A number of inline assembly constraints are currently supported by LLVM, but rejected as invalid by Clang:
Target independent constraints:
s: An integer constant, but allowing only relocatable values
ARM specific constraints:
j: An immediate integer between 0 and 65535 (valid for MOVW)
x: A 32, 64, or 128-bit floating-point/SIMD register: s0-s15, d0-d7, or q0-q3
N: An immediate integer between 0 and 31 (Thumb1 only)
O: An immediate integer which is a multiple of 4 between -508 and 508. (Thumb1 only)
This patch adds support to Clang for the missing constraints along with some checks to ensure that the constraints are used with the correct target and Thumb mode, and that immediates are within valid ranges (at least where possible). The constraints are already implemented in LLVM, but just a couple of minor corrections to checks (V8M Baseline includes MOVW so should work with 'j', 'N' and 'O' shouldn't be valid in Thumb2) so that Clang and LLVM are in line with each other and the documentation.
Differential Revision: https://reviews.llvm.org/D65863
Change-Id: I18076619e319bac35fbb60f590c069145c9d9a0a
llvm-svn: 371079
As discussed on D64551 and PR43227, we don't correctly handle cases where the base load has a non-zero byte offset.
Until we can properly handle this, we must bail from EltsFromConsecutiveLoads.
llvm-svn: 371078
This attempts to just fix the creation of VPT blocks, fixing up the iterating,
which instructions are considered in the bundle, and making sure that we do not
overrun the end of the block.
Differential Revision: https://reviews.llvm.org/D67219
llvm-svn: 371064
G_FENCE comes form fence instruction. For MIPS fence is generated in
AtomicExpandPass when atomic instruction gets surrounded with fence
instruction when needed.
G_FENCE arguments don't have LLT, because of that there is no job for
legalizer and regbankselect. Instruction select G_FENCE for MIPS32.
Differential Revision: https://reviews.llvm.org/D67181
llvm-svn: 371056
Select G_INTRINSIC_W_SIDE_EFFECTS for Intrinsic::trap for MIPS32
via legalizeIntrinsic.
Differential Revision: https://reviews.llvm.org/D67180
llvm-svn: 371055
Instead of returning structure by value clang usually adds pointer
to that structure as an argument. Pointers don't require special
handling no matter the SRet flag. Remove unsuccessful exit from
lowerCall for arguments with SRet flag if they are pointers.
Differential Revision: https://reviews.llvm.org/D67179
llvm-svn: 371054
This adds support for basic sibling call lowering in AArch64. The intent here is
to only handle tail calls which do not change the ABI (hence, sibling calls.)
At this point, it is very restricted. It does not handle
- Vararg calls.
- Calls with outgoing arguments.
- Calls whose calling conventions differ from the caller's calling convention.
- Tail/sibling calls with BTI enabled.
This patch adds
- `AArch64CallLowering::isEligibleForTailCallOptimization`, which is equivalent
to the same function in AArch64ISelLowering.cpp (albeit with the restrictions
above.)
- `mayTailCallThisCC` and `canGuaranteeTCO`, which are identical to those in
AArch64ISelLowering.cpp.
- `getCallOpcode`, which is exactly what it sounds like.
Tail/sibling calls are lowered by checking if they pass target-independent tail
call positioning checks, and checking if they satisfy
`isEligibleForTailCallOptimization`. If they do, then a tail call instruction is
emitted instead of a normal call. If we have a sibling call (which is always the
case in this patch), then we do not emit any stack adjustment operations. When
we go to lower a return, we check if we've already emitted a tail call. If so,
then we skip the return lowering.
For testing, this patch
- Adds call-translator-tail-call.ll to test which tail calls we currently lower,
which ones we don't, and which ones we shouldn't.
- Updates branch-target-enforcement-indirect-calls.ll to show that we fall back
as expected.
Differential Revision: https://reviews.llvm.org/D67189
........
This fails on EXPENSIVE_CHECKS builds due to a -verify-machineinstrs test failure in CodeGen/AArch64/dllimport.ll
llvm-svn: 371051
Handle the remaining cases also by handling asm goto in
SystemZInstrInfo::getBranchInfo().
Review: Ulrich Weigand
https://reviews.llvm.org/D67151
llvm-svn: 371048
Fixes clang static-analyzer warning.
Technically the MachineInstr *Sub might still be null if we're comparing zero (IsCmpZero == true), although this probably won't happen as SrcReg2 is probably == 0.
llvm-svn: 371047
Summary:
This patch renames functions that takes or returns alignment as log2, this patch will help with the transition to llvm::Align.
The renaming makes it explicit that we deal with log(alignment) instead of a power of two alignment.
A few renames uncovered dubious assignments:
- `MirParser`/`MirPrinter` was expecting powers of two but `MachineFunction` and `MachineBasicBlock` were using deal with log2(align). This patch fixes it and updates the documentation.
- `MachineBlockPlacement` exposes two flags (`align-all-blocks` and `align-all-nofallthru-blocks`) supposedly interpreted as power of two alignments, internally these values are interpreted as log2(align). This patch updates the documentation,
- `MachineFunctionexposes` exposes `align-all-functions` also interpreted as power of two alignment, internally this value is interpreted as log2(align). This patch updates the documentation,
Reviewers: lattner, thegameg, courbet
Subscribers: dschuff, arsenm, jyknight, dylanmckay, sdardis, nemanjai, jvesely, nhaehnle, javed.absar, hiraditya, kbarton, fedor.sergeev, asb, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, jrtc27, MaskRay, zzheng, edward-jones, atanasyan, rogfer01, MartinMosbeck, brucehoult, the_o, dexonsmith, PkmX, jocewei, jsji, Jim, s.egerton, llvm-commits, courbet
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65945
llvm-svn: 371045
This adds support for basic sibling call lowering in AArch64. The intent here is
to only handle tail calls which do not change the ABI (hence, sibling calls.)
At this point, it is very restricted. It does not handle
- Vararg calls.
- Calls with outgoing arguments.
- Calls whose calling conventions differ from the caller's calling convention.
- Tail/sibling calls with BTI enabled.
This patch adds
- `AArch64CallLowering::isEligibleForTailCallOptimization`, which is equivalent
to the same function in AArch64ISelLowering.cpp (albeit with the restrictions
above.)
- `mayTailCallThisCC` and `canGuaranteeTCO`, which are identical to those in
AArch64ISelLowering.cpp.
- `getCallOpcode`, which is exactly what it sounds like.
Tail/sibling calls are lowered by checking if they pass target-independent tail
call positioning checks, and checking if they satisfy
`isEligibleForTailCallOptimization`. If they do, then a tail call instruction is
emitted instead of a normal call. If we have a sibling call (which is always the
case in this patch), then we do not emit any stack adjustment operations. When
we go to lower a return, we check if we've already emitted a tail call. If so,
then we skip the return lowering.
For testing, this patch
- Adds call-translator-tail-call.ll to test which tail calls we currently lower,
which ones we don't, and which ones we shouldn't.
- Updates branch-target-enforcement-indirect-calls.ll to show that we fall back
as expected.
Differential Revision: https://reviews.llvm.org/D67189
llvm-svn: 370996
Since an add instruction must produce an unused carry out, this
requires additional SGPRs. This can be avoided by keeping the entire
offset computation in SGPRs. If one SGPR is still available, this only
costs one extra mov. If none are available, the entire computation can
be done in place and reversed.
This does assume the use is a VGPR operand. This was already assumed,
and we currently only select frame indexes to VALU instructions. This
should probably be fixed at some point to handle more possible MIR.
llvm-svn: 370929
For any unpaired muls, we accumulate them as an input to the
reduction. Check the type of the mul and perform a sext if the
existing accumlator input type is not the same.
Differential Revision: https://reviews.llvm.org/D66993
llvm-svn: 370851
This reverts r370525 (git commit 0bb1630685)
Also reverts r370543 (git commit 185ddc08ee)
The approach I took only works for functions marked `noreturn`. In
general, a call that is not known to be noreturn may be followed by
unreachable for other reasons. For example, there could be multiple call
sites to a function that throws sometimes, and at some call sites, it is
known to always throw, so it is followed by unreachable. We need to
insert an `int3` in these cases to pacify the Windows unwinder.
I think this probably deserves its own standalone, Win64-only fixup pass
that runs after block placement. Implementing that will take some time,
so let's revert to TrapUnreachable in the mean time.
llvm-svn: 370829
Summary:
This removes all string constants for function names and compares
functions by string directly when needed. Many of these constants are
used only once or twice so the benefit of defining them separately is
not very clear, and this actually fixes a bug.
When we already have a `malloc` declaration which is an alias to
something else within the module,
```
@malloc = weak hidden alias i8* (i32), i8* (i32)* @dlmalloc
```
(this happens compiling with emscripten with `-s WASM_OBJECT_FILES=0`
because all bc files are merged before being fed into `wasm-ld` which
runs the backend optimizations as LTO)
`Module::getFunction("malloc")` in `canLongjmp` returns `nullptr`
because `Module::getFunction` dyncasts pointer into `Function`, but the
alias is a `GlobalValue` but not a `Function`. This makes `canLongjmp`
return false for `malloc` in this case, and we end up adding a lot of
longjmp handling code around malloc. This is not only a code size
increase but actually a bug because `malloc` is used in the entry block
when preparing for setjmp tables for emscripten sjlj handling, and this
makes initial setjmp preparation, which has to happen in the entry
block, move to another split block, and this interferes with SSA update
later.
This also adds two more functions, `getTempRet0` and `setTempRet0`, in
the list of not longjmp-able functions.
Fixes https://github.com/emscripten-core/emscripten/issues/8935.
Reviewers: sbc100
Subscribers: mehdi_amini, jgravelle-google, hiraditya, sunfish, dexonsmith, dschuff, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D67129
llvm-svn: 370828
Now that we have the infrastructure to support s128 types as parameters
we can expand these to libcalls.
Differential Revision: https://reviews.llvm.org/D66185
llvm-svn: 370823
On AArch64, s128 types have to be split into s64 GPRs when passed as arguments.
This change adds the generic support in call lowering for dealing with multiple
registers, for incoming and outgoing args.
Support for splitting for return types not yet implemented.
Differential Revision: https://reviews.llvm.org/D66180
llvm-svn: 370822
These flags should simply be passed through to the target, which will do
the right thing. Add an MC/X86 test that uses these directives with the
three primary object file formats and shows that they disassemble the
same everywhere.
There is a missing test for .code32 on Windows ARM, since I'm not sure
exactly how to construct one.
Fixes PR43203
llvm-svn: 370805
This pattern, when imported at -O0 adds an extra copy via the SUBREG_TO_REG.
This is because the SUBREG_TO_REG is not eliminated. At all other opt levels,
it is eliminated.
This is a 1% geomean code size savings at -O0 on CTMark.
Differential Revision: https://reviews.llvm.org/D67027
llvm-svn: 370789
The code here seems to date back to r134705, when tablegen lowering was first
being added. I don't believe that we need to include CPSR implicit operands on
the MCInst. This now works more like other backends (like AArch64), where all
implicit registers are skipped.
This allows the AliasInst for CSEL's to match correctly, as can be seen in the
test changes.
Differential revision: https://reviews.llvm.org/D66703
llvm-svn: 370745
This moves ConstantMaterializationCost into ARMBaseInstrInfo so that it can
also be used in ISel Lowering, adding codesize values to the computed costs, to
be able to compare either approximate instruction counts or codesize costs.
It also adds a HasLowerConstantMaterializationCost, which compares the
ConstantMaterializationCost of two values, returning true if the first is
smaller either in instruction count/codesize, or falling back to the other in
the case that they are equal.
This is used in constant CSEL lowering to invert the predicate if the opposite
is easier to materialise.
Differential revision: https://reviews.llvm.org/D66701
llvm-svn: 370741
Arm 8.1-M adds a number of related CSEL instructions, including CSINC, CSNEG and CSINV. These choose between two values given the content in CPSR and a condition, performing an increment, negation or inverse of the false value.
This adds some selection for them, either from constant values or patterns. It does not include CSEL directly, which is currently not always making code better. It is still useful, but we will have to check more carefully where it should and shouldn't be used.
Code by Ranjeet Singh and Simon Tatham, with some modifications from me.
Differential revision: https://reviews.llvm.org/D66483
llvm-svn: 370739
Now the last `.section` directive in the MIPS asm file preamble
is the `.section .mdebug.abi`. If assembler code injected for example
by the LLVM `module asm` or the C ` __asm` directives do not contain
explicit switching to the `.text` section it goes to the `.mdebug.abi`
section. It might be unexpected to the user and in fact for example
breaks building some existing code like FreeBSD libc [1].
The patch forces switching to the `.text` section after emitting MIPS
assembler file preamble.
[1] https://bugs.llvm.org/show_bug.cgi?id=43119
Fix PR43119.
Differential Revision: https://reviews.llvm.org/D67014
llvm-svn: 370735
We were using isShiftedInt<7, Shift>(RHSC) to detect the ranges of offsets to
fold into MVE loads/stores. The instructions actually take a 7 bit unsigned
integer which is either added or subtracted. So something more like
isShiftedUInt<7, Shift>(abs(RHSC)).
Instead I've changes this to use the isScaledConstantInRange method, same as in
SelectT2AddrModeImm7Offset used by pre/post inc, which seemed to already be
getting this correct.
Differential revision: https://reviews.llvm.org/D66997
llvm-svn: 370731
Decoding of VMSR doesn't diagnose some unpredictable encodings, as the unpredictable bits are not correctly set.
Diff-reduce this instruction's internals WRT VMRS so I can see the differences better. Mostly this is s/src/Rt/g.
Fill in the "should-be-(0)" bits.
Designate the Unpredictable{} bits for both VMRS and VMSR.
Patch by Mark Murray!
Differential revision: https://reviews.llvm.org/D66938
llvm-svn: 370729
To save a 'add sp,#val' instruction by adding registers to the final pop instruction,
the first register transferred by this pop instruction need to be found.
If the function to be optimized has a non-void return value, the operand list contains
r0 (implicit) which prevents the optimization to take place.
Therefore implicit register references should be skipped in the search loop,
because this registers are never popped from the stack.
Patch by Rainer Herbertz (rOptimizer)!
Differential revision: https://reviews.llvm.org/D66730
llvm-svn: 370728
This merges the 32-bit and 64-bit mode code to just use Custom
for both i32 and i64. We already had most of the handling in
the custom handling due to the AVX512 having legal fp_to_uint.
Just needed to add the i32->i64 promotion handling. Refactor
the fp_to_uint code in the custom handler to simplify the
number of times we check things.
Tweak cost model tables to match the default handling we were
getting due to Expand before.
llvm-svn: 370700
Use Custom lowering instead. Fall back to default expansion only
when the scalar FP type belongs in an XMM register. This improves
lowering for i32 to fp80, and also i32 to double on SSE1 only.
llvm-svn: 370699
FP128 values are passed in xmm registers so should be asssociated
with an SSE feature rather than MMX which uses a different set
of registers.
llc enables sse1 and sse2 by default with x86_64. But does not
enable mmx. Clang enables all 3 features by default.
I've tried to add command lines to test with -sse
where possible, but any test that returns a value in an xmm
register fails with a fatal error with -sse since we have no
defined ABI for that scenario.
llvm-svn: 370682
We should be using MQPR, and if we don't we can get COPYs and PHIs created for
QPR. These get folded into instructions, failing verification checks.
Differential revision: https://reviews.llvm.org/D66214
llvm-svn: 370676
Now that constrained fpto[su]i intrinsic are available,
add codegen support to the SystemZ backend.
In addition to pure back-end changes, I've also needed
to add the strict_fp_to_[su]int and any_fp_to_[su]int
pattern fragments in the obvious way.
llvm-svn: 370674
Summary:
Adds the following inline asm constraints for SVE:
- w: SVE vector register with full range, Z0 to Z31
- x: Restricted to registers Z0 to Z15 inclusive.
- y: Restricted to registers Z0 to Z7 inclusive.
This change also adds the "z" modifier to interpret a register as an SVE register.
Not all of the bitconvert patterns added by this patch are used, but they have been included here for completeness.
Reviewers: t.p.northover, sdesmalen, rovka, momchil.velikov, rengolin, cameron.mcinally, greened
Reviewed By: sdesmalen
Subscribers: javed.absar, tschuett, rkruppe, psnobl, cfe-commits, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66302
llvm-svn: 370673
Summary:
D61491 caused us to use relocs when they're not strictly necessary, to
refer to symbols in the text section. This is a pessimization and it's a
problem for some loaders that don't support relocs yet.
Reviewers: nhaehnle, arsenm, tpr
Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65813
llvm-svn: 370667
On BtVer2 conditional SIMD stores are heavily microcoded.
The latency is directly proportional to the number of packed elements extracted
from the input vector. Also, according to micro-benchmarks, most of the
computation seems to be done in the integer unit.
Only a minority of the uOPs is executed by the FPU. The observed behaviour on
the FPU looks similar to this:
- The input MASK value is moved to the Integer Unit
-- [ a VMOVMSK-like uOP-executed on JFPU0].
- In parallel, each element of the input XMM/YMM is extracted and then sent to
the IntegerUnit through JFPU1.
As expected, a (conditional) store is executed for every extracted element.
Interestingly, a (speculative) load is executed for every extracted element too.
It is as-if a "LOAD - BIT_EXTRACT- CMOV" sequence of uOPs is repeated by the
integer unit for every contionally stored element.
VMASKMOVDQU is a special case: the number of speculative loads is always 2
(presumably, one load per quadword). That means, extra shifts and masking is
performed on (one of) the loaded quadwords before each conditional store (that
also explains the big number of non-FP uOPs retired).
This patch replaces the existing writes for conditional SIMD stores (i.e.
WriteFMaskedStore, and WriteFMaskedStoreY) with the following new writes:
WriteFMaskedStore32 [ XMM Packed Single ]
WriteFMaskedStore32Y [ YMM Packed Single ]
WriteFMaskedStore64 [ XMM Packed Double ]
WriteFMaskedStore64Y [ YMM Packed Double ]
Added a wrapper class named X86SchedWriteMaskMove in X86Schedule.td to describe
both RM and MR variants for conditional SIMD moves in a single tablegen
definition.
Instances of that class are then passed in input to multiclass avx_movmask_rm
when constructing MASKMOVPS/PD definitions.
Since this patch introduces new writes, I had to update all the X86 scheduling
models.
Differential Revision: https://reviews.llvm.org/D66801
llvm-svn: 370649
MachineLICM can hoist an invariant load, but if that load is folded it needs to be unfolded. On AVX512 sometimes this load is an broadcast load which we were previously unable to unfold. This patch adds initial support for that with a very basic list of supported instructions as a starting point.
Differential Revision: https://reviews.llvm.org/D67017
llvm-svn: 370620
Rename to lowerShuffleAsLanePermuteAndShuffle to make it clear that not just blends are performed.
Cleanup the in-lane shuffle mask generation to make it more obvious what's going on.
Some prep work noticed while investigating the poor shuffle code mentioned in D66004.
llvm-svn: 370613
These were never enabled correctly and are causing other problems. Taking them
out for the moment, whilst we work on the issues.
This reverts r370329.
llvm-svn: 370607
This is what the copies will eventually be turned into. We don't
use COPY_TO_REGCLASS for scalar_to_vector patterns. So we should
use the real instruction here too.
llvm-svn: 370601
EltsFromConsecutiveLoads was assuming that the number of input elts was the same as the number of elements in the output vector type when creating a zeroing shuffle, causing an assert when subvectors were being combined instead of just scalars.
llvm-svn: 370592
Summary:
Adds clang builtins and LLVM intrinsics for these experimental
instructions. They are not implemented in engines yet, but that is ok
because the user must opt into using them by calling the builtins.
Reviewers: aheejin, dschuff
Reviewed By: aheejin
Subscribers: sbc100, jgravelle-google, hiraditya, sunfish, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D67020
llvm-svn: 370556
Also improve assembler parser register validation for .seh_ directives.
This requires moving X86-specific seh directive handling into the x86
backend, which addresses some assembler FIXMEs.
Differential Revision: https://reviews.llvm.org/D66625
llvm-svn: 370533
Users have complained llvm.trap produce two ud2 instructions on Win64,
one for the trap, and one for unreachable. This change fixes that.
TrapUnreachable was added and enabled for Win64 in r206684 (April 2014)
to avoid poorly understood issues with the Windows unwinder.
There seem to be two major things in play:
- the unwinder
- C++ EH, _CxxFrameHandler3 & co
The unwinder disassembles forward from the return address to scan for
epilogues. Inserting a ud2 had the effect of stopping the unwinder, and
ensuring that it ran the EH personality function for the current frame.
However, it's not clear what the unwinder does when the return address
happens to be the last address of one function and the first address of
the next function.
The Visual C++ EH personality, _CxxFrameHandler3, needs to figure out
what the current EH state number is. It does this by consulting the
ip2state table, which maps from PC to state number. This seems to go
wrong when the return address is the last PC of the function or catch
funclet.
I'm not sure precisely which system is involved here, but in order to
address these real or hypothetical problems, I believe it is enough to
insert int3 after a call site if it would otherwise be the last
instruction in a function or funclet. I was able to reproduce some
similar problems locally by arranging for a noreturn call to appear at
the end of a catch block immediately before an unrelated function, and I
confirmed that the problems go away when an extra trailing int3
instruction is added.
MSVC inserts int3 after every noreturn function call, but I believe it's
only necessary to do it if the call would be the last instruction. This
change inserts a pseudo instruction that expands to int3 if it is in the
last basic block of a function or funclet. I did what I could to run the
Microsoft compiler EH tests, and the ones I was able to run showed no
behavior difference before or after this change.
Differential Revision: https://reviews.llvm.org/D66980
llvm-svn: 370525
gcc and icc pass these types in zmm registers in zmm registers.
This patch implements a quick hack to override the register
type before calling convention handling to one that is legal.
Longer term we might want to do something similar to 256-bit
integer registers on AVX1 where we just split all the operations.
Fixes PR42957
Differential Revision: https://reviews.llvm.org/D66708
llvm-svn: 370495
Summary:
MTE allows memory access to bypass tag check iff the address argument
is [SP, #imm]. This change takes advantage of this to demote uses of
tagged addresses to regular FrameIndex operands, reducing register
pressure in large functions.
MO_TAGGED target flag is used to signal that the FrameIndex operand
refers to memory that might be tagged, and needs to be handled with
care. Such operand must be lowered to [SP, #imm] directly, without a
scratch register.
The transformation pass attempts to predict when the offset will be
out of range and disable the optimization.
AArch64RegisterInfo::eliminateFrameIndex has an escape hatch in case
this prediction has been wrong, but it is quite inefficient and should
be avoided.
Reviewers: pcc, vitalybuka, ostannard
Subscribers: mgorny, javed.absar, kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66457
llvm-svn: 370490
I'm looking at unfolding broadcast loads on AVX512 which will
require refactoring this code to select broadcast opcodes instead
of regular load/stores in some cases. Merging them to avoid
further complicating their interfaces.
llvm-svn: 370484
Add lower for G_FPTOUI. Algorithm is similar to the SDAG version
in TargetLowering::expandFP_TO_UINT.
Lower G_FPTOUI for MIPS32.
Differential Revision: https://reviews.llvm.org/D66929
llvm-svn: 370431
Unlike ppc64, which has ADDISgotTprelHA+LDgotTprelL pairs,
ppc32 just uses LDgotTprelL32, so it does not make lots of sense to use
_LO without a paired _HA.
Emit R_PPC_GOT_TPREL16 instead R_PPC_GOT_TPREL16_LO to match GCC, and
get better linker relocation check. Note, R_PPC_GOT_TPREL16_{HA,LO}
don't have good linker support:
(a) lld does not support R_PPC_GOT_TPREL16_{HA,LO}.
(b) Top of tree ld.bfd does not support R_PPC_GOT_REL16_HA Initial-Exec -> Local-Exec relaxation:
// a.o
addis 3, 3, tsd_tls@got@tprel@ha
lwz 3, tsd_tls@got@tprel@l(3)
add 3, 3, tsd_tls@tls
// b.o
.section .tdata,"awT"; .globl tsd_tls; tsd_tls:
// ld/ld-new a.o b.o
internal error, aborting at ../../bfd/elf32-ppc.c:7952 in ppc_elf_relocate_section
Reviewed By: adalava
Differential Revision: https://reviews.llvm.org/D66925
llvm-svn: 370426
Add a default with an llvm_unreachable for anything we don't expect.
This seems safer that just blindly returning true for anything
missing from the switch.
llvm-svn: 370424
Add an WASM_SYMBOL_NO_STRIP flag, so that __attribute__((used)) doesn't
need to imply exporting. When targeting Emscripten, have
WASM_SYMBOL_NO_STRIP imply exporting.
Differential Revision: https://reviews.llvm.org/D62542
llvm-svn: 370415
Summary:
Reported in https://github.com/opencv/opencv/issues/15413.
We have serveral extended mnemonics for Move To/From Vector-Scalar Register Instructions
eg: mffprd,mtfprd etc.
We only support one of them, this patch add the others.
Reviewers: nemanjai, steven.zhang, hfinkel, #powerpc
Reviewed By: hfinkel
Subscribers: wuzish, qcolombet, hiraditya, kbarton, MaskRay, shchenz, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66963
llvm-svn: 370411
This teaches GISel to select patterns which fold an extend plus optional shift
into the addressing mode. In particular, adds and subs.
Factor out the arith extended register ComplexPatterns in AArch64InstrFormats.td
and create GISel equivalents.
Add some equivalent functions to the ones in AArch64ISelDAGToDAG:
- `selectArithExtendedRegister`
- `narrowExtendRegIfNeeded`
- `getExtendTypeForInst`
`getExtendTypeForInst` includes the checks for loads and stores. This will be
used for WRO addressing modes in loads + stores.
Teach selectCopy to properly handle subregister copies on the same bank in
order to support `narrowExtendRegIfNeeded`. The extended register must be a
GPR32, so we need to support same-bank subregister copies.
Fix a bug in getSubRegForClass which would cause registers on things like
GPR32common to end up getting ssub. Just change the check to look for FPR32
rather than GPR32.
For tests:
- Add select-arith-extended-reg.mir
- Update addsub_ext.ll to include GlobalISel checks
Differential Revision: https://reviews.llvm.org/D66835
llvm-svn: 370410
Summary:
This is a minor improvement on our past attempts to do this. Fixes
PR43155.
Reviewers: hans
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66905
llvm-svn: 370409
Summary:
There is no reason to differ in assembler behavior here between -msvc
and -gnu targets. Without this setting, the text after the '@' is
interpreted as a symbol variable, like foo@IMGREL.
Reviewers: mstorsjo
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66974
llvm-svn: 370408
ISD::isBuildVectorAllZeros permits undef elements to be present, which means we can't return it as a zero vector. PMULDQ/PMULUDQ is an extending multiply so a multiply by zero of the lower 32-bits should result in a zero 64-bit element.
llvm-svn: 370404
-Deprecate -mmpx and -mno-mpx command line options
-Remove CPUID detection of mpx for -march=native
-Remove MPX from all CPUs
-Remove MPX preprocessor define
I've left the "mpx" string in the backend so we don't fail on old IR, but its not connected to anything.
gcc has also deprecated these command line options. https://www.phoronix.com/scan.php?page=news_item&px=GCC-Patch-To-Drop-MPX
Differential Revision: https://reviews.llvm.org/D66669
llvm-svn: 370393
AMDGPU uses this for some addressing mode selection patterns. The
analysis run itself doesn't do anything so it seems easier to just
always require this than adding a way to opt in.
llvm-svn: 370388
Add a GISelPredicateCode to the stxr_* PatFrags in AArch64InstrAtomics.td.
This allows us to select these intrinsics.
Differential Revision: https://reviews.llvm.org/D65779
llvm-svn: 370382
Remove manual selection code for this intrinsic and use a GISelPredicateCode
instead.
This allows us to fully select this intrinsic without any tricky custom C++
matching.
Differential Revision: https://reviews.llvm.org/D65780
llvm-svn: 370380
Same thing as D66897, but for ldxr.* instead. Add a GISelPredicateCode to the
ldxr_* definitions, which allows us to import them.
Add select-ldxr-intrin.mir, and update arm64-ldxr-stxr.ll.
Differential Revision: https://reviews.llvm.org/D66898
llvm-svn: 370378
Add a GISelPredicateCode to ldaxr_*. This allows us to import the patterns for
@llvm.aarch64.ldaxr.*, and thus select them.
Add `isLoadStoreOfNumBytes` for the GISelPredicateCode, since each of these
intrinsics involves the same check.
Add select-ldaxr-intrin.mir, and update arm64-ldxr-stxr.ll.
Differential Revision: https://reviews.llvm.org/D66897
llvm-svn: 370377
Both methods `MipsTargetStreamer::emitStoreWithSymOffset` and
`MipsTargetStreamer::emitLoadWithSymOffset` are almost the same and
differ argument names only. These methods are used in the single place
so it's better to inline their code and remove original methods.
llvm-svn: 370354
When a "base" in the `lw/sw $reg1, symbol($reg2)` instruction is
a register and generated code is position independent, backend
does not add the "base" value to the symbol address.
```
lw $reg1, %got(symbol)($gp)
lw/sw $reg1, 0($reg1)
```
This patch fixes the bug and adds the missed `addu` instruction by
passing `BaseReg` into the `loadAndAddSymbolAddress` routine and handles
the case when the `BaseReg` is the zero register to escape redundant
`move reg, reg` instruction:
```
lw $reg1, %got(symbol)($gp)
addu $reg1, $reg1, $reg2
lw/sw $reg1, 0($reg1)
```
Differential Revision: https://reviews.llvm.org/D66894
llvm-svn: 370353
Masked loads and store fit naturally with MVE, the instructions being easily
predicated. This adds lowering for the simple cases of masked loads and stores.
It does not yet deal with widening/narrowing or pre/post inc.
The llvm masked load intrinsic will accept a "passthru" value, dictating the
values used for the zero masked lanes. In MVE the instructions write 0 to the
zero predicated lanes, so we need to match a passthru that isn't 0 (or undef)
with a select instruction to pull in the correct data after the load.
We also need to do something with unaligned loads/stores. Currently this uses a
similar method used in big endian, using an VLDRB.8 (and potentially a VREV in
BE). This does mean that the predicate mask is converted from, for example, a
v4i1 to a v16i1. The VLDR instructions are defined as using the first bit of
the relevant mask lane, so this could potentially load different results if the
predicate is little odd. As the input is a v4i1 however, I believe this is OK
and all the bits required should be set in the predicate, making the VLDRB.8
load the same data.
Differential Revision: https://reviews.llvm.org/D66534
llvm-svn: 370329
Summary:
We were previously doing it in DAGCombine.
But we also want to do `sub %x, C` -> `add %x, (sub 0, C)` for vectors in DAGCombine.
So if we had `sub %x, -1`, we'll transform it to `add %x, 1`,
which `combineIncDecVector()` will immediately transform back into `sub %x, -1`,
and here we go again...
I've marked this as NFC since not a single test changes,
but since that 'changes' DAGCombine, probably this isn't fully NFC.
Reviewers: RKSimon, craig.topper, spatel
Reviewed By: craig.topper
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62327
llvm-svn: 370327
We had an isel pattern to perform this, but its better to
do it in DAG combine as a simplification. This also fixes the lack
of patterns for AVX512 targets.
llvm-svn: 370294
Including a type legalizer fix to make bitcast operand promotion
work correctly when getSoftenedFloat returns f128 instead of i128.
Fixes PR43157
llvm-svn: 370293
SGPR spills aren't really handled after SILowerSGPRSpills. In order to
directly control what happens if the scavenger needs to spill, the
scavenger needs to be used directly. There is an alternative to
spilling in these contexts anyway since the frame register can be
increment and restored.
This does present another possible issue if spilling is needed for the
unused carry out if an add is needed. I think this can be avoided by
using a scalar add (although that clobbers SCC, which happens anyway).
llvm-svn: 370281
This is a special case because one node maps to two different G_
instructions, and the operand order is changed.
This mostly enables G_FCMP for AMDPGPU. G_ICMP is still manually
selected for now since it has the SALU and VALU complication to deal
with.
llvm-svn: 370280
Also add a FIXME because I'm not sure why these patterns exist. Looks like a missing combine.
And another FIXME because the AVX512 equivalent one of the patterns is missing.
llvm-svn: 370276
The patch fixed the issue that RV64 didn't clear the upper bits
when return complex floating value with lp64 ABI.
float _Complex
complex_add(float _Complex a, float _Complex b)
{
return a + b;
}
RealResult = zero_extend(RealA + RealB)
ImageResult = ImageA + ImageB
Return (RealResult | (ImageResult << 32))
The patch introduces shouldExtendTypeInLibCall target hook to suppress
the AssertZext generation when lowering floating LibCall.
Thanks to Eli's comments from the Bugzilla
https://bugs.llvm.org/show_bug.cgi?id=42820
Differential Revision: https://reviews.llvm.org/D65497
llvm-svn: 370275
If result of 64-bit address loading combines with 32-bit mask, LLVM
tries to optimize the code and remove "redundant" loading of upper
32-bits of the address. It leads to incorrect code on MIPS64 targets.
MIPS backend creates the following chain of commands to load 64-bit
address in the `MipsTargetLowering::getAddrNonPICSym64` method:
```
(add (shl (add (shl (add %highest(sym), %higher(sym)),
16),
%hi(sym)),
16),
%lo(%sym))
```
If the mask presents, LLVM decides to optimize the chain of commands. It
really does not make sense to load upper 32-bits because the 0x0fffffff
mask anyway clears them. After removing redundant commands we get this
chain:
```
(add (shl (%hi(sym), 16), %lo(%sym))
```
There is no patterns matched `(MipsHi (i64 symbol))`. Due a bug in `SYM_32`
predicate definition, backend incorrectly selects a pattern for a 32-bit
symbols and uses the `lui` instruction for loading `%hi(sym)`.
As a result we get incorrect set of instructions with unnecessary 16-bit
left shifting:
```
lui at,0x0
R_MIPS_HI16 foo
dsll at,at,0x10
daddiu at,at,0
R_MIPS_LO16 foo
```
This patch resolves two problems:
- Fix `SYM_32/SYM_64` predicates to prevent selection of patterns dedicated
to 32-bit symbols in case of using N64 ABI.
- Add missed patterns for 64-bit symbols for `%hi/%lo`.
Fix PR42736.
Differential Revision: https://reviews.llvm.org/D66228
llvm-svn: 370268
Stop counting explicitly disabled user_spgr's in the user_sgpr_count field of the kernel descriptor.
Differential Revision: https://reviews.llvm.org/D66900
llvm-svn: 370250
These are currently translated as normal functions calls in AArch64.
Until we have proper tail call lowering, we shouldn't translate these.
Differential Revision: https://reviews.llvm.org/D66842
llvm-svn: 370225
This reduces the number of SGPRs due to some concerns about running
out of SGPRs if you make all the SGPRs that aren't reserved available
for the calling convention.
Change-Id: Idb4ca4dc72f5b6808cb524ff7270915a8de5b4c1
llvm-svn: 370215
Neither libgcc or compiler-rt are usually used on Windows, so these
functions can't be called.
Differential revision: https://reviews.llvm.org/D66880
llvm-svn: 370204
There is no pattern matched `add hi, (MipsLo texternalsym)`. As a result,
loading an address of 32-bit symbol requires two registers and one more
additional instruction:
```
addiu $1, $zero, %lo(foo)
lui $2, %hi(foo)
addu $25, $2, $1
```
This patch adds the missed pattern and enables generation more effective
set of instructions:
```
lui $1, %hi(foo)
addiu $25, $1, %lo(foo)
```
Differential Revision: https://reviews.llvm.org/D66771
llvm-svn: 370196
Summary: There are at least 2 ways to express the same shuffle. Various pieces of code explicit check for both option, but other places do not when they would benefit from doing it. This patches refactor the codebase to use buildLegalVectorShuffle in order to make that behavior more consistent.
Reviewers: craig.topper, efriedma, RKSimon, lebedev.ri
Subscribers: javed.absar, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66804
llvm-svn: 370190
This just pulls the MVEVPTBlockPass into a separate file, as opposed to being
wrapped up in Thumb2ITBlockPass.
Differential revision: https://reviews.llvm.org/D66579
llvm-svn: 370187
This adds fp16 VMOVX patterns, using the same patterns as rL362482 with some
adjustments for MVE. It allows us to move fp16 registers without going into and
out of gprs.
VMOVX is able to move the top bits from a fp16 in a fp reg into the bottom bits
of another register, zeroing the rest. This can be used for odd MVE register
lanes. The top bits are not read by fp16 instructions, so no move is required
there if we are dealing with even lanes.
Differential revision: https://reviews.llvm.org/D66793
llvm-svn: 370184
rL369567 reverted a couple of recent changes made to ARMParallelDSP
because of a miscompilation error: PR43073.
The issue stemmed from an underlying bug that was caused by adding
muls into a reduction before it was proved that they could be executed
in parallel with another mul.
Most of the changes here are from the previously reverted commits.
The additional changes have been made area:
1) The Search function now doesn't insert any muls into the Reduction
object. That now happens once the search has successfully finished.
2) For any muls added into the reduction but that weren't paired, we
accumulate their values as an input into the smlad.
Differential Revision: https://reviews.llvm.org/D66660
llvm-svn: 370171
This change moves the actual stack pointer manipulation into the legalizer,
available to targets via lower(). The codegen is slightly different because
we're using explicit masks instead of G_PTRMASK, and using G_SUB rather than
adding a negative amount via G_GEP.
Differential Revision: https://reviews.llvm.org/D66678
llvm-svn: 370104
There are 5 instructions here that are converted from TAILJMP opcodes to regular JMP/JCC opcodes during MCInstLowering. So normally there encoding information isn't used. The exception being when XRay wraps them in PATCHABLE_TAIL_CALL.
For the ones that weren't already handled in MCInstLowering, add handling for those and remove their encoding information.
This patch fixes PATCHABLE_TAIL_CALL to do the same opcode conversion as the regular lowering patch. Then removes the encoding information.
Differential Revision: https://reviews.llvm.org/D66561
llvm-svn: 370079
Inserting a value into Visited has the effect of terminating a search for
predecessors if that node is seen. This is legitimate for the base address, and
acts as a slight performance optimization, but the vector-building node can be
paert of a legitimate cycle so we shouldn't stop searching there.
PR43056.
llvm-svn: 370036
Summary:
This is an alternate approach to D63396
Currently funclets reuse the same stack slots that are used in the
parent function for saving callee-saved xmm registers. If the parent
function modifies a callee-saved xmm register before an excpetion is
thrown, the catch handler will overwrite the original saved value.
This patch allocates space in funclets stack for saving callee-saved xmm
registers and uses RSP instead RBP to access memory.
Signed-off-by: Pengfei Wang <pengfei.wang@intel.com>
Reviewers: rnk, RKSimon, craig.topper, annita.zhang, LuoYuanke, andrew.w.kaylor
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66596
Signed-off-by: Pengfei Wang <pengfei.wang@intel.com>
llvm-svn: 370005
The problem these are supposed to work around can occur before the
intrinsics are lowered into the nodes. Try to directly simplify them
so they are matched before the bit assert operations can be optimized
out.
llvm-svn: 369994
The mul24 matching could interfere with SLSR and the other addressing
mode related passes. This probably is not the optimal placement, but
is an intermediate step. This should probably be moved after all the
generic IR passes, particularly LSR. Moving this after LSR seems to
help in some cases, and hurts others.
As-is in this patch, in idiv-licm, it saves 1-2 instructions inside
some of the loop bodies, but increases the number in others. Moving
this later helps these loops. In the new lsr tests in
mul24-pass-ordering, the intrinsic prevents introducing more
instructions in the loop preheader, so moving this later ends up
hurting them. This shouldn't be any worse than before the intrinsics
were introduced in r366094, and LSR should probably be smarter. I
think it's because it doesn't know the and inside the loop will be
folded away.
llvm-svn: 369991
Probably better to keep add over sub in early DAG combines.
It might make sense to push this to lowering or delay it all
the way to isel. But this was the simplest change.
llvm-svn: 369981
Summary:
Previously we skipped uses within the same BB as a def when rebuilding
SSA after SjLj transformation. For example, before transformation,
```
for.cond:
%0 = phi i32 [ %var, %for.inc ] ...
%var = ...
br label %for.inc
for.inc: ; preds = %for.cond
call i32 @setjmp(...)
br %for.cond
```
In this BB, %var should be defined in all paths from %for.inc to make %0
valid. In the input it was true; %for.inc's only predecessor was
%for.cond. But after SjLj transformation, it is possible that %for.inc
has other predecessors that are reachable without reaching %for.cond.
```
entry.split:
...
br i1 %a, label %bb.1, label %for.inc
for.cond:
%0 = phi i32 [ %var, %for.inc ] ... ; Not valid!
%var = ...
br label %for.inc
for.inc: ; preds = %for.cond, %entry.split
call i32 @setjmp(...)
...
br %for.cond
```
In this case, we can't use %var in the `phi` instruction in %for.cond,
because %var is not defined in all paths through %for.inc (If the
control flow is %entry -> %entry.split -> %for.inc -> %for.cond, %var
has not been defined until we reach the `phi`). But the previous code
excluded users within the same BB, skipping instructions within the same
BB so they are not rewritten properly. User instructions within the same
BB also should be candidates for rewriting if they are _before_ the
original definition.
Fixes PR43097.
Reviewers: dschuff
Subscribers: sbc100, jgravelle-google, hiraditya, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66729
llvm-svn: 369978
ANY_EXTEND_VECTOR_INREG isn't currently marked Legal which prevents SimplifyDemandedBits from turning SIGN/ZERO_EXTEND_VECTOR_INREG into it after op legalization. And even if we did make it Legal, combineExtInVec doesn't do shuffle combining on the VECTOR_INREG nodes until AVX1.
This patch adds a quick hack to combinePMULDQ to directly emit a vector shuffle corresponding to an ANY_EXTEND_VECTOR_INREG operation. This avoids both of those issues without creating any other regressions on our tests. The xop-ifma.ll change here also showed up when I tried to resurrect D56306 and seemed to be the only improvement that patch creates now. This is a more direct way to get the benefit.
Differential Revision: https://reviews.llvm.org/D66436
llvm-svn: 369942
Summary:
Concat_vectors is more canonical during early DAG combine. For example, its what's used by SelectionDAGBuilder when converting IR shuffles into SelectionDAG shuffles when element counts between inputs and mask don't match. We also have combines in DAGCombiner than can pull concat_vectors through a shuffle. See partitionShuffleOfConcats. So it seems like concat_vectors is a better operation to use here. I had to teach DAGCombiner's SimplifyVBinOp to also handle concat_vectors with undef. I haven't checked yet if we can remove the INSERT_SUBVECTOR version in there or not.
I didn't want to mess with the other caller of getShuffleHalfVectors that's used during shuffle lowering where insert_subvector probably is what we want to produce so I've enabled this via a boolean passed to the function.
Reviewers: spatel, RKSimon
Reviewed By: RKSimon
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66504
llvm-svn: 369872
Summary:
Adds support for generating the .data section in assembly files for global variables with a non-zero initialization. The support for writing the .data section in XCOFF object files will be added in a follow-on patch. Any relocations are not included in this patch.
Reviewers: hubert.reinterpretcast, sfertile, jasonliu, daltenty, Xiangling_L
Reviewed by: hubert.reinterpretcast
Subscribers: nemanjai, hiraditya, kbarton, MaskRay, jsji, wuzish, shchenz, DiggerLin, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66154
llvm-svn: 369869
This requires std::intializer_list to be a literal type, which it is
starting with C++14. The downside is that std::bitset is still not
constexpr-friendly so this change contains a re-implementation of most
of it.
Shrinks clang by ~60k.
llvm-svn: 369847
Summary: Removes a not so useful function from DataLayout and cleans up Support/MathExtras.h
Reviewers: courbet
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66691
llvm-svn: 369824
Instead of using custom C++ in `earlySelect` for loads and stores, just import
the patterns.
Remove `earlySelectLoad`, since we can just import the work it's doing.
Some minor changes to how `ComplexRendererFns` are returned for the XRO
addressing modes. If you add immediates in two steps, sometimes they are not
imported properly and you only end up with one immediate. I'm not sure if this
is intentional.
- Update load-addressing-modes.mir to include the instructions we can now
import.
- Add a similar test, store-addressing-modes.mir to show which store opcodes we
currently import, and show that we can pull in shifts etc.
- Update arm64-fastisel-gep-promote-before-add.ll to use FastISel instead of
GISel. This test failed with GISel because GISel folds the gep into the load.
The test checks that FastISel doesn't fold non-pointer-width adds into loads.
GISel on the other hand, produces a G_CONSTANT of -128 for the add, and then
a G_GEP, which must be pointer-width.
Note that we don't get STRBRoX right now. It seems like the importer can't
handle `FPR8Op:{ *:[Untyped] }:$Rt` source operands. So, those are not currently
supported.
Differential Revision: https://reviews.llvm.org/D66679
llvm-svn: 369806
CONCAT_VECTORS and INSERT_SUBVECTORS can both call combineConcatVectorOps,
but we shouldn't produce INSERT_SUBVECTORS from there. We should
keep CONCAT_VECTORS until vector legalization.
Noticed while looking at the madd_quad_reduction test from madd.ll
llvm-svn: 369802
The smin opcode and friends for v1i128 are incorrectly marked as legal for PPC.
Change them to expand.
Differential Revision: https://reviews.llvm.org/D64960
llvm-svn: 369797
Patch showing the effect of enabling bool vector oversimplification.
Non-VLX builds can simplify a kshift shuffle, but VLX builds simplify:
insert_subvector v8i zeroinitializer, v2i --> insert_subvector v8i undef, v2i
Preventing the removal of the AND to clear the upper bits of result
Differential Revision: https://reviews.llvm.org/D53022
llvm-svn: 369780
Now `lw/sw $reg, sym+offset` pseudo instructions for global symbol `sym`
are lowering into the following three instructions.
```
lw $reg, %got(symbol)($gp)
addiu $reg, $reg, offset
lw/sw $reg, 0($reg)
```
It's possible to reduce the number of instructions by taking the offset
in account in the final `lw/sw` command. This patch implements that
optimization.
```
lw $reg, %got(symbol)($gp)
lw/sw $reg, offset($reg)
```
Differential Revision: https://reviews.llvm.org/D66553
llvm-svn: 369756
Now pseudo instruction `la $6, symbol+8($6)` is expanding into the following
chain of commands:
```
lw $1, %got(symbol+8)($gp)
addiu $1, $1, 8
addu $6, $1, $6
```
This is incorrect. When a linker handles the `R_MIPS_GOT16` relocation,
it does not expect to get any addend and breaks on assertion. Otherwise
it has to create new GOT entry for each unique "sym + offset" pair.
Offset for a global symbol should be added to result of loading GOT
entry by a separate `add` command.
The patch fixes the problem by stripping off an offset from the expression
passed to the `%got`. That's interesting that even current code inserts
a separate `add` command.
Differential Revision: https://reviews.llvm.org/D66552
llvm-svn: 369755
This is a follow up of r369642.
This patch assigns a ReadAfterLd to every implicit register use of instruction
CMPXCHG8B and instruction CMPXCHG16B. Perf micro-benchmarks show that implicit
registers are read after 3cy from the start of execution.
llvm-svn: 369750
Excluding ADC/SBB and the bit-test instructions (BTR/BTS/BTC), the observed
latency of all other RMW integer arithmetic/logic instructions is 6cy and not
5cy.
Example (ADD):
```
addb $0, (%rsp) # Latency: 6cy
addb $7, (%rsp) # Latency: 6cy
addb %sil, (%rsp) # Latency: 6cy
addw $0, (%rsp) # Latency: 6cy
addw $511, (%rsp) # Latency: 6cy
addw %si, (%rsp) # Latency: 6cy
addl $0, (%rsp) # Latency: 6cy
addl $511, (%rsp) # Latency: 6cy
addl %esi, (%rsp) # Latency: 6cy
addq $0, (%rsp) # Latency: 6cy
addq $511, (%rsp) # Latency: 6cy
addq %rsi, (%rsp) # Latency: 6cy
```
The same latency profile applies to SUB/AND/OR/XOR/INC/DEC.
The observed latency of ADC/SBB is 7-8cy. So we need a different write to model
those. Latency of BTS/BTR/BTC is not fixed by this patch (they are much slower
than what the model for btver2 currently reports).
Differential Revision: https://reviews.llvm.org/D66636
llvm-svn: 369748
Summary:
Add support for gfx10, where all DPP operations are confined to work
within a single row of 16 lanes, and wave32.
Reviewers: arsenm, sheredom, critson, rampitec
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, t-tye, hiraditya, jfb, dstuttard, tpr, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65644
llvm-svn: 369745
For v2i32 we only feed 2 i8 elements into the psadbw instructions
with 0s in the other 14 bytes. The resulting psadbw instruction
will produce zeros in bits [127:16] of the output. We need to take
the result and feed it to a v2i32 add where the first element
includes bits [15:0] of the sad result. The other element should
be zero.
Prior to this patch we were using a truncate to take 0 from
bits 95:64 of the psadbw. This results in a pshufd to move those
bits to 63:32. But since we also have zeroes in bits 63:32 of
the psadbw output, we should just take those bits.
The previous code probably worked better with promoting legalization,
but now we use widening legalization. I've preserved the old
behavior if -x86-experimental-vector-widening-legalization=false
until we get that option removed.
llvm-svn: 369733
Prefer `MCFixupKind` where possible and add getTargetKind() to
convert to `unsigned` when needed rather than scattering cast
operators around the place.
Differential Revision: https://reviews.llvm.org/D59890
llvm-svn: 369720
I noticed another instance of the issue where references to aliases were
being replaced with aliasees, this time in InstCombine. In the instance that
I saw it turned out to be only a QoI issue (a symbol ended up being missing
from the symbol table due to the last reference to the alias being removed,
preventing HWASAN from symbolizing a global reference), but it could easily
have manifested as incorrect behaviour.
Since this is the third such issue encountered (previously: D65118, D65314)
it seems to be time to address this common error/QoI issue once and for all
and make the strip* family of functions not look through aliases.
Includes a test for the specific issue that I saw, but no doubt there are
other similar bugs fixed here.
As with D65118 this has been tested to make sure that the optimization isn't
load bearing. I built Clang, Chromium for Linux, Android and Windows as well
as the test-suite and there were no size regressions.
Differential Revision: https://reviews.llvm.org/D66606
llvm-svn: 369697
Local symbols in the indirect symbol table contain the value
`INDIRECT_SYMBOL_LOCAL` and the corresponding __pointers entry must
contain the address of the target.
In r349060, I added support for local symbols in the indirect symbol
table, which was checking if the symbol `isDefined` && `!isExternal` to
determine if the symbol is local or not.
It turns out that `isDefined` will return false if the user of the
symbol comes before its definition, and we'll again generate .long 0
which will be the symbol at the adress 0x0.
Instead of doing that, use GlobalValue::hasLocalLinkage() to check if
the symbol is local.
Differential Revision: https://reviews.llvm.org/D66563
llvm-svn: 369671
It appears the FIXME here was handled at some point. r159728 from 2012 seems to be at least aportion of fixing it.
Differential Revision: https://reviews.llvm.org/D66570
llvm-svn: 369665
A lot of places in the code combine checks for both ABI (SVR4/Darwin/AIX) and
addressing mode (64-bit vs 32-bit). In an attempt to make some of the code more
readable I've added a couple functions that combine checking for the ELF abi and
64-bit/32-bit code at once. As we add more AIX support I intend to add similar
functions for the AIX ABI.
Differential Revision: https://reviews.llvm.org/D65814
llvm-svn: 369658
Previously we would get the csect a symbol was contained in through its
fragment. This works only if we are writing an object file, and only for
defined symbols. To fix this we set the contating csect explicitly on the
MCSymbolXCOFF object.
Differential Revision: https://reviews.llvm.org/D66032
llvm-svn: 369657
On Jaguar, XCHG has a latency of 1cy and decodes to 2 macro-opcodes. Maximum
throughput for XCHG is 1 IPC. The byte exchange has worse latency and decodes to
1 extra uOP; maximum observed throughput is 0.5 IPC.
```
xchgb %cl, %dl # Latency: 2cy - uOPs: 3 - 2 ALU
xchgw %cx, %dx # Latency: 1cy - uOPs: 2 - 2 ALU
xchgl %ecx, %edx # Latency: 1cy - uOPs: 2 - 2 ALU
xchgq %rcx, %rdx # Latency: 1cy - uOPs: 2 - 2 ALU
```
The reg-mem forms of XCHG are atomic operations with an observed latency of
16cy. The resource usage is similar to the XCHGrr variants. The biggest
difference is obviously the bus-locking, which prevents the LS to issue other
memory uOPs in parallel until the unlocking store uOP is executed.
```
xchgb %cl, (%rsp) # Latency: 16cy - uOPs: 3 - ECX latency: 11cy
xchgw %cx, (%rsp) # Latency: 16cy - uOPs: 3 - ECX latency: 11cy
xchgl %ecx, (%rsp) # Latency: 16cy - uOPs: 3 - ECX latency: 11cy
xchgq %rcx, (%rsp) # Latency: 16cy - uOPs: 3 - ECX latency: 11cy
```
The exchanged in/out register operand becomes available after 11cy from the
start of execution. Added test xchg.s to verify that we correctly see that
register write committed in 11cy (and not 16cy).
Reg-reg XADD instructions have the same latency/throughput than the byte
exchange (register-register variant).
```
xaddb %cl, %dl # latency: 2cy - uOPs: 3 - 3 ALU
xaddw %cx, %dx # latency: 2cy - uOPs: 3 - 3 ALU
xaddl %ecx, %edx # latency: 2cy - uOPs: 3 - 3 ALU
xaddq %rcx, %rdx # latency: 2cy - uOPs: 3 - 3 ALU
```
The non-atomic RM variants have a latency of 11cy, and decode to 4
macro-opcodes. They still consume 2 ALU pipes, and the exchange in/out register
operand becomes available in 3cy (it matches the 'load-to-use latency').
```
xaddb %cl, (%rsp) # latency: 11cy - uOPs: 4 - 3 ALU
xaddw %cx, (%rsp) # latency: 11cy - uOPs: 4 - 3 ALU
xaddl %ecx, (%rsp) # latency: 11cy - uOPs: 4 - 3 ALU
xaddq %rcx, (%rsp) # latency: 11cy - uOPs: 4 - 3 ALU
```
The atomic XADD variants execute in 16cy. The in/out register operand is
available after 11cy from the start of execution.
```
lock xaddb %cl, (%rsp) # latency: 16cy - uOPs: 4 - 3 ALU -- ECX latency: 11cy
lock xaddw %cx, (%rsp) # latency: 16cy - uOPs: 4 - 3 ALU -- ECX latency: 11cy
lock xaddl %ecx, (%rsp) # latency: 16cy - uOPs: 4 - 3 ALU -- ECX latency: 11cy
lock xaddq %rcx, (%rsp) # latency: 16cy - uOPs: 4 - 3 ALU -- ECX latency: 11cy
```
Added test xadd.s to verify those latencies as well as read-advance values.
Differential Revision: https://reviews.llvm.org/D66535
llvm-svn: 369642
The CodeGen/Thumb2/mve-vaddv.ll test needed to be amended to reflect the
changes from the above patch.
This reverts commit cd53ff6, reapplying 7c6b229.
llvm-svn: 369638
It broke the bots, see e.g. http://lab.llvm.org:8011/builders/clang-cuda-build/builds/36275/
> This patch fixes shifts by a 128/256 bit shift amount. It also fixes
> codegen for shifts of 32 by delegating to LLVM's default optimisation
> instead of emitting a long shift.
>
> Tests that used to generate long shifts of 32 are updated to check for the
> more optimised codegen.
>
> Differential revision: https://reviews.llvm.org/D66519
>
> llvm-svn: 369626
llvm-svn: 369636
I don't really understand the costs we're using for fp_to_sint,
but prior to widening legalization we used 20 as the cost for this
via the v2i64->v2f64 entry. That number seems better than the 40
we got with widening legalization. So now we need either a
v2i32->v2f64 entry or a v4i32->v2f64 entry depending on whether
AVX is enabled or not since we skip the first SSE2 table look up
under AVX.
llvm-svn: 369628
This patch fixes shifts by a 128/256 bit shift amount. It also fixes
codegen for shifts of 32 by delegating to LLVM's default optimisation
instead of emitting a long shift.
Tests that used to generate long shifts of 32 are updated to check for the
more optimised codegen.
Differential revision: https://reviews.llvm.org/D66519
llvm-svn: 369626
The patch introduces MakeLibCallOptions struct as suggested by @efriedma on D65497.
The struct contain argument flags which will pass to makeLibCall function.
The patch should not has any functionality changes.
Differential Revision: https://reviews.llvm.org/D65795
llvm-svn: 369622
We had an odd combination of WriteJump applied to some memory
instructions and WriteJumpLd applied to register and immediate
instructions.
Thsi should hopefully assign them all correctly.
llvm-svn: 369599
I might look at improving PR43065 which will require being
able to mark a 256 and 512 bit vector of f16 as Legal.
Differential Revision: https://reviews.llvm.org/D66515
llvm-svn: 369565
In case of expanding `lw/sw $reg, symbol($reg)` instruction for PIC it's
enough to call the `loadAndAddSymbolAddress` method. Additional work
performed by the `expandLoadAddress` is not required here.
llvm-svn: 369563
This is necessary for handling <3 x s16> on AMDGPU, assuming this
should be handled as 2 separate legalization actions. The alternative
would be for fewerElementsVector to handle 3->2.
llvm-svn: 369547
The hint instructions are enabled by default (if the standard C extension is
enabled). To disable them pass -mattr=-rvc-hints.
Differential Revision: https://reviews.llvm.org/D62592
llvm-svn: 369528
r351882 allows different type for shift amount then result and value
being shifted. Fix MIPS Legalizer rules to take r351882 into account.
Differential Revision: https://reviews.llvm.org/D66203
llvm-svn: 369510
Add NarrowScalar for G_TRUNC when NarrowTy is half the size of source.
NarrowScalar G_TRUNC to s32 for MIPS32.
Differential Revision: https://reviews.llvm.org/D66202
llvm-svn: 369509
Add a GlobalISel equivalent for the logical_imm32_XFORM and logical_imm64_XFORM
SDNodeXForms in AArch64InstrFormats.td.
- Add select-logical-imm.mir, which contains tests for each imported pattern.
- Update select-pr32733.mir and select-scalar-shift-imm.mir, since they now
select instructions of this form.
Differential Revision: https://reviews.llvm.org/D66162
llvm-svn: 369465
This adds GlobalISel equivalents for the following from AArch64InstrFormats:
- arith_shifted_reg32
- arith_shifted_reg64
And partial support for
- logical_shifted_reg32
- logical_shifted_reg32
The only thing missing for the logical cases is support for rotates. Other than
the missing support, the transformation is identical for the arithmetic shifted
register and the logical shifted register.
Lots of tests here:
- Add select-arith-shifted-reg.mir to show that we correctly select add and
sub instructions which use this pattern.
- Add select-logical-shifted-reg.mir to cover patterns which are not shared
between the arithmetic and logical cases.
- Update addsub-shifted.ll to show that we correctly fold shifts into
adds/subs.
- Update eon.ll to show that we can select the eon instruction by folding xors.
Differential Revision: https://reviews.llvm.org/D66163
llvm-svn: 369460
I also had to add a new combine to X86's combineExtractSubvector to prevent a regression.
This helps our vXi1 code see the full concat operation and allow it optimize undef to a zero if there is already a zero in the concat. This helped us use a movzx instead of an AND in some of the tests. In those tests, one concat comes from SelectionDAGBuilder and the second comes from type legalization of v4i1->i4 bitcasts which uses an additional concat. Though these changes weren't my original motivation.
I'm looking at making X86ISelLowering's narrowShuffle emit a concat_vectors instead of an insert_subvector since concat_vectors is more canonical during early DAG combine. This patch helps prevent a regression from my experiments with that.
Differential Revision: https://reviews.llvm.org/D66456
llvm-svn: 369459
Adds Wrapper classes for MCSymbol and MCSection into the XCOFF target
object writer. Also adds a class to represent the top-level sections, which we
materialize in the ObjectWriter.
executePostLayoutBinding will map all csects into the appropriate
container depending on its storage mapping class, and map all symbols
into their containing csect. Once all symbols have been processed we
- Assign addresses and symbol table indices.
- Calaculte section sizes.
- Build the section header table.
- Assign the sections raw-pointer value for non-virtual sections.
Since the .bss section is virtual, writing the header table is enough to
add support. Writing of a sections raw data, or of any relocations is
not included in this patch.
Testing is done by dumping the section header table, but it needs to be
extended to include dumping the symbol table once readobj support for
dumping auxiallary entries lands.
Differential Revision: https://reviews.llvm.org/D65159
llvm-svn: 369454
Without AVX512DQ we don't have KMOVB so we can't really copy 8-bits of a k-register to a GPR. We have to copy 16 bits instead. We do this even if the DAG copy is from v8i1->v16i1. If we detect the (i8 (bitcast (v8i1 (extract_subvector (v16i1 X), 0)))) we should rewrite the types to match the copy we do support. By doing this, we can help known bits to propagate without losing the upper 8 bits of the input to the extract_subvector. This allows some zero extends to be removed since we have an isel pattern to use kmovw for (zero_extend (i16 (bitcast (v16i1 X))).
Differential Revision: https://reviews.llvm.org/D66489
llvm-svn: 369434
We already had patterns for extending to i32 to take advantage of
the impliciting zeroing of the upper bits of a 32-bit GPR that is
done by KMOVW/KMOVB. But the extend might be all the way to i64,
in which case the existing patterns would fail and we'd get a
KMOVW/B followed by a MOVZX. By adding patterns for i64 we can
use the fact that KMOVW/B zero the upper bits of the 32-bit GPR
and the normal property that 32-bit GPR writes implicitly zero the
upper 32-bits of the full 64-bit GPR.
The anyextend patterns are slightly different since we don't care
about the upper zeros. For the i8->i64 I think this avoids selecting
the anyextend as a MOVZX to prevent a partial register issue that
doesn't exist. For i16->i64 I think we would have just emitted an
insert_subreg on top of the extract_subreg that the vXi16->i16
bitcast pattern emits. The register coalescer or peephole pass
should combine those, but this saves that work and makes i8/16
consistent.
llvm-svn: 369431
Latency and throughput of LOCK INC/DEC/NEG/NOT is always 19cy.
Number of uOPs is still 1.
Differential Revision: https://reviews.llvm.org/D66469
llvm-svn: 369388
Follow binutils in using RISCV_32_PCREL for the FDE initial location. As
explained in the relevant binutils commit
<a6cbf936e3>,
the ADD/SUB pair of relocations is problematic in the presence of linker
relaxation.
This patch has the same end goal as D64715 but includes test changes and
avoids adding a new global VariantKind to MCExpr.h (preferring
RISCVMCExpr VKs like the rest of the RISC-V backend).
Differential Revision: https://reviews.llvm.org/D66419
llvm-svn: 369375
On Jaguar, CMPXCHG has a latency of 11cy, and a maximum throughput of 0.33 IPC.
Throughput is superiorly limited to 0.33 because of the implicit in/out
dependency on register EAX. In the case of repeated non-atomic CMPXCHG with the
same memory location, store-to-load forwarding occurs and values for sequent
loads are quickly forwarded from the store buffer.
Interestingly, the functionality in LLVM that computes the reciprocal throughput
doesn't seem to know about RMW instructions. That functionality only looks at
the "consumed resource cycles" for the throughput computation. It should be
fixed/improved by a future patch. In particular, for RMW instructions, that
logic should also take into account for the write latency of in/out register
operands.
An atomic CMPXCHG has a latency of ~17cy. Throughput is also limited to
~17cy/inst due to cache locking, which prevents other memory uOPs to start
executing before the "lock releasing" store uOP.
CMPXCHG8rr and CMPXCHG8rm are treated specially because they decode to one less
macro opcode. Their latency tend to be the same as the other RR/RM variants. RR
variants are relatively fast 3cy (but still microcoded - 5 macro opcodes).
CMPXCHG8B is 11cy and unfortunately doesn't seem to benefit from store-to-load
forwarding. That means, throughput is clearly limited by the in/out dependency
on GPR registers. The uOP composition is sadly unknown (due to the lack of PMCs
for the Integer pipes). I have reused the same mix of consumed resource from the
other CMPXCHG instructions for CMPXCHG8B too.
LOCK CMPXCHG8B is instead 18cycles.
CMPXCHG16B is 32cycles. Up to 38cycles when the LOCK prefix is specified. Due to
the in/out dependencies, throughput is limited to 1 instruction every 32 (or 38)
cycles dependeing on whether the LOCK prefix is specified or not.
I wouldn't be surprised if the microcode for CMPXCHG16B is similar to 2x
microcode from CMPXCHG8B. So, I have speculatively set the JALU01 consumption to
2x the resource cycles used for CMPXCHG8B.
The two new hasLockPrefix() functions are used by the btver2 scheduling model
check if a MCInst/MachineInst has a LOCK prefix. Calls to hasLockPrefix() have
been encoded in predicates of variant scheduling classes that describe lat/thr
of CMPXCHG.
Differential Revision: https://reviews.llvm.org/D66424
llvm-svn: 369365
Google is reporting performance issues with the new default behavior
and have asked for a way to switch back to the old behavior while we
investigate and make fixes.
I've restored all of the code that had since been removed and added
additional checks of the command flag onto code paths that are
not otherwise guarded by a check of getTypeAction.
I've also modified the cost model tables to hopefully get us back
to the previous costs.
Hopefully we won't need to support this for very long since we
have no test coverage of the old behavior so we can very easily
break it.
llvm-svn: 369332
Overriders may want to modify state in it. AMDGPU wants
to, but has to make its members mutable in order to do so.
Besides, EmitBasicBlockEnd is not const, so why should
Start be?
Patch by Bevin Hansson.
Reviewed By: nickdesaulniers
Differential Revision: https://reviews.llvm.org/D66341
llvm-svn: 369325
Summary:
Simplify the API using Optional<> and address comments in
https://reviews.llvm.org/D66165
Reviewers: vitalybuka
Subscribers: hiraditya, llvm-commits, ostannard, pcc
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66317
llvm-svn: 369300
Summary:
MTE provides instructions to update memory tags and data at the same
time. This change makes use of those to generate more compact code for
stack variable tagging + initialization.
We collect memory store and memset instructions following an alloca or a
lifetime.start call, and replace them with the corresponding MTE
intrinsics. Since the intrinsics work on 16-byte aligned chunks, the
stored values are combined as necessary.
Reviewers: pcc, vitalybuka, ostannard
Subscribers: srhines, javed.absar, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66167
llvm-svn: 369297
The motivating case are the changes in vector-reduce-add.ll where
we were doing extra work in the scalar domain instead of shuffling.
There may be some one use check that needs to be looked into there,
but this patch sidesteps the issue by avoiding broadcasts that
aren't really broadcasting.
Differential Revision: https://reviews.llvm.org/D66071
llvm-svn: 369287
Summary:
If we have a MI marked with bitcast bits, but without input operands,
PeepholeOptimizer might crash with assert.
eg:
If we apply the changes in PPCInstrVSX.td as in this patch:
[(set v4i32:$XT, (bitconvert (v16i8 immAllOnesV)))]>;
We will get assert in PeepholeOptimizer.
```
llvm-lit llvm-project/llvm/test/CodeGen/PowerPC/build-vector-tests.ll -v
llvm-project/llvm/include/llvm/CodeGen/MachineInstr.h:417: const
llvm::MachineOperand &llvm::MachineInstr::getOperand(unsigned int)
const: Assertion `i < getNumOperands() && "getOperand() out of range!"'
failed.
```
The fix is to abort if we found out of bound access.
Reviewers: qcolombet, MatzeB, hfinkel, arsenm
Reviewed By: qcolombet
Subscribers: wdng, arsenm, steven.zhang, wuzish, nemanjai, hiraditya, kbarton, MaskRay, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65542
llvm-svn: 369261
The current behavior of shouldForceRelocation forces relocations for the
majority of fixups when relaxation is enabled. This makes sense for
fixups which incorporate symbols but is unnecessary for simple data
fixups where the fixup target is already resolved to an absolute value.
Differential Revision: https://reviews.llvm.org/D63404
Patch by Edward Jones.
llvm-svn: 369257
This patch adds vecreduce_add and the relevant instruction selection for
vaddv.
Differential revision: https://reviews.llvm.org/D66085
llvm-svn: 369245
This adds some sext costs for MVE, taken from the length of assembly sequences
that we currently generate.
Differential Revision: https://reviews.llvm.org/D66010
llvm-svn: 369244
We can support these by widening to a supported type,
then shifting all the way to the left and then
back to the right to ensure that we shift in zeroes.
llvm-svn: 369232
Not sure how to test this as we have tests that exercise this code,
but nothing failed for the types not matching. Since all the k-registers
use equivalent register classes everything just ends up working.
llvm-svn: 369228
This allows us to widen the type when the KSHIFTR instruction
doesn't exist for the type. If we need to shift in zeroes into
the upper elements we would need more work to guarantee zeroes
when widening.
llvm-svn: 369227
For such a case we should only need a KSHIFTL, but we were
previously generating a KSHIFTL followed by a KSHIFTR because
we mistakenly believed we need to zero the undef elements.
llvm-svn: 369224
Add similar functionality to isShuffleEquivalent - if the mask elements don't match, try matching the BUILD_VECTOR scalars instead.
As target shuffles need to handle SM_Sentinel values, this can get a bit tricky, so commit just adds actual mask element index handling - full SM_SentinelZero support will be added when the need arises.
Also, enables support in matchVectorShuffleWithPACK
llvm-svn: 369212
Simplifies shuffle mask comparisons by just bailing out if the shuffle mask has any out of range values - will make an upcoming patch much simpler.
llvm-svn: 369211
Currently the searchable tables report the number of dwords. These
round to the same number for 3 and 4 component d16
instructions. Change this to report the number of elements so this
isn't ambiguous.
llvm-svn: 369202
Krzysztof Parzyszek