This occurs during UINT_TO_FP v2f64 lowering.
We can easily generalize this to other horizontal ops (FHSUB, PACKSS, PACKUS) as required - we are doing something similar with PACKUS in lowerV2I64VectorShuffle
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287676 91177308-0d34-0410-b5e6-96231b3b80d8
This test is very brittle as small changes to block layout break the
check patterns. Hack around a change one more time.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287637 91177308-0d34-0410-b5e6-96231b3b80d8
Add basic ComputeNumSignBits support for TRUNCATE ops for cases where the source's number of sign bits overlaps with the truncated size.
Improves X86 SIGN_EXTEND_IN_REG vector cases which were needlessly sign extending boolean vector results.
Differential Revision: https://reviews.llvm.org/D26851
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287635 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
The index and one of the table operands can be swapped by changing the opcode to the other version. Neither of these operands are the one that can load from memory so this can't be used to increase memory folding opportunities.
We need to handle the unmasked forms and the kz forms. Since the load operand isn't being commuted we can commute the load and broadcast instructions too.
Reviewers: igorb, delena, Ayal, Farhana, RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D25652
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287621 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
Shuffle lowering widens the element size of a shuffle if elements are contiguous. This is sometimes help because wider element types have more shuffle options. If the shuffle is one of the arguments to a vselect this shuffle widening can introduce a bitcast between the vselect and the shuffle. This will prevent isel from selecting a masked operation. If the shuffle can be written equally efficiently with a different element size to match the vselect type we should change the shuffle type to allow masking.
This patch does this conversion for all VALIGND/VALIGNQ sizes. It also supports turning 128-bit PALIGNR into VALIGND/VALIGNQ. This fixes the case shown in PR31018.
I plan to add support for more operations in future patches.
Reviewers: RKSimon, zvi, delena
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D26902
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287612 91177308-0d34-0410-b5e6-96231b3b80d8
A target intrinsic may be defined as possibly reading memory,
but the call site may have additional knowledge that it doesn't read
memory. The intrinsic lowering will expect the pessimistic
assumption of the intrinsic definition, so the chain should
still be used.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287593 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
When searching for load/store instructions to pair/merge don't treat
writes to WZR/XZR as clobbers since they don't change the value read
from WZR/XZR (which is always 0).
Reviewers: mcrosier, junbuml, jmolloy, t.p.northover
Subscribers: aemerson, llvm-commits, rengolin
Differential Revision: https://reviews.llvm.org/D26921
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287592 91177308-0d34-0410-b5e6-96231b3b80d8
Summary: Merging an empty case block into the header block of switch could cause
ISel to add COPY instructions in the header of switch, instead of the case
block, if the case block is used as an incoming block of a PHI. This could
potentially increase dynamic instructions, especially when the switch is in a
loop. I added a test case which was reduced from the benchmark I was targetting.
Reviewers: t.p.northover, mcrosier, manmanren, wmi, davidxl
Subscribers: qcolombet, danielcdh, hfinkel, mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D22696
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287553 91177308-0d34-0410-b5e6-96231b3b80d8
At the moment we only use truncateVectorCompareWithPACKSS with direct vector comparison results (just one example of a known all/none signbits input).
This change relaxes the direct matching of a SETCC opcode by moving the logic up into SelectionDAG::ComputeNumSignBits and accepting any input with a known splatted signbit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287535 91177308-0d34-0410-b5e6-96231b3b80d8
- teach RelocVisitor to recognize bpf relocations
- fix AsmInfo->PointerSize to make sure dwarf is emitted correctly
- add a test for the above
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287521 91177308-0d34-0410-b5e6-96231b3b80d8
This patch adds a test for the assembly code emitted with XRay
instrumentation. It also fixes a bug where the operand of a jump
instruction must be not the number of bytes to jump over, but rather the
number of 4-byte instructions.
Author: rSerge
Reviewers: dberris, rengolin
Differential Revision: https://reviews.llvm.org/D26805
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287516 91177308-0d34-0410-b5e6-96231b3b80d8
The tail call optimization was being used without proper consideration of
ABI requirements for saving and restoring the GP. This patch restricts tail
call optimization to functions within the same translation unit.
Reviewers: vkalintiris
Differential Revision: https://reviews.llvm.org/D24763
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287505 91177308-0d34-0410-b5e6-96231b3b80d8
Many of these problems are because shuffle lowering widens element size and reduces element count when possible. This causes the shuffle to become separated from the select by a bitcast. Future patches will work to improve these cases by rewriting the shuffle back to a narrow element type if we think it can result in folding the mask.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287503 91177308-0d34-0410-b5e6-96231b3b80d8
The change is part of RegCall calling convention support for LLVM.
Long double (f80) requires special treatment as the first f80 parameter is saved in FP0 (floating point stack).
This review present the change and the corresponding tests.
Differential Revision: https://reviews.llvm.org/D26151
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287485 91177308-0d34-0410-b5e6-96231b3b80d8
add BPF disassembler, so tools like llvm-objdump can be used:
$ llvm-objdump -d -no-show-raw-insn ./sockex1_kern.o
./sockex1_kern.o: file format ELF64-BPF
Disassembly of section socket1:
bpf_prog1:
0: r6 = r1
8: r0 = *(u8 *)skb[23]
10: *(u32 *)(r10 - 4) = r0
18: r1 = *(u32 *)(r6 + 4)
20: if r1 != 4 goto 8
28: r2 = r10
30: r2 += -4
ld_imm64 (the only 16-byte insn) and special ld_abs/ld_ind instructions
had to be treated in a special way. The decoders for the rest of the insns
are automatically generated.
Add tests to cover new functionality.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287477 91177308-0d34-0410-b5e6-96231b3b80d8
This test introduced in r287368 is failing on powerpc for reasons
unrelated to branch probabilities. See PR31062.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287375 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
The 32-bit instructions don't zero the high 16-bits like the 16-bit
instructions do.
Reviewers: arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, llvm-commits, tony-tye
Differential Revision: https://reviews.llvm.org/D26828
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287342 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
The addr64-based legalization is incorrect for MUBUF instructions with idxen
set as well as for BUFFER_LOAD/STORE_FORMAT_* instructions. This affects
e.g. shaders that access buffer textures.
Since we never actually need the addr64-legalization in shaders, this patch
takes the easy route and keys off the calling convention. If this ever
affects (non-OpenGL) compute, the type of legalization needs to be chosen
based on some TSFlag.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=98664
Reviewers: arsenm, tstellarAMD
Subscribers: kzhuravl, wdng, yaxunl, tony-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D26747
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287339 91177308-0d34-0410-b5e6-96231b3b80d8
When we see a SETCC whose only users are zero extend operations, we can replace
it with a subtraction. This results in doing all calculations in GPRs and
avoids CR use.
Currently we do this only for ULT, ULE, UGT and UGE condition codes. There are
ways that this can be extended. For example for signed condition codes. In that
case we will be introducing additional sign extend instructions, so more careful
profitability analysis may be required.
Another direction to extend this is for equal, not equal conditions. Also when
users of SETCC are any_ext or sign_ext, we might be able to do something
similar.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287329 91177308-0d34-0410-b5e6-96231b3b80d8
The same thing was done to 32-bit and 64-bit element sizes previously.
This will allow us to support these shuffls in InstCombineCalls along with the other variable shift intrinsics.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@287312 91177308-0d34-0410-b5e6-96231b3b80d8
