Recommiting after fixup of 32-bit aliasing sign offset bug in DAGCombiner.
* Simplify Consecutive Merge Store Candidate Search
Now that address aliasing is much less conservative, push through
simplified store merging search and chain alias analysis which only
checks for parallel stores through the chain subgraph. This is cleaner
as the separation of non-interfering loads/stores from the
store-merging logic.
When merging stores search up the chain through a single load, and
finds all possible stores by looking down from through a load and a
TokenFactor to all stores visited.
This improves the quality of the output SelectionDAG and the output
Codegen (save perhaps for some ARM cases where we correctly constructs
wider loads, but then promotes them to float operations which appear
but requires more expensive constant generation).
Some minor peephole optimizations to deal with improved SubDAG shapes (listed below)
Additional Minor Changes:
1. Finishes removing unused AliasLoad code
2. Unifies the chain aggregation in the merged stores across code
paths
3. Re-add the Store node to the worklist after calling
SimplifyDemandedBits.
4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is
arbitrary, but seems sufficient to not cause regressions in
tests.
5. Remove Chain dependencies of Memory operations on CopyfromReg
nodes as these are captured by data dependence
6. Forward loads-store values through tokenfactors containing
{CopyToReg,CopyFromReg} Values.
7. Peephole to convert buildvector of extract_vector_elt to
extract_subvector if possible (see
CodeGen/AArch64/store-merge.ll)
8. Store merging for the ARM target is restricted to 32-bit as
some in some contexts invalid 64-bit operations are being
generated. This can be removed once appropriate checks are
added.
This finishes the change Matt Arsenault started in r246307 and
jyknight's original patch.
Many tests required some changes as memory operations are now
reorderable, improving load-store forwarding. One test in
particular is worth noting:
CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store
forwarding converts a load-store pair into a parallel store and
a memory-realized bitcast of the same value. However, because we
lose the sharing of the explicit and implicit store values we
must create another local store. A similar transformation
happens before SelectionDAG as well.
Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle
llvm-svn: 296252
When generating a floating point comparison we currently unconditionally
generate VCMPE. This has the sideeffect of setting the cumulative Invalid
bit in FPSCR if any of the operands are QNaN.
It is expected that use of a relational predicate on a QNaN value should
raise Invalid. Quoting from the C standard:
The relational and equality operators support the usual mathematical
relationships between numeric values. For any ordered pair of numeric
values exactly one of relationships the less, greater, equal and is true.
Relational operators may raise the floating-point exception when argument
values are NaNs.
The standard doesn't explicitly state the expectation for equality operators,
but the implication and obvious expectation is that equality operators
should not raise Invalid on a QNaN input, as those predicates are wholly
defined on unordered inputs (to return not equal).
Therefore, add a new operand to ARMISD::FPCMP and FPCMPZ indicating if
QNaN should raise Invalid, and pipe that through to TableGen.
llvm-svn: 294945
Recommiting after fixing X86 inc/dec chain bug.
* Simplify Consecutive Merge Store Candidate Search
Now that address aliasing is much less conservative, push through
simplified store merging search and chain alias analysis which only
checks for parallel stores through the chain subgraph. This is cleaner
as the separation of non-interfering loads/stores from the
store-merging logic.
When merging stores search up the chain through a single load, and
finds all possible stores by looking down from through a load and a
TokenFactor to all stores visited.
This improves the quality of the output SelectionDAG and the output
Codegen (save perhaps for some ARM cases where we correctly constructs
wider loads, but then promotes them to float operations which appear
but requires more expensive constant generation).
Some minor peephole optimizations to deal with improved SubDAG shapes (listed below)
Additional Minor Changes:
1. Finishes removing unused AliasLoad code
2. Unifies the chain aggregation in the merged stores across code
paths
3. Re-add the Store node to the worklist after calling
SimplifyDemandedBits.
4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is
arbitrary, but seems sufficient to not cause regressions in
tests.
5. Remove Chain dependencies of Memory operations on CopyfromReg
nodes as these are captured by data dependence
6. Forward loads-store values through tokenfactors containing
{CopyToReg,CopyFromReg} Values.
7. Peephole to convert buildvector of extract_vector_elt to
extract_subvector if possible (see
CodeGen/AArch64/store-merge.ll)
8. Store merging for the ARM target is restricted to 32-bit as
some in some contexts invalid 64-bit operations are being
generated. This can be removed once appropriate checks are
added.
This finishes the change Matt Arsenault started in r246307 and
jyknight's original patch.
Many tests required some changes as memory operations are now
reorderable, improving load-store forwarding. One test in
particular is worth noting:
CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store
forwarding converts a load-store pair into a parallel store and
a memory-realized bitcast of the same value. However, because we
lose the sharing of the explicit and implicit store values we
must create another local store. A similar transformation
happens before SelectionDAG as well.
Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle
llvm-svn: 293893
* Simplify Consecutive Merge Store Candidate Search
Now that address aliasing is much less conservative, push through
simplified store merging search and chain alias analysis which only
checks for parallel stores through the chain subgraph. This is cleaner
as the separation of non-interfering loads/stores from the
store-merging logic.
When merging stores search up the chain through a single load, and
finds all possible stores by looking down from through a load and a
TokenFactor to all stores visited.
This improves the quality of the output SelectionDAG and the output
Codegen (save perhaps for some ARM cases where we correctly constructs
wider loads, but then promotes them to float operations which appear
but requires more expensive constant generation).
Some minor peephole optimizations to deal with improved SubDAG shapes (listed below)
Additional Minor Changes:
1. Finishes removing unused AliasLoad code
2. Unifies the chain aggregation in the merged stores across code
paths
3. Re-add the Store node to the worklist after calling
SimplifyDemandedBits.
4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is
arbitrary, but seems sufficient to not cause regressions in
tests.
5. Remove Chain dependencies of Memory operations on CopyfromReg
nodes as these are captured by data dependence
6. Forward loads-store values through tokenfactors containing
{CopyToReg,CopyFromReg} Values.
7. Peephole to convert buildvector of extract_vector_elt to
extract_subvector if possible (see
CodeGen/AArch64/store-merge.ll)
8. Store merging for the ARM target is restricted to 32-bit as
some in some contexts invalid 64-bit operations are being
generated. This can be removed once appropriate checks are
added.
This finishes the change Matt Arsenault started in r246307 and
jyknight's original patch.
Many tests required some changes as memory operations are now
reorderable, improving load-store forwarding. One test in
particular is worth noting:
CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store
forwarding converts a load-store pair into a parallel store and
a memory-realized bitcast of the same value. However, because we
lose the sharing of the explicit and implicit store values we
must create another local store. A similar transformation
happens before SelectionDAG as well.
Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle
llvm-svn: 293184
GCC changes the CC between the user-code and the builtins based on the
value of `-target` rather than `-mfloat-abi`. When a HF target is used,
the VFP variant of the AAPCS CC is used. Otherwise, the AAPCS variant
is used. In all cases, the AEABI functions use the AAPCS CC. Adjust
the calling convention based on the target.
Resolves PR30543!
llvm-svn: 291909
See https://reviews.llvm.org/D6678 for the history of
isExtractSubvectorCheap. Essentially the same considerations apply
to ARM.
This temporarily breaks the formation of vpadd/vpaddl in certain cases;
AddCombineToVPADDL essentially assumes that we won't form VUZP shuffles.
See https://reviews.llvm.org/D27779 for followup fix.
Differential Revision: https://reviews.llvm.org/D27774
llvm-svn: 290198
Currently, there are substantial problems forming vld1_dup even if the
VDUP survives legalization. The lack of an actual node
leads to terrible results: not only can we not form post-increment vld1_dup
instructions, but we form scalar pre-increment and post-increment
loads which force the loaded value into a GPR. This patch fixes that
by combining the vdup+load into an ARMISD node before DAGCombine
messes it up.
Also includes a crash fix for vld2_dup (see testcase @vld2dupi8_postinc_variable).
Recommiting with fix to avoid forming vld1dup if the type of the load
doesn't match the type of the vdup (see
https://llvm.org/bugs/show_bug.cgi?id=31404).
Differential Revision: https://reviews.llvm.org/D27694
llvm-svn: 289972
Add two public methods to ARMTargetLowering: CCAssignFnForCall and
CCAssignFnForReturn, which are just calling the already existing private method
CCAssignFnForNode. These will come in handy for GlobalISel on ARM.
We also replace all calls to CCAssignFnForNode in ARMISelLowering.cpp, because
the new methods are friendlier to the reader.
llvm-svn: 289932
Currently, there are substantial problems forming vld1_dup even if the
VDUP survives legalization. The lack of an actual node
leads to terrible results: not only can we not form post-increment vld1_dup
instructions, but we form scalar pre-increment and post-increment
loads which force the loaded value into a GPR. This patch fixes that
by combining the vdup+load into an ARMISD node before DAGCombine
messes it up.
Also includes a crash fix for vld2_dup (see testcase @vld2dupi8_postinc_variable).
Differential Revision: https://reviews.llvm.org/D27694
llvm-svn: 289703
This patch assigns cost of the scaling used in addressing.
On many ARM cores, a negated register offset takes longer than a
non-negated register offset, in a register-offset addressing mode.
For instance:
LDR R0, [R1, R2 LSL #2]
LDR R0, [R1, -R2 LSL #2]
Above, (1) takes less cycles than (2).
By assigning appropriate scaling factor cost, we enable the LLVM
to make the right trade-offs in the optimization and code-selection phase.
Differential Revision: http://reviews.llvm.org/D24857
Reviewers: jmolloy, rengolin
llvm-svn: 284127
Move the target specific setup into the target specific lowering setup. As
pointed out by Anton, the initial change was moving this too high up the stack
resulting in a violation of the layering (the target generic code path setup
target specific bits). Sink this into the ARM specific setup. NFC.
llvm-svn: 281088
At higher optimization levels, we generate the libcall for DIVREM_Ix, which is
fine: aeabi_{u|i}divmod. At -O0 we generate the one for REM_Ix, which is the
default {u}mod{q|h|s|d}i3.
This commit makes sure that we don't generate REM_Ix calls for ABIs that
don't support them (i.e. where we need to use DIVREM_Ix instead). This is
achieved by bailing out of FastISel, which can't handle non-double multi-reg
returns, and letting the legalization infrastructure expand the REM_Ix calls.
It also updates the divmod-eabi.ll test to run under -O0 as well, and adds some
Windows checks to it to make sure we don't break things for it.
Fixes PR27068
Differential Revision: https://reviews.llvm.org/D21926
llvm-svn: 275773
This is a mechanical change to make TargetLowering API take MachineInstr&
(instead of MachineInstr*), since the argument is expected to be a valid
MachineInstr. In one case, changed a parameter from MachineInstr* to
MachineBasicBlock::iterator, since it was used as an insertion point.
As a side effect, this removes a bunch of MachineInstr* to
MachineBasicBlock::iterator implicit conversions, a necessary step
toward fixing PR26753.
llvm-svn: 274287
Summary:
SSAT saturates an integer, making sure that its value lies within
an interval [-k, k]. Since the constant is given to SSAT as the
number of bytes set to one, k + 1 must be a power of 2, otherwise
the optimization is not possible. Also, the select_cc must use <
and > respectively so that they define an interval.
Reviewers: mcrosier, jmolloy, rengolin
Subscribers: aemerson, rengolin, llvm-commits
Differential Revision: http://reviews.llvm.org/D21372
llvm-svn: 273581
TargetLowering and DAGToDAG are used to combine ADDC, ADDE and UMLAL
dags into UMAAL. Selection is split into the two phases because it
is easier to match the two patterns at those different times.
Differential Revision: http://http://reviews.llvm.org/D21461
llvm-svn: 273165
Reduces a bit of code duplication and clarify where we are interested
just on position independence and no the location of the symbol.
llvm-svn: 273164
This used to be free, copying and moving DebugLocs became expensive
after the metadata rewrite. Passing by reference eliminates a ton of
track/untrack operations. No functionality change intended.
llvm-svn: 272512
I'm really not sure why we were in the first place, it's the linker's job to
convert between BL/BLX as necessary. Even worse, using BLX left Thumb calls
that could be locally resolved completely unencodable since all offsets to BLX
are multiples of 4.
rdar://26182344
llvm-svn: 269101
Summary:
This patch adds support for the X asm constraint.
To do this, we lower the constraint to either a "w" or "r" constraint
depending on the operand type (both constraints are supported on ARM).
Fixes PR26493
Reviewers: t.p.northover, echristo, rengolin
Subscribers: joker.eph, jgreenhalgh, aemerson, rengolin, llvm-commits
Differential Revision: http://reviews.llvm.org/D19061
llvm-svn: 267411
This introduces a custom lowering for ISD::SETCCE (introduced in r253572)
that allows us to emit a short code sequence for 64-bit compares.
Before:
push {r7, lr}
cmp r0, r2
mov.w r0, #0
mov.w r12, #0
it hs
movhs r0, #1
cmp r1, r3
it ge
movge.w r12, #1
it eq
moveq r12, r0
cmp.w r12, #0
bne .LBB1_2
@ BB#1: @ %bb1
bl f
pop {r7, pc}
.LBB1_2: @ %bb2
bl g
pop {r7, pc}
After:
push {r7, lr}
subs r0, r0, r2
sbcs.w r0, r1, r3
bge .LBB1_2
@ BB#1: @ %bb1
bl f
pop {r7, pc}
.LBB1_2: @ %bb2
bl g
pop {r7, pc}
Saves around 80KB in Chromium's libchrome.so.
Some notes on this patch:
- I don't much like the ARMISD::BRCOND and ARMISD::CMOV combines I
introduced (nothing else needs them). However, they are necessary in
order to avoid poor codegen, and they seem similar to existing combines
in other backends (e.g. X86 combines (brcond (cmp (setcc Compare))) to
(brcond Compare)).
- No support for Thumb-1. This is in principle possible, but we'd need
to implement ARMISD::SUBE for Thumb-1.
Differential Revision: http://reviews.llvm.org/D15256
llvm-svn: 263962
- Rename getATOMIC to getSYNC, as llvm will soon be able to emit both
'__sync' libcalls and '__atomic' libcalls, and this function is for
the '__sync' ones.
- getInsertFencesForAtomic() has been replaced with
shouldInsertFencesForAtomic(Instruction), so that the decision can be
made per-instruction. This functionality will be used soon.
- emitLeadingFence/emitTrailingFence are no longer called if
shouldInsertFencesForAtomic returns false, and thus don't need to
check the condition themselves.
llvm-svn: 263665
Add support for TLS access for Windows on ARM. This generates a similar access
to MSVC for ARM.
The changes to the tablegen data is needed to support loading an external symbol
global that is not for a call. The adjustments to the DAG to DAG transforms are
needed to preserve the 32-bit move.
llvm-svn: 259676
Darwin TLS accesses most closely resemble ELF's general-dynamic situation,
since they have to be able to handle all possible situations. The descriptors
and so on are obviously slightly different though.
llvm-svn: 257039
Building on r253865 the crash is not limited to signed overflows.
Disable custom handling of unsigned 32-bit and 64-bit integer divide.
Add test cases for both 32-bit and 64-bit unsigned integer overflow.
llvm-svn: 254158
Disable custom handling of signed 32-bit and 64-bit integer divide.
Add test cases for both 32-bit and 64-bit integer overflow crashes.
llvm-svn: 253865
ARM V6T2 has instructions for efficient count-leading/trailing-zeros, so this should be
considered a cheap operation (and therefore fair game for speculation) for any ARM V6T2
implementation.
The net result of allowing this speculation for the regression tests in this patch is
that we get this code:
ctlz:
clz r0, r0
bx lr
cttz:
rbit r0, r0
clz r0, r0
bx lr
Instead of:
ctlz:
cmp r0, #0
moveq r0, #32
clzne r0, r0
bx lr
cttz:
cmp r0, #0
moveq r0, #32
rbitne r0, r0
clzne r0, r0
bx lr
This will help solve a general speculation/despeculation problem noted in PR24818:
https://llvm.org/bugs/show_bug.cgi?id=24818
Differential Revision: http://reviews.llvm.org/D14469
llvm-svn: 252639
Added fixes for stage2 failures: CMOV is not commutable; commuting the operands results in the condition being flipped! d'oh!
Original commit message:
If we have a CMOV, OR and AND combination such as:
if (x & CN)
y |= CM;
And:
* CN is a single bit;
* All bits covered by CM are known zero in y;
Then we can convert this to a sequence of BFI instructions. This will always be a win if CM is a single bit, will always be no worse than the TST & OR sequence if CM is two bits, and for thumb will be no worse if CM is three bits (due to the extra IT instruction).
llvm-svn: 252606
Summary:
The CLR's personality routine passes these in rdx/edx, not rax/eax.
Make getExceptionPointerRegister a virtual method parameterized by
personality function to allow making this distinction.
Similarly make getExceptionSelectorRegister a virtual method parameterized
by personality function, for symmetry.
Reviewers: pgavlin, majnemer, rnk
Subscribers: jyknight, dsanders, llvm-commits
Differential Revision: http://reviews.llvm.org/D14344
llvm-svn: 252383
If we have a CMOV, OR and AND combination such as:
if (x & CN)
y |= CM;
And:
* CN is a single bit;
* All bits covered by CM are known zero in y;
Then we can convert this to a sequence of BFI instructions. This will always be a win if CM is a single bit, will always be no worse than the TST & OR sequence if CM is two bits, and for thumb will be no worse if CM is three bits (due to the extra IT instruction).
llvm-svn: 252057
In PIC mode we were previously computing global variable addresses (or GOT
entry addresses) by adding the PC, the PC-relative GOT displacement and
the GOT-relative symbol/GOT entry displacement. Because the latter two
displacements are fixed, we ended up performing one more addition than
necessary.
This change causes us to compute addresses using a single PC-relative
displacement, resulting in a shorter code sequence. This reduces code size
by about 4% in a recent build of Chromium for Android.
As a result of this change we no longer need to compute the GOT base address
in the ARM backend, which allows us to remove the Global Base Reg pass and
SDAG lowering for the GOT.
We also now no longer use the GOT when addressing a symbol which is known
to be defined in the same linkage unit. Specifically, the symbol must have
either hidden visibility or a strong definition in the current module in
order to not use the the GOT.
This is a change from the previous behaviour where we would use the GOT to
address externally visible symbols defined in the same module. I think the
only cases where this could matter are cases involving symbol interposition,
but we don't really support that well anyway.
Differential Revision: http://reviews.llvm.org/D13650
llvm-svn: 251322
We were previously codegen'ing memcpy as regular load/store operations and
hoping that the register allocator would allocate registers in ascending order
so that we could apply an LDM/STM combine after register allocation. According
to the commit that first introduced this code (r37179), we planned to teach the
register allocator to allocate the registers in ascending order. This never got
implemented, and up to now we've been stuck with very poor codegen.
A much simpler approach for achieving better codegen is to create MEMCPY pseudo
instructions, attach scratch virtual registers to them and then, post register
allocation, expand the MEMCPYs into LDM/STM pairs using the scratch registers.
The register allocator will have picked arbitrary registers which we sort when
expanding the MEMCPY. This approach also avoids the need to repeatedly calculate
offsets which ultimately ought to be eliminated pre-RA in order to decrease
register pressure.
Fixes PR9199 and PR23768.
[This is based on Peter Collingbourne's r238473 which was reverted.]
Differential Revision: http://reviews.llvm.org/D13239
Change-Id: I727543c2e94136e0f80b8e22d5642d7b9ee5b458
Author: Peter Collingbourne <peter@pcc.me.uk>
llvm-svn: 249322
We now emit the compiler generated divide by zero check that was needed for the
MSVC routines. We construct a psuedo-instruction for the DBZ check as the
operation requires splitting up the BB. For the 64-bit operations, we need to
custom expand the node as we need to insert the DBZ check and then emit the
libcall to the appropriate name. Because this is target specific, it seemed
better to reproduce the expansion operation from the target-agnostic type
legalization rather than sink this there to avoid the duplication. The division
library calls now match MSVC semantically.
llvm-svn: 248561
ARM counterpart to r248291:
In the comparison failure block of a cmpxchg expansion, the initial
ldrex/ldxr will not be followed by a matching strex/stxr.
On ARM/AArch64, this unnecessarily ties up the execution monitor,
which might have a negative performance impact on some uarchs.
Instead, release the monitor in the failure block.
The clrex instruction was designed for this: use it.
Also see ARMARM v8-A B2.10.2:
"Exclusive access instructions and Shareable memory locations".
Differential Revision: http://reviews.llvm.org/D13033
llvm-svn: 248294
We used to have this magic "hasLoadLinkedStoreConditional()" callback,
which really meant two things:
- expand cmpxchg (to ll/sc).
- expand atomic loads using ll/sc (rather than cmpxchg).
Remove it, and, instead, introduce explicit callbacks:
- bool shouldExpandAtomicCmpXchgInIR(inst)
- AtomicExpansionKind shouldExpandAtomicLoadInIR(inst)
Differential Revision: http://reviews.llvm.org/D12557
llvm-svn: 247429
llvm.eh.sjlj.setjmp was used as part of the SjLj exception handling
style but is also used in clang to implement __builtin_setjmp. The ARM
backend needs to output additional dispatch tables for the SjLj
exception handling style, these tables however can't be emitted if
llvm.eh.sjlj.setjmp is simply used for __builtin_setjmp and no actual
landing pad blocks exist.
To solve this issue a new llvm.eh.sjlj.setup_dispatch intrinsic is
introduced which is used instead of llvm.eh.sjlj.setjmp in the SjLj
exception handling lowering, so we can differentiate between the case
where we actually need to setup a dispatch table and the case where we
just need the __builtin_setjmp semantic.
Differential Revision: http://reviews.llvm.org/D9313
llvm-svn: 242481
This patch allows the read_register and write_register intrinsics to
read/write the RBP/EBP registers on X86 iff the targeted register is
the frame pointer for the containing function.
Differential Revision: http://reviews.llvm.org/D10977
llvm-svn: 241827
Summary:
This change is part of a series of commits dedicated to have a single
DataLayout during compilation by using always the one owned by the
module.
Reviewers: echristo
Subscribers: jholewinski, llvm-commits, rafael, yaron.keren
Differential Revision: http://reviews.llvm.org/D11040
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 241778
Summary:
This change is part of a series of commits dedicated to have a single
DataLayout during compilation by using always the one owned by the
module.
Reviewers: echristo
Subscribers: jholewinski, ted, yaron.keren, rafael, llvm-commits
Differential Revision: http://reviews.llvm.org/D11028
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 241775
There is some functional change here because it changes target code from
atoi(3) to StringRef::getAsInteger which has error checking. For valid
constraints there should be no difference.
llvm-svn: 241411
The patch is generated using this command:
tools/clang/tools/extra/clang-tidy/tool/run-clang-tidy.py -fix \
-checks=-*,llvm-namespace-comment -header-filter='llvm/.*|clang/.*' \
llvm/lib/
Thanks to Eugene Kosov for the original patch!
llvm-svn: 240137
Summary:
But still handle them the same way since I don't know how they differ on
this target.
Of these, /U[qytnms]/ do not have backend tests but are accepted by clang.
No functional change intended.
Reviewers: t.p.northover
Reviewed By: t.p.northover
Subscribers: t.p.northover, aemerson, llvm-commits
Differential Revision: http://reviews.llvm.org/D8203
llvm-svn: 238921
This is important because of different addressing modes
depending on the address space for GPU targets.
This only adds the argument, and does not update
any of the uses to provide the correct address space.
llvm-svn: 238723
We were previously codegen'ing these as regular load/store operations and
hoping that the register allocator would allocate registers in ascending order
so that we could apply an LDM/STM combine after register allocation. According
to the commit that first introduced this code (r37179), we planned to teach
the register allocator to allocate the registers in ascending order. This
never got implemented, and up to now we've been stuck with very poor codegen.
A much simpler approach for achiveing better codegen is to create LDM/STM
instructions with identical sets of virtual registers, let the register
allocator pick arbitrary registers and order register lists when printing an
MCInst. This approach also avoids the need to repeatedly calculate offsets
which ultimately ought to be eliminated pre-RA in order to decrease register
pressure.
This is implemented by lowering the memcpy intrinsic to a series of SD-only
MCOPY pseudo-instructions which performs a memory copy using a given number
of registers. During SD->MI lowering, we lower MCOPY to LDM/STM. This is a
little unusual, but it avoids the need to encode register lists in the SD,
and we can take advantage of SD use lists to decide whether to use the _UPD
variant of the instructions.
Fixes PR9199.
Differential Revision: http://reviews.llvm.org/D9508
llvm-svn: 238473
to use the information in the module rather than TargetOptions.
We've had and clang has used the use-soft-float attribute for some
time now so have the backends set a subtarget feature based on
a particular function now that subtargets are created based on
functions and function attributes.
For the one middle end soft float check go ahead and create
an overloadable TargetLowering::useSoftFloat function that
just checks the TargetSubtargetInfo in all cases.
Also remove the command line option that hard codes whether or
not soft-float is set by using the attribute for all of the
target specific test cases - for the generic just go ahead and
add the attribute in the one case that showed up.
llvm-svn: 237079
Anton tried this 5 years ago but it was reverted due to extra VMOVs
being emitted. This can be easily fixed with a liberal application
of patterns - matching loads/stores and extractelts.
llvm-svn: 232958
Memcpy, and other memory intrinsics, typically tries to use LDM/STM if
the source and target addresses are 4-byte aligned. In CodeGenPrepare
look for calls to memory intrinsics and, if the object is on the
stack, 4-byte align it if it's large enough that we expect that memcpy
would want to use LDM/STM to copy it.
Differential Revision: http://reviews.llvm.org/D7908
llvm-svn: 232627
Summary:
This is instead of doing this in target independent code and is the last
non-functional change before targets begin to distinguish between
different memory constraints when selecting code for the ISD::INLINEASM
node.
Next, each target will individually move away from the idea that all
memory constraints behave like 'm'.
Subscribers: jholewinski, llvm-commits
Differential Revision: http://reviews.llvm.org/D8173
llvm-svn: 232373
The main issue being fixed here is that APCS targets handling a "byval align N"
parameter with N > 4 were miscounting what objects were where on the stack,
leading to FrameLowering setting the frame pointer incorrectly and clobbering
the stack.
But byval handling had grown over many years, and had multiple layers of cruft
trying to compensate for each other and calculate padding correctly. This only
really needs to be done once, in the HandleByVal function. Elsewhere should
just do what it's told by that call.
I also stripped out unnecessary APCS/AAPCS distinctions (now that Clang emits
byvals with the correct C ABI alignment), which simplified HandleByVal.
rdar://20095672
llvm-svn: 231959
This commit enables forming vector extloads for ARM.
It only does so for legal types, and when we can't fold the extension
in a wide/long form of the user instruction.
Enabling it for larger types isn't as good an idea on ARM as it is on
X86, because:
- we pretend that extloads are legal, but end up generating vld+vmov
- we have instructions like vld {dN, dM}, which can't be generated
when we "manually expand" extloads to vld+vmov.
For legal types, the combine doesn't fire that often: in the
integration tests only in a big endian testcase, where it removes a
pointless AND.
Related to rdar://19723053
Differential Revision: http://reviews.llvm.org/D7423
llvm-svn: 231396
Summary:
In PNaCl, most atomic instructions have their own @llvm.nacl.atomic.* function, each one, with a few exceptions, represents a consistent behaviour across all NaCl-supported targets. Unfortunately, the atomic RMW operations nand, [u]min, and [u]max aren't directly represented by any such @llvm.nacl.atomic.* function. This patch refines shouldExpandAtomicRMWInIR in TargetLowering so that a future `Le32TargetLowering` class can selectively inform the caller how the target desires the atomic RMW instruction to be expanded (ie via load-linked/store-conditional for ARM/AArch64, via cmpxchg for X86/others?, or not at all for Mips) if at all.
This does not represent a behavioural change and as such no tests were added.
Patch by: Richard Diamond.
Reviewers: jfb
Reviewed By: jfb
Subscribers: jfb, aemerson, t.p.northover, llvm-commits
Differential Revision: http://reviews.llvm.org/D7713
llvm-svn: 231250
a lookup, pass that in rather than use a naked call to getSubtargetImpl.
This involved passing down and around either a TargetMachine or
TargetRegisterInfo. Update all callers/definitions around the targets
and SelectionDAG.
llvm-svn: 230699
This required plumbing a TargetRegisterInfo through computeRegisterProperties
and into findRepresentativeClass which uses it for register class
iteration. This required passing a subtarget into a few target specific
initializations of TargetLowering.
llvm-svn: 230583
It was previously using the subtarget to get values for the global
offset without actually checking each function as it was generating
code. Go ahead and solidify the current behavior and make the
existing FIXMEs more prominent.
As a note the ARM backend previously had a thumb1 and non-thumb1
set of defaults. Only the former was tested so I've changed the
behavior to only use that for now.
llvm-svn: 230245
This patch adds an optimization in CodeGenPrepare to move an extractelement
right before a store when the target can combine them.
The optimization may promote any scalar operations to vector operations in the
way to make that possible.
** Context **
Some targets use different register files for both vector and scalar operations.
This means that transitioning from one domain to another may incur copy from one
register file to another. These copies are not coalescable and may be expensive.
For example, according to the scheduling model, on cortex-A8 a vector to GPR
move is 20 cycles.
** Motivating Example **
Let us consider an example:
define void @foo(<2 x i32>* %addr1, i32* %dest) {
%in1 = load <2 x i32>* %addr1, align 8
%extract = extractelement <2 x i32> %in1, i32 1
%out = or i32 %extract, 1
store i32 %out, i32* %dest, align 4
ret void
}
As it is, this IR generates the following assembly on armv7:
vldr d16, [r0] @vector load
vmov.32 r0, d16[1] @ cross-register-file copy: 20 cycles
orr r0, r0, #1 @ scalar bitwise or
str r0, [r1] @ scalar store
bx lr
Whereas we could generate much faster code:
vldr d16, [r0] @ vector load
vorr.i32 d16, #0x1 @ vector bitwise or
vst1.32 {d16[1]}, [r1:32] @ vector extract + store
bx lr
Half of the computation made in the vector is useless, but this allows to get
rid of the expensive cross-register-file copy.
** Proposed Solution **
To avoid this cross-register-copy penalty, we promote the scalar operations to
vector operations. The penalty will be removed if we manage to promote the whole
chain of computation in the vector domain.
Currently, we do that only when the chain of computation ends by a store and the
target is able to combine an extract with a store.
Stores are the most likely candidates, because other instructions produce values
that would need to be promoted and so, extracted as some point[1]. Moreover,
this is customary that targets feature stores that perform a vector extract (see
AArch64 and X86 for instance).
The proposed implementation relies on the TargetTransformInfo to decide whether
or not it is beneficial to promote a chain of computation in the vector domain.
Unfortunately, this interface is rather inaccurate for this level of details and
although this optimization may be beneficial for X86 and AArch64, the inaccuracy
will lead to the optimization being too aggressive.
Basically in TargetTransformInfo, everything that is legal has a cost of 1,
whereas, even if a vector type is legal, usually a vector operation is slightly
more expensive than its scalar counterpart. That will lead to too many
promotions that may not be counter balanced by the saving of the
cross-register-file copy. For instance, on AArch64 this penalty is just 4
cycles.
For now, the optimization is just enabled for ARM prior than v8, since those
processors have a larger penalty on cross-register-file copies, and the scope is
limited to basic blocks. Because of these two factors, we limit the effects of
the inaccuracy. Indeed, I did not want to build up a fancy cost model with block
frequency and everything on top of that.
[1] We can imagine targets that can combine an extractelement with other
instructions than just stores. If we want to go into that direction, the current
interfaces must be augmented and, moreover, I think this becomes a global isel
problem.
Differential Revision: http://reviews.llvm.org/D5921
<rdar://problem/14170854>
llvm-svn: 220978
Summary:
The goal is to eventually remove all the code related to getInsertFencesForAtomic
in SelectionDAGBuilder as it is wrong (designed for ARM, not really portable, works
mostly by accident because the backends are overly conservative), and repeats the
same logic that goes in emitLeading/TrailingFence.
In this patch, I make AtomicExpandPass insert the fences as it knows better
where to put them. Because this requires getting the fences and not just
passing an IRBuilder around, I had to change the return type of
emitLeading/TrailingFence.
This code only triggers on ARM for now. Because it is earlier in the pipeline
than SelectionDAGBuilder, it triggers and lowers atomic accesses to atomic so
SelectionDAGBuilder does not add barriers anymore on ARM.
If this patch is accepted I plan to implement emitLeading/TrailingFence for all
backends that setInsertFencesForAtomic(true), which will allow both making them
less conservative and simplifying SelectionDAGBuilder once they are all using
this interface.
This should not cause any functionnal change so the existing tests are used
and not modified.
Test Plan: make check-all, benefits from existing tests of atomics on ARM
Reviewers: jfb, t.p.northover
Subscribers: aemerson, llvm-commits
Differential Revision: http://reviews.llvm.org/D5179
llvm-svn: 218329
Summary:
This patch was originally in D5304 (I could not find a way to reopen that revision).
It was accepted, commited and broke the build bots because the overloading of
the constructor of ArrayRef for braced initializer lists is not supported by all
toolchains. I then reverted it, and propose this fixed version that uses a plain
C array instead in makeDMB (that array is then converted implicitly to an
ArrayRef, but that is not behind an ifdef). Could someone confirm me whether
initialization lists for plain C arrays are supported by every toolchain used
to build llvm ? Otherwise I can just initialize the array in the old way:
args[0] = ...; .. ; args[5] = ...;
Below is the description of the original patch:
```
I had only tested this code for ARMv7 and ARMv8. This patch adds several
fallback paths if the processor does not support dmb ish:
- dmb sy if a cortex-M with support for dmb
- mcr p15, #0, r0, c7, c10, #5 for ARMv6 (special instruction equivalent to a DMB)
These fallback paths were chosen based on the code for fence seq_cst.
Thanks to luqmana for having noticed this bug.
```
Test Plan: Added more cases to atomic-load-store.ll + make check-all
Reviewers: jfb, t.p.northover, luqmana
Subscribers: llvm-commits, aemerson
Differential Revision: http://reviews.llvm.org/D5386
llvm-svn: 218066
It is breaking the build on the buildbots but works fine on my machine, I revert
while trying to understand what happens (it appears to depend on the compiler used
to build, I probably used a C++11 feature that is not perfectly supported by some
of the buildbots).
This reverts commit feb3176c4d006f99af8b40373abd56215a90e7cc.
llvm-svn: 217973
Summary:
I had only tested this code for ARMv7 and ARMv8. This patch adds several
fallback paths if the processor does not support dmb ish:
- dmb sy if a cortex-M with support for dmb
- mcr p15, #0, r0, c7, c10, #5 for ARMv6 (special instruction equivalent to a DMB)
These fallback paths were chosen based on the code for fence seq_cst.
Thanks to luqmana for having noticed this bug.
Test Plan: Added more cases to atomic-load-store.ll + make check-all
Reviewers: jfb, t.p.northover, luqmana
Subscribers: aemerson, llvm-commits
Differential Revision: http://reviews.llvm.org/D5304
llvm-svn: 217965
This required a new hook called hasLoadLinkedStoreConditional to know whether
to expand atomics to LL/SC (ARM, AArch64, in a future patch Power) or to
CmpXchg (X86).
Apart from that, the new code in AtomicExpandPass is mostly moved from
X86AtomicExpandPass. The main result of this patch is to get rid of that
pass, which had lots of code duplicated with AtomicExpandPass.
llvm-svn: 217928
Summary:
Split shouldExpandAtomicInIR() into different versions for Stores/Loads/RMWs/CmpXchgs.
Makes runOnFunction cleaner (no more redundant checking/casting), and will help moving
the X86 backend to this pass.
This requires a way of easily detecting which instructions are atomic.
I followed the pattern of mayReadFromMemory, mayWriteOrReadMemory, etc.. in making
isAtomic() a method of Instruction implemented by a switch on the opcodes.
Test Plan: make check
Reviewers: jfb
Subscribers: mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D5035
llvm-svn: 217080
Fixes two latent bugs:
- There was no fence inserted before expanded seq_cst load (unsound on Power)
- There was only a fence release before seq_cst stores (again unsound, in particular on Power)
It is not even clear if this is correct on ARM swift processors (where release fences are
DMB ishst instead of DMB ish). This behaviour is currently preserved on ARM Swift
as it is not clear whether it is incorrect. I would love to get documentation stating
whether it is correct or not.
These two bugs were not triggered because Power is not (yet) using this pass, and these
behaviours happen to be (mostly?) working on ARM
(although they completely butchered the semantics of the llvm IR).
See:
http://lists.cs.uiuc.edu/pipermail/llvmdev/2014-August/075821.html
for an example of the problems that can be caused by the second of these bugs.
I couldn't see a way of fixing these in a completely target-independent way without
adding lots of unnecessary fences on ARM, hence the target-dependent parts of this
patch.
This patch implements the new target-dependent parts only for ARM (the default
of not doing anything is enough for AArch64), other architectures will use this
infrastructure in later patches.
llvm-svn: 217076
The FPv4-SP floating-point unit is generally referred to as
single-precision only, but it does have double-precision registers and
load, store and GPR<->DPR move instructions which operate on them.
This patch enables the use of these registers, the main advantage of
which is that we now comply with the AAPCS-VFP calling convention.
This partially reverts r209650, which added some AAPCS-VFP support,
but did not handle return values or alignment of double arguments in
registers.
This patch also adds tests for Thumb2 code generation for
floating-point instructions and intrinsics, which previously only
existed for ARM.
llvm-svn: 216172
Add header guards to files that were missing guards. Remove #endif comments
as they don't seem common in LLVM (we can easily add them back if we decide
they're useful)
Changes made by clang-tidy with minor tweaks.
llvm-svn: 215558
Rename to allowsMisalignedMemoryAccess.
On R600, 8 and 16 byte accesses are mostly OK with 4-byte alignment,
and don't need to be split into multiple accesses. Vector loads with
an alignment of the element type are not uncommon in OpenCL code.
llvm-svn: 214055
address of the stack guard was being spilled to the stack.
Previously the address of the stack guard would get spilled to the stack if it
was impossible to keep it in a register. This patch introduces a new target
independent node and pseudo instruction which gets expanded post-RA to a
sequence of instructions that load the stack guard value. Register allocator
can now just remat the value when it can't keep it in a register.
<rdar://problem/12475629>
llvm-svn: 213967
The armv7-windows-itanium environment is nearly identical to the MSVC ABI. It
has a few divergences, mostly revolving around the use of the Itanium ABI for
C++. VLA support is one of the extensions that are amongst the set of the
extensions.
This adds support for proper VLA emission for this environment. This is
somewhat similar to the handling for __chkstk emission on X86 and the large
stack frame emission for ARM. The invocation style for chkstk is still
controlled via the -mcmodel flag to clang.
Make an explicit note that this is an extension.
llvm-svn: 210489
We must validate the value type in TLI::getRegisterByName, because if we
don't and the wrong type was used with the IR intrinsic, then we'll assert
(because we won't be able to find a valid register class with which to
construct the requested copy operation). For PPC64, additionally, the type
information is necessary to decide between the 64-bit register and the 32-bit
subregister.
No functionality change.
llvm-svn: 208508
This patch adds support to ARM for custom lowering of the
llvm.{u|s}add.with.overflow.i32 intrinsics for i32/i64. This is particularly useful
for handling idiomatic saturating math functions as generated by
InstCombineCompare.
Test cases included.
rdar://14853450
llvm-svn: 208435
When using the ARM AAPCS, HFAs (Homogeneous Floating-point Aggregates) must
be passed in a block of consecutive floating-point registers, or on the stack.
This means that unused floating-point registers cannot be back-filled with
part of an HFA, however this can currently happen. This patch, along with the
corresponding clang patch (http://reviews.llvm.org/D3083) prevents this.
llvm-svn: 208413
Handle lowering of global addresses for PIC mode compilation on Windows. Always
use the movw/movt load to load the address as Windows on ARM requires ARMv7+ and
is a pure Thumb environment.
llvm-svn: 208385
This patch implements the infrastructure to use named register constructs in
programs that need access to specific registers (bare metal, kernels, etc).
So far, only the stack pointer is supported as a technology preview, but as it
is, the intrinsic can already support all non-allocatable registers from any
architecture.
llvm-svn: 208104
Still only 32-bit ARM using it at this stage, but the promotion allows
direct testing via opt and is a reasonably self-contained patch on the
way to switching ARM64.
At this point, other targets should be able to make use of it without
too much difficulty if they want. (See ARM64 commit coming soon for an
example).
llvm-svn: 206485
The previous situation where ATOMIC_LOAD_WHATEVER nodes were expanded
at MachineInstr emission time had grown to be extremely large and
involved, to account for the subtly different code needed for the
various flavours (8/16/32/64 bit, cmpxchg/add/minmax).
Moving this transformation into the IR clears up the code
substantially, and makes future optimisations much easier:
1. an atomicrmw followed by using the *new* value can be more
efficient. As an IR pass, simple CSE could handle this
efficiently.
2. Making use of cmpxchg success/failure orderings only has to be done
in one (simpler) place.
3. The common "cmpxchg; did we store?" idiom can be exposed to
optimisation.
I intend to gradually improve this situation within the ARM backend
and make sure there are no hidden issues before moving the code out
into CodeGen to be shared with (at least ARM64/AArch64, though I think
PPC & Mips could benefit too).
llvm-svn: 205525
After some discussion on IRC, emitting a call to the library function seems
like a better default, since it will move from a compiler internal error to
a linker error, that the user can work around until LLVM is fixed.
I'm also adding a note on the responsibility of the user to confirm that
the cache was cleared on platforms where nothing is done.
llvm-svn: 204806
Implementing the LLVM part of the call to __builtin___clear_cache
which translates into an intrinsic @llvm.clear_cache and is lowered
by each target, either to a call to __clear_cache or nothing at all
incase the caches are unified.
Updating LangRef and adding some tests for the implemented architectures.
Other archs will have to implement the method in case this builtin
has to be compiled for it, since the default behaviour is to bail
unimplemented.
A Clang patch is required for the builtin to be lowered into the
llvm intrinsic. This will be done next.
llvm-svn: 204802
Nirav Dave