This is a variant of scavengeRegister() that works for
enterBasicBlockEnd()/backward(). The benefit of the backward mode is
that it is not affected by incomplete kill flags.
This patch also changes
PrologEpilogInserter::doScavengeFrameVirtualRegs() to use the register
scavenger in backwards mode.
Differential Revision: http://reviews.llvm.org/D21885
llvm-svn: 276044
This patch corresponds to review:
https://reviews.llvm.org/D21354
We use direct moves for extracting integer elements from vectors. We also use
direct moves when converting integers to FP. When these operations are chained,
we get a direct move out of a VSR followed by a direct move back into a VSR.
These are redundant - all we need to do is line up the element and convert.
llvm-svn: 275796
Currently the MIR framework prints all its outputs (errors and actual
representation) on stderr.
This patch fixes that by printing the regular output in the output
specified with -o.
Differential Revision: http://reviews.llvm.org/D22251
llvm-svn: 275314
This patch corresponds to review:
http://reviews.llvm.org/D21358
Vector shifts that have the same semantics as a vector swap are cannonicalized
as such to provide additional opportunities for swap removal optimization to
remove unnecessary swaps.
llvm-svn: 275168
An identity COPY like this:
%AL = COPY %AL, %EAX<imp-def>
has no semantic effect, but encodes liveness information: Further users
of %EAX only depend on this instruction even though it does not define
the full register.
Replace the COPY with a KILL instruction in those cases to maintain this
liveness information. (This reverts a small part of r238588 but this
time adds a comment explaining why a KILL instruction is useful).
llvm-svn: 274952
There is a problem in VSXSwapRemoval where it is incorrectly removing permute instructions.
In this case, the permute is feeding both a vector store and also a non-store instruction. In this case, the permute cannot be removed.
The fix is to simply look at all the uses of the vector register defined by the permute and ensure that all the uses are vector store instructions.
This problem was reported in PR 27735 (https://llvm.org/bugs/show_bug.cgi?id=27735).
Test case based on the original problem reported.
Phabricator Review: http://reviews.llvm.org/D21802
llvm-svn: 274645
Summary:
findBetterNeighborChains may or may not find a better chain for each node it finds, which include the node ("St") that visitSTORE is currently processing. If no better chain is found for St, visitSTORE should continue instead of return SDValue(St, 0), as if it's CombinedTo'ed.
This fixes bug 28130. There might be other ways to make the test pass (see D21409). I think both of the patches are fixing actual bugs revealed by the same testcase.
Reviewers: echristo, wschmidt, hfinkel, kbarton, amehsan, arsenm, nemanjai, bogner
Subscribers: mehdi_amini, nemanjai, llvm-commits
Differential Revision: http://reviews.llvm.org/D21692
llvm-svn: 274644
This patch corresponds to review:
http://reviews.llvm.org/D20443
It changes the legalization strategy for illegal vector types from integer
promotion to widening. This only applies for vectors with elements of width
that is a multiple of a byte since we have hardware support for vectors with
1, 2, 3, 8 and 16 byte elements.
Integer promotion for vectors is quite expensive on PPC due to the sequence
of breaking apart the vector, extending the elements and reconstituting the
vector. Two of these operations are expensive.
This patch causes between minor and major improvements in performance on most
benchmarks. There are very few benchmarks whose performance regresses. These
regressions can be handled in a subsequent patch with a DAG combine (similar
to how this patch handles int -> fp conversions of illegal vector types).
llvm-svn: 274535
In bidirectional scheduling this gives more stable results than just
comparing the "reason" fields of the top/bottom node because the reason
field may be higher depending on what other nodes are in the queue.
Differential Revision: http://reviews.llvm.org/D19401
llvm-svn: 273755
If a local_unnamed_addr attribute is attached to a global, the address
is known to be insignificant within the module. It is distinct from the
existing unnamed_addr attribute in that it only describes a local property
of the module rather than a global property of the symbol.
This attribute is intended to be used by the code generator and LTO to allow
the linker to decide whether the global needs to be in the symbol table. It is
possible to exclude a global from the symbol table if three things are true:
- This attribute is present on every instance of the global (which means that
the normal rule that the global must have a unique address can be broken without
being observable by the program by performing comparisons against the global's
address)
- The global has linkonce_odr linkage (which means that each linkage unit must have
its own copy of the global if it requires one, and the copy in each linkage unit
must be the same)
- It is a constant or a function (which means that the program cannot observe that
the unique-address rule has been broken by writing to the global)
Although this attribute could in principle be computed from the module
contents, LTO clients (i.e. linkers) will normally need to be able to compute
this property as part of symbol resolution, and it would be inefficient to
materialize every module just to compute it.
See:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20160509/356401.htmlhttp://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20160516/356738.html
for earlier discussion.
Part of the fix for PR27553.
Differential Revision: http://reviews.llvm.org/D20348
llvm-svn: 272709
The exit-on-error flag in the ARM test is necessary in order to avoid an
unreachable in the DAGTypeLegalizer, when trying to expand a physical register.
We can also avoid this situation by introducing a bitcast early on, where the
invalid scalar-to-vector conversion is detected.
We also add a test for PowerPC, which goes through a similar code path in the
SelectionDAGBuilder.
Fixes PR27765.
Differential Revision: http://reviews.llvm.org/D21061
llvm-svn: 272644
Using an LLVM IR aggregate return value type containing three
or more integer values causes an abort in the fast isel pass.
This patch adds two more registers to RetCC_PPC64_ELF_FIS to
allow returning up to four integers with fast isel, just the
same as is currently supported with regular isel (RetCC_PPC).
This is needed for Swift and (possibly) other non-clang frontends.
Fixes PR26190.
llvm-svn: 272005
Summary:
Also convert test/CodeGen/PowerPC/vsx-ldst-builtin-le.ll to use
FileCheck instead of two grep and count runs.
This change is needed to avoid spurious diffs in these tests when
EarlyCSE is improved to use MemorySSA and can do more load elimination.
Reviewers: hfinkel
Subscribers: mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D20238
llvm-svn: 271553
Fix PR27943 "Bad machine code: Using an undefined physical register".
SUBFC8 implicitly defines the CR0 register, but this was omitted in
the instruction definition.
Patch by Jameson Nash <jameson@juliacomputing.com>
Reviewers: hfinkel
Differential Revision: http://reviews.llvm.org/D20802
llvm-svn: 271425
When processing inline asm that contains errors, make sure we can recover
gracefully by creating an UNDEF SDValue for the inline asm statement before
returning from SelectionDAGBuilder::visitInlineAsm. This is necessary for
consumers that don't exit on the first error that is emitted (e.g. clang)
and that would assert later on.
Fixes PR24071.
Patch by Diana Picus.
llvm-svn: 269811
Without a diagnostic handler installed, llc's behaviour is to exit on the first
error that it encounters. This is very different from the behaviour of clang
and other front ends, which try to gather as many errors as possible before
exiting.
This commit adds a diagnostic handler to llc, allowing it to find and report
more than one error. The old behaviour is preserved under a flag (-exit-on-error).
Some of the tests fail with the new diagnostic handler, so they have to use the
new flag in order to run under the previous behaviour. Some of these are known
bugs, others need further investigation. Ideally, we should fix the tests and
remove the flag at some point in the future.
Reapplied after fixing the LLDB build that was broken due to the new
DiagnosticSeverity in LLVMContext.h, and fixed an UB in the new change.
Patch by Diana Picus.
llvm-svn: 269655
Without a diagnostic handler installed, llc's behaviour is to exit on the first
error that it encounters. This is very different from the behaviour of clang
and other front ends, which try to gather as many errors as possible before
exiting.
This commit adds a diagnostic handler to llc, allowing it to find and report
more than one error. The old behaviour is preserved under a flag (-exit-on-error).
Some of the tests fail with the new diagnostic handler, so they have to use the
new flag in order to run under the previous behaviour. Some of these are known
bugs, others need further investigation. Ideally, we should fix the tests and
remove the flag at some point in the future.
Reapplied after fixing the LLDB build that was broken due to the new
DiagnosticSeverity in LLVMContext.h.
Patch by Diana Picus.
llvm-svn: 269563
This reverts commit r269428, as it breaks the LLDB build. We need to
understand how to change LLDB in the same way as LLC before landing this
again.
llvm-svn: 269432
Without a diagnostic handler installed, llc's behaviour is to exit on the first
error that it encounters. This is very different from the behaviour of clang
and other front ends, which try to gather as many errors as possible before
exiting.
This commit adds a diagnostic handler to llc, allowing it to find and report
more than one error. The old behaviour is preserved under a flag (-exit-on-error).
Some of the tests fail with the new diagnostic handler, so they have to use the
new flag in order to run under the previous behaviour. Some of these are known
bugs, others need further investigation. Ideally, we should fix the tests and
remove the flag at some point in the future.
Patch by Diana Picus.
llvm-svn: 269428
While promoting nodes in PPCTargetLowering::DAGCombineExtBoolTrunc, it is
possible for one of the nodes to be replaced by another. To make sure we do not
visit the deleted nodes, and to make sure we visit the replacement nodes, use a
list of HandleSDNodes to track the to-be-promoted nodes during the promotion
process.
The same fix has been applied to the analogous code in
PPCTargetLowering::DAGCombineTruncBoolExt.
Fixes PR26985.
llvm-svn: 269272
An oddity of the .ll syntax is that the "@var = " in
@var = global i32 42
is optional. Writing just
global i32 42
is equivalent to
@0 = global i32 42
This means that there is a pretty big First set at the top level. The
current implementation maintains it manually. I was trying to refactor
it, but then started wondering why keep it a all. I personally find the
above syntax confusing. It looks like something is missing.
This patch removes the feature and simplifies the parser.
llvm-svn: 269096
This patch corresponds to review:
http://reviews.llvm.org/D19683
Simply adds the bits for being able to specify -mcpu=pwr9 to the back end.
llvm-svn: 268950
This patch fixes register alignment for long double type in
soft float mode. Before this patch alignment was 8 and this
patch changes it to 4.
Differential Revision: http://reviews.llvm.org/D18034
llvm-svn: 268909
This patch corresponds to review:
http://reviews.llvm.org/D18592
It allows the PPC back end to generate the xxspltw instruction where we
previously only emitted vspltw.
llvm-svn: 268516
This instruction is just a control flow marker - it should not
actually exist in the object file. Unfortunately, nothing catches
it before it gets to AsmPrinter. If integrated assembler is used,
it's considered to be a normal 4-byte instruction, and emitted as
an all-0 word, crashing the program. With external assembler,
a comment is emitted.
Fixed by setting Size to 0 and handling it in MCCodeEmitter - this
means the comment will still be emitted if integrated assembler
is not used.
This broke an ASan test, which has been disabled for a long time
as a result (see the discussion on D19657). We can reenable it
once this lands.
llvm-svn: 267943
visitAND, when folding and (load) forgets to check which output of
an indexed load is involved, happily folding the updated address
output on the following testcase:
target datalayout = "e-m:e-i64:64-n32:64"
target triple = "powerpc64le-unknown-linux-gnu"
%typ = type { i32, i32 }
define signext i32 @_Z8access_pP1Tc(%typ* %p, i8 zeroext %type) {
%b = getelementptr inbounds %typ, %typ* %p, i64 0, i32 1
%1 = load i32, i32* %b, align 4
%2 = ptrtoint i32* %b to i64
%3 = and i64 %2, -35184372088833
%4 = inttoptr i64 %3 to i32*
%_msld = load i32, i32* %4, align 4
%zzz = add i32 %1, %_msld
ret i32 %zzz
}
Fix this by checking ResNo.
I've found a few more places that currently neglect to check for
indexed load, and tightened them up as well, but I don't have test
cases for them. In fact, they might not be triggerable at all,
at least with current targets. Still, better safe than sorry.
Differential Revision: http://reviews.llvm.org/D19202
llvm-svn: 267420
ADD8TLS, a variant of add instruction used for initial-exec TLS,
currently accepts r0 as a source register. While add itself supports
r0 just fine, linker can relax it to a local-exec sequence, converting
it to addi - which doesn't support r0.
Differential Revision: http://reviews.llvm.org/D19193
llvm-svn: 267388
Currently each Function points to a DISubprogram and DISubprogram has a
scope field. For member functions the scope is a DICompositeType. DIScopes
point to the DICompileUnit to facilitate type uniquing.
Distinct DISubprograms (with isDefinition: true) are not part of the type
hierarchy and cannot be uniqued. This change removes the subprograms
list from DICompileUnit and instead adds a pointer to the owning compile
unit to distinct DISubprograms. This would make it easy for ThinLTO to
strip unneeded DISubprograms and their transitively referenced debug info.
Motivation
----------
Materializing DISubprograms is currently the most expensive operation when
doing a ThinLTO build of clang.
We want the DISubprogram to be stored in a separate Bitcode block (or the
same block as the function body) so we can avoid having to expensively
deserialize all DISubprograms together with the global metadata. If a
function has been inlined into another subprogram we need to store a
reference the block containing the inlined subprogram.
Attached to https://llvm.org/bugs/show_bug.cgi?id=27284 is a python script
that updates LLVM IR testcases to the new format.
http://reviews.llvm.org/D19034
<rdar://problem/25256815>
llvm-svn: 266446
[PPC] Previously when casting generic loads to LXV2DX/ST instructions we
would leave the original load return type in place allowing for an
assertion failure when we merge two equivalent LXV2DX nodes with
different types.
This fixes PR27350.
Reviewers: nemanjai
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D19133
llvm-svn: 266438
Resolve Bug 27046 (https://llvm.org/bugs/show_bug.cgi?id=27046).
The PPCInstrInfo::optimizeCompareInstr function could create a new use of
CR0, even if CR0 were previously dead. This patch marks CR0 live if a use of
CR0 is created.
Author: Tom Jablin (tjablin)
Reviewers: hfinkel kbarton cycheng
http://reviews.llvm.org/D18884
llvm-svn: 266040
In the ELFv2 ABI, we are not required to save all CR fields. If only one
nonvolatile CR field is clobbered, use mfocrf instead of mfcr to
selectively save the field, because mfocrf has short latency compares to
mfcr.
Thanks Nemanja's invaluable hint!
Reviewers: nemanjai tjablin hfinkel kbarton
http://reviews.llvm.org/D17749
llvm-svn: 266038
In Memcpy lowering we had missed a dependence from the load of the
operation to successor operations. This causes us to potentially
construct an in initial DAG with a memory dependence not fully
represented in the chain sub-DAG but rather require looking at the
entire DAG breaking alias analysis by allowing incorrect repositioning
of memory operations.
To work around this, r200033 changed DAGCombiner::GatherAllAliases to be
conservative if any possible issues to happen. Unfortunately this check
forbade many non-problematic situations as well. For example, it's
common for incoming argument lowering to add a non-aliasing load hanging
off of EntryNode. Then, if GatherAllAliases visited EntryNode, it would
find that other (unvisited) use of the EntryNode chain, and just give up
entirely. Furthermore, the check was incomplete: it would not actually
detect all such potentially problematic DAG constructions, because
GatherAllAliases did not guarantee to visit all chain nodes going up to
the root EntryNode. This is in general fine -- giving up early will just
miss a potential optimization, not generate incorrect results. But, for
this non-chain dependency detection code, it's possible that you could
have a load attached to a higher-up chain node than any which were
visited. If that load aliases your store, but the only dependency is
through the value operand of a non-aliasing store, it would've been
missed by this code, and potentially reordered.
With the dependence added, this check can be removed and Alias Analysis
can be much more aggressive. This fixes code quality regression in the
Consecutive Store Merge cleanup (D14834).
Test Change:
ppc64-align-long-double.ll now may see multiple serializations
of its stores
Differential Revision: http://reviews.llvm.org/D18062
llvm-svn: 265836
This is the same change on PPC64 as r255821 on AArch64. I have even borrowed
his commit message.
The access function has a short entry and a short exit, the initialization
block is only run the first time. To improve the performance, we want to
have a short frame at the entry and exit.
We explicitly handle most of the CSRs via copies. Only the CSRs that are not
handled via copies will be in CSR_SaveList.
Frame lowering and prologue/epilogue insertion will generate a short frame
in the entry and exit according to CSR_SaveList. The majority of the CSRs will
be handled by register allcoator. Register allocator will try to spill and
reload them in the initialization block.
We add CSRsViaCopy, it will be explicitly handled during lowering.
1> we first set FunctionLoweringInfo->SplitCSR if conditions are met (the target
supports it for the given machine function and the function has only return
exits). We also call TLI->initializeSplitCSR to perform initialization.
2> we call TLI->insertCopiesSplitCSR to insert copies from CSRsViaCopy to
virtual registers at beginning of the entry block and copies from virtual
registers to CSRsViaCopy at beginning of the exit blocks.
3> we also need to make sure the explicit copies will not be eliminated.
Author: Tom Jablin (tjablin)
Reviewers: hfinkel kbarton cycheng
http://reviews.llvm.org/D17533
llvm-svn: 265781
Summary:
EHPad BB are not entered the classic way and therefor do not need to be placed after their predecessors. This patch make sure EHPad BB are not chosen amongst successors to form chains, and are selected as last resort when selecting the best candidate.
EHPad are scheduled in reverse probability order in order to have them flow into each others naturally.
Reviewers: chandlerc, majnemer, rafael, MatzeB, escha, silvas
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D17625
llvm-svn: 265726
http://reviews.llvm.org/D18562
A large number of testcases has been modified so they pass after this test.
One testcase is deleted, because I realized even after undoing the original
change that was committed with this testcase, the testcase still passes. So
I removed it. The change to one other testcase (test/CodeGen/PowerPC/pr25802.ll)
is an arbitrary change to keep it passing. Given the original intention of the
testcase, and the fact that fixing it will require some time to change the testcase,
we concluded that this quick change will be enough.
llvm-svn: 265683
http://reviews.llvm.org/D18405
When the integer value loaded is never used directly as integer we should use VSX
or Floating Point Facility integer loads and avoid extra direct move
llvm-svn: 265593
This patch enable sibling call optimization on ppc64 ELFv1/ELFv2 abi, and
add a couple of test cases. This patch also passed llvm/clang bootstrap
test, and spec2006 build/run/result validation.
Original issue: https://llvm.org/bugs/show_bug.cgi?id=25617
Great thanks to Tom's (tjablin) help, he contributed a lot to this patch.
Thanks Hal and Kit's invaluable opinions!
Reviewers: hfinkel kbarton
http://reviews.llvm.org/D16315
llvm-svn: 265506
We missed a handful of .mir tests that existed outside the
test/CodeGen/MIR directory.
Also fix the three powerpc .mir tests that nobody noticed were broken.
llvm-svn: 265350
Previously, HandleLastUse would delete RegRef information for sub-registers
if they were dead even if their corresponding super-register were still live.
If the super-register were later renamed, then the definitions of the
sub-register would not be updated appropriately. This patch alters the
behavior so that RegInfo information for sub-registers is only deleted when
the sub-register and super-register are both dead.
This resolves PR26775. This is the mirror image of Hal's r227311 commit.
Author: Tom Jablin (tjablin)
Reviewers: kbarton uweigand nemanjai hfinkel
http://reviews.llvm.org/D18448
llvm-svn: 265097
This mostly cosmetic patch moves the DebugEmissionKind enum from DIBuilder
into DICompileUnit. DIBuilder is not the right place for this enum to live
in — a metadata consumer should not have to include DIBuilder.h.
I also added a Verifier check that checks that the emission kind of a
DICompileUnit is actually legal.
http://reviews.llvm.org/D18612
<rdar://problem/25427165>
llvm-svn: 265077
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
The test case added in r265023 is failing on ninja-x64-msvc-RA-centos6.
Update the test to make less specific assumptions on code generation.
llvm-svn: 265026
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
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
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
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
Minimum density for both optsize and non optsize are now options
-sparse-jump-table-density (default 10) for non optsize functions
-dense-jump-table-density (default 40) for optsize functions, which
matches the current default. This improves several benchmarks at google
at the cost of a small codesize increase. For code compiled with -Os,
the old behavior continues
llvm-svn: 264689
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
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
This patch corresponds to review:
http://reviews.llvm.org/D17711
It disables direct moves on these operations in 32-bit mode since the patterns
assume 64-bit registers. The final patch is slightly different from the
Phabricator review as the bitcast operations needed to be disabled in 32-bit
mode as well. This fixes PR26617.
llvm-svn: 264282
For fcmp, major concern about the following 6 cases is NaN result. The
comparison result consists of 4 bits, indicating lt, eq, gt and un (unordered),
only one of which will be set. The result is generated by fcmpu
instruction. However, bc instruction only inspects one of the first 3
bits, so when un is set, bc instruction may jump to to an undesired
place.
More specifically, if we expect an unordered comparison and un is set, we
expect to always go to true branch; in such case UEQ, UGT and ULT still
give false, which are undesired; but UNE, UGE, ULE happen to give true,
since they are tested by inspecting !eq, !lt, !gt, respectively.
Similarly, for ordered comparison, when un is set, we always expect the
result to be false. In such case OGT, OLT and OEQ is good, since they are
actually testing GT, LT, and EQ respectively, which are false. OGE, OLE
and ONE are tested through !lt, !gt and !eq, and these are true.
llvm-svn: 263753
This patch prevents CTR loops optimization when using soft float operations
inside loop body. Soft float operations use function calls, but function
calls are not allowed inside CTR optimized loops.
Patch by Aleksandar Beserminji.
Differential Revision: http://reviews.llvm.org/D17600
llvm-svn: 263727
This patch corresponds to review:
http://reviews.llvm.org/D17712
We were not clearing the TOC vector in PPCAsmPrinter when initializing it. This
caused duplicate definition asserts when the pass is reused on the module
(i.e. with -compile-twice or in JIT contexts).
llvm-svn: 263338
Corresponds to Phabricator review:
http://reviews.llvm.org/D16592
This fix includes both an update to how we handle the "generic" CPU on LE
systems as well as Anton's fix for the Fast Isel issue.
llvm-svn: 262233
Currently we always expand ISD::FNEG. For v4f32 and v2f64 vector types VSX has
native support for this opcode
Phabricator: http://reviews.llvm.org/D17647
llvm-svn: 262079
This is what was meant to be in the initial commit to fix this bug. The
parens were missing. This commit also adds a test case for the bug and
has undergone full testing on PPC and X86.
llvm-svn: 261546
Summary:
Without this, this command
$ llvm-run llc -stop-after machine-cp -o - <( echo '' )
outputs an error, because we close stdout twice -- once when closing the
file opened for "-o", and again when closing outs().
Also clarify in the outs() definition that you can't ever call it if you
want to open your own raw_fd_ostream on stdout.
Reviewers: jroelofs, tstellarAMD
Subscribers: jholewinski, qcolombet, dsanders, llvm-commits
Differential Revision: http://reviews.llvm.org/D17422
llvm-svn: 261286
Using the load immediate only when the immediate (whether signed or unsigned)
can fit in a 16-bit signed field. Namely, from -32768 to 32767 for signed and
0 to 65535 for unsigned. This patch also ensures that we sign-extend under the
right conditions.
llvm-svn: 259840
This patch consists of two parts: a performance fix in DAGCombiner.cpp
and a correctness fix in SelectionDAG.cpp.
The test case tests the bug that's uncovered by the performance fix, and
fixed by the correctness fix.
The performance fix keeps the containers required by the
hasPredecessorHelper (which is a lazy DFS) and reuse them. Since
hasPredecessorHelper is called in a loop, the overall efficiency reduced
from O(n^2) to O(n), where n is the number of SDNodes.
The correctness fix keeps iterating the neighbor list even if it's time
to early return. It will return after finishing adding all neighbors to
Worklist, so that no neighbors are discarded due to the original early
return.
llvm-svn: 259691
Recommited, after some fixing with test cases.
Updated test cases:
test/CodeGen/AArch64/arm64-misched-memdep-bug.ll
test/CodeGen/AArch64/tailcall_misched_graph.ll
Temporarily disabled test cases:
test/CodeGen/AMDGPU/split-vector-memoperand-offsets.ll
test/CodeGen/PowerPC/ppc64-fastcc.ll (partially updated)
test/CodeGen/PowerPC/vsx-fma-m.ll
test/CodeGen/PowerPC/vsx-fma-sp.ll
http://reviews.llvm.org/D8705
Reviewers: Hal Finkel, Andy Trick.
llvm-svn: 259673
The purpose of PPCVSXFMAMutate is to elide copies by changing FMA forms
on PPC.
%vreg6<def> = COPY %vreg96
%vreg6<def,tied1> = XSMADDASP %vreg6<tied0>, %vreg5<kill>, %vreg7
;v6 = v6 + v5 * v7
is replaced by
%vreg5<def,tied1> = XSMADDMSP %vreg5<tied0>, %vreg7, %vreg96
;v5 = v5 * v7 + v96
This was broken in the case where the target register was also used as a
multiplicand. Fix this case by checking for it and replacing both uses
with the copied register.
%vreg6<def> = COPY %vreg96
%vreg6<def,tied1> = XSMADDASP %vreg6<tied0>, %vreg5<kill>, %vreg6
;v6 = v6 + v5 * v6
is replaced by
%vreg5<def,tied1> = XSMADDMSP %vreg5<tied0>, %vreg96, %vreg96
;v5 = v5 * v96 + v96
llvm-svn: 259617
check that the sign extended constant fits into 16-bits if we want a
zero extended value, otherwise go ahead and put it together piecemeal.
Fixes PR26356.
llvm-svn: 259177
For historic reasons, the behavior of .align differs between targets.
Fortunately, there are alternatives, .p2align and .balign, which make the
interpretation of the parameter explicit, and which behave consistently across
targets.
This patch teaches MC to use .p2align instead of .align, so that people reading
code for multiple architectures don't have to remember which way each platform
does its .align directive.
Differential Revision: http://reviews.llvm.org/D16549
llvm-svn: 258750
The global entry point prologue currently assumes that the TOC
associated with a function is less than 2GB away from the function
entry point. This is always true when using the medium or small
code model, but may not be the case when using the large code model.
This patch adds a new variant of the ELFv2 global entry point prologue
that lifts the 2GB restriction when building with -mcmodel=large.
This works by emitting a quadword containing the distance from the
function entry point to its associated TOC immediately before the
entry point, and then using a prologue like:
ld r2,-8(r12)
add r2,r2,r12
Since creation of the entry point prologue is now split across two
separate routines (PPCLinuxAsmPrinter::EmitFunctionEntryLabel emits
the data word, PPCLinuxAsmPrinter::EmitFunctionBodyStart the prolog
code), I've switched to using named labels instead of just temporaries
to indicate the locations of the global and local entry points and the
new TOC offset data word.
These names are provided by new routines in PPCFunctionInfo modeled
after the existing PPCFunctionInfo::getPICOffsetSymbol.
Note that a corresponding change was committed to GCC here:
https://gcc.gnu.org/ml/gcc-patches/2015-12/msg00355.html
Reviewers: hfinkel
Differential Revision: http://reviews.llvm.org/D15500
llvm-svn: 257597
Only non-weighted predicates were handled in PPCInstrInfo::insertSelect. Handle
the weighted predicates as well.
This latent bug was triggered by r255398, because it added use of the
branch-weighted predicates.
While here, switch over an enum instead of an int to get the compiler to enforce
totality in the future.
llvm-svn: 257518
This is a fix for bug http://llvm.org/bugs/show_bug.cgi?id=25839.
For a PIC TLS variable access in a function, prologue (mflr followed by std and
stdu) gets scheduled after a tls_get_addr call. tls_get_addr messed up LR but
no one saves/restores it.
Also added a test for save/restore clobbered registers during calling __tls_get_addr.
Patch by Tim Shen
llvm-svn: 257137
This is the second in a set of patches for soft float support for ppc32,
it enables soft float operations.
Patch by Strahinja Petrovic.
Differential Revision: http://reviews.llvm.org/D13700
llvm-svn: 255516
This branch adds hints for highly biased branches on the PPC architecture. Even
in absence of profiling information, LLVM will mark code reaching unreachable
terminators and other exceptional control flow constructs as highly unlikely to
be reached.
Patch by Tom Jablin!
llvm-svn: 255398
Access to aligned globals gives us a chance to peephole optimize nonzero
offsets. If a struct is 4 byte aligned, then accesses to bytes 0-3 won't
overflow the available displacement. For example:
addis 3, 2, b4v@toc@ha
addi 4, 3, b4v@toc@l
lbz 5, b4v@toc@l(3) ; This is the result of the current peephole
lbz 6, 1(4) ; optimizer
lbz 7, 2(4)
lbz 8, 3(4)
If b4v is 4-byte aligned, we can skip using register 4 because we know
that b4v@toc@l+{1,2,3} won't overflow 32K, and instead generate:
addis 3, 2, b4v@toc@ha
lbz 4, b4v@toc@l(3)
lbz 5, b4v@toc@l+1(3)
lbz 6, b4v@toc@l+2(3)
lbz 7, b4v@toc@l+3(3)
Saving a register and an addition.
Larger alignments allow larger structures/arrays to be optimized.
llvm-svn: 255319
This was causing bad code gen and assembly that won't assemble, as
mixed altivec and vsx code would end up with a vsx high register
assigned to an altivec instruction, which won't work. Constraining the
classes allows the optimization to proceed.
llvm-svn: 255299
This patch corresponds to review:
http://reviews.llvm.org/D15286
LLVM IR frequently contains bitcast operations between floating point and
integer values of the same width. Doing this through memory operations is
quite expensive on PPC. This patch allows the use of direct register moves
between FPRs and GPRs for lowering bitcasts.
llvm-svn: 255246
AggressiveAntiDepBreaker was renaming registers specified by the user
for inline assembly. While this will work for compiler-specified
registers, it won't work for user-specified registers, and at the time
this runs, I don't currently see a way to distinguish them.
llvm-svn: 254532
The @llvm.get.dynamic.area.offset.* intrinsic family is used to get the offset
from native stack pointer to the address of the most recent dynamic alloca on
the caller's stack. These intrinsics are intendend for use in combination with
@llvm.stacksave and @llvm.restore to get a pointer to the most recent dynamic
alloca. This is useful, for example, for AddressSanitizer's stack unpoisoning
routines.
Patch by Max Ostapenko.
Differential Revision: http://reviews.llvm.org/D14983
llvm-svn: 254404
Re-enable shrink wrapping for PPC64 Little Endian.
One minor modification to PPCFrameLowering::findScratchRegister was necessary to handle fall-thru blocks (blocks with no terminator) correctly.
Tested with all LLVM test, clang tests, and the self-hosting build, with no problems found.
PHabricator: http://reviews.llvm.org/D14778
llvm-svn: 254314
The e500mc does not actually support the mfocrf instruction; update the
processor definitions to reflect that fact.
Patch by Tom Rix (with some test-case cleanup by me).
llvm-svn: 254064
The patch in http://reviews.llvm.org/D13745 is broken into four parts:
1. New interfaces without functional changes.
2. Use new interfaces in SelectionDAG, while in other passes treat probabilities
as weights.
3. Use new interfaces in all other passes.
4. Remove old interfaces.
This the second patch above. In this patch SelectionDAG starts to use
probability-based interfaces in MBB to add successors but other MC passes are
still using weight-based interfaces. Therefore, we need to maintain correct
weight list in MBB even when probability-based interfaces are used. This is
done by updating weight list in probability-based interfaces by treating the
numerator of probabilities as weights. This change affects many test cases
that check successor weight values. I will update those test cases once this
patch looks good to you.
Differential revision: http://reviews.llvm.org/D14361
llvm-svn: 253965
incorrect, as the chosen representative of the weak symbol may not live
with the code in question. Always indirect the access through the TOC
instead.
Patch by Kyle Butt!
llvm-svn: 253708
Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
These intrinsics currently have an explicit alignment argument which is
required to be a constant integer. It represents the alignment of the
source and dest, and so must be the minimum of those.
This change allows source and dest to each have their own alignments
by using the alignment attribute on their arguments. The alignment
argument itself is removed.
There are a few places in the code for which the code needs to be
checked by an expert as to whether using only src/dest alignment is
safe. For those places, they currently take the minimum of src/dest
alignments which matches the current behaviour.
For example, code which used to read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false)
will now read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false)
For out of tree owners, I was able to strip alignment from calls using sed by replacing:
(call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\)
with:
$1i1 false)
and similarly for memmove and memcpy.
I then added back in alignment to test cases which needed it.
A similar commit will be made to clang which actually has many differences in alignment as now
IRBuilder can generate different source/dest alignments on calls.
In IRBuilder itself, a new argument was added. Instead of calling:
CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false)
you now call
CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false)
There is a temporary class (IntegerAlignment) which takes the source alignment and rejects
implicit conversion from bool. This is to prevent isVolatile here from passing its default
parameter to the source alignment.
Note, changes in future can now be made to codegen. I didn't change anything here, but this
change should enable better memcpy code sequences.
Reviewed by Hal Finkel.
llvm-svn: 253511
Several backends have instructions to reverse the order of bits in an integer. Conceptually matching such patterns is similar to @llvm.bswap, and it was mentioned in http://reviews.llvm.org/D14234 that it would be best if these patterns were matched in InstCombine instead of reimplemented in every different target.
This patch introduces an intrinsic @llvm.bitreverse.i* that operates similarly to @llvm.bswap. For plumbing purposes there is also a new ISD node ISD::BITREVERSE, with simple expansion and promotion support.
The intention is that InstCombine's BSWAP detection logic will be extended to support BITREVERSE too, and @llvm.bitreverse intrinsics emitted (if the backend supports lowering it efficiently).
llvm-svn: 252878
This patch adds a pass for doing PowerPC peephole optimizations at the
MI level while the code is still in SSA form. This allows for easy
modifications to the instructions while depending on a subsequent pass
of DCE. Both passes are very fast due to the characteristics of SSA.
At this time, the only peepholes added are for cleaning up various
redundancies involving the XXPERMDI instruction. However, I would
expect this will be a useful place to add more peepholes for
inefficiencies generated during instruction selection. The pass is
placed after VSX swap optimization, as it is best to let that pass
remove unnecessary swaps before performing any remaining clean-ups.
The utility of these clean-ups are demonstrated by changes to four
existing test cases, all of which now have tighter expected code
generation. I've also added Eric Schweiz's bugpoint-reduced test from
PR25157, for which we now generate tight code. One other test started
failing for me, and I've fixed it
(test/Transforms/PlaceSafepoints/finite-loops.ll) as well; this is not
related to my changes, and I'm not sure why it works before and not
after. The problem is that the CHECK-NOT: of "statepoint" from test1
fails because of the "statepoint" in test2, and so forth. Adding a
CHECK-LABEL in between keeps the different occurrences of that string
properly scoped.
llvm-svn: 252651
Under most circumstances, if SCEV can simplify X-Y to a constant, then it can
also simplify Y-X to a constant. However, there is no guarantee that this is
always true, and concensus is not to consider that a correctness bug in SCEV
(although it is undesirable).
PPCLoopPreIncPrep gathers pointers used to access memory (via loads, stores and
prefetches) into buckets, where in each bucket the relative pointer offsets are
constant. We used to keep each bucket as a multimap, where SCEV's subtraction
operation was used to define the ordering predicate. Instead, use a fixed SCEV
base expression for each bucket, record the constant offsets from that base
expression, and adjust it later, if desirable, once all pointers have been
collected.
Doing it this way should be more compile-time efficient than the previous
scheme (in addition to making the implementation less sensitive to SCEV
simplification quirks).
Fixes PR25170.
llvm-svn: 252417
Previously, subprograms contained a metadata reference to the function they
described. Because most clients need to get or set a subprogram for a given
function rather than the other way around, this created unneeded inefficiency.
For example, many passes needed to call the function llvm::makeSubprogramMap()
to build a mapping from functions to subprograms, and the IR linker needed to
fix up function references in a way that caused quadratic complexity in the IR
linking phase of LTO.
This change reverses the direction of the edge by storing the subprogram as
function-level metadata and removing DISubprogram's function field.
Since this is an IR change, a bitcode upgrade has been provided.
Fixes PR23367. An upgrade script for textual IR for out-of-tree clients is
attached to the PR.
Differential Revision: http://reviews.llvm.org/D14265
llvm-svn: 252219
This revision has introduced an issue that only affects bootstrapped compiler
when it is printing the ASM. It turns out that the new code path taken due to
legalizing a scalar_to_vector of i64 -> v2i64 exposes a missing check in a
micro optimization to change a load followed by a scalar_to_vector into a
load and splat instruction on PPC.
llvm-svn: 251798
We cannot form ctr-based loops around function calls, including calls to
__tls_get_addr used for PIC TLS variables. References to such TLS variables,
however, might be buried within constant expressions, and so we need to search
the entire constant expression to be sure that no references to such TLS
variables exist.
Fixes PR25256, reported by Eric Schweitz. This is a slightly-modified version
of the patch suggested by Eric in the bug report, and a test case I created.
llvm-svn: 251582
As a follow-up to r251566, do the same for the other optionally-supported
register classes (mostly for vector registers). Don't return an unavailable
register class (which would cause an assert later), but fail cleanly when
provided an unsupported inline asm constraint.
llvm-svn: 251575
cntlz is the old POWER mnemonic. cntlzw is the PowerPC mnemonic.
This change fixes an issue when -no-integrated-as: The opcode cntlz is
unrecognized by gas
Alias the POWER mnemonic cntlz[.] to the PowerPC mnemonic cntlzw[.]
This is done for because the POWER cntlz mnemonic has be used by LLVM for
a very long time. We need to make sure that assembly programs
that are using the cntlz[.] do not break with this change.
Change PowerPC tests to reflect the insn change from cntlz to cntlzw.
Add assembly test to verify cntlz[.] is encoded correctly.
Patch by Tom Rix!
llvm-svn: 251489
Summary:
Don't call `computeKnownBitsFromRangeMetadata` for extended loads --
this can cause a mismatch between the width of the !range metadata and
the width of the APInt's accumulating `KnownZero` (and `KnownOne` in the
future). This isn't a problem now, but will be after a future change.
Note: this can be made more aggressive in the future.
Reviewers: nlewycky
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D14107
llvm-svn: 251486
Recommit r250342: move coal-sections-powerpc.s to subdirectory for powerpc.
Some background on why we don't have to use *coal* sections anymore:
Long ago when C++ was new and "weak" had not been standardized, an attempt was
made in cctools to support C++ inlines that can be coalesced by putting them
into their own section (TEXT/textcoal_nt instead of TEXT/text).
The current macho linker supports the weak-def bit on any symbol to allow it to
be coalesced, but the compiler still puts weak-def functions/data into alternate
section names, which the linker must map back to the base section name.
This patch makes changes that are necessary to prevent the compiler from using
the "coal" sections and have it use the non-coal sections instead when the
target architecture is not powerpc:
TEXT/textcoal_nt instead use TEXT/text
TEXT/const_coal instead use TEXT/const
DATA/datacoal_nt instead use DATA/data
If the target is powerpc, we continue to use the *coal* sections since anyone
targeting powerpc is probably using an old linker that doesn't have support for
the weak-def bits.
Also, have the assembler issue a warning if it encounters a *coal* section in
the assembly file and inform the users to use the non-coal sections instead.
rdar://problem/14265330
Differential Revision: http://reviews.llvm.org/D13188
llvm-svn: 250370
Recommit r250342: add -arch=ppc32 to the RUN lines of powerpc tests.
Some background on why we don't have to use *coal* sections anymore:
Long ago when C++ was new and "weak" had not been standardized, an attempt was
made in cctools to support C++ inlines that can be coalesced by putting them
into their own section (TEXT/textcoal_nt instead of TEXT/text).
The current macho linker supports the weak-def bit on any symbol to allow it to
be coalesced, but the compiler still puts weak-def functions/data into alternate
section names, which the linker must map back to the base section name.
This patch makes changes that are necessary to prevent the compiler from using
the "coal" sections and have it use the non-coal sections instead when the
target architecture is not powerpc:
TEXT/textcoal_nt instead use TEXT/text
TEXT/const_coal instead use TEXT/const
DATA/datacoal_nt instead use DATA/data
If the target is powerpc, we continue to use the *coal* sections since anyone
targeting powerpc is probably using an old linker that doesn't have support for
the weak-def bits.
Also, have the assembler issue a warning if it encounters a *coal* section in
the assembly file and inform the users to use the non-coal sections instead.
rdar://problem/14265330
Differential Revision: http://reviews.llvm.org/D13188
llvm-svn: 250349
Some background on why we don't have to use *coal* sections anymore:
Long ago when C++ was new and "weak" had not been standardized, an attempt was
made in cctools to support C++ inlines that can be coalesced by putting them
into their own section (TEXT/textcoal_nt instead of TEXT/text).
The current macho linker supports the weak-def bit on any symbol to allow it to
be coalesced, but the compiler still puts weak-def functions/data into alternate
section names, which the linker must map back to the base section name.
This patch makes changes that are necessary to prevent the compiler from using
the "coal" sections and have it use the non-coal sections instead when the
target architecture is not powerpc:
TEXT/textcoal_nt instead use TEXT/text
TEXT/const_coal instead use TEXT/const
DATA/datacoal_nt instead use DATA/data
If the target is powerpc, we continue to use the *coal* sections since anyone
targeting powerpc is probably using an old linker that doesn't have support for
the weak-def bits.
Also, have the assembler issue a warning if it encounters a *coal* section in
the assembly file and inform the users to use the non-coal sections instead.
rdar://problem/14265330
Differential Revision: http://reviews.llvm.org/D13188
llvm-svn: 250342
PR25157 identifies a bug where a load plus a vector shuffle is
incorrectly converted into an LXVDSX instruction. That optimization
is only valid if the load is of a doubleword, and in the noted case,
it was not. This corrects that problem.
Joint patch with Eric Schweitz, who provided the bugpoint-reduced test
case.
llvm-svn: 250324
This patch corresponds to review:
http://reviews.llvm.org/D12032
This patch builds onto the patch that provided scalar to vector conversions
without stack operations (D11471).
Included in this patch:
- Vector element extraction for all vector types with constant element number
- Vector element extraction for v16i8 and v8i16 with variable element number
- Removal of some unnecessary COPY_TO_REGCLASS operations that ended up
unnecessarily moving things around between registers
Not included in this patch (will be in upcoming patch):
- Vector element extraction for v4i32, v4f32, v2i64 and v2f64 with
variable element number
- Vector element insertion for variable/constant element number
Testing is provided for all extractions. The extractions that are not
implemented yet are just placeholders.
llvm-svn: 249822
When AA is being used, non-aliasing stores are canonicalized to use the same
chain, and DAGCombiner::getStoreMergeAndAliasCandidates can take advantage of
this by looking only as users of a store's chain operand. However, user
iteration is not result-number specific, we need to check that the use is as a
chain operand, and not via some other operand. It is certainly possible to have
another potentially-aliasing store, which shares the first's base pointer, and
uses the first's chain's node via some other operand.
Failure to catch this situation caused, at least in the included test case, an
assert later because the relative sequence-number ordering caused later
replacement to create a cycle in the DAG.
llvm-svn: 248698
The algorithm would not modify the live-in list of blocks below the save
block point which is correct unless it happens to be a restore point at
the same time.
Also fixes the benign issue of live-in registers being added twice in
some cases.
The testcase is based on a test submitted by Kit Barton.
Differential Revision: http://reviews.llvm.org/D13176
llvm-svn: 248620
If storing multiple FP constants, some subset of the stores
would be replaced with integers due to visit order, so
MergeConsecutiveStores would only partially merge
these.
llvm-svn: 248169
- Strenghten the logic to be sure we hoist the restore point out of the current
loop. (The fixes a bug with infinite loop, added as part of the patch.)
- Walk over the exit blocks of the current loop to conver to the desired restore
point in one iteration of the update loop.
llvm-svn: 247958
When building LLVM as a (potentially dynamic) library that can be linked against
by multiple compilers, the default triple is not really meaningful.
We allow to explicitely set it to an empty string when configuring LLVM.
In this case, said "target independent" tests in the test suite that are using
the default triple are disabled by matching the newly available feature
"default_triple".
Reviewers: probinson, echristo
Differential Revision: http://reviews.llvm.org/D12660
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 247775
The changes in this patch are as follows:
1. Modify the emitPrologue and emitEpilogue methods to work properly when the prologue and epilogue blocks are not the first/last blocks in the function
2. Fix a bug in PPCEarlyReturn optimization caused by an empty entry block in the function
3. Override the runShrinkWrap PredicateFtor (defined in TargetMachine) to check whether shrink wrapping should run:
Shrink wrapping will run on PPC64 (Little Endian and Big Endian) unless -enable-shrink-wrap=false is specified on command line
A new test case, ppc-shrink-wrapping.ll was created based on the existing shrink wrapping tests for x86, arm, and arm64.
Phabricator review: http://reviews.llvm.org/D11817
llvm-svn: 247237
To commute a trivial rlwimi instructions (meaning one with a full mask and zero
shift), we'd need to ability to form an all-zero mask (instead of an all-one
mask) using rlwimi. We can't represent this, however, and we'll miscompile code
if we try.
The code quality problem that this highlights (that SDAG simplification can
lead to us generating an ISD::OR node with a constant zero LHS) will be fixed
as a follow-up.
Fixes PR24719.
llvm-svn: 246937
PPCISelDAGToDAG has a transformation that generates a rlwimi instruction from
an input pattern that looks like this:
and(or(x, c1), c2)
but the associated logic does not work if there are bits that are 1 in c1 but 0
in c2 (these are normally canonicalized away, but that can't happen if the 'or'
has other users. Make sure we abort the transformation if such bits are
discovered.
Fixes PR24704.
llvm-svn: 246900
When forming permutation-based unaligned vector loads, we need to know whether
it is valid to read ahead of the requested address by a full vector length.
Doing so is more efficient (and allows for more CSE with later loads), but
could trigger a page fault if invalid. To determine validity, we look for other
loads in the same block that access the relevant address range.
The relevant point here is that we need to do this as part of the process of
forming permutation-based vector loads, and this happens quite early in the
SDAG pipeline - specifically before many of the address calculations are fully
canonicalized. As a result, we need to try harder to recognize base+offset
address computations, because they still might appear as chain of adds
(base+offset+offset, for example). To account for this, we'll look through
chains of adds, accumulating the constant offsets.
llvm-svn: 246813
If you compute the MMO offset using unsigned arithmetic, you end up with a
large positive offset instead of a small negative one. In theory, this could
cause bad instruction-scheduling decisions later.
I noticed this by inspection from the debug output, and using that for the
regression test is the best I can do right now.
llvm-svn: 246805
I'm adding a regression test to better cover code generation for unaligned
vector loads and stores, but there's no functional change to the code
generation here. There is an improvement to the cost model for unaligned vector
loads and stores, mostly for QPX (for which we were not previously accounting
for the permutation-based loads), and the cost model implementation is cleaner.
llvm-svn: 246712
LowerVECTOR_SHUFFLE needs to decide whether to pass a vector shuffle off to the
TableGen-generated matching code, and it does this by testing the same
predicates used by the TableGen files. Unfortunately, when we added new
P8Altivec-only predicates, we started universally testing them in
LowerVECTOR_SHUFFLE, and if then matched when targeting a system prior to a P8,
we'd end up with a selection failure.
llvm-svn: 246675
SETCC is one of those special node types for which operation actions (legality,
etc.) is keyed off of an operand type, not the node's value type. This makes
sense because the value type of a legal SETCC node is determined by its
operands' value type (via the TLI function getSetCCResultType). When the
SDAGBuilder creates SETCC nodes, it either creates them with an MVT::i1 value
type, or directly with the value type provided by TLI.getSetCCResultType.
The first problem being fixed here is that DAGCombine had several places
querying TLI.isOperationLegal on SETCC, but providing the return of
getSetCCResultType, instead of the operand type directly. This does not mean
what the author thought, and "luckily", most in-tree targets have SETCC with
Custom lowering, instead of marking them Legal, so these checks return false
anyway.
The second problem being fixed here is that two of the DAGCombines could create
SETCC nodes with arbitrary (integer) value types; specifically, those that
would simplify:
(setcc a, b, op1) and|or (setcc a, b, op2) -> setcc a, b, op3
(which is possible for some combinations of (op1, op2))
If the operands of the and|or node are actual setcc nodes, then this is not an
issue (because the and|or must share the same type), but, the relevant code in
DAGCombiner::visitANDLike and DAGCombiner::visitORLike actually calls
DAGCombiner::isSetCCEquivalent on each operand, and that function will
recognise setcc-like select_cc nodes with other return types. And, thus, when
creating new SETCC nodes, we need to be careful to respect the value-type
constraint. This is even true before type legalization, because it is quite
possible for the SELECT_CC node to have a legal type that does not happen to
match the corresponding TLI.getSetCCResultType type.
To be explicit, there is nothing that later fixes the value types of SETCC
nodes (if the type is legal, but does not happen to match
TLI.getSetCCResultType). Creating SETCCs with an MVT::i1 value type seems to
work only because, either MVT::i1 is not legal, or it is what
TLI.getSetCCResultType returns if it is legal. Fixing that is a larger change,
however. For the time being, restrict the relevant transformations to produce
only SETCC nodes with a value type matching TLI.getSetCCResultType (or MVT::i1
prior to type legalization).
Fixes PR24636.
llvm-svn: 246507
AggressiveAntiDepBreaker was doing some EarlyClobber checking, but was not
checking that the register being potentially renamed was defined by an
early-clobber def where there was also a use, in that instruction, of the
register being considered as the target of the rename. Fixes PR24014.
llvm-svn: 246423
There were really two problems here. The first was that we had the truth tables
for signed i1 comparisons backward. I imagine these are not very common, but if
you have:
setcc i1 x, y, LT
this has the '0 1' and the '1 0' results flipped compared to:
setcc i1 x, y, ULT
because, in the signed case, '1 0' is really '-1 0', and the answer is not the
same as in the unsigned case.
The second problem was that we did not have patterns (at all) for the unsigned
comparisons select_cc nodes for i1 comparison operands. This was the specific
cause of PR24552. These had to be added (and a missing Altivec promotion added
as well) to make sure these function for all types. I've added a bunch more
test cases for these patterns, and there are a few FIXMEs in the test case
regarding code-quality.
Fixes PR24552.
llvm-svn: 246400
Add support for MIR serialization of PowerPC-specific operand target flags
(based on the generic infrastructure added in r244185 and r245383).
I won't even pretend that this is good test coverage, but this includes the
regression test associated with r246372. Adding an MIR test for that fix is far
superior to adding an IR-level test because particular instruction-scheduling
decisions are necessary in order to expose the bug, and using an MIR test we
can start the pipeline post-scheduling.
llvm-svn: 246373
As a follow-up to r246098, require `DISubprogram` definitions
(`isDefinition: true`) to be 'distinct'. Specifically, add an assembler
check, a verifier check, and bitcode upgrading logic to combat testcase
bitrot after the `DIBuilder` change.
While working on the testcases, I realized that
test/Linker/subprogram-linkonce-weak-odr.ll isn't relevant anymore. Its
purpose was to check for a corner case in PR22792 where two subprogram
definitions match exactly and share the same metadata node. The new
verifier check, requiring that subprogram definitions are 'distinct',
precludes that possibility.
I updated almost all the IR with the following script:
git grep -l -E -e '= !DISubprogram\(.* isDefinition: true' |
grep -v test/Bitcode |
xargs sed -i '' -e 's/= \(!DISubprogram(.*, isDefinition: true\)/= distinct \1/'
Likely some variant of would work for out-of-tree testcases.
llvm-svn: 246327
When combiner AA is enabled, look at stores on the same chain.
Non-aliasing stores are moved to the same chain so the existing
code fails because it expects to find an adajcent store on a consecutive
chain.
Because of how DAGCombiner tries these store combines,
MergeConsecutiveStores doesn't see the correct set of stores on the chain
when it visits the other stores. Each store individually has its chain
fixed before trying to merge consecutive stores, and then tries to merge
stores from that point before the other stores have been processed to
have their chains fixed. To fix this, attempt to use FindBetterChain
on any possibly neighboring stores in visitSTORE.
Suppose you have 4 32-bit stores that should be merged into 1 vector
store. One store would be visited first, fixing the chain. What happens is
because not all of the store chains have yet been fixed, 2 of the stores
are merged. The other 2 stores later have their chains fixed,
but because the other stores were already merged, they have different
memory types and merging the two different sized stores is not
supported and would be more difficult to handle.
llvm-svn: 246307
We might end up with a trivial copy as the addend, and if so, we should ignore
the corresponding FMA instruction. The trivial copy can be coalesced away later,
so there's nothing to do here. We should not, however, assert. Fixes PR24544.
llvm-svn: 245907
This patch fixes PR24546, which demonstrates a segfault during the VSX
swap removal pass. The problem is that debug value instructions were
not excluded from the list of instructions to be analyzed for webs of
related computation. I've added the test case from the PR as a crash
test in test/CodeGen/PowerPC.
llvm-svn: 245862
When PPCVSXFMAMutate would look at the input addend register, it would get its
input value number. This would fail, however, if the register was undef,
causing a segfault. Don't segfault (just skip such FMA instructions).
Fixes the test case from PR24542 (although that may have been over-reduced).
llvm-svn: 245741
XVCMPEQDP is used for VSX v2f64 equality comparisons, but the value type needs
to be v2i64 (as that's the corresponding SETCC type).
Fixes PR24225.
llvm-svn: 245535
This DAGCombine was creating custom SDAG nodes with an illegal ppc_fp128
operand type because it was triggering on f64/f32 int2fp(fp2int(ppc_fp128 x)),
but shouldn't (it should only apply to f32/f64 types). The result was a crash.
llvm-svn: 245530
This revision has introduced an issue that only affects bootstrapped compiler
when it is printing the ASM. I am working on resolving the issue, but in the
meantime, I'm disabling the legalization of scalar_to_vector operation for v2i64
and the associated testing until I can get this fixed.
llvm-svn: 245481
This patch corresponds to review:
http://reviews.llvm.org/D11471
It improves the code generated for converting a scalar to a vector value. With
direct moves from GPRs to VSRs, we no longer require expensive stack operations
for this. Subsequent patches will handle the reverse case and more general
operations between vectors and their scalar elements.
llvm-svn: 244921
frame setup instruction.
This commit ensures that the stack map lowering code in FastISel adds an
appropriate number of immediate operands to the frame setup instruction.
The previous code added just one immediate operand, which was fine for a target
like AArch64, but on X86 the ADJCALLSTACKDOWN64 instruction needs two explicit
operands. This caused the machine verifier to report an error when the old code
added just one.
Reviewers: Juergen Ributzka
Differential Revision: http://reviews.llvm.org/D11853
llvm-svn: 244508
I looked into adding a warning / error for this to FileCheck, but there doesn't
seem to be a good way to avoid it triggering on the instances of it in RUN lines.
llvm-svn: 244481
In r242277, I updated the MachineCombiner to work with itineraries, but I
missed a call that is scheduling-model-only (the opcode-only form of
computeInstrLatency). Using the form that takes an MI* allows this to work with
itineraries (and should be NFC for subtargets with scheduling models).
llvm-svn: 244020
Since r241097, `DIBuilder` has only created distinct `DICompileUnit`s.
The backend is liable to start relying on that (if it hasn't already),
so make uniquable `DICompileUnit`s illegal and automatically upgrade old
bitcode. This is a nice cleanup, since we can remove an unnecessary
`DenseSet` (and the associated uniquing info) from `LLVMContextImpl`.
Almost all the testcases were updated with this script:
git grep -e '= !DICompileUnit' -l -- test |
grep -v test/Bitcode |
xargs sed -i '' -e 's,= !DICompileUnit,= distinct !DICompileUnit,'
I imagine something similar should work for out-of-tree testcases.
llvm-svn: 243885
Remove the fake `DW_TAG_auto_variable` and `DW_TAG_arg_variable` tags,
using `DW_TAG_variable` in their place Stop exposing the `tag:` field at
all in the assembly format for `DILocalVariable`.
Most of the testcase updates were generated by the following sed script:
find test/ -name "*.ll" -o -name "*.mir" |
xargs grep -l 'DILocalVariable' |
xargs sed -i '' \
-e 's/tag: DW_TAG_arg_variable, //' \
-e 's/tag: DW_TAG_auto_variable, //'
There were only a handful of tests in `test/Assembly` that I needed to
update by hand.
(Note: a follow-up could change `DILocalVariable::DILocalVariable()` to
set the tag to `DW_TAG_formal_parameter` instead of `DW_TAG_variable`
(as appropriate), instead of having that logic magically in the backend
in `DbgVariable`. I've added a FIXME to that effect.)
llvm-svn: 243774
Given certain shuffle-vector masks, LLVM emits splat instructions
which splat the wrong bytes from the source register. The issue is
that the function PPC::isSplatShuffleMask() in PPCISelLowering.cpp
does not ensure that the splat pattern found is requesting bytes that
are aligned on an EltSize boundary. This patch detects this situation
as not a valid splat mask, resulting in a permute being generated
instead of a splat.
Patch and test case by Tyler Kenney, cleaned up a bit by me.
This is a simple bug fix that would be good to incorporate into 3.7.
llvm-svn: 243519
extension property we're requesting - zero or sign extended.
This fixes cases where we want to return a zero extended 32-bit -1
and not be sign extended for the entire register. Also updated the
already out of date comment with the current behavior.
llvm-svn: 243192
This makes one substantive change and a few stylistic changes to the
VSX swap optimization pass.
The substantive change is to permit LXSDX and LXSSPX instructions to
participate in swap optimization computations. The previous change to
insert a swap following a SUBREG_TO_REG widening operation makes this
almost trivial.
I experimented with also permitting STXSDX and STXSSPX instructions.
This can be done using similar techniques: we could insert a swap
prior to a narrowing COPY operation, and then permit these stores to
participate. I prototyped this, but discovered that the pattern of a
narrowing COPY followed by an STXSDX does not occur in any of our
test-suite code. So instead, I added commentary indicating that this
could be done.
Other TLC:
- I changed SH_COPYSCALAR to SH_COPYWIDEN to more clearly indicate
the direction of the copy.
- I factored the insertion of swap instructions into a separate
function.
Finally, I added a new test case to check that the scalar-to-vector
loads are working properly with swap optimization.
llvm-svn: 242838
I was looking at some vector code generation and kept seeing
unnecessary vector copies into the Altivec half of the VSX registers.
I discovered that we overlooked v4i32 when adding the register classes
for VSX; we only added v4f32 and v2f64. This means that anything that
canonicalizes into v4i32 (which is a LOT of stuff) ends up being
forced into VRRC on its way to VSRC.
The fix is one line. The rest of the patch is fixing up some test
cases whose code generation has changed as a result.
This seems like it would be a good candidate for backport to 3.7.
llvm-svn: 242442
This is a direct port of the code from the X86 backend (r239486/r240361), which
uses the MachineCombiner to reassociate (floating-point) adds/muls to increase
ILP, to the PowerPC backend. The rationale is the same.
There is a lot of copy-and-paste here between the X86 code and the PowerPC
code, and we should extract at least some of this into CodeGen somewhere.
However, I don't want to do that until this code is enhanced to handle FMAs as
well. After that, we'll be in a better position to extract the common parts.
llvm-svn: 242279
Follow-up r235483, with the corresponding support in PPC. We use a regular call
for symbolic targets (because they're much cheaper than indirect calls).
llvm-svn: 242239
We used to take the address specified as the direct target of the patchpoint
and did no TOC-pointer handling. This, however, as not all that useful,
because MCJIT tends to create a lot of modules, and they have their own TOC
sections. Thus, to call from the generated code to other generated code, you
really need to switch TOC pointers. Make this work as expected, and under
ELFv1, tread the address as the function descriptor address so that the correct
TOC pointer can be loaded.
llvm-svn: 242217
PowerPC uses itineraries to describe processor pipelines (and dispatch-group
restrictions for P7/P8 cores). Unfortunately, the target-independent
implementation of TII.getInstrLatency calls ItinData->getStageLatency, and that
looks for the largest cycle count in the pipeline for any given instruction.
This, however, yields the wrong answer for the PPC itineraries, because we
don't encode the full pipeline. Because the functional units are fully
pipelined, we only model the initial stages (there are no relevant hazards in
the later stages to model), and so the technique employed by getStageLatency
does not really work. Instead, we should take the maximum output operand
latency, and that's what PPCInstrInfo::getInstrLatency now does.
This caused some test-case churn, including two unfortunate side effects.
First, the new arrangement of copies we get from function parameters now
sometimes blocks VSX FMA mutation (a FIXME has been added to the code and the
test cases), and we have one significant test-suite regression:
SingleSource/Benchmarks/BenchmarkGame/spectral-norm
56.4185% +/- 18.9398%
In this benchmark we have a loop with a vectorized FP divide, and it with the
new scheduling both divides end up in the same dispatch group (which in this
case seems to cause a problem, although why is not exactly clear). The grouping
structure is hard to predict from the bottom of the loop, and there may not be
much we can do to fix this.
Very few other test-suite performance effects were really significant, but
almost all weakly favor this change. However, in light of the issues
highlighted above, I've left the old behavior available via a
command-line flag.
llvm-svn: 242188
This patch allows VSX swap optimization to succeed more frequently.
Specifically, it is concerned with common code sequences that occur
when copying a scalar floating-point value to a vector register. This
patch currently handles cases where the floating-point value is
already in a register, but does not yet handle loads (such as via an
LXSDX scalar floating-point VSX load). That will be dealt with later.
A typical case is when a scalar value comes in as a floating-point
parameter. The value is copied into a virtual VSFRC register, and
then a sequence of SUBREG_TO_REG and/or COPY operations will convert
it to a full vector register of the class required by the context. If
this vector register is then used as part of a lane-permuted
computation, the original scalar value will be in the wrong lane. We
can fix this by adding a swap operation following any widening
SUBREG_TO_REG operation. Additional COPY operations may be needed
around the swap operation in order to keep register assignment happy,
but these are pro forma operations that will be removed by coalescing.
If a scalar value is otherwise directly referenced in a computation
(such as by one of the many XS* vector-scalar operations), we
currently disable swap optimization. These operations are
lane-sensitive by definition. A MentionsPartialVR flag is added for
use in each swap table entry that mentions a scalar floating-point
register without having special handling defined.
A common idiom for PPC64LE is to convert a double-precision scalar to
a vector by performing a splat operation. This ensures that the value
can be referenced as V[0], as it would be for big endian, whereas just
converting the scalar to a vector with a SUBREG_TO_REG operation
leaves this value only in V[1]. A doubleword splat operation is one
form of an XXPERMDI instruction, which takes one doubleword from a
first operand and another doubleword from a second operand, with a
two-bit selector operand indicating which doublewords are chosen. In
the general case, an XXPERMDI can be permitted in a lane-swapped
region provided that it is properly transformed to select the
corresponding swapped values. This transformation is to reverse the
order of the two input operands, and to reverse and complement the
bits of the selector operand (derivation left as an exercise to the
reader ;).
A new test case that exercises the scalar-to-vector and generalized
XXPERMDI transformations is added as CodeGen/PowerPC/swaps-le-5.ll.
The patch also requires a change to CodeGen/PowerPC/swaps-le-3.ll to
use CHECK-DAG instead of CHECK for two independent instructions that
now appear in reverse order.
There are two small unrelated changes that are added with this patch.
First, the XXSLDWI instruction was incorrectly omitted from the list
of lane-sensitive instructions; this is now fixed. Second, I observed
that the same webs were being rejected over and over again for
different reasons. Since it's sufficient to reject a web only once, I
added a check for this to speed up the compilation time slightly.
llvm-svn: 242081
r238842 added the TargetRecip system for controlling use of reciprocal
estimates for sqrt and division using a set of parameters that can be set by
the frontend. Clang now supports a sophisticated -mrecip option, and this will
allow that option to effectively control the relevant code-generation
functionality of the PPC backend.
llvm-svn: 241985
This adds support for the 'nest' attribute, which allows the static chain
register to be set for functions calls under non-Darwin PPC/PPC64 targets. r11
is the chain register (which the PPC64 ELF ABI calls the "environment
pointer"). For indirect calls under PPC64 ELFv1, this would normally be loaded
from the function descriptor, but providing an explicit 'nest' parameter will
override that process and use the value provided.
This allows __builtin_call_with_static_chain to work as expected on PowerPC.
llvm-svn: 241984
In r241285, I removed the SUBREG_TO_REG restriction from VSX swap
removal, determining that this was overly conservative. We have
another form of the same restriction in that we check for the presence
of implicit subregs in vector operations. As with SUBREG_TO_REG for
partial register conversions, an implicit subreg is safe in and of
itself, provided no other operation makes a lane-sensitive assumption
about the result. This patch removes that restriction, by removing
the HasImplicitSubreg flag and all code that relies on it.
I've added a test case that fails to optimize before this patch is
applied, and optimizes properly with the patch. Test based on a
report from Anton Blanchard.
llvm-svn: 241290
With a previous patch, the VSX swap optimization is able to recognize
the doubleword load-splat idiom that can be implemented using lxvdsx.
However, that does not cover a doubleword splat where the source is a
register. We can implement this using xxspltd (a special form of
xxpermdi). This patch teaches the swap optimization pass about this
idiom.
As a prerequisite, it also permits swap optimization to succeed for
all forms of SUBREG_TO_REG. Previously we were conservative and only
allowed SUBREG_TO_REG when it copied a full register. However, on
reflection any form of SUBREG_TO_REG is safe in and of itself, so long
as an unsafe operation is not performed on its result. In particular,
a widening SUBREG_TO_REG often occurs as an input to a doubleword
splat idiom, particularly in auto-vectorized code.
The doubleword splat idiom is an XXPERMDI operation where both source
registers are identical, and the selection mask is either 0 (splat the
first element) or 3 (splat the second element). To determine whether
the registers are identical, we use the existing mechanism for looking
through "copy-like" operations. That mechanism has a side effect of
marking the XXPERMDI operation as using a physical register, which
would invalidate its presence in a swap-optimized region. This is
correct for the form of XXPERMDI that performs a swap and hence would
be removed, but is not what we want for a doubleword-splat variety of
XXPERMDI. Therefore we reset the physical-register flag on the
XXPERMDI when it represents a splat.
A simple test case is added to verify that we generate the splat and
that we also remove the xxswapd instructions that would otherwise be
associated with the load and store of another operand.
llvm-svn: 241285
When adding little-endian vector support for PowerPC last year, I
inadvertently disabled an optimization that recognizes a load-splat
idiom and generates the lxvdsx instruction. This patch moves the
offending logic so lxvdsx is once again generated.
This pattern is frequently generated by the vectorizer for scalar
loads of an effective constant. Previously the lxvdsx instruction was
wrongly listed as lane-sensitive for the VSX swap optimization (since
both doublewords are identical, swaps are safe). This patch fixes
this as well, so that vectorized code using lxvdsx can now have swaps
removed from the computation.
There is an existing test (@test50) in test/CodeGen/PowerPC/vsx.ll
that checks for the missing optimization. However, vsx.ll was only
being tested for POWER7 with big-endian code generation. I've added
a little-endian RUN statement and expected LE code generation for all
the tests in vsx.ll to give us a bit better VSX coverage, including
what's needed for this patch.
llvm-svn: 241183
This patch corresponds to review:
http://reviews.llvm.org/D10638
This is the back end portion of patch
http://reviews.llvm.org/D10637
It just adds the code gen and intrinsic functions necessary to support that patch to the back end.
llvm-svn: 240820
This patch adds support for the vector merge even word and vector merge odd word
instructions introduced in POWER8.
Phabricator review: http://reviews.llvm.org/D10704
llvm-svn: 240650
In a relocation target can take 3 basic forms
* A r_value in scattered relocations.
* A symbol in external relocations.
* A section is non-external relocations.
Have the dump reflect that. With this change we go from
CHECK-NEXT: Extern: 0
CHECK-NEXT: Type: X86_64_RELOC_SUBTRACTOR (5)
CHECK-NEXT: Symbol: 0x2
CHECK-NEXT: Scattered: 0
To just
// CHECK-NEXT: Type: X86_64_RELOC_SUBTRACTOR (5)
// CHECK-NEXT: Section: __data (2)
Since the relocation is with a section, we print the seciton name and don't
need to say that it is not scattered or external.
Someone motivated can add further special cases for things like
ARM64_RELOC_ADDEND and ARM_RELOC_PAIR.
llvm-svn: 240073
The personality routine currently lives in the LandingPadInst.
This isn't desirable because:
- All LandingPadInsts in the same function must have the same
personality routine. This means that each LandingPadInst beyond the
first has an operand which produces no additional information.
- There is ongoing work to introduce EH IR constructs other than
LandingPadInst. Moving the personality routine off of any one
particular Instruction and onto the parent function seems a lot better
than have N different places a personality function can sneak onto an
exceptional function.
Differential Revision: http://reviews.llvm.org/D10429
llvm-svn: 239940
The mftb instruction was incorrectly marked as deprecated in the PPC
Backend. Instead, it should not be treated as deprecated, but rather be
implemented using the mfspr instruction. A similar patch was put into GCC last
year. Details can be found at:
https://sourceware.org/ml/binutils/2014-11/msg00383.html.
This change will replace instances of the mftb instruction with the mfspr
instruction for all CPUs except 601 and pwr3. This will also be the default
behaviour.
Additional details can be found in:
https://llvm.org/bugs/show_bug.cgi?id=23680
Phabricator review: http://reviews.llvm.org/D10419
llvm-svn: 239827
This patch corresponds to review:
http://reviews.llvm.org/D10096
This is the back end portion of the patch related to D10095.
The patch adds the instructions and back end intrinsics for:
vbpermq
vgbbd
llvm-svn: 239505
This patch corresponds to review:
http://reviews.llvm.org/D9941
It adds the various FMA instructions introduced in the version 2.07 of
the ISA along with the testing for them. These are operations on single
precision scalar values in VSX registers.
llvm-svn: 238578
in POWER8:
vadduqm
vaddeuqm
vaddcuq
vaddecuq
vsubuqm
vsubeuqm
vsubcuq
vsubecuq
In addition to adding the instructions themselves, it also adds support for the
v1i128 type for intrinsics (Intrinsics.td, Function.cpp, and
IntrinsicEmitter.cpp).
http://reviews.llvm.org/D9081
llvm-svn: 238144
When the compare feeding a branch was in a different BB from the branch, we'd
try to "regenerate" the compare in the block with the branch, possibly trying
to make use of values not available there. Copy a page from AArch64's play book
here to fix the problem (at least in terms of correctness).
Fixes PR23640.
llvm-svn: 238097
My recent patch to add support for ISA 2.07 vector pack/unpack
instructions didn't properly check for availability of the vpkudum
instruction when recognizing it as a special vector shuffle case.
This causes us to leave the vector shuffle in place (rather than
converting it to a vector permute) so that it can be recognized later
as a vpkudum, but that pattern is invalid for processors prior to
POWER8. Thus LLVM crashes with an "unable to select" message. We
observed this since one of our buildbots is configured to generate
code for a POWER7.
This patch fixes the problem by checking for availability of the
vpkudum instruction during custom lowering of vector shuffles.
I've added a test case variant for the vpkudum pattern when the
instruction isn't available.
llvm-svn: 237952
http://reviews.llvm.org/D9891
Following up on the VSX single precision loads and stores added earlier, this
adds support for elementary arithmetic operations on single precision values
in VSX registers. These instructions utilize the new VSSRC register class.
Instructions added:
xsaddsp
xsdivsp
xsmulsp
xsresp
xsrsqrtesp
xssqrtsp
xssubsp
llvm-svn: 237937
If some commits are happy, and some commits are sad, this is a sad commit. It
is sad because it restricts instruction scheduling to work around a binutils
linker bug, and moreover, one that may never be fixed. On 2012-05-21, GCC was
updated not to produce code triggering this bug, and now we'll do the same...
When resolving an address using the ELF ABI TOC pointer, two relocations are
generally required: one for the high part and one for the low part. Only
the high part generally explicitly depends on r2 (the TOC pointer). And, so,
we might produce code like this:
.Ltmp526:
addis 3, 2, .LC12@toc@ha
.Ltmp1628:
std 2, 40(1)
ld 5, 0(27)
ld 2, 8(27)
ld 11, 16(27)
ld 3, .LC12@toc@l(3)
rldicl 4, 4, 0, 32
mtctr 5
bctrl
ld 2, 40(1)
And there is nothing wrong with this code, as such, but there is a linker bug
in binutils (https://sourceware.org/bugzilla/show_bug.cgi?id=18414) that will
misoptimize this code sequence to this:
nop
std r2,40(r1)
ld r5,0(r27)
ld r2,8(r27)
ld r11,16(r27)
ld r3,-32472(r2)
clrldi r4,r4,32
mtctr r5
bctrl
ld r2,40(r1)
because the linker does not know (and does not check) that the value in r2
changed in between the instruction using the .LC12@toc@ha (TOC-relative)
relocation and the instruction using the .LC12@toc@l(3) relocation.
Because it finds these instructions using the relocations (and not by
scanning the instructions), it has been asserted that there is no good way
to detect the change of r2 in between. As a result, this bug may never be
fixed (i.e. it may become part of the definition of the ABI). GCC was
updated to add extra dependencies on r2 to instructions using the @toc@l
relocations to avoid this problem, and we'll do the same here.
This is done as a separate pass because:
1. These extra r2 dependencies are not really properties of the
instructions, but rather due to a linker bug, and maybe one day we'll be
able to get rid of them when targeting linkers without this bug (and,
thus, keeping the logic centralized here will make that
straightforward).
2. There are ISel-level peephole optimizations that propagate the @toc@l
relocations to some user instructions, and so the exta dependencies do
not apply only to a fixed set of instructions (without undesirable
definition replication).
The test case was reduced with the help of bugpoint, with minimal cleaning. I'm
looking forward to our upcoming MI serialization support, and with that, much
better tests can be created.
llvm-svn: 237556
This patch adds support for the following new instructions in the
Power ISA 2.07:
vpksdss
vpksdus
vpkudus
vpkudum
vupkhsw
vupklsw
These instructions are available through the vec_packs, vec_packsu,
vec_unpackh, and vec_unpackl built-in interfaces. These are
lane-sensitive instructions, so the built-ins have different
implementations for big- and little-endian, and the instructions must
be marked as killing the vector swap optimization for now.
The first three instructions perform saturating pack operations. The
fourth performs a modulo pack operation, which means it can be
represented with a vector shuffle, and conversely the appropriate
vector shuffles may cause this instruction to be generated. The other
instructions are only generated via built-in support for now.
Appropriate tests have been added.
There is a companion patch to clang for the rest of this support.
llvm-svn: 237499
1) check whether the alignment of the memory is sufficient for the
*merged* store or load to be efficient.
Not doing so can result in some ridiculously poor code generation, if
merging creates a vector operation which must be aligned but isn't.
2) DON'T check that the alignment of each load/store is equal. If
you're merging 2 4-byte stores, the first *might* have 8-byte
alignment, but the second certainly will have 4-byte alignment. We do
want to allow those to be merged.
llvm-svn: 236850
This patch corresponds to review:
http://reviews.llvm.org/D9440
It adds a new register class to the PPC back end to contain single precision
values in VSX registers. Additionally, it adds scalar loads and stores for
VSX registers.
llvm-svn: 236755
The initial code drop for VSX swap optimization permitted the
optimization only when all operations in a web of related computation
are lane-insensitive. For some lane-sensitive operations, we can
still permit the optimization provided that we make adjustments to
those operations. This patch adds special handling for vector splats
so that their presence doesn't kill the optimization.
Vector splats are lane-sensitive since they identify by number a
vector element to be used as the source of a splat. When swap
optimizations take place, the desired vector element will move to the
opposite doubleword of the quadword vector. We thus replace the index
I by (I + N/2) % N, where N is the number of elements in the vector.
A new test case is added to test that swap optimization succeeds when
vector splats are present, and that the proper input element is used
as the source of the splat.
An ancillary change removes SH_BUILDVEC as one of the kinds of special
handling that may be required by VSX swap optimization. From
experience with GCC, I had expected to need some modifications for
vector build operations, but I did not find that to be the case.
llvm-svn: 236606
It adds v1i128 to the appropriate register classes and checks parameter passing
and return values.
This is related to http://reviews.llvm.org/D9081, which will add instructions
that exploit the v1i128 datatype.
Phabricator review: http://reviews.llvm.org/D9475
llvm-svn: 236503
Finish off PR23080 by renaming the debug info IR constructs from `MD*`
to `DI*`. The last of the `DIDescriptor` classes were deleted in
r235356, and the last of the related typedefs removed in r235413, so
this has all baked for about a week.
Note: If you have out-of-tree code (like a frontend), I recommend that
you get everything compiling and tests passing with the *previous*
commit before updating to this one. It'll be easier to keep track of
what code is using the `DIDescriptor` hierarchy and what you've already
updated, and I think you're extremely unlikely to insert bugs. YMMV of
course.
Back to *this* commit: I did this using the rename-md-di-nodes.sh
upgrade script I've attached to PR23080 (both code and testcases) and
filtered through clang-format-diff.py. I edited the tests for
test/Assembler/invalid-generic-debug-node-*.ll by hand since the columns
were off-by-three. It should work on your out-of-tree testcases (and
code, if you've followed the advice in the previous paragraph).
Some of the tests are in badly named files now (e.g.,
test/Assembler/invalid-mdcompositetype-missing-tag.ll should be
'dicompositetype'); I'll come back and move the files in a follow-up
commit.
llvm-svn: 236120
This patch adds a new SSA MI pass that runs on little-endian PPC64
code with VSX enabled. Loads and stores of 4x32 and 2x64 vectors
without alignment constraints are accomplished for little-endian using
lxvd2x/xxswapd and xxswapd/stxvd2x. The existence of the additional
xxswapd instructions hurts performance in comparison with big-endian
code, but they are necessary in the general case to support correct
semantics.
However, the general case does not apply to most vector code. Many
vector instructions are lane-insensitive; they do not "care" which
lanes the parallel computations are performed within, provided that
the resulting data is stored into the correct locations. Thus this
pass looks for computations that perform only lane-insensitive
operations, and remove the unnecessary swaps from loads and stores in
such computations.
Future improvements will allow computations using certain
lane-sensitive operations to also be optimized in this manner, by
modifying the lane-sensitive operations to account for the permuted
order of the lanes. However, this patch only adds the infrastructure
to permit this; no lane-sensitive operations are optimized at this
time.
This code is heavily exercised by the various vectorizing applications
in the projects/test-suite tree. For the time being, I have only added
one simple test case to demonstrate what the pass is doing. Although
it is quite simple, it provides coverage for much of the code,
including the special case handling of copies and subreg-to-reg
operations feeding the swaps. I plan to add additional tests in the
future as I fill in more of the "special handling" code.
Two existing tests were affected, because they expected the swaps to
be present, but they are now removed.
llvm-svn: 235910
TableGen had been nicely generating code to print a number of instructions using
shorter aliases (and PowerPC has plenty of short mnemonics), but we were not
calling it. For some of the aliases we support in the parser, TableGen can't
infer the "inverse" alias relationship, so there is still more to do.
Thus, after some hours of updating test cases...
llvm-svn: 235616
Third time's the charm. The previous commit was reverted as a
reverse for-loop in SelectionDAGBuilder::lowerWorkItem did 'I--'
on an iterator at the beginning of a vector, causing asserts
when using debugging iterators. This commit fixes that.
llvm-svn: 235608
This is a re-commit of r235101, which also fixes the problems with the previous patch:
- Switches with only a default case and non-fallthrough were handled incorrectly
- The previous patch tickled a bug in PowerPC Early-Return Creation which is fixed here.
> This is a major rewrite of the SelectionDAG switch lowering. The previous code
> would lower switches as a binary tre, discovering clusters of cases
> suitable for lowering by jump tables or bit tests as it went along. To increase
> the likelihood of finding jump tables, the binary tree pivot was selected to
> maximize case density on both sides of the pivot.
>
> By not selecting the pivot in the middle, the binary trees would not always
> be balanced, leading to performance problems in the generated code.
>
> This patch rewrites the lowering to search for clusters of cases
> suitable for jump tables or bit tests first, and then builds the binary
> tree around those clusters. This way, the binary tree will always be balanced.
>
> This has the added benefit of decoupling the different aspects of the lowering:
> tree building and jump table or bit tests finding are now easier to tweak
> separately.
>
> For example, this will enable us to balance the tree based on profile info
> in the future.
>
> The algorithm for finding jump tables is quadratic, whereas the previous algorithm
> was O(n log n) for common cases, and quadratic only in the worst-case. This
> doesn't seem to be major problem in practice, e.g. compiling a file consisting
> of a 10k-case switch was only 30% slower, and such large switches should be rare
> in practice. Compiling e.g. gcc.c showed no compile-time difference. If this
> does turn out to be a problem, we could limit the search space of the algorithm.
>
> This commit also disables all optimizations during switch lowering in -O0.
>
> Differential Revision: http://reviews.llvm.org/D8649
llvm-svn: 235560
This turned up after r235333, but was a pre-existing bug. The optimization
which transforms select(c, load, load) into a load of a select of the addresses
does not handle indexed loads (pre/post inc/dec). However, it did not check for
them either, leading to a crash if it tried to transform one of them.
llvm-svn: 235497
When an inline asm call has an output register marked as early-clobber, but
that same register is also an input operand, what should we do? GCC accepts
this, and is documented to accept this for read/write operands saying,
"Furthermore, if the earlyclobber operand is also a read/write operand, then
that operand is written only after it's used." For write-only operands, the
situation seems less clear, but I have at least one existing codebase that
assumes this will work, in part because it has syscall macros like this:
({ \
register uint64_t r0 __asm__ ("r0") = (__NR_ ## name); \
register uint64_t r3 __asm__ ("r3") = ((uint64_t) (arg0)); \
register uint64_t r4 __asm__ ("r4") = ((uint64_t) (arg1)); \
register uint64_t r5 __asm__ ("r5") = ((uint64_t) (arg2)); \
__asm__ __volatile__ \
("sc" \
: "=&r"(r0),"=&r"(r3),"=&r"(r4),"=&r"(r5) \
: "0"(r0), "1"(r3), "2"(r4), "3"(r5) \
: "r6","r7","r8","r9","r10","r11","r12","cr0","memory"); \
r3; \
})
Furthermore, with register aliases and subregister relationships that only the
backend knows about, rejecting this in the frontend seems like a difficult
proposition (if we wanted to do so). However, keeping the early-clobber flag on
the INLINEASM MI does not work for us, because it will cause the register's
live interval to end to soon (so it will not appear defined to be used as an
input).
Fortunately, fixing this does not seem hard: When forming the INLINEASM MI,
check to see if any of the early-clobber outputs are also inputs, and if so,
remove the early-clobber flag.
llvm-svn: 235283
See r230786 and r230794 for similar changes to gep and load
respectively.
Call is a bit different because it often doesn't have a single explicit
type - usually the type is deduced from the arguments, and just the
return type is explicit. In those cases there's no need to change the
IR.
When that's not the case, the IR usually contains the pointer type of
the first operand - but since typed pointers are going away, that
representation is insufficient so I'm just stripping the "pointerness"
of the explicit type away.
This does make the IR a bit weird - it /sort of/ reads like the type of
the first operand: "call void () %x(" but %x is actually of type "void
()*" and will eventually be just of type "ptr". But this seems not too
bad and I don't think it would benefit from repeating the type
("void (), void () * %x(" and then eventually "void (), ptr %x(") as has
been done with gep and load.
This also has a side benefit: since the explicit type is no longer a
pointer, there's no ambiguity between an explicit type and a function
that returns a function pointer. Previously this case needed an explicit
type (eg: a function returning a void() function was written as
"call void () () * @x(" rather than "call void () * @x(" because of the
ambiguity between a function returning a pointer to a void() function
and a function returning void).
No ambiguity means even function pointer return types can just be
written alone, without writing the whole function's type.
This leaves /only/ the varargs case where the explicit type is required.
Given the special type syntax in call instructions, the regex-fu used
for migration was a bit more involved in its own unique way (as every
one of these is) so here it is. Use it in conjunction with the apply.sh
script and associated find/xargs commands I've provided in rr230786 to
migrate your out of tree tests. Do let me know if any of this doesn't
cover your cases & we can iterate on a more general script/regexes to
help others with out of tree tests.
About 9 test cases couldn't be automatically migrated - half of those
were functions returning function pointers, where I just had to manually
delete the function argument types now that we didn't need an explicit
function type there. The other half were typedefs of function types used
in calls - just had to manually drop the * from those.
import fileinput
import sys
import re
pat = re.compile(r'((?:=|:|^|\s)call\s(?:[^@]*?))(\s*$|\s*(?:(?:\[\[[a-zA-Z0-9_]+\]\]|[@%](?:(")?[\\\?@a-zA-Z0-9_.]*?(?(3)"|)|{{.*}}))(?:\(|$)|undef|inttoptr|bitcast|null|asm).*$)')
addrspace_end = re.compile(r"addrspace\(\d+\)\s*\*$")
func_end = re.compile("(?:void.*|\)\s*)\*$")
def conv(match, line):
if not match or re.search(addrspace_end, match.group(1)) or not re.search(func_end, match.group(1)):
return line
return line[:match.start()] + match.group(1)[:match.group(1).rfind('*')].rstrip() + match.group(2) + line[match.end():]
for line in sys.stdin:
sys.stdout.write(conv(re.search(pat, line), line))
llvm-svn: 235145
This is a major rewrite of the SelectionDAG switch lowering. The previous code
would lower switches as a binary tre, discovering clusters of cases
suitable for lowering by jump tables or bit tests as it went along. To increase
the likelihood of finding jump tables, the binary tree pivot was selected to
maximize case density on both sides of the pivot.
By not selecting the pivot in the middle, the binary trees would not always
be balanced, leading to performance problems in the generated code.
This patch rewrites the lowering to search for clusters of cases
suitable for jump tables or bit tests first, and then builds the binary
tree around those clusters. This way, the binary tree will always be balanced.
This has the added benefit of decoupling the different aspects of the lowering:
tree building and jump table or bit tests finding are now easier to tweak
separately.
For example, this will enable us to balance the tree based on profile info
in the future.
The algorithm for finding jump tables is O(n^2), whereas the previous algorithm
was O(n log n) for common cases, and quadratic only in the worst-case. This
doesn't seem to be major problem in practice, e.g. compiling a file consisting
of a 10k-case switch was only 30% slower, and such large switches should be rare
in practice. Compiling e.g. gcc.c showed no compile-time difference. If this
does turn out to be a problem, we could limit the search space of the algorithm.
This commit also disables all optimizations during switch lowering in -O0.
Differential Revision: http://reviews.llvm.org/D8649
llvm-svn: 235101
Many of these predate llvm-readobj. With elf-dump we had to match
a relocation to symbol number and symbol number to symbol name or
section number.
llvm-svn: 235015
When I fixed these a couple of days ago to iterate over all loops, not just
depth == 1 loops, I inadvertently made it such that we'd only look at the first
top-level loop. Make sure that we really look at all of them.
llvm-svn: 234705
As it turns out, even though these are part of ISA 2.06, the P7 does not
support them (or, at least, not any P7s we're tested so far).
llvm-svn: 234686
This patch corresponds to review:
http://reviews.llvm.org/D8928
It adds direct move instructions to/from VSX registers to GPR's. These are
exploited for FP <-> INT conversions.
llvm-svn: 234682
This pass had the same problem as the data-prefetching pass: it was only
checking for depth == 1 loops in practice. Fix that, add some debugging
statements, and make sure that, when we grab an AddRec, it is for the loop we
expect.
llvm-svn: 234670
Iterating over loops from the LoopInfo instance only provides top-level loops.
We need to search the whole tree of loops to find the inner ones.
llvm-svn: 234603
When we have an instruction for this (and, thus, don't generate a runtime
call), we need to custom type legalize this (in a trivial way, just as we do
for fp_to_sint).
Fixes PR23173.
llvm-svn: 234561
This is the patch corresponding to review:
http://reviews.llvm.org/D8406
It adds some missing instructions from ISA 2.06 to the PPC back end.
llvm-svn: 234546
When enabling PPC64LE, I disabled some optimizations of BUILD_VECTOR
nodes for little endian because wrong results were produced. I've
subsequently investigated and found this is due to a call to
BuildVectorSDNode::isConstantSplat that was always specifying
big-endian. With this changed to correctly identify the target
endianness, the optimizations work as expected.
I found another case of a call to the same method with big-endian
hardcoded, in PPC::isAllNegativeZeroVector(). I discovered this was
an orphaned method with no callers, so I've just removed it.
The existing test/CodeGen/PowerPC/vec_constants.ll checks these
optimizations, so for testing I've just added a variant for little
endian.
llvm-svn: 234011
This patch attempts to fold the shuffling of 'scalar source' inputs - BUILD_VECTOR and SCALAR_TO_VECTOR nodes - if the shuffle node is the only user. This folds away a lot of unnecessary shuffle nodes, and allows quite a bit of constant folding that was being missed.
Differential Revision: http://reviews.llvm.org/D8516
llvm-svn: 234004
Under normal circumstances, use of CR bits is disabled when running at -O0, but
it is enabled by default otherwise, and if you have optnone functions, they'll
still generally be generated with crbits turned on (because nothing else turns
them off). FastISel can't handle most things dealing with i1 values when using
CR bits, and checks for that, but was not checking the return type on
functions; we can't fast-isel function calls with i1 return values either when
using CR bits for boolean values.
Fixes PR22664.
llvm-svn: 233775
Even at -O0, we fall back to SDAG when we hit intrinsics, and if the intrinsic
is a memset/memcpy/etc. we might normally use vector types. At -O0, this is
probably not a good idea (because, if there is a bug in the lowering code,
there would be no good way to turn it off). At -O0, only use scalar preferred
types.
Related to PR22754.
llvm-svn: 233755
The existing code in getMemsetValue only handled integer-preferred types when
the fill value was not a constant. Make this more robust in two ways:
1. If the preferred type is a floating-point value, do the mul-splat trick on
the corresponding integer type and then bitcast.
2. If the preferred type is a vector, do the mul-splat trick on one vector
element, and then build a vector out of them.
Fixes PR22754 (although, we should also turn off use of vector types at -O0).
llvm-svn: 233749
Fix debug info in these tests, which started failing with a WIP patch to
verify compile units and types. The problems look like they were all
caused by bitrot. They fell into these categories:
- Using `!{i32 0}` instead of `!{}`.
- Using `!{null}` instead of `!{}`.
- Using `!MDExpression()` instead of `!{}`.
- Using `!8` instead of `!{!8}`.
- `file:` references that pointed at `MDCompileUnit`s instead of the
same `MDFile` as the compile unit.
- `file:` references that were numerically off-by-one or (off-by-ten).
llvm-svn: 233415
Matthias Braun