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
We currently don't use liveness information after this point, but it can
be useful to catch bugs using -verify-machineinstrs, and optimizations
could potentially use this information in the future.
Differential Revision: https://reviews.llvm.org/D66319
llvm-svn: 369162
This was a quick pass through some obvious places. I haven't tried the clang-tidy check.
I also replaced the zeroes in getX86SubSuperRegister with X86::NoRegister which is the real sentinel name.
Differential Revision: https://reviews.llvm.org/D66363
llvm-svn: 369151
Push LR register before calling __gnu_mcount_nc as it expects the value of LR register to be the top value of
the stack on ARM32.
Differential Revision: https://reviews.llvm.org/D65019
llvm-svn: 369147
Summary:
We tried to support EM_ASM with setjmp/longjmp in binaryen. But with dynamic
linking thrown into the mix, the code is no longer understandable and cannot
be maintained. We also discovered more bugs in the EM_ASM handling code.
To ensure maintainability and correctness of the binaryen code, EM_ASM will
no longer be supported with setjmp/longjmp. This is probably fine since the
support was added recently and haven't be published.
Reviewers: tlively, sbc100, jgravelle-google, kripken
Reviewed By: tlively, kripken
Subscribers: dschuff, hiraditya, aheejin, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66356
llvm-svn: 369137
Eventually we need to generalize combineExtractWithShuffle to handle all faux shuffles and handle truncate (and X86ISD::VTRUNC etc.) there, but we're not ready yet (still creates nodes on the fly, incomplete DemandedElts support, bad use of recursive Depth limit).
llvm-svn: 369134
Recommit with fixes for mac builders.
Summary:
AArch64InstrInfo::getInstSizeInBytes is incorrectly treating meta
instructions (e.g. CFI_INSTRUCTION) as normal instructions and
giving them a size of 4.
This results in branch relaxation calculating block sizes wrong.
Branch relaxation also considers alignment and thus a single
mistake can result in later blocks being incorrectly sized even
when they themselves do not contain meta instructions.
The net result is we might not relax a branch whose destination is
not within range.
Reviewers: nickdesaulniers, peter.smith
Reviewed By: peter.smith
Subscribers: javed.absar, kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66337
> llvm-svn: 369111
llvm-svn: 369133
Changes:
There was a condition for `!NeedsFrameRecord` missing in the assert. The
assert in question has changed to:
+ assert((!RPI.isPaired() || !NeedsFrameRecord || RPI.Reg2 != AArch64::FP ||
+ RPI.Reg1 == AArch64::LR) &&
+ "FrameRecord must be allocated together with LR");
This addresses PR43016.
llvm-svn: 369122
MVE also has some sext of loads, which will be free just as scalar
instructions are.
Differential Revision: https://reviews.llvm.org/D66008
llvm-svn: 369118
Only in public interfaces that have not yet been converted should there remain
registers with unsigned type.
Differential Revision: https://reviews.llvm.org/D66252
llvm-svn: 369114
Summary:
AArch64InstrInfo::getInstSizeInBytes is incorrectly treating meta
instructions (e.g. CFI_INSTRUCTION) as normal instructions and
giving them a size of 4.
This results in branch relaxation calculating block sizes wrong.
Branch relaxation also considers alignment and thus a single
mistake can result in later blocks being incorrectly sized even
when they themselves do not contain meta instructions.
The net result is we might not relax a branch whose destination is
not within range.
Reviewers: nickdesaulniers, peter.smith
Reviewed By: peter.smith
Subscribers: javed.absar, kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66337
llvm-svn: 369111
The widening and narrowing MVE instructions like VLDRH.32 are only permitted to
use low tGPR registers. This means that if they are used for a stack slot,
where the register used is only decided during frame setup, we need to be able
to correctly pick a thumb1 register over a normal GPR.
This attempts to add the required logic into eliminateFrameIndex and
rewriteT2FrameIndex, only picking the FrameReg if it is a valid register for
the operands register class, and picking a valid scratch register for the
register class.
Differential Revision: https://reviews.llvm.org/D66285
llvm-svn: 369108
We don't yet know how to generate these instructions for MVE. And in the case
of VLD3, we don't even have the instruction. For the moment don't tell the
vectoriser that we have VLD4, just to end up serialising the results.
Differential Revision: https://reviews.llvm.org/D66009
llvm-svn: 369101
This patch allows symbols followed by an expression for an offset to be
parsed as bare symbols.
Differential Revision: https://reviews.llvm.org/D57332
llvm-svn: 369097
This allows arguments with the constraint A to be lowered to input nodes
for RISC-V, which implies a memory address stored in a register.
This patch adds the minimal amount of code required to get operands with
the right constraints to compile.
https://reviews.llvm.org/D54296
llvm-svn: 369095
Two issues:
1. t2CMPri shouldn't use CPSR if it isn't predicated. This doesn't
really have any visible effect at the moment, but it might matter in the
future.
2. The t2CMPri generated for t2WhileLoopStart might need to use a
register that isn't LR.
My team found this because we have a patch to track register liveness
late in the pass pipeline. I'll look into upstreaming it to help catch
issues like this earlier.
Differential Revision: https://reviews.llvm.org/D66243
llvm-svn: 369069
Summary:
This clang-tidy check is looking for unsigned integer variables whose initializer
starts with an implicit cast from llvm::Register and changes the type of the
variable to llvm::Register (dropping the llvm:: where possible).
Partial reverts in:
X86FrameLowering.cpp - Some functions return unsigned and arguably should be MCRegister
X86FixupLEAs.cpp - Some functions return unsigned and arguably should be MCRegister
X86FrameLowering.cpp - Some functions return unsigned and arguably should be MCRegister
HexagonBitSimplify.cpp - Function takes BitTracker::RegisterRef which appears to be unsigned&
MachineVerifier.cpp - Ambiguous operator==() given MCRegister and const Register
PPCFastISel.cpp - No Register::operator-=()
PeepholeOptimizer.cpp - TargetInstrInfo::optimizeLoadInstr() takes an unsigned&
MachineTraceMetrics.cpp - MachineTraceMetrics lacks a suitable constructor
Manual fixups in:
ARMFastISel.cpp - ARMEmitLoad() now takes a Register& instead of unsigned&
HexagonSplitDouble.cpp - Ternary operator was ambiguous between unsigned/Register
HexagonConstExtenders.cpp - Has a local class named Register, used llvm::Register instead of Register.
PPCFastISel.cpp - PPCEmitLoad() now takes a Register& instead of unsigned&
Depends on D65919
Reviewers: arsenm, bogner, craig.topper, RKSimon
Reviewed By: arsenm
Subscribers: RKSimon, craig.topper, lenary, aemerson, wuzish, jholewinski, MatzeB, qcolombet, dschuff, jyknight, dylanmckay, sdardis, nemanjai, jvesely, wdng, nhaehnle, sbc100, jgravelle-google, kristof.beyls, hiraditya, aheejin, kbarton, fedor.sergeev, javed.absar, asb, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, jrtc27, MaskRay, zzheng, edward-jones, atanasyan, rogfer01, MartinMosbeck, brucehoult, the_o, tpr, PkmX, jocewei, jsji, Petar.Avramovic, asbirlea, Jim, s.egerton, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65962
llvm-svn: 369041
AMDGPU has some buffer intrinsics which theoretically could use
this. Some of the generated tables include the 3 and 4 element vector
versions of these rounded to 64-bits, which is ambiguous. Add these to
help the table disambiguate these.
Assertion change is for the path odd sized vectors now take for R600.
v3i16 is widened to v4i16, which then needs to be promoted to v4i32.
llvm-svn: 369038
Now that we're using widening legalization. We need to improve our extract_subvector cost model for these types. This patch begins by modeling these as a subvector extract followed by a permute. I've left FIXMEs in the code for future improvements.
Differential Revision: https://reviews.llvm.org/D65892
llvm-svn: 369022
Now that we've moved to C++14, we no longer need the llvm::make_unique
implementation from STLExtras.h. This patch is a mechanical replacement
of (hopefully) all the llvm::make_unique instances across the monorepo.
llvm-svn: 369013
Summary:
xxspltib/vspltisb are 3 cycle PM instructions,
xxleqv is 2 cycle ALU instruction.
We should use xxleqv to set all one vectors.
Reviewers: hfinkel, nemanjai, steven.zhang
Subscribers: hiraditya, kbarton, MaskRay, shchenz, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65529
llvm-svn: 369006
We need to allow any alignment at least 2, not just exactly 2, so that the big
endian loads and stores can be selected successfully. I've also added extra BE
testing for the load and store tests.
Thanks to Oliver for the report.
Differential Revision: https://reviews.llvm.org/D66222
llvm-svn: 368996
If the last step in an FP add reduction allows reassociation and doesn't care
about -0.0, then we are free to recognize that computation as a reduction
that may reorder the intermediate steps.
This is requested directly by PR42705:
https://bugs.llvm.org/show_bug.cgi?id=42705
and solves PR42947 (if horizontal math instructions are actually faster than
the alternative):
https://bugs.llvm.org/show_bug.cgi?id=42947
Differential Revision: https://reviews.llvm.org/D66236
llvm-svn: 368995
Stack loads and stores were already working, but direct stores were not. This
adds the patterns for them, same as predicate loads.
Differential Revision: https://reviews.llvm.org/D66213
llvm-svn: 368988
This patch changes the location of the frame-record (FP, LR) to the
bottom of the callee-saved area. According to the AAPCS the location of
the frame-record within the stackframe is unspecified (section 5.2.3 The
Frame Pointer), so the compiler should be free to choose a different
location.
The reason for changing the location of the frame-record is to prepare
the frame for allocating an SVE area below the callee-saves. This way the
compiler can use the VL-scaled addressing modes to directly access SVE
objects from the frame-pointer.
: :
| stack | | stack |
| args | | args |
+-------+ +-------+
| x30 | | x19 |
| x29 | | x20 |
FP -> |- - - -| | x21 |
| x19 | ==> | x22 |
| x20 | |- - - -|
| x21 | | x30 |
| x22 | | x29 |
+-------+ +-------+ <- FP
|///////| |///////| // realignment gap
|- - - -| |- - - -|
|spills/| |spills/|
| locals| | locals|
SP -> +-------+ +-------+ <- SP
Things to point out:
- The algorithm to find a paired register should be prevented from
accidentally pairing some callee-saved register with LR that is not
FP, since they should always be paired together when the frame
has a frame-record.
- For Darwin platforms the location of the frame-record is unchanged,
since the unwind encoding does not allow for encoding this position
dynamically and other tools currently depend on the former layout.
Reviewers: efriedma, rovka, rengolin, thegameg, greened, t.p.northover
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D65653
llvm-svn: 368987
This adds patterns for selecting trunc instructions from full vectors to i1's
vectors.
Differential Revision: https://reviews.llvm.org/D66201
llvm-svn: 368981
We already had the pattern for just the scalar to vector and bitcast,
but not the case where we wanted zeroes in the high half of the xmm.
llvm-svn: 368972
fp_to_sint is turned into X86cvttp2si during isel preprocessing.
The other redundant isel patterns were removed previously, but I
missed this one because its in the MMX td file.
llvm-svn: 368968
If the width is 256 bits, then we must have AVX so the else here
was unnecessary. Once that's removed then the >= 256 bit code is
identical to the 128 bit code with a different VT so combine them.
llvm-svn: 368956
Implement this single atomic load instruction so that we can compile stack
protector code.
Differential Revision: https://reviews.llvm.org/D66245
llvm-svn: 368923
I'm planning on handling intrinsics that will benefit from checking
the address space enums. Don't bother moving the address collection
for now, since those won't need th enums.
llvm-svn: 368895
Summary:
Fixes PR42973. Tests don't change because simd-arith.ll tests behavior
on unimplemented-simd128, which does not include any temporary
workarounds such as the one removed in this revision.
Reviewers: aheejin
Subscribers: dschuff, sbc100, jgravelle-google, hiraditya, sunfish, dmgreen, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66166
llvm-svn: 368868
Now that we legalize by widening, the element types here won't change. Previously these were modeled as the elements being widened and then the instruction might become an AND or SHL/ASHR pair. But now they'll become something like a ZERO_EXTEND_VECTOR_INREG/SIGN_EXTEND_VECTOR_INREG.
For AVX2, when the destination type is legal its clear the cost should be 1 since we have extend instructions that can produce 256 bit vectors from less than 128 bit vectors. I'm a little less sure about AVX1 costs, but I think the ones I changed were definitely too high, but they might still be too high.
Differential Revision: https://reviews.llvm.org/D66169
llvm-svn: 368858
This patch implements global address lowering for 32/64 bit with small/large code models.
1.For 32bit large code model on AIX, there are newly added pseudo opcode LWZtocL & ADDIStocHA32, the support of which on MC layer will be
provided by future patches.
2.The default code model on AIX should be small code model.
3.Since AIX does not have medium code model, "report_fatal_error" when users specify it.
Differential Revision: https://reviews.llvm.org/D63547
llvm-svn: 368744
That change (r363670) could leave a copy from vgpr to sgpr. Fixed.
Differential Revision: https://reviews.llvm.org/D66133
Change-Id: I00c3fe6fda2e8e1e36f53195b881b1449c777ea4
llvm-svn: 368736
The MVE architecture has the idea of "beats", where a vector instruction can be
executed over several ticks of the architecture. This adds a similar system
into the Arm backend cost model, multiplying the cost of all vector
instructions by a factor.
This factor essentially becomes the expected difference between scalar code
and vector code, on average. MVE Vector instructions can also overlap so the a
true cost of them is often lower. But equally scalar instructions can in some
situations be dual issued, or have other optimisations such as unrolling or
make use of dsp instructions. The default is chosen as 2. This should not
prevent vectorisation is a most cases (as the vector instructions will still be
doing at least 4 times the work), but it will help prevent over vectorising in
cases where the benefits are less likely.
This adds things so far to the obvious places in ARMTargetTransformInfo, and
updates a few related costs like not treating float instructions as cost 2 just
because they are floats.
Differential Revision: https://reviews.llvm.org/D66005
llvm-svn: 368733
Summary:
While D65962 is pending for review, I landed D65475 that added one more
use of `unsigned`. Changed it to `Register`.
Reviewers: dsanders
Subscribers: dschuff, sbc100, jgravelle-google, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66064
llvm-svn: 368727
Trying again with the code changes (and not just the new test).
Summary:
This patch fixes the offsets of fields in the stack frame linkage save
area for AIX.
Reviewers: sfertile, hubert.reinterpretcast, jasonliu, Xiangling_L, xingxue, ZarkoCA, daltenty
Reviewed By: hubert.reinterpretcast
Subscribers: wuzish, nemanjai, hiraditya, kbarton, MaskRay, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64424
Patch by Chris Bowler!
llvm-svn: 368721
Currently shufflemasks get emitted as any other constant, and you end
up with a bunch of virtual registers of G_CONSTANT with a
G_BUILD_VECTOR. The AArch64 selector then asserts on anything that
doesn't fit this pattern. This isn't an ideal representation, and
should avoid legalization and have fewer opportunities for a
representational error.
Rather than invent a new shuffle mask operand type, similar to what
ShuffleVectorSDNode does, just track the original IR Constant mask
operand. I don't completely like the idea of adding another link to
the IR, but MIR is already quite dependent on IR constants already,
and this will allow sharing the shuffle mask utility functions with
the IR.
llvm-svn: 368704
If the target shuffle mask is from a wider type, attempt to scale the mask so that the extraction can attempt to peek through.
Fixes the regression mentioned in rL368662
Reapplying this as rL368308 had to be reverted as part of rL368660 to revert rL368276
llvm-svn: 368663
If we don't demand all elements, then attempt to combine to a simpler shuffle.
At the moment we can only do this if Depth == 0 as combineX86ShufflesRecursively uses Depth to track whether the shuffle has really changed or not - we'll need to change this before we can properly start merging combineX86ShufflesRecursively into SimplifyDemandedVectorElts.
The insertps-combine.ll regression is because XFormVExtractWithShuffleIntoLoad can't see through shuffles of different widths - this will be fixed in a follow-up commit.
Reapplying this as rL368307 had to be reverted as part of rL368660 to revert rL368276
llvm-svn: 368662
This introduced a false positive MemorySanitizer warning about use of
uninitialized memory in a vectorized crc function in Chromium. That suggests
maybe something is not right with this transformation. See
https://crbug.com/992853#c7 for a reproducer.
This also reverts the follow-up commits r368307 and r368308 which
depended on this.
> This patch attempts to peek through vectors based on the demanded bits/elt of a particular ISD::EXTRACT_VECTOR_ELT node, allowing us to avoid dependencies on ops that have no impact on the extract.
>
> In particular this helps remove some unnecessary scalar->vector->scalar patterns.
>
> The wasm shift patterns are annoying - @tlively has indicated that the wasm vector shift codegen are to be refactored in the near-term and isn't considered a major issue.
>
> Differential Revision: https://reviews.llvm.org/D65887
llvm-svn: 368660
The legalizer would hit an assertion on PowerPC platform when truncating
a vector whose size is not power of 2. This patch is to add a check to
prevent vectors with such odd-size elements from being custom lowered.
Reviewed By: Hal Finkel
Differential Revision: https://reviews.llvm.org/D65261
llvm-svn: 368654
Currently we can't keep any state in the selector object that we get from
subtarget. As a result we have to plumb through all our variables through
multiple functions. This change makes it non-const and adds a virtual init()
method to allow further state to be captured for each target.
AArch64 makes use of this in this patch to cache a call to hasFnAttribute()
which is expensive to call, and is used on each selection of G_BRCOND.
Differential Revision: https://reviews.llvm.org/D65984
llvm-svn: 368652
r367088 made it so that funclets store XMM registers into their local
frame instead of storing them to the parent frame. However, that change
forgot to update the parent frame pointer offset for catch blocks. This
change does that.
Fixes crashes when an exception is rethrown in a catch block that saves
XMMs, as described in https://crbug.com/992860.
llvm-svn: 368631
This is infrastructural, will be needed for future work.
For some reason it was only used in MIMG_NoSampler, while
needed everywere we use MIMGBaseOpcode if we want to use
predicates.
Differential Revision: https://reviews.llvm.org/D66115
llvm-svn: 368626
We need AVX512BW to be able to truncate an i16 vector. If we don't
have that we have to extend i16->i32, then trunc, i32->i8. But we
won't be able to remove the min/max if we do that. At least not
without more special handling.
llvm-svn: 368623
If we're after type legalize, we should make sure we won't create
a store with an illegal type when we separate the AVG pattern
from the truncating store.
I don't know of a way to fail for this today. Just noticed while
I was in the vicinity.
llvm-svn: 368608
This teaches the cost model that the sext or zext of a load is going to be
free.
Differential Revision: https://reviews.llvm.org/D66006
llvm-svn: 368593
This pass is a port of the according pass from the HSAIL compiler.
It parses printf calls and setup runtime printf buffer.
After that it copies printf arguments to the buffer and fills in
module metadata for runtime.
Differential Revision: https://reviews.llvm.org/D24035
llvm-svn: 368592
A VDUP will perform a vector broadcast in a single instruction. Update the cost
model for MVE accordingly.
Code originally by David Sherwood.
Differential Revision: https://reviews.llvm.org/D63448
llvm-svn: 368589
This puts some of the calls in ARMTargetTransformInfo.cpp behind hasNeon()
checks, now that we have MVE, and updates all the tests accordingly.
Differential Revision: https://reviews.llvm.org/D63447
llvm-svn: 368587
Summary:
Ana Pazos reported a bug where we were not checking that an APInt would
fit into 64-bits before calling `getSExtValue()`. This caused asserts when
compiling large constants, such as i128s, as happens when compiling compiler-rt.
This patch adds a testcase and makes the callback less error-prone.
Reviewers: apazos, asb, luismarques
Reviewed By: luismarques
Subscribers: hiraditya, rbar, johnrusso, simoncook, sabuasal, niosHD, kito-cheng, shiva0217, jrtc27, MaskRay, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, rkruppe, PkmX, jocewei, psnobl, benna, Jim, s.egerton, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66081
llvm-svn: 368572
Support -march=tigerlake for x86.
Compare with Icelake Client, It include 4 more new features ,they are
avx512vp2intersect, movdiri, movdir64b, shstk.
Patch by Xiang Zhang (xiangzhangllvm)
Differential Revision: https://reviews.llvm.org/D65840
llvm-svn: 368543
Due to the nature of the beat system in the MVE architecture, along with tail
predication and low-overhead loops, unrolling has less benefit compared to
normal loops. You can not, for example, hide the latency of a load with other
instructions as you can for scalar code. Preventing unrolling also makes the
code easier to read and reason about.
So if a loop contains vector code, don't enable the runtime unrolling. At least
for the time being.
Differential Revision: https://reviews.llvm.org/D65803
llvm-svn: 368530
With enough codegen complete, we can now correctly report the number and size
of vector registers for MVE, allowing auto vectorisation. This also allows FP
auto-vectorization for MVE without -Ofast/-ffast-math, due to support for IEEE
FP arithmetic and parity between scalar and vector FP behaviour.
Patch by David Sherwood.
Differential Revision: https://reviews.llvm.org/D63728
llvm-svn: 368529
Summary:
When exceptions are repeatedly thrown in the middle of handling another
exception, we call `__clang_call_terminate` with the exception pointer
(i32) as an argument. But in case of foreign exceptions, we don't have
the pointer, so we call the function with 0. (This requires
`__clang_call_terminate` can deal with 0 argument, which will be done
later)
But previously the 0 argument was not added as a `i32.const 0` but an
immediate by mistake, causing the `call` instruction to take not an i32
but rather an exnref, because an `exnref` is left on top of the value
stack if `br_on_exn` is not taken.
```
block i32
br_on_exn 0, __cpp_exception
;; exnref is on top of stack now
i32.const 0 ;; This was missing!
call __clang_call_terminate
unreachable
end
call __clang_call_terminate ;; This takes i32 extracted by br_on_exn
```
Reviewers: dschuff
Subscribers: sbc100, jgravelle-google, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65475
llvm-svn: 368527
The test case that changed is probably better served through
allowing combineTruncatedArithmetic to create narrow vectors. It
also appears InstCombine would have simplified this test case
to remove the zext and trunc anyway.
llvm-svn: 368522
On SSE41+ targets we always lower vector shuffles to ZERO_EXTEND_VECTOR_INREG, even if we don't need the extended bits.
This patch relaxes this so that we lower to ANY_EXTEND_VECTOR_INREG if we can, meaning that shuffle combines have a better idea of what elements need to be kept zero. This helps the multiple reduction code as we can now combine away a lot more of the pack+extend codes.
Differential Revision: https://reviews.llvm.org/D65741
llvm-svn: 368515
Summary:
This patch adds a special DAG combine for SSE1 to recognize the IR pattern InstCombine gives us for movmsk. This only does the recognition for a few cases where its obvious the input won't be scalarized resulting in building a vector just do to the movmsk. I've made it separate from our existing matching for movmsk since that's called in multiple places and I didn't spend time to see if the other callers would make sense here. Plus the restrictions and additional checks would complicate that.
This fixes the case from PR42870. Buts its probably still broken the presence of logic ops feeding the movmsk pattern which would further hide the v4f32 type.
Reviewers: spatel, RKSimon, xbolva00
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65689
llvm-svn: 368506
Summary:
On windows if the frame size exceed 4096 bytes, compiler need to
generate a call to _alloca_probe. X86CallFrameOptimization pass
changes the reserved stack size and cause of stack probe function
not be inserted. This patch fix the issue by detecting the call
frame size, if the size exceed 4096 bytes, drop X86CallFrameOptimization.
Reviewers: craig.topper, wxiao3, annita.zhang, rnk, RKSimon
Reviewed By: rnk
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65923
llvm-svn: 368503
Summary:
Targets often have instructions that can sign-extend certain cases faster
than the equivalent shift-left/arithmetic-shift-right. Such cases can be
identified by matching a shift-left/shift-right pair but there are some
issues with this in the context of combines. For example, suppose you can
sign-extend 8-bit up to 32-bit with a target extend instruction.
%1:_(s32) = G_SHL %0:_(s32), i32 24 # (I've inlined the G_CONSTANT for brevity)
%2:_(s32) = G_ASHR %1:_(s32), i32 24
%3:_(s32) = G_ASHR %2:_(s32), i32 1
would reasonably combine to:
%1:_(s32) = G_SHL %0:_(s32), i32 24
%2:_(s32) = G_ASHR %1:_(s32), i32 25
which no longer matches the special case. If your shifts and extend are
equal cost, this would break even as a pair of shifts but if your shift is
more expensive than the extend then it's cheaper as:
%2:_(s32) = G_SEXT_INREG %0:_(s32), i32 8
%3:_(s32) = G_ASHR %2:_(s32), i32 1
It's possible to match the shift-pair in ISel and emit an extend and ashr.
However, this is far from the only way to break this shift pair and make
it hard to match the extends. Another example is that with the right
known-zeros, this:
%1:_(s32) = G_SHL %0:_(s32), i32 24
%2:_(s32) = G_ASHR %1:_(s32), i32 24
%3:_(s32) = G_MUL %2:_(s32), i32 2
can become:
%1:_(s32) = G_SHL %0:_(s32), i32 24
%2:_(s32) = G_ASHR %1:_(s32), i32 23
All upstream targets have been configured to lower it to the current
G_SHL,G_ASHR pair but will likely want to make it legal in some cases to
handle their faster cases.
To follow-up: Provide a way to legalize based on the constant. At the
moment, I'm thinking that the best way to achieve this is to provide the
MI in LegalityQuery but that opens the door to breaking core principles
of the legalizer (legality is not context sensitive). That said, it's
worth noting that looking at other instructions and acting on that
information doesn't violate this principle in itself. It's only a
violation if, at the end of legalization, a pass that checks legality
without being able to see the context would say an instruction might not be
legal. That's a fairly subtle distinction so to give a concrete example,
saying %2 in:
%1 = G_CONSTANT 16
%2 = G_SEXT_INREG %0, %1
is legal is in violation of that principle if the legality of %2 depends
on %1 being constant and/or being 16. However, legalizing to either:
%2 = G_SEXT_INREG %0, 16
or:
%1 = G_CONSTANT 16
%2:_(s32) = G_SHL %0, %1
%3:_(s32) = G_ASHR %2, %1
depending on whether %1 is constant and 16 does not violate that principle
since both outputs are genuinely legal.
Reviewers: bogner, aditya_nandakumar, volkan, aemerson, paquette, arsenm
Subscribers: sdardis, jvesely, wdng, nhaehnle, rovka, kristof.beyls, javed.absar, hiraditya, jrtc27, atanasyan, Petar.Avramovic, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D61289
llvm-svn: 368487
As discussed on PR42825, if we are inverting the selection mask we can just swap the inputs and avoid the inversion.
Differential Revision: https://reviews.llvm.org/D65522
llvm-svn: 368438
Fast-isel was picking AFGR64 register class for processing call
arguments when +fp64 options was used. We simply check is option +fp64
is used and pick appropriate register.
Patch by Mirko Brkusanin.
Differential Revision: https://reviews.llvm.org/D65886
llvm-svn: 368433
All TLS access on Darwin is in the "general dynamic" form where we call
a function to resolve the address, so implementation is pretty simple.
llvm-svn: 368418
I've now needed to add an extra parameter to this call twice recently. Not only
is the signature getting extremely unwieldy, but just updating all of the
callsites and implementations is a pain. Putting the parameters in a struct
sidesteps both issues.
llvm-svn: 368408
As loads are combined and widened, we replaced their sext users
operands whereas we should have been replacing the uses of the sext.
I've added a load of tests, with only a few of them originally
causing assertion failures, the rest improve pattern coverage.
Differential Revision: https://reviews.llvm.org/D65740
llvm-svn: 368404
The only way to generate these was through promoting legalization
of narrow vectors, but we widen those types now. So we shouldn't
produce these nodes.
llvm-svn: 368396
Under this configuration we'll want to split the v8i64 or v16i32 into two vectors. The default legalization will try to truncate each of those 256-bit pieces one step to 128-bit, concatenate those, then truncate one more time from the new 256 to 128 bits.
With this patch we now truncate the two splits to 64-bits then concatenate those. We have to do this two different ways depending on whether have widening legalization enabled. Without widening legalization we have to manually construct X86ISD::VTRUNC to prevent the ISD::TRUNCATE with a narrow result being promoted to 128 bits with a larger element type than what we want followed by something like a pshufb to grab the lower half of each element to finish the job. With widening legalization we just get the right thing. When we switch to widening by default we can just delete the other code path.
Differential Revision: https://reviews.llvm.org/D65626
llvm-svn: 368349
This fixes znver1 so that it properly enables CMPXHG8B. We can
probably remove explicit CMPXCHG8B from CPUs that also have
CMPXCHG16B, but keeping this simple to allow cherry pick to 9.0.
Fixes PR42935.
llvm-svn: 368324
Summary:
The A64 assembly language does not require the '#' character to
introduce constant immediate operands. Avoid the '#' since the AArch64
asm parser does not accept '#' before the lane specifier and rejects the
following:
__asm__ ("fmla v2.4s, v0.4s, v1.s[%0]" :: "I"(0x1))
Fix a test to not expect the '#' and add a new test case with the above
asm.
Fixes: https://github.com/android-ndk/ndk/issues/1036
Reviewers: peter.smith, kristof.beyls
Subscribers: javed.absar, hiraditya, llvm-commits, srhines
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65550
llvm-svn: 368320
If the target shuffle mask is from a wider type, attempt to scale the mask so that the extraction can attempt to peek through.
Fixes the regression mentioned in rL368307
llvm-svn: 368308
If we don't demand all elements, then attempt to combine to a simpler shuffle.
At the moment we can only do this if Depth == 0 as combineX86ShufflesRecursively uses Depth to track whether the shuffle has really changed or not - we'll need to change this before we can properly start merging combineX86ShufflesRecursively into SimplifyDemandedVectorElts.
The insertps-combine.ll regression is because XFormVExtractWithShuffleIntoLoad can't see through shuffles of different widths - this will be fixed in a follow-up commit.
llvm-svn: 368307
Summary:
This patch enable assembly output of local commons for AIX using .lcomm
directives. Adds a EmitXCOFFLocalCommonSymbol to MCStreamer so we can emit the
AIX version of .lcomm assembly directives which include a csect name. Handle the
case of BSS locals in PPCAIXAsmPrinter by using EmitXCOFFLocalCommonSymbol. Adds
a test for generating .lcomm on AIX Targets.
Reviewers: cebowleratibm, hubert.reinterpretcast, Xiangling_L, jasonliu, sfertile
Reviewed By: sfertile
Subscribers: wuzish, nemanjai, hiraditya, kbarton, MaskRay, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64825
llvm-svn: 368306
This adds pre- and post- increment and decrements for MVE loads and stores. It
uses the builtin pre and post load/store detection, unlike Neon. Loads are
selected with the code in tryT2IndexedLoad, stores are selected with tablegen
patterns. The immediates have a +/-7bit range, multiplied by the size of the
element.
Differential Revision: https://reviews.llvm.org/D63840
llvm-svn: 368305
This adds some missing patterns for big endian loads/stores, allowing unaligned
loads/stores to also be selected with an extra VREV, which produces better code
than aligning through a stack. Also moves VLDR_P0 to not be LE only, and
adjusts some of the tests to show all that working.
Differential Revision: https://reviews.llvm.org/D65583
llvm-svn: 368304
Summary:
Clang will replace references to registers using ABI names in inline
assembly constraints with references to architecture names, but other
frontends do not. LLVM uses the regular assembly parser to parse inline asm,
so inline assembly strings can contain references to registers using their
ABI names.
This patch adds support for parsing constraints using either the ABI name or
the architectural register name. This means we do not need to implement the
ABI name replacement code in every single frontend, especially those like
Rust which are a very thin shim on top of LLVM IR's inline asm, and that
constraints can more closely match the assembly strings they refer to.
Reviewers: asb, simoncook
Reviewed By: simoncook
Subscribers: hiraditya, rbar, johnrusso, JDevlieghere, apazos, sabuasal, niosHD, kito-cheng, shiva0217, jrtc27, MaskRay, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, rkruppe, PkmX, jocewei, psnobl, benna, Jim, s.egerton, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65947
llvm-svn: 368303
Summary:
Currently the RISC-V backend does not realign the stack. This can be an issue even for the RV32I/RV64I ABIs (where the stack is 16-byte aligned), though is rare. It will be much more comment with RV32E (though the alignment requirements for common data types remain under-documented...).
This patch adds minimal support for stack realignment. It should cope with large realignments. It will error out if the stack needs realignment and variable sized objects are present.
It feels like a lot of the code like getFrameIndexReference and determineFrameLayout could be refactored somehow, as right now it feels fiddly and brittle. We also seem to allocate a lot more memory than GCC does for equivalent C code.
Reviewers: asb
Reviewed By: asb
Subscribers: wwei, jrtc27, s.egerton, MaskRay, Jim, lenary, hiraditya, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, rkruppe, PkmX, jocewei, psnobl, benna, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62007
llvm-svn: 368300
G_JUMP_TABLE and G_BRJT appear from translation of switch statement.
Select these two instructions for MIPS32, both pic and non-pic.
Differential Revision: https://reviews.llvm.org/D65861
llvm-svn: 368274
VLDRH needs to have an alignment of at least 2, including the
widening/narrowing versions. This tightens up the ISel patterns for it and
alters allowsMisalignedMemoryAccesses so that unaligned accesses are expanded
through the stack. It also fixed some incorrect shift amounts, which seemed to
be passing a multiple not a shift.
Differential Revision: https://reviews.llvm.org/D65580
llvm-svn: 368256
If we're splitting the 512-bit vector anyway and we have zero/sign bits, then we might as well use pack instructions to concat and truncate at once.
Differential Revision: https://reviews.llvm.org/D65904
llvm-svn: 368210
The assert that caused this to be reverted should be fixed now.
Original commit message:
This patch changes our defualt legalization behavior for 16, 32, and
64 bit vectors with i8/i16/i32/i64 scalar types from promotion to
widening. For example, v8i8 will now be widened to v16i8 instead of
promoted to v8i16. This keeps the elements widths the same and pads
with undef elements. We believe this is a better legalization strategy.
But it carries some issues due to the fragmented vector ISA. For
example, i8 shifts and multiplies get widened and then later have
to be promoted/split into vXi16 vectors.
This has the potential to cause regressions so we wanted to get
it in early in the 10.0 cycle so we have plenty of time to
address them.
Next steps will be to merge tests that explicitly test the command
line option. And then we can remove the option and its associated
code.
llvm-svn: 368183
Prevent the LoadStoreOptimizer from pairing any load/store instructions with
instructions from the prologue/epilogue if the CFI information has encoded the
operations as separate instructions. This would otherwise lead to a mismatch
of the actual prologue size from the size as recorded in the Windows CFI.
Reviewers: efriedma, mstorsjo, ssijaric
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D65817
llvm-svn: 368164
Function MipsAsmParser::expandMemInst() did not properly handle
instruction `sc` with a symbol as an argument because first argument
would be counted twice. We add additional checks and handle this case
separately.
Patch by Mirko Brkusanin.
Differential Revision: https://reviews.llvm.org/D64252
llvm-svn: 368160
Currently we check whether LR is stored/loaded to/from inbetween the
loop decrement and loop end pseudo instructions. There's two problems
here:
- It relies on all load/store instructions being labelled as such in
tablegen.
- Actually any use of loop decrement is troublesome because the value
doesn't exist!
So we need to check for any read/write of LR that occurs between the
two instructions and revert if we find anything.
Differential Revision: https://reviews.llvm.org/D65792
llvm-svn: 368130
We have aliases that disambiguate memory forms of bt/btc/btr/bts
without suffixes to the 32-bit form. These aliases should have
been updated when the instructions were updated in r356413.
llvm-svn: 368127
The upper 4 bits of the immediate byte are used to encode a
register. We need to limit the explicit immediate to fit in the
remaining 4 bits.
Fixes PR42899.
llvm-svn: 368123
If we're after type legalization we should only be trying to turn
v2i64 into v2i32. So bitcast to v4i32, shuffle the even elements
together. Then use X86ISD::CVTSI2P. The alternative is to leave
the v2i64 type alone and let it scalarized. Hopefully keeping
it packed is better.
Fixes PR42905.
llvm-svn: 368091
https://reviews.llvm.org/D65698
This adds a KnownBits analysis pass for GISel. This was done as a
pass (compared to static functions) so that we can add other features
such as caching queries(within a pass and across passes) in the future.
This patch only adds the basic pass boiler plate, and implements a lazy
non caching knownbits implementation (ported from SelectionDAG). I've
also hooked up the AArch64PreLegalizerCombiner pass to use this - there
should be no compile time regression as the analysis is lazy.
llvm-svn: 368065
Summary:
This is tested by D61289 but has been pulled into a separate patch at
a reviewers request.
Reviewers: bogner, aditya_nandakumar, volkan, aemerson, paquette, arsenm, rovka
Reviewed By: arsenm
Subscribers: javed.absar, hiraditya, wdng, kristof.beyls, Petar.Avramovic, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D61321
llvm-svn: 368063
Summary:
Cleans X86.td's Barcelona entry to be more like the others,
by moving the features out of the `Proc<>`, thus potentially
making it possible to inherit from them.
Split off from D63628
Reviewers: craig.topper, RKSimon
Reviewed By: craig.topper
Subscribers: hiraditya, jfb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65791
llvm-svn: 368061
Refactor emitFrameOffset to accept a StackOffset struct as its offset argument.
This method currently only supports byte offsets (MVT::i8) but will be extended
in a later patch to support scalable offsets (MVT::nxv1i8) as well.
Reviewers: thegameg, rovka, t.p.northover, efriedma, greened
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D61436
llvm-svn: 368049
To support spilling/filling of scalable vectors we need a more generic
representation of a stack offset than simply 'int'.
For this we introduce the StackOffset struct, which comprises multiple
offsets sized by their respective MVTs. Byte-offsets will thus be a simple
tuple such as { offset, MVT::i8 }. Adding two byte-offsets will result in a
byte offset { offsetA + offsetB, MVT::i8 }. When two offsets have different
types, we can canonicalise them to use the same MVT, as long as their
runtime sizes are guaranteed to have the same size-ratio as they would have
at compile-time.
When we have both scalable- and fixed-size objects on the stack, we can
create an offset that is:
({ offset_fixed, MVT::i8 } + { offset_scalable, MVT::nxv1i8 })
The struct also contains a getForFrameOffset() method that is specific to
AArch64 and decomposes the frame-offset to be used directly in instructions
that operate on the stack or index into the stack.
Note: This patch adds StackOffset as an AArch64-only concept, but we would
like to make this a generic concept/struct that is supported by all
interfaces that take or return stack offsets (currently as 'int'). Since
that would be a bigger change that is currently pending on D32530 landing,
we thought it makes sense to first show/prove the concept in the AArch64
target before proposing to roll this out further.
Reviewers: thegameg, rovka, t.p.northover, efriedma, greened
Reviewed By: rovka, greened
Differential Revision: https://reviews.llvm.org/D61435
llvm-svn: 368024
If we don't demand any non-undef shuffle elements then the assert will fail as all shuffle inputs would still be flagged as 'identity' safe.
Exposed by an incoming patch.
llvm-svn: 368022
Summary:
Before this patch MGATHER/MSCATTER is capable of representing all
common addressing modes, but only when illegal types are used.
This patch adds an IndexType property so more representations
are available when using legal types only.
Original modes:
vector of bases
base + vector of signed scaled offsets
New modes:
base + vector of signed unscaled offsets
base + vector of unsigned scaled offsets
base + vector of unsigned unscaled offsets
The current behaviour of addressing modes for gather/scatter remains
unchanged.
Patch by Paul Walker.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D65636
llvm-svn: 368008
Summary:
When the WebAssembly backend encounters a return type that doesn't
fit within i32, SelectionDAG performs sret demotion, adding an
additional argument to the start of the function that contains
a pointer to an sret buffer to use instead. However, this conflicts
with the emscripten sjlj lowering pass. There we translate calls like:
```
call {i32, i32} @foo()
```
into (in pseudo-llvm)
```
%addr = @foo
call {i32, i32} @__invoke_{i32,i32}(%addr)
```
i.e. we perform an indirect call through an extra function.
However, the sret transform now transforms this into
the equivalent of
```
%addr = @foo
%sret = alloca {i32, i32}
call {i32, i32} @__invoke_{i32,i32}(%sret, %addr)
```
(while simultaneously translation the implementation of @foo as well).
Unfortunately, this doesn't work out. The __invoke_ ABI expected
the function address to be the first argument, causing crashes.
There is several possible ways to fix this:
1. Implementing the sret rewrite at the IR level as well and performing
it as part of lowering to __invoke
2. Fixing the wasm backend to recognize that __invoke has a special ABI
3. A change to the binaryen/emscripten ABI to recognize this situation
This revision implements the middle option, teaching the backend to
treat __invoke_ functions specially in sret lowering. This is achieved
by
1) Introducing a new CallingConv ID for invoke functions
2) When this CallingConv ID is seen in the backend and the first argument
is marked as sret (a function pointer would never be marked as sret),
swapping the first two arguments.
Reviewed By: tlively, aheejin
Differential Revision: https://reviews.llvm.org/D65463
llvm-svn: 367935
FastISel already does this since the initial arm64 port was upstreamed, so
it seems there are no issues with doing this at -O0 for very small memcpys.
Gives a 0.2% geomean code size improvement on CTMark.
Differential Revision: https://reviews.llvm.org/D65758
llvm-svn: 367919
This patch changes our defualt legalization behavior for 16, 32, and
64 bit vectors with i8/i16/i32/i64 scalar types from promotion to
widening. For example, v8i8 will now be widened to v16i8 instead of
promoted to v8i16. This keeps the elements widths the same and pads
with undef elements. We believe this is a better legalization strategy.
But it carries some issues due to the fragmented vector ISA. For
example, i8 shifts and multiplies get widened and then later have
to be promoted/split into vXi16 vectors.
This has the potential to cause regressions so we wanted to get
it in early in the 10.0 cycle so we have plenty of time to
address them.
Next steps will be to merge tests that explicitly test the command
line option. And then we can remove the option and its associated
code.
llvm-svn: 367901
Patch D56593 by @courbet results in calls to `bcmp()` in some cases, should
the target support the it. Unless `TTI::MemCmpExpansionOptions()`
is overridden by the target.
In a proprietary benchmark we see a performance drop of about 12% on PNG
compression before this patch, though it passes all tests.
This patch mirrors X86 for AArch64 and initializes
`TTI::MemCmpExpansionOptions()` to then expand calls to `bcmp()` when
appropriate. No tuning of the parameters was performed, but, at this point,
it's enough to recover the performance drop above.
This problem also exists on ARM. Once a consensus is reached for AArch64, we
can work to fix ARM as well.
Authors:
- Evandro Menezes (@evandro) <e.menezes@samsung.com>
- Brian Rzycki (@brzycki) <b.rzycki@samsung.com>
Differential revision: https://reviews.llvm.org/D64805
llvm-svn: 367898
Summary:
The Arm Neoverse N1 Software Optimization Guide [1], Section "4.8 Branch
instruction alignment" states:
"Consider aligning subroutine entry points and branch targets to 32B
boundaries, within the bounds of the code-density requirements of the
program."
This patch sets the preferred function alignment on Neoverse N1 to 2^4=16B.
This was already the case in some of the latest Cortex-A CPUs. Benchmarking
in previous Cortex-A CPUs suggested that 16B alignment is already better
than the default. See commit d04ee305.
The reason we don't set it to 32B right now (as the optimisation guide
suggests) is that this will impact code size and perhaps the instruction
cache performance. Therefore we need benchmark numbers first.
I have also added testing for A75 and A76 that we were missing.
[1] https://developer.arm.com/docs/swog309707/latest
Reviewers: fhahn, greened, samparker, dmgreen
Reviewed By: dmgreen
Subscribers: dmgreen, javed.absar, kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65654
llvm-svn: 367894
Summary:
This is a follow up to r367237. MachineFunction::getMachineMemOperand()
adds the offset parameter to the existing offset instead of resetting it.
So we need to reset the offset to the correct value after calling this
function.
Reviewers: arsenm
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65557
llvm-svn: 367881
This was switching to use a format store for a non-format store for
f16 types. Also fixes i16/f16 stores on targets without legal f16.
The corresponding loads also need to be fixed.
llvm-svn: 367872
Without context we assume SGPR. Allowing VGPR constants theoretically
helps avoid a copy. This seems to not actually work now, and the
choice isn't based on the use bank.
llvm-svn: 367871
I'm not sure what complications these present, but the current
argument lowering is pretty much directly copied from the DAG
lowering, so I assume these work as they should.
No tests because I'm lazy and things are getting pretty close to the
point where the existing calling-conventions.ll can be shared with
SelectionDAG.
llvm-svn: 367870
Summary:
This patch adds initial support for the SVE calling convention such that
SVE types can be passed as arguments and return values to/from a
subroutine.
The SVE AAPCS states [1]:
z0-z7 are used to pass scalable vector arguments to a subroutine,
and to return scalable vector results from a function. If a
subroutine takes arguments in scalable vector or predicate
registers, or if it is a function that returns results in such
registers, it must ensure that the entire contents of z8-z23 are
preserved across the call. In other cases it need only preserve the
low 64 bits of z8-z15, as described in §5.1.2.
p0-p3 are used to pass scalable predicate arguments to a subroutine
and to return scalable predicate results from a function. If a
subroutine takes arguments in scalable vector or predicate
registers, or if it is a function that returns results in these
registers, it must ensure that p4-p15 are preserved across the call.
In other cases it need not preserve any scalable predicate register
contents.
SVE predicate and data registers are passed indirectly (i.e. spilled to the
stack and pass the address) if they exceed the registers used for argument
passing defined by the PCS referenced above. Until SVE stack support is merged
we can't spill SVE registers to the stack, so currently an llvm_unreachable is
used where we will eventually handle this.
[1] https://static.docs.arm.com/100986/0000/100986_0000.pdf
Reviewed By: ostannard
Differential Revision: https://reviews.llvm.org/D65448
llvm-svn: 367859
The test case is based on the example from the post-commit thread for:
https://reviews.llvm.org/rGc9171bd0a955
This replaces the x86-specific simple-type check from:
rL367766
with a check in the DAGCombiner. Adding the check isn't
strictly necessary after the fix from:
rL367768
...but it seems likely that we're heading for trouble if
we are creating weird types in this transform.
I combined the earlier legality check into the initial
clause to simplify the code.
So we should only try the trunc/sext transform at the
earliest combine stage, but we limit the transform to
simple types anyway because the TLI hook is probably
too lax about what it considers a free truncate.
llvm-svn: 367834
We process 2 elements at a time and expect the number of elements to be
even. Similar to D60690.
Reviewers: dmgreen, samparker, t.p.northover
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D65400
llvm-svn: 367831
Summary:
This is patch is part of a serie to introduce an Alignment type.
See this thread for context: http://lists.llvm.org/pipermail/llvm-dev/2019-July/133851.html
See this patch for the introduction of the type: https://reviews.llvm.org/D64790
Reviewers: courbet, jfb, jakehehrlich
Reviewed By: jfb
Subscribers: wuzish, jholewinski, arsenm, dschuff, nemanjai, jvesely, nhaehnle, javed.absar, sbc100, jgravelle-google, hiraditya, aheejin, kbarton, asb, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, jrtc27, MaskRay, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, dexonsmith, PkmX, jocewei, jsji, s.egerton, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65514
llvm-svn: 367828
Add an explicit construction of the ArrayRef, gcc 5 and earlier don't
seem to select the ArrayRef constructor which takes a C array when the
construction is implicit.
Original commit message:
- Avoid a crash when IPRA calls ARMFrameLowering::determineCalleeSaves
with a null RegScavenger. Simply not updating the register scavenger
is fine because IPRA only cares about the SavedRegs vector, the acutal
code of the function has already been generated at this point.
- Add a new hook to TargetRegisterInfo to get the set of registers which
can be clobbered inside a call, even if the compiler can see both
sides, by linker-generated code.
Differential revision: https://reviews.llvm.org/D64908
llvm-svn: 367819
Summary:
The SimplifyDemandedVectorElts function can replace with undef
when no elements are demanded, but due to how it interacts with
TargetLoweringOpts, it can only do this when the node has
no other users.
Remove a now unneeded DAG combine from the X86 backend.
Reviewers: RKSimon, spatel
Reviewed By: RKSimon
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65713
llvm-svn: 367788
Roman Lebedev