While working on PR38197, I noticed that we don't make use of FADD/FMUL being able to commute the inputs to support the addps+movss -> addss style combine
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337375 91177308-0d34-0410-b5e6-96231b3b80d8
Summary: This is how it appears to be handled in GCC and it prevents a
"Unknown mismatch" error in the SelectionDAGBuilder.
Reviewers: venkatra, jyknight, jrtc27
Reviewed By: jyknight, jrtc27
Subscribers: eraman, fedor.sergeev, jrtc27, llvm-commits
Differential Revision: https://reviews.llvm.org/D49218
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337370 91177308-0d34-0410-b5e6-96231b3b80d8
This required an annoying amount of tablegen multiclass changes to make only VUNPCKHPDZ128rr commutable.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337357 91177308-0d34-0410-b5e6-96231b3b80d8
I'm trying to restrict the MOVLHPS/MOVHLPS ISD nodes to SSE1 only. With SSE2 we can use unpcks. I believe this will allow some patterns to be cleaned up to require fewer bitcasts.
I've put in an odd isel hack to still select MOVHLPS instruction from the unpckh node to avoid changing tests and because movhlps is a shorter encoding. Ideally we'd do execution domain switching on this, but the operands are in the wrong order and are tied. We might be able to try a commute in the domain switching using custom code.
We already support domain switching for UNPCKLPD and MOVLHPS.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337348 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
The Signal Processing Engine (SPE) is found on NXP/Freescale e500v1,
e500v2, and several e200 cores. This adds support targeting the e500v2,
as this is more common than the e500v1, and is in SoCs still on the
market.
This patch is very intrusive because the SPE is binary incompatible with
the traditional FPU. After discussing with others, the cleanest
solution was to make both SPE and FPU features on top of a base PowerPC
subset, so all FPU instructions are now wrapped with HasFPU predicates.
Supported by this are:
* Code generation following the SPE ABI at the LLVM IR level (calling
conventions)
* Single- and Double-precision math at the level supported by the APU.
Still to do:
* Vector operations
* SPE intrinsics
As this changes the Callee-saved register list order, one test, which
tests the precise generated code, was updated to account for the new
register order.
Reviewed by: nemanjai
Differential Revision: https://reviews.llvm.org/D44830
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337347 91177308-0d34-0410-b5e6-96231b3b80d8
The presence of these symbols in the symbol table can cause symbol type
mismatch errors (or undefined symbol errors on emulated TLS targets)
and they can't be ICF'd anyway.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337338 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
The only thing he suggested that I've skipped here is the double-wide
multiply instructions. Multiply is an area I'm nervous about there being
some hidden data-dependent behavior, and it doesn't seem important for
any benchmarks I have, so skipping it and sticking with the minimal
multiply support that matches what I know is widely used in existing
crypto libraries. We can always add double-wide multiply when we have
clarity from vendors about its behavior and guarantees.
I've tried to at least cover the fundamentals here with tests, although
I've not tried to cover every width or permutation. I can add more tests
where folks think it would be helpful.
Reviewers: craig.topper
Subscribers: sanjoy, mcrosier, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D49413
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337308 91177308-0d34-0410-b5e6-96231b3b80d8
Previously we were assuming whole program compilation. Now that
separate compilation is a thing we need to update this pass.
Firstly, it can no longer assert on the existence of malloc and free.
This functions might not be in the current translation unit. If we
need them then we will generate not imports for them.
Secondly the global helper function we create should be marked as
weak since we will be generating a separate copy in each translation
unit.
Finally the names of the symbols used must be unique and fixed since
they need to agree across translation units.
Differential Revision: https://reviews.llvm.org/D49263
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337301 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
Part of the adjustCopiesBackFrom method wasn't correctly dealing with SubRange
intervals when updating.
2 changes. The first to ensure that bogus SubRange Segments aren't propagated when
encountering Segments of the form [1234r, 1234d:0) when preparing to merge value
numbers. These can be removed in this case.
The second forces a shrinkToUses call if SubRanges end on the copy index
(instead of just the parent register).
V2: Addressed review comments, plus MIR test instead of ll test
Subscribers: MatzeB, qcolombet, nhaehnle
Differential Revision: https://reviews.llvm.org/D40308
Change-Id: I1d2b2b4beea802fce11da01edf71feb2064aab05
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337273 91177308-0d34-0410-b5e6-96231b3b80d8
The ta instruction will always trap, regardless of the value
of the integer condition codes. TRAPri is marked as using icc,
so we cannot use a pattern for TRAPri to implement ta 1, as
verify-machineinstrs can complain that icc is not defined.
Instead we implement ta 1 the same way as ta 5.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337236 91177308-0d34-0410-b5e6-96231b3b80d8
This amounts to pretty ridiculous number of patterns. Ideally we'd canonicalize the X86ISD::VRNDSCALE earlier to reuse those patterns. I briefly looked into doing that, but some strict FP operations could still get converted to rint and nearbyint during isel. It's probably still worthwhile to look into. This patch is meant as a starting point to work from.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337234 91177308-0d34-0410-b5e6-96231b3b80d8
This allows us to use 231 form to fold an insertelement on the add input to the fma. There is technically no software intrinsic that can use this until AVX512F, but it can be manually built up from other intrinsics.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337223 91177308-0d34-0410-b5e6-96231b3b80d8
As discussed here:
http://lists.llvm.org/pipermail/llvm-dev/2018-May/123292.htmlhttp://lists.llvm.org/pipermail/llvm-dev/2018-July/124400.html
We want to add rotate intrinsics because the IR expansion of that pattern is 4+ instructions,
and we can lose pieces of the pattern before it gets to the backend. Generalizing the operation
by allowing 2 different input values (plus the 3rd shift/rotate amount) gives us a "funnel shift"
operation which may also be a single hardware instruction.
Initially, I thought we needed to define new DAG nodes for these ops, and I spent time working
on that (much larger patch), but then I concluded that we don't need it. At least as a first
step, we have all of the backend support necessary to match these ops...because it was required.
And shepherding these through the IR optimizer is the primary concern, so the IR intrinsics are
likely all that we'll ever need.
There was also a question about converting the intrinsics to the existing ROTL/ROTR DAG nodes
(along with improving the oversized shift documentation). Again, I don't think that's strictly
necessary (as the test results here prove). That can be an efficiency improvement as a small
follow-up patch.
So all we're left with is documentation, definition of the IR intrinsics, and DAG builder support.
Differential Revision: https://reviews.llvm.org/D49242
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337221 91177308-0d34-0410-b5e6-96231b3b80d8
trivially rematerializable.
We run into a case where machineLICM hoists a large number of live ranges
outside of a big loop because it thinks those live ranges are trivially
rematerializable. In regalloc, global splitting is tried out first for those
live ranges before they are spilled and rematerialized. Because the global
splitting algorithm is quadratic, increasing a lot of global splitting
candidates causes huge compile time increase (50s to 1400s on my local
machine when compiling a module).
However, we think for live ranges which are very large and are trivially
rematerialiable, it is better to just skip global splitting so as to save
compile time with little chance of sacrificing performance. We uses the
segment size of live range to indirectly evaluate whether the global
splitting of the live range can introduce high cost, and use an option
as a knob to adjust the size limit threshold.
Differential Revision: https://reviews.llvm.org/D49353
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337186 91177308-0d34-0410-b5e6-96231b3b80d8
invariant instructions to be both more correct and much more powerful.
While testing, I continued to find issues with sinking post-load
hardening. Unfortunately, it was amazingly hard to create any useful
tests of this because we were mostly sinking across copies and other
loading instructions. The fact that we couldn't sink past normal
arithmetic was really a big oversight.
So first, I've ported roughly the same set of instructions from the data
invariant loads to also have their non-loading varieties understood to
be data invariant. I've also added a few instructions that came up so
often it again made testing complicated: inc, dec, and lea.
With this, I was able to shake out a few nasty bugs in the validity
checking. We need to restrict to hardening single-def instructions with
defined registers that match a particular form: GPRs that don't have
a NOREX constraint directly attached to their register class.
The (tiny!) test case included catches all of the issues I was seeing
(once we can sink the hardening at all) except for the NOREX issue. The
only test I have there is horrible. It is large, inexplicable, and
doesn't even produce an error unless you try to emit encodings. I can
keep looking for a way to test it, but I'm out of ideas really.
Thanks to Ben for giving me at least a sanity-check review. I'll follow
up with Craig to go over this more thoroughly post-commit, but without
it SLH crashes everywhere so landing it for now.
Differential Revision: https://reviews.llvm.org/D49378
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337177 91177308-0d34-0410-b5e6-96231b3b80d8
Summary: Software trap number one is the trap used for breakpoints
in the Sparc ABI.
Reviewers: jyknight, venkatra
Reviewed By: jyknight
Subscribers: fedor.sergeev, jrtc27, llvm-commits
Differential Revision: https://reviews.llvm.org/D48637
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337163 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
If the high part of the load is not used the offset to the next element
will not be set correctly.
For example, on Sparc V8, the following code will read val2 from offset 4
instead of 8.
```
int val = __builtin_va_arg(va, long long);
int val2 = __builtin_va_arg(va, int);
```
Reviewers: jyknight
Reviewed By: jyknight
Subscribers: fedor.sergeev, jrtc27, llvm-commits
Differential Revision: https://reviews.llvm.org/D48595
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337161 91177308-0d34-0410-b5e6-96231b3b80d8
Found cases that hit the assert I added. This patch factors the validity
checking into a nice helper routine and calls it when deciding to harden
post-load, and asserts it when doing so later.
I've added tests for the various ways of loading a floating point type,
as well as loading all vector permutations. Even though many of these go
to identical instructions, it seems good to somewhat comprehensively
test them.
I'm confident there will be more fixes needed here, I'll try to add
tests each time as I get this predicate adjusted.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337160 91177308-0d34-0410-b5e6-96231b3b80d8
Memory legalizer, waitcnt, and shrink passes can perturb the instructions,
which means that the post-RA hazard recognizer pass should run after them.
Otherwise, one of those passes may invalidate the work done by the hazard
recognizer. Note that this has adverse side-effect that any consecutive
S_NOP 0's, emitted by the hazard recognizer, will not be shrunk into a
single S_NOP <N>. This should be addressed in a follow-on patch.
Differential Revision: https://reviews.llvm.org/D49288
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337154 91177308-0d34-0410-b5e6-96231b3b80d8
This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid.
The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337147 91177308-0d34-0410-b5e6-96231b3b80d8
indices used by AVX2 and AVX-512 gather instructions.
The index vector is hardened by broadcasting the predicate state
into a vector register and then or-ing. We don't even have to worry
about EFLAGS here.
I've added a test for all of the gather intrinsics to make sure that we
don't miss one. A particularly interesting creation is the gather
prefetch, which needs to be marked as potentially "loading" to get the
correct behavior. It's a memory access in many ways, and is actually
relevant for SLH. Based on discussion with Craig in review, I've moved
it to be `mayLoad` and `mayStore` rather than generic side effects. This
matches how we model other prefetch instructions.
Many thanks to Craig for the review here.
Differential Revision: https://reviews.llvm.org/D49336
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337144 91177308-0d34-0410-b5e6-96231b3b80d8
AVX512F only has integer domain logic instructions. AVX512DQ added FP domain logic instructions.
Execution domain fixing runs before EVEX->VEX. So if we have AVX512F and not AVX512DQ we fail to do execution domain switching of the logic operations. This leads to mismatches in execution domain and more test differences.
This patch adds custom domain fixing that switches EVEX integer logic operations to VEX fp logic operations if XMM16-31 are not used.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337137 91177308-0d34-0410-b5e6-96231b3b80d8
128-bit ops implicitly zero the upper bits. This should address the comment about domain crossing for the integer version without AVX2 since we can use a 128-bit VBLENDW without AVX2.
The only bad thing I see here is that we failed to reuse an vxorps in some of the tests, but I think that's already known issue.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337134 91177308-0d34-0410-b5e6-96231b3b80d8
This is almost the same as an existing IR canonicalization in instcombine,
so I'm assuming this is a good early generic DAG combine too.
The motivation comes from reduced bit-hacking for select-of-constants in IR
after rL331486. We want to restore that functionality in the DAG as noted in
the commit comments for that change and the llvm-dev discussion here:
http://lists.llvm.org/pipermail/llvm-dev/2018-July/124433.html
The PPC and AArch tests show that those targets are already doing something
similar. x86 will be neutral in the minimal case and generally better when
this pattern is extended with other ops as shown in the signbit-shift.ll tests.
Note the asymmetry: we don't include the (extend (ifneg X)) transform because
it already exists in SimplifySelectCC(), and that is verified in the later
unchanged tests in the signbit-shift.ll files. Without the 'not' op, the
general transform to use a shift is always a win because that's a single
instruction.
Alive proofs:
https://rise4fun.com/Alive/ysli
Name: if pos, get -1
%c = icmp sgt i16 %x, -1
%r = sext i1 %c to i16
=>
%n = xor i16 %x, -1
%r = ashr i16 %n, 15
Name: if pos, get 1
%c = icmp sgt i16 %x, -1
%r = zext i1 %c to i16
=>
%n = xor i16 %x, -1
%r = lshr i16 %n, 15
Differential Revision: https://reviews.llvm.org/D48970
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337130 91177308-0d34-0410-b5e6-96231b3b80d8
This was improved with rL337127, but I missed the failure in this test.
I'm not sure what the expected result will be, so I've generalized it
and added a FIXME comment.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337128 91177308-0d34-0410-b5e6-96231b3b80d8
The MachineOutliner was doing an std::for_each from the call (inserted
before the outlined sequence) to the iterator at the end of the
sequence.
std::for_each needs the iterator past the end, so the last instruction
was not taken into account when propagating the liveness information.
This fixes the machine verifier issue in machine-outliner-disubprogram.ll.
Differential Revision: https://reviews.llvm.org/D49295
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337090 91177308-0d34-0410-b5e6-96231b3b80d8
no conditions.
This is only valid to do if we're hardening calls and rets with LFENCE
which results in an LFENCE guarding the entire entry block for us.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337089 91177308-0d34-0410-b5e6-96231b3b80d8
The code tried to find the immediate by using getNumOperands() on the MachineInstr, but there might be implicit-defs after the immediate that get counted.
Instead use getNumOperands() from the instruction description which will only count the operands that are defined in the td file.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337088 91177308-0d34-0410-b5e6-96231b3b80d8
AVX512 doesn't have an immediate controlled blend instruction. But blend throughput is still better than movss/sd on SKX.
This commit changes AVX512 to use the AVX blend instructions instead of MOVSS/MOVSD. This constrains the register allocation since it won't be able to use XMM16-31, but hopefully the increased throughput and reduced port 5 pressure makes up for that.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337083 91177308-0d34-0410-b5e6-96231b3b80d8
This reverts commit r337021.
WARNING: MemorySanitizer: use-of-uninitialized-value
#0 0x1415cd65 in void write_signed<long>(llvm::raw_ostream&, long, unsigned long, llvm::IntegerStyle) /code/llvm-project/llvm/lib/Support/NativeFormatting.cpp:95:7
#1 0x1415c900 in llvm::write_integer(llvm::raw_ostream&, long, unsigned long, llvm::IntegerStyle) /code/llvm-project/llvm/lib/Support/NativeFormatting.cpp:121:3
#2 0x1472357f in llvm::raw_ostream::operator<<(long) /code/llvm-project/llvm/lib/Support/raw_ostream.cpp:117:3
#3 0x13bb9d4 in llvm::raw_ostream::operator<<(int) /code/llvm-project/llvm/include/llvm/Support/raw_ostream.h:210:18
#4 0x3c2bc18 in void printField<unsigned int, &(amd_kernel_code_s::amd_kernel_code_version_major)>(llvm::StringRef, amd_kernel_code_s const&, llvm::raw_ostream&) /code/llvm-project/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp:78:23
#5 0x3c250ba in llvm::printAmdKernelCodeField(amd_kernel_code_s const&, int, llvm::raw_ostream&) /code/llvm-project/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp:104:5
#6 0x3c27ca3 in llvm::dumpAmdKernelCode(amd_kernel_code_s const*, llvm::raw_ostream&, char const*) /code/llvm-project/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp:113:5
#7 0x3a46e6c in llvm::AMDGPUTargetAsmStreamer::EmitAMDKernelCodeT(amd_kernel_code_s const&) /code/llvm-project/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp:161:3
#8 0xd371e4 in llvm::AMDGPUAsmPrinter::EmitFunctionBodyStart() /code/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp:204:26
[...]
Uninitialized value was created by an allocation of 'KernelCode' in the stack frame of function '_ZN4llvm16AMDGPUAsmPrinter21EmitFunctionBodyStartEv'
#0 0xd36650 in llvm::AMDGPUAsmPrinter::EmitFunctionBodyStart() /code/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp:192
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337079 91177308-0d34-0410-b5e6-96231b3b80d8
If an HVX vector register is to be coalesced into a vector pair, make
sure that the vector pair will not have a function call in its live range,
unless it already had one. All HVX vector registers are volatile, so
any vector register live across a function call will have to be spilled.
If a vector needs to be spilled, and it's coalesced into a vector pair
then the whole pair will need to be spilled (even if only a part of it is
live), taking extra stack space.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337073 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
By looking at the callers of getUse(), we can see that even though
IVUsers may offer uses, but they may not be interesting to
LSR. It's possible that none of them is interesting.
Reviewers: sanjoy
Subscribers: jlebar, hiraditya, bixia, llvm-commits
Differential Revision: https://reviews.llvm.org/D49049
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337072 91177308-0d34-0410-b5e6-96231b3b80d8
Simon Pilgrim