coalescer) handle sub-register classes.
- Add heuristics to avoid non-profitable cse. Given the current lack of live
range splitting, avoid cse when an expression has PHI use and the would be
new use is in a BB where the expression wasn't already being used.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@98043 91177308-0d34-0410-b5e6-96231b3b80d8
and add a FIXME about how we are eventually going to zap this
lookup table once mc world domination is complete.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@98031 91177308-0d34-0410-b5e6-96231b3b80d8
physreg becomes ridiculously high.
std::upper_bound may be log(N), but for sufficiently large live intervals, it
becomes log(N)*cachemiss = a long long time.
This patch improves coalescer time by 4500x for a function with 20000
function calls. The generated code is different, but not significantly worse -
the allocator hints are almost as good as physreg coalescing anyway.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@98023 91177308-0d34-0410-b5e6-96231b3b80d8
available, the only thing this affects is that we produce
.set in one case we didn't before, which shouldn't harm
anything. Make EmitSectionOffset call EmitDifference
instead of duplicating it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@98005 91177308-0d34-0410-b5e6-96231b3b80d8
This is a first step towards eliminating unncessary constructor checks in light weight DIDescriptor wrappers.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97947 91177308-0d34-0410-b5e6-96231b3b80d8
is a workaround for <rdar://problem/7672401/> (which I filed).
This let's us build Wine on Darwin, and it gets the Qt build there a little bit
further (so Doug says).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97845 91177308-0d34-0410-b5e6-96231b3b80d8
CALL ... %RAX<imp-def>
... [not using %RAX]
%EAX = ..., %RAX<imp-use, kill>
RET %EAX<imp-use,kill>
Now we do this:
CALL ... %RAX<imp-def, dead>
... [not using %RAX]
%EAX = ...
RET %EAX<imp-use,kill>
By not artificially keeping %RAX alive, we lower register pressure a bit.
The correct number of instructions for 2008-08-05-SpillerBug.ll is obviously
55, anybody can see that. Sheesh.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97838 91177308-0d34-0410-b5e6-96231b3b80d8
node which has a flag. That flag in turn was used by an
already-selected adde which turned into an ADC32ri8 which
used a selected load which was chained to the load we
folded. This flag use caused us to form a cycle. Fix
this by not ignoring chains in IsLegalToFold even in
cases where the isel thinks it can.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97791 91177308-0d34-0410-b5e6-96231b3b80d8
rounding correctly. This implementation is a generalization of
the x86_64 code in compiler-rt.
This fixes rdar://7683708.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97778 91177308-0d34-0410-b5e6-96231b3b80d8
as nounwind are marked with a -1 call-site value. This is necessary to, for
example, correctly process exceptions thrown from within an "unexpected"
execption handler (see SingleSource/Regression/C++/EH/expection_spec_test.cpp).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97757 91177308-0d34-0410-b5e6-96231b3b80d8
as the very last thing before node emission. This should
dramatically reduce the number of times we do 'MatchAddress'
on X86, speeding up compile time. This also improves comments
in the tables and shrinks the table a bit, now down to
80506 bytes for x86.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97703 91177308-0d34-0410-b5e6-96231b3b80d8
CSE and recursive RAUW calls delete a node from the use list,
invalidating the use list iterator. There's currently no known
way to reproduce this in an unmodified LLVM, however there's no
fundamental reason why a SelectionDAG couldn't be formed which
would trigger this case.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97665 91177308-0d34-0410-b5e6-96231b3b80d8
entry we're about to process is obviously going to fail, don't
bother pushing a scope only to have it immediately be popped.
This avoids a lot of scope stack traffic in common cases.
Unfortunately, this requires duplicating some of the predicate
dispatch. To avoid duplicating the actual logic I pulled each
predicate out to its own static function which gets used in
both places.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97651 91177308-0d34-0410-b5e6-96231b3b80d8
SwitchOpcodeMatcher) and have DAGISelMatcherOpt form it. This
speeds up selection, particularly for X86 which has lots of
variants of instructions with only type differences.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97645 91177308-0d34-0410-b5e6-96231b3b80d8
- Eliminate TargetInstrInfo::isIdentical and replace it with produceSameValue. In the default case, produceSameValue just checks whether two machine instructions are identical (except for virtual register defs). But targets may override it to check for unusual cases (e.g. ARM pic loads from constant pools).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97628 91177308-0d34-0410-b5e6-96231b3b80d8
long test(long x) { return (x & 123124) | 3; }
Currently compiles to:
_test:
orl $3, %edi
movq %rdi, %rax
andq $123127, %rax
ret
This is because instruction and DAG combiners canonicalize
(or (and x, C), D) -> (and (or, D), (C | D))
However, this is only profitable if (C & D) != 0. It gets in the way of the
3-addressification because the input bits are known to be zero.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97616 91177308-0d34-0410-b5e6-96231b3b80d8
CopyToReg/CopyFromReg/INLINEASM. These are annoying because
they have the same opcode before an after isel. Fix this by
setting their NodeID to -1 to indicate that they are selected,
just like what automatically happens when selecting things that
end up being machine nodes.
With that done, give IsLegalToFold a new flag that causes it to
ignore chains. This lets the HandleMergeInputChains routine be
the one place that validates chains after a match is successful,
enabling the new hotness in chain processing. This smarter
chain processing eliminates the need for "PreprocessRMW" in the
X86 and MSP430 backends and enables MSP to start matching it's
multiple mem operand instructions more aggressively.
I currently #if out the dead code in the X86 backend and MSP
backend, I'll remove it for real in a follow-on patch.
The testcase changes are:
test/CodeGen/X86/sse3.ll: we generate better code
test/CodeGen/X86/store_op_load_fold2.ll: PreprocessRMW was
miscompiling this before, we now generate correct code
Convert it to filecheck while I'm at it.
test/CodeGen/MSP430/Inst16mm.ll: Add a testcase for mem/mem
folding to make anton happy. :)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97596 91177308-0d34-0410-b5e6-96231b3b80d8
was that we weren't properly handling the case when interior
nodes of a matched pattern become dead after updating chain
and flag uses. Now we handle this explicitly in
UpdateChainsAndFlags.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97561 91177308-0d34-0410-b5e6-96231b3b80d8
DoInstructionSelection. Inline "SelectRoot" into it from DAGISelHeader.
Sink some other stuff out of DAGISelHeader into SDISel.
Eliminate the various 'Indent' stuff from various targets, which dates
to when isel was recursive.
17 files changed, 114 insertions(+), 430 deletions(-)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97555 91177308-0d34-0410-b5e6-96231b3b80d8
stuff now that we don't care about emulating the old broken
behavior of the old isel. This eliminates the
'CheckChainCompatible' check (along with IsChainCompatible) which
did an incorrect and inefficient scan *up* the chain nodes which
happened as the pattern was being formed and does the validation
at the end in HandleMergeInputChains when it forms a structural
pattern. This scans "down" the graph, which means that it is
quickly bounded by nodes already selected. This also handles
token factors that get "trapped" in the dag.
Removing the CheckChainCompatible nodes also shrinks the
generated tables by about 6K for X86 (down to 83K).
There are two pieces remaining before I can nuke PreprocessRMW:
1. I xfailed a test because we're now producing worse code in a
case that has nothing to do with the change: it turns out that
our use of MorphNodeTo will leave dead nodes in the graph
which (depending on how the graph is walked) end up causing
bogus uses of chains and blocking matches. This is really
bad for other reasons, so I'll fix this in a follow-up patch.
2. CheckFoldableChainNode needs to be improved to handle the TF.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97539 91177308-0d34-0410-b5e6-96231b3b80d8
ComplexPattern at the root be generated multiple times, once
for each opcode they are part of. This encourages factoring
because the opcode checks get treated just like everything
else in the matcher.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97439 91177308-0d34-0410-b5e6-96231b3b80d8
to a scope where every child starts with a CheckOpcode, but
executes more efficiently. Enhance DAGISelMatcherOpt to
form it.
This also fixes a bug in CheckOpcode: apparently the SDNodeInfo
objects are not pointer comparable, we have to compare the
enum name.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97438 91177308-0d34-0410-b5e6-96231b3b80d8
(which gets #included into the middle of each
target's DAGISel class) into a .cpp file where it is
only compiled once.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97425 91177308-0d34-0410-b5e6-96231b3b80d8
defs or uses. The regular def and use checking below covers them, and
can be more precise. It's safe to hoist an instruction with a dead
implicit def if the register isn't live into the loop header.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97352 91177308-0d34-0410-b5e6-96231b3b80d8
for alignment into the LSDA. If the TType base offset is emitted, then put the
padding there. Otherwise, put it in the call site table length. There will be no
conflict between the two sites when placing the padding in one place.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97277 91177308-0d34-0410-b5e6-96231b3b80d8
The PowerPC floating point registers can represent both f32 and f64 via the
two register classes F4RC and F8RC. F8RC is considered a subclass of F4RC to
allow cross-class coalescing. This coalescing only affects whether registers
are spilled as f32 or f64.
Spill slots must be accessed with load/store instructions corresponding to the
class of the spilled register. PPCInstrInfo::foldMemoryOperandImpl was looking
at the instruction opcode which is wrong.
X86 has similar floating point register classes, but doesn't try to fold
memory operands, so there is no problem there.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97262 91177308-0d34-0410-b5e6-96231b3b80d8
the alignment requirement, if it no longer makes the TType base offset overflow
into extra bytes, then we need to pad to those bytes ourselves.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97196 91177308-0d34-0410-b5e6-96231b3b80d8
will eliminate the need for padding in the "Call site table length". E.g., if
we have this:
GCC_except_table1:
Lexception1:
.byte 0xff ## @LPStart Encoding = omit
.byte 0x9b ## @TType Encoding = indirect pcrel sdata4
.byte 0x7f ## @TType base offset
.byte 0x03 ## Call site Encoding = udata4
.byte 0x89 ## Call site table length
with padding of 1. We want to emit the padding like this:
GCC_except_table1:
Lexception1:
.byte 0xff ## @LPStart Encoding = omit
.byte 0x9b ## @TType Encoding = indirect pcrel sdata4
.byte 0xff ## @TType base offset
.space 1,0 ## Padding
.byte 0x03 ## Call site Encoding = udata4
.byte 0x89 ## Call site table length
and not with padding on the "Call site table length" entry.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97183 91177308-0d34-0410-b5e6-96231b3b80d8
terms of store and load, which means bitcasting between scalar
integer and vector has endian-specific results, which undermines
this whole approach.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97137 91177308-0d34-0410-b5e6-96231b3b80d8
GCC_except_table label but before the Lexception, which the FDE references.
This causes problems as the FDE does not point to the start of an LSDA chunk.
Use an unnormalized uleb128 for the call-site table length that includes the
padding.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97078 91177308-0d34-0410-b5e6-96231b3b80d8
the number of value bits, not the number of bits of allocation for in-memory
storage.
Make getTypeStoreSize and getTypeAllocSize work consistently for arrays and
vectors.
Fix several places in CodeGen which compute offsets into in-memory vectors
to use TargetData information.
This fixes PR1784.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97064 91177308-0d34-0410-b5e6-96231b3b80d8
necessary to swap the operands to handle NaN and negative zero properly.
Also, reintroduce logic for checking for NaN conditions when forming
SSE min and max instructions, fixed to take into consideration NaNs and
negative zeros. This allows forming min and max instructions in more
cases.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97025 91177308-0d34-0410-b5e6-96231b3b80d8
to adding them in a determinstic order (bottom up from
the root) based on the structure of the graph itself.
This updates tests for some random changes, interesting
bits: CodeGen/Blackfin/promote-logic.ll no longer crashes.
I have no idea why, but that's good right?
CodeGen/X86/2009-07-16-LoadFoldingBug.ll also fails, but
now compiles to have one fewer constant pool entry, making
the expected load that was being folded disappear. Since it
is an unreduced mass of gnast, I just removed it.
This fixes PR6370
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97023 91177308-0d34-0410-b5e6-96231b3b80d8