A new basic block ordering improving existing MachineBlockPlacement.
The algorithm tries to find a layout of nodes (basic blocks) of a given CFG
optimizing jump locality and thus processor I-cache utilization. This is
achieved via increasing the number of fall-through jumps and co-locating
frequently executed nodes together. The name follows the underlying
optimization problem, Extended-TSP, which is a generalization of classical
(maximum) Traveling Salesmen Problem.
The algorithm is a greedy heuristic that works with chains (ordered lists)
of basic blocks. Initially all chains are isolated basic blocks. On every
iteration, we pick a pair of chains whose merging yields the biggest increase
in the ExtTSP value, which models how i-cache "friendly" a specific chain is.
A pair of chains giving the maximum gain is merged into a new chain. The
procedure stops when there is only one chain left, or when merging does not
increase ExtTSP. In the latter case, the remaining chains are sorted by
density in decreasing order.
An important aspect is the way two chains are merged. Unlike earlier
algorithms (e.g., based on the approach of Pettis-Hansen), two
chains, X and Y, are first split into three, X1, X2, and Y. Then we
consider all possible ways of gluing the three chains (e.g., X1YX2, X1X2Y,
X2X1Y, X2YX1, YX1X2, YX2X1) and choose the one producing the largest score.
This improves the quality of the final result (the search space is larger)
while keeping the implementation sufficiently fast.
Differential Revision: https://reviews.llvm.org/D113424
LLVM loops cannot represent irreducible structures in the CFG. This
change introduce the concept of cycles as a generalization of loops,
along with a CycleInfo analysis that discovers a nested
hierarchy of such cycles. This is based on Havlak (1997), Nesting of
Reducible and Irreducible Loops.
The cycle analysis is implemented as a generic template and then
instatiated for LLVM IR and Machine IR. The template relies on a new
GenericSSAContext template which must be specialized when used for
each IR.
This review is a restart of an older review request:
https://reviews.llvm.org/D83094
Original implementation by Nicolai Hähnle <nicolai.haehnle@amd.com>,
with recent refactoring by Sameer Sahasrabuddhe <sameer.sahasrabuddhe@amd.com>
Differential Revision: https://reviews.llvm.org/D112696
When compiling with indirect branch tracking and fentry (-fcf-protection=branch -mfentry -pg) the X86IndirectBranchTrackingPass will attempt to place endbr in basic blocks, checking for Calls/IsCallReturnTwice. For calling the function IsCallReturnTwice(), the pass attempts to retrieve the first operand of the respective machine instruction. Since FENTRY_CALL is considered a call, and it does not have any argument, the condition inside the pass will attempt to call IsCallReturnTwice on the machine instruction, but since it does not have operands, it will lead into a crash.
Kudos to Alyssa Milburn for helping in the issue triage. The diff brings a test, but to reproduce the problem, follow the steps below.
```
echo "int main() {};" > repro.c
clang repro.c -fcf-protection=branch -mfentry -pg
```
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D111108
A new basic block ordering improving existing MachineBlockPlacement.
The algorithm tries to find a layout of nodes (basic blocks) of a given CFG
optimizing jump locality and thus processor I-cache utilization. This is
achieved via increasing the number of fall-through jumps and co-locating
frequently executed nodes together. The name follows the underlying
optimization problem, Extended-TSP, which is a generalization of classical
(maximum) Traveling Salesmen Problem.
The algorithm is a greedy heuristic that works with chains (ordered lists)
of basic blocks. Initially all chains are isolated basic blocks. On every
iteration, we pick a pair of chains whose merging yields the biggest increase
in the ExtTSP value, which models how i-cache "friendly" a specific chain is.
A pair of chains giving the maximum gain is merged into a new chain. The
procedure stops when there is only one chain left, or when merging does not
increase ExtTSP. In the latter case, the remaining chains are sorted by
density in decreasing order.
An important aspect is the way two chains are merged. Unlike earlier
algorithms (e.g., based on the approach of Pettis-Hansen), two
chains, X and Y, are first split into three, X1, X2, and Y. Then we
consider all possible ways of gluing the three chains (e.g., X1YX2, X1X2Y,
X2X1Y, X2YX1, YX1X2, YX2X1) and choose the one producing the largest score.
This improves the quality of the final result (the search space is larger)
while keeping the implementation sufficiently fast.
Differential Revision: https://reviews.llvm.org/D113424
Expanding on D109750.
Since `DBG_VALUE` instructions have final register validity determined in
`LDVImpl::handleDebugValue`, there is no apparent reason to immediately prune
unused register operands as their defs are erased. Consequently, this renders
`MachineInstr::eraseFromParentAndMarkDBGValuesForRemoval` moot; gaining a
substantial performance improvement.
The only necessary changes involve making relevant passes consider invalid
DBG_VALUE vregs uses as valid.
Reviewed By: MatzeB
Differential Revision: https://reviews.llvm.org/D112852
When Control Flow Guard Check is inserted, funclet bundle was not checked. Therefore, it didn't generate code correctly when a target function has "funclet" bundle.
Reviewed By: rnk
Differential Revision: https://reviews.llvm.org/D114914
Prior to this patch, tail duplication handled debug info poorly -
specifically, debug instructions would be dropped instead of being set
undef, potentially extending the lifetimes of prior debug values that
should be killed. The pass was also very aggressive with dropping debug
info, dropping debug info even when the SSA value it referred to was
still present. This patch attempts to handle debug info more carefully,
checking to see whether each affected debug value can still be live,
setting it undef if not.
Reviewed By: jmorse
Differential Revision: https://reviews.llvm.org/D106875
Changed registers to R10 and R11 because PLT resolution clobbers them. Also changed the implementation to use R11 instead of RCX, which saves a push/pop.
Reviewed By: vitalybuka
Differential Revision: https://reviews.llvm.org/D115002
We have reasonable fast sqrt and accurate rsqrt for half type due to the
limited fractions. So neither do we need multi steps refinement for
rsqrt nor replace sqrt by rsqrt.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D114844
combinePMULH currently only truncates vXi32/vXi64 multiplies to PMULHW/PMULUW if the source operands are SEXT/ZEXT instructions for a 'free' truncation.
But we can generalize this to any source operand with sufficient leading sign/zero bits that would allow PACKS/PACKUS to be used as a 'cheap' truncation.
This helps us avoid the wider multiplies, in exchange for truncation on both source operands instead of the result.
Differential Revision: https://reviews.llvm.org/D113371
This adds a fold in DAGCombine to create fptosi_sat from sequences for
smin(smax(fptosi(x))) nodes, where the min/max saturate the output of
the fp convert to a specific bitwidth (say INT_MIN and INT_MAX). Because
it is dealing with smin(/smax) in DAG they may currently be ISD::SMIN,
ISD::SETCC/ISD::SELECT, ISD::VSELECT or ISD::SELECT_CC nodes which need
to be handled similarly.
A shouldConvertFpToSat method was added to control when converting may
be profitable. The original fptosi will have a less strict semantics
than the fptosisat, with less values that need to produce defined
behaviour.
This especially helps on ARM/AArch64 where the vcvt instructions
naturally saturate the result.
Differential Revision: https://reviews.llvm.org/D111976
It causes builds to fail with this assert:
llvm/include/llvm/ADT/APInt.h:990:
bool llvm::APInt::operator==(const llvm::APInt &) const:
Assertion `BitWidth == RHS.BitWidth && "Comparison requires equal bit widths"' failed.
See comment on the code review.
> This adds a fold in DAGCombine to create fptosi_sat from sequences for
> smin(smax(fptosi(x))) nodes, where the min/max saturate the output of
> the fp convert to a specific bitwidth (say INT_MIN and INT_MAX). Because
> it is dealing with smin(/smax) in DAG they may currently be ISD::SMIN,
> ISD::SETCC/ISD::SELECT, ISD::VSELECT or ISD::SELECT_CC nodes which need
> to be handled similarly.
>
> A shouldConvertFpToSat method was added to control when converting may
> be profitable. The original fptosi will have a less strict semantics
> than the fptosisat, with less values that need to produce defined
> behaviour.
>
> This especially helps on ARM/AArch64 where the vcvt instructions
> naturally saturate the result.
>
> Differential Revision: https://reviews.llvm.org/D111976
This reverts commit 52ff3b009388f1bef4854f1b6470b4ec19d10b0e.
This adds a fold in DAGCombine to create fptosi_sat from sequences for
smin(smax(fptosi(x))) nodes, where the min/max saturate the output of
the fp convert to a specific bitwidth (say INT_MIN and INT_MAX). Because
it is dealing with smin(/smax) in DAG they may currently be ISD::SMIN,
ISD::SETCC/ISD::SELECT, ISD::VSELECT or ISD::SELECT_CC nodes which need
to be handled similarly.
A shouldConvertFpToSat method was added to control when converting may
be profitable. The original fptosi will have a less strict semantics
than the fptosisat, with less values that need to produce defined
behaviour.
This especially helps on ARM/AArch64 where the vcvt instructions
naturally saturate the result.
Differential Revision: https://reviews.llvm.org/D111976
Currently we create register mappings for registers used only once in current
MBB. For registers with multiple uses, when all the uses are in the current MBB,
we can also create mappings for them similarly according to the last use.
For example
%reg101 = ...
= ... reg101
%reg103 = ADD %reg101, %reg102
We can create mapping between %reg101 and %reg103.
Differential Revision: https://reviews.llvm.org/D113193
These are some final test changes for using instruction referencing on X86:
* Most of these tests just have the flag switched so that they run with
instr-ref, and just work: these tests were fixed by earlier patches.
* There are some spurious differences in textual outputs,
* A few have different temporary labels in the output because more
MCSymbols are printed to the output.
Differential Revision: https://reviews.llvm.org/D114588
If we only demand bits from one half of a rotation pattern, see if we can simplify to a logical shift.
For the ARM/AArch64 rev16/32 patterns, I had to drop a fold to prevent srl(bswap()) -> rotr(bswap) -> srl(bswap) infinite loops. I've replaced this with an isel PatFrag which should do the same task.
Reapplied with fix for AArch64 rev patterns to matching the ARM fix.
https://alive2.llvm.org/ce/z/iroxki (rol -> shl by amt iff demanded bits has at least as many trailing zeros as the shift amount)
https://alive2.llvm.org/ce/z/4ez_U- (ror -> shl by revamt iff demanded bits has at least as many trailing zeros as the reverse shift amount)
https://alive2.llvm.org/ce/z/cD7dR- (ror -> lshr by amt iff demanded bits has at least as many leading zeros as the shift amount)
https://alive2.llvm.org/ce/z/_XGHtQ (rol -> lshr by revamt iff demanded bits has at least as many leading zeros as the reverse shift amount)
Differential Revision: https://reviews.llvm.org/D114354
The changes in D113888 / 32b6c17b29079e7d altered the memory size of a
masked store, as it will store an unknown number of bytes not the full
vector size. We can have situations where the masked stores is legalized
and then turned to a normal store, as the mask is known to be all ones.
This creates a store with an unknown size MMO that was hitting this
assert.
The store created can be given a better size in a followup patch. This
currently adjusts the assert to handle unknown sizes.
Enabling instruction referencing causes a few variable locations to switch
order -- i.e., they switch position in the output DWARF, or sometimes the
order of DBG_VALUEs. Update a few tests to reflect this.
Differential Revision: https://reviews.llvm.org/D114261
[NFC] As part of using inclusive language within the llvm project, this patch
renames the master label in `x86-shrink-wrapping.ll` to main.
Reviewed By: ZarkoCA
Differential Revision: https://reviews.llvm.org/D113940
In these test updates for instruction referencing, I've added specific
instr-ref RUN lines, and kep thte DBG_VALUE-based variable location check
lines too. This is because argument handling is really fiddly, and I figure
it's worth duplicating the testing to ensure it's definitely correct.
There's also dbg-value-superreg-copy2.mir, a dtest for where varaible
locations go when virtual registers are coalesced together. I don't think
there's an instruction referencing specific test for this, so have
duplicated that to for instruction referencing.
Differential Revision: https://reviews.llvm.org/D114262
If we only demand bits from one half of a rotation pattern, see if we can simplify to a logical shift.
For the ARM rev16 patterns, I had to drop a fold to prevent srl(bswap()) -> rotr(bswap) -> srl(bswap) infinite loops. I've replaced this with an isel PatFrag which should do the same task.
https://alive2.llvm.org/ce/z/iroxki (rol -> shl by amt iff demanded bits has at least as many trailing zeros as the shift amount)
https://alive2.llvm.org/ce/z/4ez_U- (ror -> shl by revamt iff demanded bits has at least as many trailing zeros as the reverse shift amount)
https://alive2.llvm.org/ce/z/cD7dR- (ror -> lshr by amt iff demanded bits has at least as many leading zeros as the shift amount)
https://alive2.llvm.org/ce/z/_XGHtQ (rol -> lshr by revamt iff demanded bits has at least as many leading zeros as the reverse shift amount)
Differential Revision: https://reviews.llvm.org/D114354
The MIR sample loader changes the branch probability but not BFI.
Here we force a recompute of BFI if the branch probabilities are
changed.
Also register the MIR FSAFDO passes properly.
Differential Revision: https://reviews.llvm.org/D114400
A masked load or store will load a potentially unknown number of bytes
from a memory location - that is not generally known at compile time.
They do not necessarily load/store the entire vector width, and treating
them as such can lead to incorrect aliasing information (for example, if
the underlying object is smaller than the size of the vector).
This makes sure that the MMO is given an unknown size to represent this.
which is less accurate that "may load/store from up to 16 bytes", but
less incorrect that "will load/store from 16 bytes".
Differential Revision: https://reviews.llvm.org/D113888
This makes a line in llvm/test/CodeGen/X86/asm-block-labels.ll pass
with `asm inteldialect` too.
I don't know if this is something one can hit in practice with inline
asm. The test is from 2007 (4646aa3e337aa) but in 2009 blockaddr was
introduced and e.g. `__asm__ __volatile__("brl %0" :: "X"(&&foo) : "memory");`
compiles to
call void asm sideeffect "brl $0", "X,..."(i8* blockaddress(@func, %1))
nowadays (thanks to jrtc27 for that example!).
(6c4d255bf3d64 switched clang to blockaddress on an opt-in basis,
e4801f7844bb added docs for it, 31b132c0b781 added IR support.)
I half-heartedly tried to build clang 2.8 locally, but it didn't
just build. And 2.8 didn't have a prebuilt clang binary yet.
The motivation is to make EmitGCCInlineAsmStr() and EmitMSInlineAsmStr()
more alike, and maybe we should delete this code form EmitGCCInlineAsmStr()
instead. But since it's just 3 lines and it's reachable from LLVM IR,
let's do the safer thing for now.
Differential Revision: https://reviews.llvm.org/D114329
We have transform that tries turn a pmovmskb into movmskps/pd or
movmskps to movmskpd. This transform isn't valid if the truncate
discarded bits that might be set by the original movmsk.
We could fix this by inserting an AND after the new movmsk to discard
the equivalent of the truncated bits, but I've left that for later
patch.
Fixes PR52567.
Differential Revision: https://reviews.llvm.org/D114306
For tagged-globals, we only need to disable relaxation for globals that
we actually tag. With this patch function pointer relocations, which
we do not instrument, can be relaxed.
This patch also makes tagged-globals work properly with LTO, as
-Wa,-mrelax-relocations=no doesn't work with LTO.
Reviewed By: pcc
Differential Revision: https://reviews.llvm.org/D113220
