We can only perform a tail call to a callee that preserves all the
registers that the caller needs to preserve.
This situation happens with calling conventions like preserver_mostcc or
cxx_fast_tls. It was explicitely handled for fast_tls and failing for
preserve_most. This patch generalizes the check to any calling
convention.
Related to rdar://24207743
Differential Revision: http://reviews.llvm.org/D18680
llvm-svn: 265329
Summary:
This adds the same checks that were added in r264593 to all
target-specific passes that run after register allocation.
Reviewers: qcolombet
Subscribers: jyknight, dsanders, llvm-commits
Differential Revision: http://reviews.llvm.org/D18525
llvm-svn: 265313
Summary:
At this point we should be able to enable IAS by default for O32 without
breaking check-all, or recursion.
Reviewers: vkalintiris
Subscribers: dsanders, llvm-commits
Differential Revision: http://reviews.llvm.org/D18439
llvm-svn: 265302
This adds MC support for fused compare + indirect branch instructions,
ie. CRB, CGRB, CLRB, CLGRB, CIB, CGIB, CLIB, CLGIB. They aren't actually
generated yet -- this is preparation for their use for conditional
returns in the next iteration of D17339.
Author: koriakin
Differential Revision: http://reviews.llvm.org/D18742
llvm-svn: 265296
A cross-thread sequentially consistent fence should be lowered into
z/Architecture's BCR serialization instruction, instead of causing a
fatal error in the back-end.
Author: bryanpkc
Differential Revision: http://reviews.llvm.org/D18644
llvm-svn: 265292
Enable the SystemZ back-end to lower FRAMEADDR and RETURNADDR, which
previously would cause the back-end to crash. Currently, only a
frame count of zero is supported.
Author: bryanpkc
Differential Revision: http://reviews.llvm.org/D18514
llvm-svn: 265291
Implemented truncstore for KNL and skylake-avx512.
Covered vectors from v2i1 to v64i1. We save the value in bits (not in bytes) - v32i1 is saved in 4 bytes.
Differential Revision: http://reviews.llvm.org/D18740
llvm-svn: 265283
Add support for lowering with the MOVMSK instruction to extract vector element signbits to a GPR.
This is an early step towards more optimal handling of vector comparison results.
Differential Revision: http://reviews.llvm.org/D18741
llvm-svn: 265266
Tidied up comments, stripped trailing whitespace, split apart nodes that aren't related.
No change in ordering although there is definitely some scope for it.
llvm-svn: 265263
Summary:
* Fix to stop delay slot filler from inserting SP modifying instructions in the newly expanded call/return instructions.
* In LowerSymbol the outermost type was not LanaiMCExpr if there was a binary expression
* Remove printExpr in LanaiInstPrinter
Subscribers: joker.eph, llvm-commits
Differential Revision: http://reviews.llvm.org/D18734
llvm-svn: 265251
Add support for the AArch64 .cpu directive. This is a slightly involved
directive since the parameter is actually a variable encoded string. The
general structure is:
<cpu>[[+-]<feature>]*
We now map some of the supported string names for features for internal
representation of feature flags. If we encounter one which we do not support,
bail out as we cannot validate the assembly any longer.
Resolves PR27010.
llvm-svn: 265240
ThreadModel::Single is already handled already by ARMPassConfig adding
LowerAtomicPass to the pass list, which lowers all atomics to non-atomic
ops and deletes fences.
So by the time we get to ISel, there's no atomic fences left, so they
don't need special handling.
llvm-svn: 265178
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
Follow-up to http://reviews.llvm.org/D18566 and http://reviews.llvm.org/D18676 -
where we noticed that an intermediate splat was being generated for memsets of
non-zero chars.
That was because we told getMemsetStores() to use a 32-bit vector element type,
and it happily obliged by producing that constant using an integer multiply.
The 16-byte test that was added in D18566 is now equivalent for AVX1 and AVX2
(no splats, just a vector load), but we have PR27141 to track that splat difference.
Note that the SSE1 path is not changed in this patch. That can be a follow-up.
This patch should resolve PR27100.
llvm-svn: 265161
Follow-up to D18566 - where we noticed that an intermediate splat was being
generated for memsets of non-zero chars.
That was because we told getMemsetStores() to use a 32-bit vector element type,
and it happily obliged by producing that constant using an integer multiply.
The tests that were added in the last patch are now equivalent for AVX1 and AVX2
(no splats, just a vector load), but we have PR27141 to track that splat difference.
In the new tests, the splat via shuffling looks ok to me, but there might be some
room for improvement depending on uarch there.
Note that the SSE1/2 paths are not changed in this patch. That can be a follow-up.
This patch should resolve PR27100.
Differential Revision: http://reviews.llvm.org/D18676
llvm-svn: 265148
Summary: The assembler was picking the wrong JR variant because the pre-R6 one was still enabled at R6.
Author: nitesh.jain
Reviewers: vkalintiris, dsanders
Subscribers: dsanders, llvm-commits, mohit.bhakkad, sagar, bhushan, jaydeep
Differential: D18387
llvm-svn: 265134
Some ARM instructions encode 32-bit immediates as a 8-bit integer (0-255)
and a 4-bit rotation (0-30, even) in its least significant 12 bits. The
original fixup, FK_Data_4, patches the instruction by the value bit-to-bit,
regardless of the encoding. For example, assuming the label L1 and L2 are
0x0 and 0x104 respectively, the following instruction:
add r0, r0, #(L2 - L1) ; expects 0x104, i.e., 260
would be assembled to the following, which adds 1 to r0, instead of 260:
e2800104 add r0, r0, #4, 2 ; equivalently 1
The new fixup kind fixup_arm_mod_imm takes care of the encoding:
e2800f41 add r0, r0, #260
Patch by Ting-Yuan Huang!
llvm-svn: 265122
When a fixup that can be resolved by the assembler is out of range, we should
report an error in the source, rather than crashing.
Differential Revision: http://reviews.llvm.org/D18402
llvm-svn: 265120
Summary:
Previously, we were running afoul of the assertion
EVT(CLI.Ins[i].VT) == InVals[i].getValueType() && "LowerCall emitted a value with the wrong type!"
in SelectionDAGBuilder.cpp when running the NVPTX/i8-param.ll test.
This is because our backend (for some reason) treats small return values
as i32, but it wasn't ever truncating the i32 back down to the expected
width in the DAG.
Unclear to me whether this fixes any actual bugs -- in this test, at
least, the generated code is unchanged.
Reviewers: jingyue
Subscribers: llvm-commits, tra, jholewinski
Differential Revision: http://reviews.llvm.org/D17872
llvm-svn: 265091
Summary:
Previously the NVVMReflect pass would read its configuration from
command-line flags or a static configuration given to the pass at
instantiation time.
This doesn't quite work for clang's use-case. It needs to pass a value
for __CUDA_FTZ down on a per-module basis. We use a module flag for
this, so the NVVMReflect pass needs to be updated to read said flag.
Reviewers: tra, rnk
Subscribers: cfe-commits, jholewinski
Differential Revision: http://reviews.llvm.org/D18672
llvm-svn: 265090
Summary:
Tablegen tries to infer this from the selection DAG patterns defined for
the instructions, but it can't always.
An instructive example is CLZr64. CLZr32 is correctly inferred to have
no side-effects, but the selection DAG pattern for CLZr64 is slightly
more complicated, and in particular the ctlz DAG node is not at the root
of the pattern. Thus tablegen can't infer that CLZr64 has no
side-effects.
Reviewers: jholewinski
Subscribers: jholewinski, tra, llvm-commits
Differential Revision: http://reviews.llvm.org/D17472
llvm-svn: 265089
Summary:
This change will allow loads with imp-def to be clustered in machine-scheduler pass.
areMemAccessesTriviallyDisjoint() can also handle loads with imp-def.
Reviewers: mcrosier, jmolloy, t.p.northover
Subscribers: aemerson, rengolin, mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D18665
llvm-svn: 265051
Chapter 3 of the QPX manual states that, "Scalar floating-point load
instructions, defined in the Power ISA, cause a replication of the source data
across all elements of the target register." Thus, if we have a load followed
by a QPX splat (from the first lane), the splat is redundant. This adds a late
MI-level pass to remove the redundant splats in some of these cases
(specifically when both occur in the same basic block).
This optimization is scheduled just prior to post-RA scheduling. It can't happen
before anything that might replace the load with some already-computed quantity
(i.e. store-to-load forwarding).
llvm-svn: 265047
This will become necessary in a subsequent change to make this method
merge adjacent stack adjustments, i.e. it might erase the previous
and/or next instruction.
It also greatly simplifies the calls to this function from Prolog-
EpilogInserter. Previously, that had a bunch of logic to resume iteration
after the call; now it just continues with the returned iterator.
Note that this changes the behaviour of PEI a little. Previously,
it attempted to re-visit the new instruction created by
eliminateCallFramePseudoInstr(). That code was added in r36625,
but I can't see any reason for it: the new instructions will obviously
not be pseudo instructions, they will not have FrameIndex operands,
and we have already accounted for the stack adjustment.
Differential Revision: http://reviews.llvm.org/D18627
llvm-svn: 265036
isBrImm should accept any non-constant immediate. Previously it was only accepting LanaiMCExpr ones which was wrong.
Differential Revision: http://reviews.llvm.org/D18571
llvm-svn: 265032
PPCSimplifyAddress contains this code:
IntegerType *OffsetTy = ((VT == MVT::i32) ? Type::getInt32Ty(*Context)
: Type::getInt64Ty(*Context));
to determine the type to be used for an index register, if one needs
to be created. However, the "VT" here is the type of the data being
loaded or stored, *not* the type of an address. This means that if
a data element of type i32 is accessed using an index that does not
not fit into 32 bits, a wrong address is computed here.
Note that PPCFastISel is only ever used on 64-bit currently, so the type
of an address is actually *always* MVT::i64. Other parts of the code,
even in this same PPCSimplifyAddress routine, already rely on that fact.
Thus, this patch changes the code to simply unconditionally use
Type::getInt64Ty(*Context) as OffsetTy.
llvm-svn: 265023
This patch corresponds to review:
http://reviews.llvm.org/D18032
This patch provides asm implementation for the following instructions:
lwat, ldat, stwat, stdat, ldmx, mcrxrx
llvm-svn: 265022
Summary:
This change will handle missing store pair opportunity where the first store
instruction stores zero followed by the non-zero store. For example, this change
will convert :
str wzr, [x8]
str w1, [x8, #4]
into:
stp wzr, w1, [x8]
Reviewers: jmolloy, t.p.northover, mcrosier
Subscribers: flyingforyou, aemerson, rengolin, mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D18570
llvm-svn: 265021
The fast isel pass currently emits a COPY_TO_REGCLASS node to convert
from a F4RC to a F8RC register class during conversion of a
floating-point number to integer. There is actually no support in the
common code instruction printers to emit COPY_TO_REGCLASS nodes, so the
PowerPC back-end has special code there to simply ignore
COPY_TO_REGCLASS.
This is correct *if and only if* the source and destination registers of
COPY_TO_REGCLASS are the same (except for the different register class).
But nothing guarantees this to be the case, and if the register
allocator does end up allocating source and destination to different
registers after all, the back-end simply generates incorrect code. I've
included a test case that shows such incorrect code generation.
However, it seems that COPY_TO_REGCLASS is actually not intended to be
used at the MI layer at all. It is used during SelectionDAG, but always
lowered to a plain COPY before emitting MI. Other back-end's fast isel
passes never emit COPY_TO_REGCLASS at all. I suspect it is simply wrong
for the PowerPC back-end to emit it here.
This patch changes the PowerPC back-end to directly emit COPY instead of
COPY_TO_REGCLASS and removes the special handling in the instruction
printers.
Differential Revision: http://reviews.llvm.org/D18605
llvm-svn: 265020
Summary:
There are too many instructions to exhaustively test so addiu and lwc2 are
used as representative examples.
It should be noted that many memory instructions that should have simm16
range checking do not because it is also necessary to support the macro
of the same name which accepts simm32. The range checks for these occur in
the macro expansion.
Reviewers: vkalintiris
Subscribers: dsanders, llvm-commits
Differential Revision: http://reviews.llvm.org/D18437
llvm-svn: 265019
Summary:
ldc2/sdc2 now emit slightly worse diagnostics for MIPS-I. The problem
is that they don't trigger the custom parser because all the candidates
are disabled by feature bits. On all other subtargets, the diagnostics are
accurate but are subject to the usual issues of needing to report multiple
ways to correct the code (e.g. smaller offset, enable a CPU feature) but
only being able to report one error.
Reviewers: vkalintiris
Subscribers: dsanders, llvm-commits
Differential Revision: http://reviews.llvm.org/D18436
llvm-svn: 265018
Summary:
Also, made test_mi10.s formatting consistent with the majority of the
MC tests.
Reviewers: vkalintiris
Subscribers: dsanders, llvm-commits
Differential Revision: http://reviews.llvm.org/D18435
llvm-svn: 265014
Change isConsecutiveLoads to check that loads are non-volatile as this
is a requirement for any load merges. Propagate change to two callers.
Reviewers: RKSimon
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D18546
llvm-svn: 265013
Summary:
The bug was that microMIPS's [ls]w[lr]e instructions claimed to support a
12-bit offset when it is only 9-bit.
Reviewers: vkalintiris
Subscribers: llvm-commits, dsanders
Differential Revision: http://reviews.llvm.org/D18434
llvm-svn: 265010
When dealing with complex<float>, and similar structures with two
single-precision floating-point numbers, especially when such things are being
passed around by value, we'll sometimes end up loading both float values by
extracting them from one 64-bit integer load. It looks like this:
t13: i64,ch = load<LD8[%ref.tmp]> t0, t6, undef:i64
t16: i64 = srl t13, Constant:i32<32>
t17: i32 = truncate t16
t18: f32 = bitcast t17
t19: i32 = truncate t13
t20: f32 = bitcast t19
The problem, especially before the P8 where those bitcasts aren't legal (and
get expanded via the stack), is that it would have been better to use two
floating-point loads directly. Here we add a target-specific DAGCombine to do
just that. In short, we turn:
ld 3, 0(5)
stw 3, -8(1)
rldicl 3, 3, 32, 32
stw 3, -4(1)
lfs 3, -4(1)
lfs 0, -8(1)
into:
lfs 3, 4(5)
lfs 0, 0(5)
llvm-svn: 264988
The size savings are significant, and from what I can tell, both ICC and GCC do this.
Differential Revision: http://reviews.llvm.org/D18573
llvm-svn: 264966
Fix for issue introduced D17297, where we were breaking early from the loop detecting consecutive loads which could leave us thinking a consecutive load with zeros was possible.
llvm-svn: 264922
Summary:
Currently it's a module pass. Make it a function pass so that we can
move it to PassManagerBuilder's EP_EarlyAsPossible extension point,
which only accepts function passes.
Reviewers: rnk
Subscribers: tra, llvm-commits, jholewinski
Differential Revision: http://reviews.llvm.org/D18615
llvm-svn: 264919
Summary:
This results in higher register usage, but should make it easier for
the compiler to hide latency.
This pass is a prerequisite for some more scheduler improvements, and I
think the increase register usage with this patch is acceptable, because
when combined with the scheduler improvements, the total register usage
will decrease.
shader-db stats:
2382 shaders in 478 tests
Totals:
SGPRS: 48672 -> 49088 (0.85 %)
VGPRS: 34148 -> 34847 (2.05 %)
Code Size: 1285816 -> 1289128 (0.26 %) bytes
LDS: 28 -> 28 (0.00 %) blocks
Scratch: 492544 -> 573440 (16.42 %) bytes per wave
Max Waves: 6856 -> 6846 (-0.15 %)
Wait states: 0 -> 0 (0.00 %)
Depends on D18451
Reviewers: nhaehnle, arsenm
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D18452
llvm-svn: 264876
For compatability with GAS, nop and nopr are recognized as alises for
bc and bcr, respectively. A mask of 0 turns these instructions
effectively into no-operations.
Reviewed by Ulrich Weigand.
llvm-svn: 264875
These checks are redundant and can be removed
Reviewers: hans
Subscribers: llvm-commits, mzolotukhin
Differential Revision: http://reviews.llvm.org/D18564
llvm-svn: 264872
XOP's VPPERM has some great 'permute operations' that it can do as well as part of shuffling the bytes of a 128-bit vector - in this case we use it to perform BITREVERSE in a single instruction.
llvm-svn: 264870
operations.
Specifically, we had code that tried to badly approximate reconstructing
all of the possible variations on addressing modes in two x86
instructions based on those in one pseudo instruction. This is not the
first bug uncovered with doing this, so stop doing it altogether.
Instead generically and pedantically copy every operand from the address
over to both new instructions, and strip kill flags from any register
operands.
This fixes a subtle bug seen in the wild where we would mysteriously
drop parts of the addressing mode, causing for example the index
argument in the added test case to just be completely ignored.
Hypothetically, this was an extremely bad miscompile because it actually
caused a predictable and leveragable write of a 64bit quantity to an
unintended offset (the first element of the array intead of whatever
other element was intended). As a consequence, in theory this could even
have introduced security vulnerabilities.
However, this was only something that could happen with an atomic
floating point add. No other operation could trigger this bug, so it
seems extremely unlikely to have occured widely in the wild.
But it did in fact occur, and frequently in scientific applications
which were using relaxed atomic updates of a floating point value after
adding a delta. Those would end up being quite badly miscompiled by
LLVM, which is how we found this. Of course, this often looks like
a race condition in the code, but it was actually a miscompile.
I suspect that this whole RELEASE_FADD thing was a complete mistake.
There is no such operation, and I worry that anything other than add
will get remarkably worse codegeneration. But that's not for this
change....
llvm-svn: 264845
This is effectively NFC, minus the renaming of the options
(-cyclone-prefetch-distance -> -prefetch-distance).
The change was requested by Tim in D17943.
llvm-svn: 264806
They were previously expanded to CAS loops in a custom isel expansion,
but AtomicExpandPass knows how to do that generically.
Testing is covered by the existing sparc atomics.ll testcases.
llvm-svn: 264771
Summary:
However, this has no effect at this time because the instructions affected
are marked 'isCodeGenOnly=1' and have no alternative for the MC layer.
Reviewers: vkalintiris
Subscribers: llvm-commits, dsanders
Differential Revision: http://reviews.llvm.org/D18179
llvm-svn: 264712
Fixed fp_to_uint instruction selection on KNL.
One pattern was missing for <4 x double> to <4 x i32>
Differential Revision: http://reviews.llvm.org/D18512
llvm-svn: 264701
Instead of using two feature bits, one to indicate the availability of the
popcnt[dw] instructions, and another to indicate whether or not they're fast,
use a single enum. This allows more consistent control via target attribute
strings, and via Clang's command line.
llvm-svn: 264690
If all a BUILD_VECTOR's source elements are the same bit (AND/XOR/OR) operation type and each has one constant operand, lower to a pair of BUILD_VECTOR and just apply the bit operation to the vectors.
The constant operands will form a constant vector meaning that we still only have a single BUILD_VECTOR to lower and we will have replaced all the scalarized operations with a single SSE equivalent.
Its not in our interest to start make a general purpose vectorizer from this, but I'm seeing enough of these scalar bit operations from the later legalization/scalarization stages to support them at least.
Differential Revision: http://reviews.llvm.org/D18492
llvm-svn: 264666
The A2 cores support the popcntw/popcntd instructions, but they're microcoded,
and slower than our default software emulation. Specifically, popcnt[dw] take
approximately 74 cycles, whereas our software emulation takes only 24-28
cycles.
I've added a new target feature to indicate a slow popcnt[dw], instead of just
removing the existing target feature from the a2/a2q processor models, because:
1. This allows us to return more accurate information via the TTI interface
(I recognize that this currently makes no practical difference)
2. Is hopefully easier to understand (it allows the core's features to match
its manual while still having the desired effect).
llvm-svn: 264600
MachineFunctionProperties represents a set of properties that a MachineFunction
can have at particular points in time. Existing examples of this idea are
MachineRegisterInfo::isSSA() and MachineRegisterInfo::tracksLiveness() which
will eventually be switched to use this mechanism.
This change introduces the AllVRegsAllocated property; i.e. the property that
all virtual registers have been allocated and there are no VReg operands
left.
With this mechanism, passes can declare that they require a particular property
to be set, or that they set or clear properties by implementing e.g.
MachineFunctionPass::getRequiredProperties(). The MachineFunctionPass base class
verifies that the requirements are met, and handles the setting and clearing
based on the delcarations. Passes can also directly query and update the current
properties of the MF if they want to have conditional behavior.
This change annotates the target-independent post-regalloc passes; future
changes will also annotate target-specific ones.
Reviewers: qcolombet, hfinkel
Differential Revision: http://reviews.llvm.org/D18421
llvm-svn: 264593
Summary:
This helps prevent load clustering from drastically increasing register
pressure by trying to cluster 4 SMRDx8 loads together. The limit of 16
bytes was chosen, because it seems like that was the original intent
of setting the limit to 4 instructions, but more analysis could show
that a different limit is better.
This fixes yields small decreases in register usage with shader-db, but
also helps avoid a large increase in register usage when lane mask
tracking is enabled in the machine scheduler, because lane mask tracking
enables more opportunities for load clustering.
shader-db stats:
2379 shaders in 477 tests
Totals:
SGPRS: 49744 -> 48600 (-2.30 %)
VGPRS: 34120 -> 34076 (-0.13 %)
Code Size: 1282888 -> 1283184 (0.02 %) bytes
LDS: 28 -> 28 (0.00 %) blocks
Scratch: 495616 -> 492544 (-0.62 %) bytes per wave
Max Waves: 6843 -> 6853 (0.15 %)
Wait states: 0 -> 0 (0.00 %)
Reviewers: nhaehnle, arsenm
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D18451
llvm-svn: 264589
- Do not optimize stack slots in optnone functions.
- Get aligned-base register from HexagonMachineFunctionInfo instead of
looking for ALIGNA instruction in the function's body.
llvm-svn: 264580
ICMP instruction selection fails on SKX and KNL for i1 operand.
I use XOR to resolve:
(A == B) is equivalent to (A xor B) == 0
Differential Revision: http://reviews.llvm.org/D18511
llvm-svn: 264566
Intrinsic::maxnum and Intrinsic::minnum, along with the associated libc
function calls (fmax[f], etc.) generally map to function calls after lowering.
For some vector types with QPX at least, however, we can legally lower these,
and we don't need to prohibit CTR-based loops on their account.
It turned out, however, that the logic that checked the opcodes associated with
intrinsics was broken (it would set the Opcode variable, but that variable was
later checked only if set for some otherwise-external function call.
This fixes the latter problem and adds the FMAX/MINNUM mappings.
llvm-svn: 264532
Matthias Braun