to v32i8 to legalize the v32i1. This results in a bunch of extract_vector_elts and a build_vector that ultimately gets scalarized.
This patch checks to see if v16i8 is legal and inserts a any_extend to that so that we can concat v16i8 to v32i8 and avoid creating the extracts.
llvm-svn: 320674
If so go ahead and get the promoted input vector to extract from. Previously, we would create a bunch of any_extends of extract_vector_elts with illegal input type that needs to be promoted. The legalization of those extract_vector_elts would then potentially introduce a truncate. So now we have a bunch of any_extends of truncates. By legalizing both parts together we avoid creating these extra nodes.
The test changes seem to be because we were previously combining the build_vector with the any_extend before the any_extend got combined with the truncate.
llvm-svn: 320669
Two issues were found about machine inst scheduler when compiling ProRender
with -g for amdgcn target:
GCNScheduleDAGMILive::schedule tries to update LiveIntervals for DBG_VALUE, which it
should not since DBG_VALUE is not mapped in LiveIntervals.
when DBG_VALUE is the last instruction of MBB, ScheduleDAGInstrs::buildSchedGraph and
ScheduleDAGMILive::scheduleMI does not move RPTracker properly, which causes assertion.
This patch fixes that.
Differential Revision: https://reviews.llvm.org/D41132
llvm-svn: 320650
Shrink wrapping should ignore DBG_VALUEs referring to frame indices,
since the presence of debug information must not affect code
generation.
Differential Revision: https://reviews.llvm.org/D41187
llvm-svn: 320606
The initial implementation of an MI SSA pass to reduce cr-logical operations.
Currently, the only operations handled by the pass are binary operations where
both CR-inputs come from the same block and the single use is a conditional
branch (also in the same block).
Committing this off by default to allow for a period of field testing. Will
enable it by default in a follow-up patch soon.
Differential Revision: https://reviews.llvm.org/D30431
llvm-svn: 320584
Pass the input vector through SimplifyDemandedBits as we only need the sign bit from each vector element of MOVMSK
We'd probably get more hits if SimplifyDemandedBits was better at handling vectors...
Differential Revision: https://reviews.llvm.org/D41119
llvm-svn: 320570
Work towards the unification of MIR and debug output by printing
`%const.0 + 8` instead of `<cp#0+8>` and `%const.0 - 8` instead of
`<cp#0-8>`.
Only debug syntax is affected.
Differential Revision: https://reviews.llvm.org/D41116
llvm-svn: 320564
Previously, v2i16 -> f32 bitcast could not be matched.
Add patterns to support matching this and similar types of bitcasts.
Differential revision: https://reviews.llvm.org/D40959
llvm-svn: 320562
Shuffle generation uses vmux to collapse vectors resulting from two
individual shuffles into one. The indexes of the elements selected
from the first operand were indicated by 0xFF in the constant vector
used in the compare instruction, but the compare (veqb) set the bits
corresponding to the 0x00 elements, thus inverting the selection.
Reverse the order of operands to vmux to get the correct output.
llvm-svn: 320516
This reverts commit r320508, in effect re-applying r320308. Simon has already
reverted the parts that caused the crash that motivated the revert in r320492.
llvm-svn: 320512
Summary:
Simplify and generalize chain handling and search for 64-bit load-store pairs.
Nontemporal test now converts 64-bit integer load-store into f64 which it realizes directly instead of splitting into two i32 pairs.
Reviewers: craig.topper, spatel
Reviewed By: craig.topper
Subscribers: hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D40918
llvm-svn: 320505
Summary:
Add isRenamable() predicate to MachineOperand. This predicate can be
used by machine passes after register allocation to determine whether it
is safe to rename a given register operand. Register operands that
aren't marked as renamable may be required to be assigned their current
register to satisfy constraints that are not captured by the machine
IR (e.g. ABI or ISA constraints).
Reviewers: qcolombet, MatzeB, hfinkel
Subscribers: nemanjai, mcrosier, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D39400
llvm-svn: 320503
The checks we have for complete models are not great and miss many cases - e.g. in PR35636 it failed to recognise that only the first output (of 2) was actually tagged by the InstRW
Raised PR35639 and PR35643 as examples
llvm-svn: 320492
Recognize constant arrays with the following values:
0x0, 0x1, 0x3, 0x7, 0xF, 0x1F, .... , 2^(size - 1) -1
where //size// is the size of the array.
the result of a load with index //idx// from this array is equivalent to the result of the following:
(0xFFFFFFFF >> (sub 32, idx)) (assuming the array of type 32-bit integer).
And the result of an 'AND' operation on the returned value of such a load and another input, is exactly equivalent to the X86 BZHI instruction behavior.
See test cases in the LIT test for better understanding.
Differential Revision: https://reviews.llvm.org/D34141
llvm-svn: 320481
The last of the three patches that https://reviews.llvm.org/D40348 was
broken up into.
Canonicalize the materialization of constants so that they are more likely
to be CSE'd regardless of the bit-width of the use. If a constant can be
materialized using PPC::LI, materialize it the same way always.
For example:
li 4, -1
li 4, 255
li 4, 65535
are equivalent if the uses only use the low byte. Canonicalize it to the
first form.
Differential Revision: https://reviews.llvm.org/D40348
llvm-svn: 320473
The pass to expand ISEL instructions into if-then-else sequences in patch D23630
is currently disabled. This patch partially enable it by always removing the
unnecessary ISELs (all registers used by the ISELs are the same one) and folding
the ISELs which have the same input registers into unconditional copies.
Differential Revision: https://reviews.llvm.org/D40497
llvm-svn: 320414
This is due to PR26161 needing to be resolved before we can fix
big endian bugs like PR35359. The work to split aggregates into smaller LLTs
instead of using one large scalar will take some time, so in the mean time
we'll fall back to SDAG.
Some ARM BE tests xfailed for now as a result.
Differential Revision: https://reviews.llvm.org/D40789
llvm-svn: 320388
At first, I tried to thread the x86 needle and use a target hook (isVectorShiftByScalarCheap())
to disable the transform only for non-splat pow-of-2 constants, but not AVX2, but only some
element types, but...it's difficult.
Here we just avoid the loop with the x86 vector transform that conflicts with the general DAG
combine and preserve all of the existing behavior AFAICT otherwise.
Some tests that will probably fail if someone does try to restrict this in a more targeted way
for x86-only may be found in:
test/CodeGen/X86/combine-mul.ll
test/CodeGen/X86/vector-mul.ll
test/CodeGen/X86/widen_arith-5.ll
This should prevent the infinite looping seen with:
https://bugs.llvm.org/show_bug.cgi?id=35579
Differential Revision: https://reviews.llvm.org/D41040
llvm-svn: 320374
A wrong type was passed to insertVector, causing an out-of-bounds value
to be added an an operand to HexagonISD::INSERT. This later failed in
instruction selection.
llvm-svn: 320369
Second part of https://reviews.llvm.org/D40348.
Revision r318436 has extended all constants feeding a store to 64 bits
to allow for CSE on the SDAG. However, negative constants were zero extended
which made the constant being loaded appear to be a positive value larger than
16 bits. This resulted in long sequences to materialize such constants
rather than simply a "load immediate". This patch just sign-extends those
updated constants so that they remain 16-bit signed immediates if they started
out that way.
llvm-svn: 320368
The TableGen-based calling convention definitions are inflexible, while
writing a function to implement the calling convention is very
straight-forward, and allows difficult cases to be handled more easily. With
this patch adds support for:
* Passing large scalars according to the RV32I calling convention
* Byval arguments
* Passing values on the stack when the argument registers are exhausted
The custom CC_RISCV calling convention is also used for returns.
This patch also documents the ABI lowering that a language frontend is
expected to perform. I would like to work to simplify these requirements over
time, but this will require further discussion within the LLVM community.
We add PendingArgFlags CCState, as a companion to PendingLocs.
The PendingLocs vector is used by a number of backends to handle arguments
that are split during legalisation. However CCValAssign doesn't keep track of
the original argument alignment. Therefore, add a PendingArgFlags vector which
can be used to keep track of the ISD::ArgFlagsTy for every value added to
PendingLocs.
Differential Revision: https://reviews.llvm.org/D39898
llvm-svn: 320359
As frame pointer elimination isn't implemented until a later patch and we make
extensive use of update_llc_test_checks.py, this changes touches a lot of the
RISC-V tests.
Differential Revision: https://reviews.llvm.org/D39849
llvm-svn: 320357
This is a preparatory step for D34515.
This change:
- makes nodes ISD::ADDCARRY and ISD::SUBCARRY legal for i32
- lowering is done by first converting the boolean value into the carry flag
using (_, C) ← (ARMISD::ADDC R, -1) and converted back to an integer value
using (R, _) ← (ARMISD::ADDE 0, 0, C). An ARMISD::ADDE between the two
operations does the actual addition.
- for subtraction, given that ISD::SUBCARRY second result is actually a
borrow, we need to invert the value of the second operand and result before
and after using ARMISD::SUBE. We need to invert the carry result of
ARMISD::SUBE to preserve the semantics.
- given that the generic combiner may lower ISD::ADDCARRY and
ISD::SUBCARRYinto ISD::UADDO and ISD::USUBO we need to update their lowering
as well otherwise i64 operations now would require branches. This implies
updating the corresponding test for unsigned.
- add new combiner to remove the redundant conversions from/to carry flags
to/from boolean values (ARMISD::ADDC (ARMISD::ADDE 0, 0, C), -1) → C
- fixes PR34045
- fixes PR34564
- fixes PR35103
Differential Revision: https://reviews.llvm.org/D35192
llvm-svn: 320355
Introduces the AddrFI "addressing mode", which is necessary simply because
it's not possible to write a pattern that directly matches a frameindex.
Ensure callee-saved registers are accessed relative to the stackpointer. This
is necessary as callee-saved register spills are performed before the frame
pointer is set.
Move HexagonDAGToDAGISel::isOrEquivalentToAdd to SelectionDAGISel, so we can
make use of it in the RISC-V backend.
Differential Revision: https://reviews.llvm.org/D39848
llvm-svn: 320353
Test (some of) the patterns for selecting PKHBT and PKHTB. The others
are just very similar to the ones we're testing and there would be
little value in covering them as well.
llvm-svn: 320352
All files and parts of files related to microMIPS4R6 are removed.
When target is microMIPS4R6, errors are printed.
This is LLVM part of patch.
Differential Revision: https://reviews.llvm.org/D35625
llvm-svn: 320350
This matches AVX512 version and is more consistent overall. And improves our scheduler models.
In some cases this adds _Int to instructions that didn't have any Int_ before. It's a side effect of the adjustments made to some of the multiclasses.
llvm-svn: 320325
If the question mark is inside the parentheses it only applies to the single character proceeding it.
I had to make a few additional cleanups to fix some duplicate warnings that were exposed by fixing this.
llvm-svn: 320279
We may need to widen the vector to make the shifts legal, but if we do that we need to make sure we shift left/right after accounting for the new size. If not we can't guarantee we are shifting in zeros.
The test cases affected actually show cases where we should move the shifts all together, but that's another problem.
llvm-svn: 320248
We were previously using kunpck with zero inputs unnecessarily. And we had cases where we would insert into a zero vector and then insert into larger zero vector incurring two sets of shifts.
llvm-svn: 320244
Summary:
This relaxes an assertion inside SelectionDAGBuilder which is overly
restrictive on targets which have no concept of alignment (such as AVR).
In these architectures, all types are aligned to 8-bits.
After this, LLVM will only assert that accesses are aligned on targets
which actually require alignment.
This patch follows from a discussion on llvm-dev a few months ago
http://llvm.1065342.n5.nabble.com/llvm-dev-Unaligned-atomic-load-store-td112815.html
Reviewers: bogner, nemanjai, joerg, efriedma
Reviewed By: efriedma
Subscribers: efriedma, cactus, llvm-commits
Differential Revision: https://reviews.llvm.org/D39946
llvm-svn: 320243
The outliner previously would never outline calls. Calls are pretty common in
files, so it makes sense to outline them. In fact, in the LLVM test suite, if
you count the number of instructions that the outliner misses when you outline
calls vs when you don't, it turns out that, on average, around 6% of the
instructions encountered are calls. So, if we outline calls, we can find more
candidates, and thus save some more space.
This commit adds that functionality and updates the mir test to reflect that.
llvm-svn: 320229
MachineSink attempts to place instructions near the basic blocks where
they are needed. Once an instruction has been sunk, its location
relative to other instructions no longer is consistent with the
original source code. In order to ensure correct stepping in the
debugger, the debug location for sunk instructions is either merged
with the insertion point or erased if the target successor block is
empty.
Originally submitted as r318679, revised to fix sanitizer failure and
improve testing.
Patch by Matthew Voss!
Differential Revision: https://reviews.llvm.org/D39933
llvm-svn: 320216
This includes a fix so that it doesn't transform declarations, and it
puts the functionality under control of a command-line option which is off
by default to avoid breaking existing setups.
llvm-svn: 320196
For narrow sizes we'll widen the zero vector and widen the insert. Then do an extract_subvector to get back down to correct size.
This allows us to remove some patterns from the isel table that had to COPY_TO_REGCLASS to an oversized register, do the shift and then COPY_TO_REGCLASS back to the narrow register. Now this is represented explicitly in the DAG.
This seems to have perturbed the register allocation in one of the tests, but the number of instructions didn't change.
llvm-svn: 320190
Updated the scheduling information for the Haswell subtarget with the following changes:
Regrouped the instructions after adding appropriate load + store latencies.
Added scheduling for missing instructions such as the GATHER instrs.
The changes were made after revisiting the latencies impact of all memory uOps.
Reviewers: RKSimon, zvi, craig.topper, apilipenko
Differential Revision: https://reviews.llvm.org/D40021
Change-Id: Iaf6c1f5169add1552845a8a566af4e5a359217a7
llvm-svn: 320137
Replace interleaved store instructions by equivalent and more efficient instructions based on latency cost model.
Https://reviews.llvm.org/D38196
llvm-svn: 320123
This reverts commit 959e37e669b0c3cfad4cb9f1f7c9261ce9f5e9ae.
That commit doesn't handle the case where main is declared rather than defined,
in particular the even-more special case where main is a prototypeless
declaration (which is of course the one actually used by musl currently).
llvm-svn: 320121
We previously only supported inserting to the LSB or MSB where it was easy to zero to perform an OR to insert.
This change effectively extracts the old value and the new value, xors them together and then xors that single bit with the correct location in the original vector. This will cancel out the old value in the first xor leaving the new value in the position.
The way I've implemented this uses 3 shifts and two xors and uses an additional register. We can avoid the additional register at the cost of another shift.
llvm-svn: 320120
It is causing sanitizer failures on llvm tests in a bootstrapped compiler. No bot link since it's currently down, but following up to get the bot up.
This reverts commit r319218.
llvm-svn: 320106
The offset overflow check before was incorrect. It would always give the
correct result, but it was comparing the SCALED potential fixed-up offset
against an UNSCALED minimum/maximum. As a result, the outliner was missing a
bunch of frame setup/destroy instructions that ought to have been safe to
outline. This fixes that, and adds an instruction to the .mir test that
failed the old test.
llvm-svn: 320090
-amdgpu-waitcnt-forcezero={1|0} Force all waitcnt instrs to be emitted as s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-amdgpu-waitcnt-forceexp=<n> Force emit a s_waitcnt expcnt(0) before the first <n> instrs
-amdgpu-waitcnt-forcelgkm=<n> Force emit a s_waitcnt lgkmcnt(0) before the first <n> instrs
-amdgpu-waitcnt-forcevm=<n> Force emit a s_waitcnt vmcnt(0) before the first <n> instrs
Differential Revision: https://reviews.llvm.org/D40091
llvm-svn: 320084
There's no v2i1 or v4i1 kshift, and v8i1 is only supported with AVXDQ. Isel has fake patterns to extend these types to native shifts, but makes no guarantees about the value of any bits shifted in when shifting right.
This patch promotes the vector to a type that supports a native shift first and only allows inserting into the msb of a native sized shift.
I've constructed this in a way that doesn't do the promotion if we're going to fallback to using a xmm/ymm/zmm shuffle. I think I have a plan to remove the shuffle fall back entirely. In which case we this can be simplified, but I wanted to fix the correctness issue first.
llvm-svn: 320081
Tagged as IMUL instructions for a reasonable approximation (ALU tends to be a lot faster) - POPCNT is currently tagged as FAdd which I think should be replaced with IMUL as well
llvm-svn: 320051
I noticed this pattern in D38316 / D38388. We failed to combine a shuffle that is either
repeating a scalar insertion at the same position in a vector or translated to a different
element index.
Like the earlier patch, this could be an instcombine too, but since we opted to make this
a DAG transform earlier, I've made this one a DAG patch too.
We do not need any legality checking because the new insert is identical to the existing
insert except that it may have a different constant insertion operand.
The constant insertion test in test/CodeGen/X86/vector-shuffle-combining.ll was the
motivation for D38756.
Differential Revision: https://reviews.llvm.org/D40209
llvm-svn: 320050
WebAssembly requires caller and callee signatures to match, so the usual
C runtime trick of calling main and having it just work regardless of
whether main is defined as '()' or '(int argc, char *argv[])' doesn't
work. Extend the FixFunctionBitcasts pass to rewrite main to use the
latter form.
llvm-svn: 320041
This patch includes all missing functionality needed to provide first
compilation of a simple program that just returns from a function.
I've added a test case that checks for "ret" instruction printed in assembly
output.
Patch by Andrei Grischenko (andrei.l.grischenko@intel.com)
Differential revision: https://reviews.llvm.org/D39688
llvm-svn: 320035
Summary:
Changed use_instructions() to use_nodbg_instructions() when
building an instruction set.
We don't want the presence of debug info to affect the code
we generate.
Reviewers: dblaikie, Eugene.Zelenko, chandlerc, aprantl
Reviewed By: aprantl
Subscribers: aprantl, llvm-commits
Differential Revision: https://reviews.llvm.org/D40882
llvm-svn: 320010
Summary:
This patch adds MachineCombiner patterns for transforming
(fsub (fmul x y) z) into (fma x y (fneg z)). This has a lower
latency on micro architectures where fneg is cheap.
Patch based on work by George Steed.
Reviewers: rengolin, joelkevinjones, joel_k_jones, evandro, efriedma
Reviewed By: evandro
Subscribers: aemerson, javed.absar, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D40306
llvm-svn: 319980
Csmith discovered a program that caused wrong code generation with -O0:
When handling a SIGN_EXTEND in expandRxSBG(), RxSBG.BitSize may be less than
the Input width (if a truncate was previously traversed), so maskMatters()
should be called with a masked based on the width of the sign extend result
instead.
Review: Ulrich Weigand
llvm-svn: 319892
The patch originally broke Chromium (crbug.com/791714) due to its failing to
specify that the new pseudo instructions clobber EFLAGS. This commit fixes
that.
> Summary: This strengthens the guard and matches MSVC.
>
> Reviewers: hans, etienneb
>
> Subscribers: hiraditya, JDevlieghere, vlad.tsyrklevich, llvm-commits
>
> Differential Revision: https://reviews.llvm.org/D40622
llvm-svn: 319824
When folding a shift into a test-under-mask comparison, make sure that
there is no loss of precision when creating the shifted comparison
value. This usually never happens, except for certain always-true
comparisons in unoptimized code.
Fixes PR35529.
llvm-svn: 319818
Surprisingly SIOptimizeExecMaskingPreRA can infinite loop
in some case with DBG_VALUE. Most tests using dbg_value are
run at -O0, so don't run this pass. This seems to only
happen when the value argument is undef.
llvm-svn: 319808
This patch, together with a matching clang patch (https://reviews.llvm.org/D39719), implements the lowering of X86 kunpack intrinsics to IR.
Differential Revision: https://reviews.llvm.org/D39720
Change-Id: I4088d9428478f9457f6afddc90bd3d66b3daf0a1
llvm-svn: 319778
Search from AND nodes to find whether they can be propagated back to
loads, so that the AND and load can be combined into a narrow load.
We search through OR, XOR and other AND nodes and all bar one of the
leaves are required to be loads or constants. The exception node then
needs to be masked off meaning that the 'and' isn't removed, but the
loads(s) are narrowed still.
Differential Revision: https://reviews.llvm.org/D39604
llvm-svn: 319773
Summary:
Found out, at code inspection, that there was a fault in
DAGCombiner::CombineConsecutiveLoads for big-endian targets.
A BUILD_PAIR is always having the least significant bits of
the composite value in element 0. So when we are doing the checks
for consecutive loads, for big endian targets, we should check
if the load to elt 1 is at the lower address and the load
to elt 0 is at the higher address.
Normally this bug only resulted in missed oppurtunities for
doing the load combine. I guess that in some rare situation it
could lead to faulty combines, but I've not seen that happen.
Note that this patch actually will trigger load combine for
some big endian regression tests.
One example is test/CodeGen/PowerPC/anon_aggr.ll where we now get
t76: i64,ch = load<LD8[FixedStack-9]
instead of
t37: i32,ch = load<LD4[FixedStack-10]>
t35: i32,ch = load<LD4[FixedStack-9]>
t41: i64 = build_pair t37, t35
before legalization. Then the legalization will split the LD8
into two loads, so the end result is the same. That should
verify that the transfomation is correct now.
Reviewers: niravd, hfinkel
Reviewed By: niravd
Subscribers: nemanjai, llvm-commits
Differential Revision: https://reviews.llvm.org/D40444
llvm-svn: 319771
Mark Searles