This patch uses AtomicExpandPass to implement quadword lock free atomic operations. It adopts the method introduced in https://reviews.llvm.org/D47882, which expand atomic operations post RA to avoid spilling that might prevent LL/SC progress.
Reviewed By: jsji
Differential Revision: https://reviews.llvm.org/D103614
This only applies to FastIsel. GlobalIsel seems to sidestep
the issue.
This fixes https://bugs.llvm.org/show_bug.cgi?id=46996
One of the things we do in llvm is decide if a type needs
consecutive registers. Previously, we just checked if it
was an array or not.
(plus an SVE specific check that is not changing here)
This causes some confusion when you arbitrary IR like:
```
%T1 = type { double, i1 };
define [ 1 x %T1 ] @foo() {
entry:
ret [ 1 x %T1 ] zeroinitializer
}
```
We see it is an array so we call CC_AArch64_Custom_Block
which bails out when it sees the i1, a type we don't want
to put into a block.
This leaves the location of the double in some kind of
intermediate state and leads to odd codegen. Which then crashes
the backend because it doesn't know how to implement
what it's been asked for.
You get this:
```
renamable $d0 = FMOVD0
$w0 = COPY killed renamable $d0
```
Rather than this:
```
$d0 = FMOVD0
$w0 = COPY $wzr
```
The backend knows how to copy 64 bit to 64 bit registers,
but not 64 to 32. It can certainly be taught how but the real
issue seems to be us even trying to assign a register block
in the first place.
This change makes the logic of
AArch64TargetLowering::functionArgumentNeedsConsecutiveRegisters
a bit more in depth. If we find an array, also check that all the
nested aggregates in that array have a single member type.
Then CC_AArch64_Custom_Block's assumption of a type that looks
like [ N x type ] will be valid and we get the expected codegen.
New tests have been added to exercise these situations. Note that
some of the output is not ABI compliant. The aim of this change is
to simply handle these situations and not to make our processing
of arbitrary IR ABI compliant.
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D104123
Don't require a specific kind of IRBuilder for TargetLowering hooks.
This allows us to drop the IRBuilder.h include from TargetLowering.h.
Differential Revision: https://reviews.llvm.org/D103759
AIX use `__ssp_canary_word` instead of `__stack_chk_guard`.
This patch update the target hook to use correct symbol,
so that the basic stackprotect feature can work.
The traceback will be handled in follow up patch.
Reviewed By: #powerpc, shchenz
Differential Revision: https://reviews.llvm.org/D103100
getVectorNumElements() returns a value for scalable vectors
without any warning so it is effectively getVectorMinNumElements().
By renaming it and making getVectorNumElements() forward to
it, we can insert a check for scalable vectors into getVectorNumElements()
similar to EVT. I didn't do that in this patch because there are still more
fixes needed, but I was able to temporarily do it and passed the RISCV
lit tests with these changes.
The changes to isPow2VectorType and getPow2VectorType are copied from EVT.
The change to TypeInfer::EnforceSameNumElts reduces the size of AArch64's isel table.
We're now considering SameNumElts to require the scalable property to match which
removes some unneeded type checks.
This was motivated by the bug I fixed yesterday in 80b9510806
Reviewed By: frasercrmck, sdesmalen
Differential Revision: https://reviews.llvm.org/D102262
This patch introduces a new infrastructure that is used to select the load and
store instructions in the PPC backend.
The primary motivation is that the current implementation of selecting load/stores
is dependent on the ordering of patterns in TableGen. Given this limitation, we
are not able to easily and reliably generate the P10 prefixed load and stores
instructions (such as when the immediates that fit within 34-bits). This
refactoring is meant to provide us with more control over the patterns/different
forms to exploit, as well as eliminating dependency of pattern declaration in TableGen.
The idea of this refactoring is that it introduces a set of addressing modes that
correspond to different instruction formats of a particular load and store
instruction, along with a set of common flags that describes a load/store.
Whenever a load/store instruction is being selected, we analyze the instruction
and compute a set of flags for it. The computed flags are then used to
select the most optimal load/store addressing mode.
This patch is the first of a series of patches to be committed - it contains the
initial implementation of the refactored load/store selection infrastructure and
also updates P8/P9 patterns to adopt this infrastructure. The idea is that
incremental patches will add more implementation and support, and eventually
the old implementation will be removed.
Differential Revision: https://reviews.llvm.org/D93370
These constraints are machine agnostic; there's no reason to handle
these per-arch. If arches don't support these constraints, then they
will fail elsewhere during instruction selection. We don't need virtual
calls to look these up; TargetLowering::getInlineAsmMemConstraint should
only be overridden by architectures with additional unique memory
constraints.
Reviewed By: echristo, MaskRay
Differential Revision: https://reviews.llvm.org/D100416
This patch exploits the xxsplti32dx instruction available on Power10
in place of constant pool loads where xxspltidp would not be able to,
usually because the immediate cannot fit into 32 bits.
Differential Revision: https://reviews.llvm.org/D95458
Adds support for the TLS general dynamic access model to
assembly files on AIX 32-bit.
To generate the correct code sequence when accessing a TLS variable
`v`, we first create two TOC entry nodes, one for the variable offset, one
for the region handle. These nodes are followed by a `PPCISD::TLSGD_AIX`
node (new node introduced by this patch).
The `PPCISD::TLSGD_AIX` node (`TLSGDAIX` pseudo instruction) is
expanded to 2 copies (to put the variable offset and region handle in
the right registers) and a call to `__tls_get_addr`.
This patch also changes the way TC entries are generated in asm files.
If the generated TC entry is for the region handle of a TLS variable,
we add the `@m` relocation and the `.` prefix to the entry name.
For example:
```
L..C0:
.tc .v[TC],v[TL]@m -> region handle
L..C1:
.tc v[TC],v[TL] -> variable offset
```
Reviewed By: nemanjai, sfertile
Differential Revision: https://reviews.llvm.org/D97948
As of commit 284f2bffc9, the DAG Combiner gets rid of the masking of the
input to this node if the mask only keeps the bottom 16 bits. This is because
the underlying library function does not use the high order bits. However, on
PowerPC's ELFv2 ABI, it is the caller that is responsible for clearing the bits
from the register. Therefore, the library implementation of __gnu_h2f_ieee will
return an incorrect result if the bits aren't cleared.
This combine is desired for ARM (and possibly other targets) so this patch adds
a query to Target Lowering to check if this zeroing needs to be kept.
Fixes: https://bugs.llvm.org/show_bug.cgi?id=49092
Differential revision: https://reviews.llvm.org/D96283
X86 and AArch64 expand it as libcall inside the target. And PowerPC also
want to expand them as libcall for P8. So, propose an implement in the
legalizer to common the logic and remove the code for X86/AArch64 to
avoid the duplicate code.
Reviewed By: Craig Topper
Differential Revision: https://reviews.llvm.org/D91331
For now, we will hardcode the result as 0.0 if the input is denormal or 0. That will
have the impact the precision. As the fsqrt added belong to the cold path of the
cmp+branch, it won't impact the performance for normal inputs for PowerPC, but improve
the precision if the input is denormal.
Reviewed By: Spatel
Differential Revision: https://reviews.llvm.org/D80974
If smax() is legal, this is likely to result in smaller codegen expansion for abs(x) than the xor(add,ashr) method.
This is also what PowerPC has been doing for its abs implementation, so it lets us get rid of a load of custom lowering code there (and which was never updated when they added smax lowering).
Alive2: https://alive2.llvm.org/ce/z/xRk3cD
Differential Revision: https://reviews.llvm.org/D92095
PowerPC has instruction ftsqrt/xstsqrtdp etc to do the input test for software square root.
LLVM now tests it with smallest normalized value using abs + setcc. We should add hook to
target that has test instructions.
Reviewed By: Spatel, Chen Zheng, Qiu Chao Fang
Differential Revision: https://reviews.llvm.org/D80706
The default version only works if the returned node has a single
result. The X86 and PowerPC versions support multiple results
and allow a single result to be returned from a node with
multiple outputs. And allow a single result that is not result 0
of the node.
Also replace the Mips version since the new version should work
for it. The original version handled multiple results, but only
if the new node and original node had the same number of results.
Differential Revision: https://reviews.llvm.org/D91846
MULH is often expanded on targets.
This patch removes the isMulhCheaperThanMulShift hook and uses
isOperationLegalOrCustom instead.
Differential Revision: https://reviews.llvm.org/D80485
Summary: This patch is derived from D87384.
In this patch we expand the existing decomposition of mul-by-constant to be more general by implementing 2 patterns:
```
mul x, (2^N + 2^M) --> (add (shl x, N), (shl x, M))
mul x, (2^N - 2^M) --> (sub (shl x, N), (shl x, M))
```
The conversion will be trigged if the multiplier is a big constant that the target can't use a single multiplication instruction to handle. This is controlled by the hook `decomposeMulByConstant`.
More over, the conversion benefits from an ILP improvement since the instructions are independent. A case with the sequence like following also gets benefit since a shift instruction is saved.
```
*res1 = a * 0x8800;
*res2 = a * 0x8080;
```
Reviewed By: spatel
Differential Revision: https://reviews.llvm.org/D88201
This patch legalizes the v256i1 and v512i1 types that will be used for MMA.
It implements loads and stores of these types.
v256i1 is a pair of VSX registers, so for this type, we load/store the two
underlying registers. v512i1 is used for MMA accumulators. So in addition to
loading and storing the 4 associated VSX registers, we generate instructions to
prime (copy the VSX registers to the accumulator) after loading and unprime
(copy the accumulator back to the VSX registers) before storing.
This patch also adds the UACC register class that is necessary to implement the
loads and stores. This class represents accumulator in their unprimed form and
allow the distinction between primed and unprimed accumulators to avoid invalid
copies of the VSX registers associated with primed accumulators.
Differential Revision: https://reviews.llvm.org/D84968
This patch is the initial support for the Local Dynamic Thread Local Storage
model to produce code sequence and relocation correct to the ABI for the model
when using PC relative memory operations.
Differential Revision: https://reviews.llvm.org/D87721
This patch is the initial support for the Local Exec Thread Local
Storage model to produce code sequence and relocations correct
to the ABI for the model when using PC relative memory operations.
Patch by: Kamau Bridgeman
Differential Revision: https://reviews.llvm.org/D83404
Libcall __gcc_qtou is not available, which breaks some tests needing
it. On PowerPC, we have code to manually expand the operation, this
patch applies it to constrained conversion. To keep it strict-safe,
it's using the algorithm similar to expandFP_TO_UINT.
For constrained operations marking FP exception behavior as 'ignore',
we should set the NoFPExcept flag. However, in some custom lowering
the flag is missed. This should be fixed by future patches.
Reviewed By: uweigand
Differential Revision: https://reviews.llvm.org/D86605
This patch implements the builtins for Vector Load with Zero and Signed Extend Builtins (lxvr_x for b, h, w, d), and adds the appropriate test cases for these builtins. The builtins utilize the vector load instructions itnroduced with ISA 3.1.
Differential Revision: https://reviews.llvm.org/D82502#inline-797941
This patch makes these operations legal, and add necessary codegen
patterns.
There's still some issue similar to D77033 for conversion from v1i128
type. But normal type tests synced in vector-constrained-fp-intrinsic
are passed successfully.
Reviewed By: uweigand
Differential Revision: https://reviews.llvm.org/D83654
This patch adds support for constrained scalar int to fp operations on
PowerPC. Besides, this also fixes the FP exception bit of FCFID*
instructions.
Reviewed By: steven.zhang, uweigand
Differential Revision: https://reviews.llvm.org/D81669
This patch is the initial support for the General Dynamic Thread Local
Local Storage model to produce code sequence and relocations correct
to the ABI for the model when using PC relative memory operations.
Patch by: NeHuang
Reviewed By: stefanp
Differential Revision: https://reviews.llvm.org/D82315
This patch adds support for constrained scalar fp to int operations on
PowerPC. Besides, this fixes the FP exception bit of quad-precision
convert & truncate instructions.
Reviewed By: steven.zhang, uweigand
Differential Revision: https://reviews.llvm.org/D81537
The custom lowering saves an instruction over the generic expansion, by
taking advantage of the fact that PowerPC shift instructions are well
defined in the shift-by-bitwidth case.
Differential Revision: https://reviews.llvm.org/D83948
This patch aims to exploit the xxsplti32dx XT, IX, IMM32 instruction when lowering VECTOR_SHUFFLEs.
We implement lowerToXXSPLTI32DX when lowering vector shuffles to check if:
- Element size is 4 bytes
- The RHS is a constant vector (and constant splat of 4-bytes)
- The shuffle mask is a suitable mask for the XXSPLTI32DX instruction where it is one of the 32 masks:
<0, 4-7, 2, 4-7>
<4-7, 1, 4-7, 3>
Differential Revision: https://reviews.llvm.org/D83245
Summary: As Bugzilla-35090 reported, the rationale for using custom lowering SREM/UREM should no longer be true. At the IR level, the div-rem-pairs pass performs the transformation where the remainder is computed from the result of the division when both a required. We should now be able to lower these directly on P9. And the pass also fixed the problem that divide is in a different block than the remainder. This is a patch to remove redundant code and make SREM/UREM legal directly on P9.
Reviewed By: lkail
Differential Revision: https://reviews.llvm.org/D82145
This patch is part of supporting `-fstack-clash-protection`. Mainly do
such things compared to existing `lowerDynamicAlloc`
- Added a new pseudo instruction PPC::PREPARE_PROBED_ALLOC to get
actual frame pointer and final stack pointer.
- Synthesize a loop to probe by blocks.
- Use DYNAREAOFFSET to get MaxCallFrameSize which is calculated in
prologepilog.
Differential Revision: https://reviews.llvm.org/D81358
We currently miss a number of opportunities to emit single-instruction
VMRG[LH][BHW] instructions for shuffles on little endian subtargets. Although
this in itself is not a huge performance opportunity since loading the permute
vector for a VPERM can always be pulled out of loops, producing such merge
instructions is useful to downstream optimizations.
Since VPERM is essentially opaque to all subsequent optimizations, we want to
avoid it as much as possible. Other permute instructions have semantics that can
be reasoned about much more easily in later optimizations.
This patch does the following:
- Canonicalize shuffles so that the first element comes from the first vector
(since that's what most of the mask matching functions want)
- Switch the elements that come from splat vectors so that they match the
corresponding elements from the other vector (to allow for merges)
- Adds debugging messages for when a shuffle is matched to a VPERM so that
anyone interested in improving this further can get the info for their code
Differential revision: https://reviews.llvm.org/D77448
Summary: A bug is reported in bugzilla-45628, where the swap_with_shift case can’t be matched to a single HW instruction xxswapd as expected.
In fact the case matches the idiom of rotate. We have MatchRotate to handle an ‘or’ of two operands and generate a rot[lr] if the case matches the idiom of rotate. While PPC doesn’t support ROTL v1i128. We can custom lower ROTL v1i128 to the vector_shuffle. The vector_shuffle will be matched to a single HW instruction during the phase of instruction selection.
Reviewed By: steven.zhang
Differential Revision: https://reviews.llvm.org/D81076
On PowerPC, FNMSUB (both VSX and non-VSX version) means -(a*b-c). But
the backend used to generate these instructions regardless whether nsz
flag exists or not. If a*b-c==0, such transformation changes sign of
zero.
This patch introduces PPC specific FNMSUB ISD opcode, which may help
improving combined FMA code sequence.
Reviewed By: steven.zhang
Differential Revision: https://reviews.llvm.org/D76585
These two nodes were added by 69caef2b78 in 2005
and they are not used by PowerPC backend anymore. And the ISD::FMA is a prefer
way for VMADDFP if we really want to create that node. For VNMSUBFP, we will
also add a more generic node FNMSUB in D76585 if we really want it.
Reviewed By: qiucf
Differential Revision: https://reviews.llvm.org/D80429
Kai Luo