This patch will optimize -(x != 0) on X86
FROM
cmpl $0x01,%edi
sbbl %eax,%eax
notl %eax
TO
negl %edi
sbbl %eax %eax
In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td:
def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>;
rdar: 10961709
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156312 91177308-0d34-0410-b5e6-96231b3b80d8
The primitive conservative heuristic seems to give a slight overall
improvement while not regressing stuff. Make it available to wider
testing. If you notice any speed regressions (or significant code
size regressions) let me know!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156258 91177308-0d34-0410-b5e6-96231b3b80d8
This came up when a change in block placement formed a cmov and slowed down a
hot loop by 50%:
ucomisd (%rdi), %xmm0
cmovbel %edx, %esi
cmov is a really bad choice in this context because it doesn't get branch
prediction. If we emit it as a branch, an out-of-order CPU can do a better job
(if the branch is predicted right) and avoid waiting for the slow load+compare
instruction to finish. Of course it won't help if the branch is unpredictable,
but those are really rare in practice.
This patch uses a dumb conservative heuristic, it turns all cmovs that have one
use and a direct memory operand into branches. cmovs usually save some code
size, so we disable the transform in -Os mode. In-Order architectures are
unlikely to benefit as well, those are included in the
"predictableSelectIsExpensive" flag.
It would be better to reuse branch probability info here, but BPI doesn't
support select instructions currently. It would make sense to use the same
heuristics as the if-converter pass, which does the opposite direction of this
transform.
Test suite shows a small improvement here and there on corei7-level machines,
but the actual results depend a lot on the used microarchitecture. The
transformation is currently disabled by default and available by passing the
-enable-cgp-select2branch flag to the code generator.
Thanks to Chandler for the initial test case to him and Evan Cheng for providing
me with comments and test-suite numbers that were more stable than mine :)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156234 91177308-0d34-0410-b5e6-96231b3b80d8
The new target machines are:
nvptx (old ptx32) => 32-bit PTX
nvptx64 (old ptx64) => 64-bit PTX
The sources are based on the internal NVIDIA NVPTX back-end, and
contain more functionality than the current PTX back-end currently
provides.
NV_CONTRIB
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156196 91177308-0d34-0410-b5e6-96231b3b80d8
to catch cases like:
%reg1024<def> = MOV r1
%reg1025<def> = MOV r0
%reg1026<def> = ADD %reg1024, %reg1025
r0 = MOV %reg1026
By commuting ADD, it let coalescer eliminate all of the copies. However, there
was a bug in the heuristics where it ended up commuting the ADD in:
%reg1024<def> = MOV r0
%reg1025<def> = MOV 0
%reg1026<def> = ADD %reg1024, %reg1025
r0 = MOV %reg1026
That did no benefit but rather ensure the last MOV would not be coalesced.
rdar://11355268
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156048 91177308-0d34-0410-b5e6-96231b3b80d8
This patch will optimize -(x != 0) on X86
FROM
cmpl $0x01,%edi
sbbl %eax,%eax
notl %eax
TO
negl %edi
sbbl %eax %eax
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155853 91177308-0d34-0410-b5e6-96231b3b80d8
On x86-32, structure return via sret lets the callee pop the hidden
pointer argument off the stack, which the caller then re-pushes.
However if the calling convention is fastcc, then a register is used
instead, and the caller should not adjust the stack. This is
implemented with a check of IsTailCallConvention
X86TargetLowering::LowerCall but is now checked properly in
X86FastISel::DoSelectCall.
(this time, actually commit what was reviewed!)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155825 91177308-0d34-0410-b5e6-96231b3b80d8
ARM BUILD_VECTORs created after type legalization cannot use i8 or i16
operands, since those types are not legal. Instead use i32 operands, which
will be implicitly truncated by the BUILD_VECTOR to match the element type.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155824 91177308-0d34-0410-b5e6-96231b3b80d8
This time, also fix the caller of AddGlue to properly handle
incomplete chains. AddGlue had failure modes, but shamefully hid them
from its caller. It's luck ran out.
Fixes rdar://11314175: BuildSchedUnits assert.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155749 91177308-0d34-0410-b5e6-96231b3b80d8
On x86-32, structure return via sret lets the callee pop the hidden
pointer argument off the stack, which the caller then re-pushes.
However if the calling convention is fastcc, then a register is used
instead, and the caller should not adjust the stack. This is
implemented with a check of IsTailCallConvention
X86TargetLowering::LowerCall but is now checked properly in
X86FastISel::DoSelectCall.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155745 91177308-0d34-0410-b5e6-96231b3b80d8
x == -y --> x+y == 0
x != -y --> x+y != 0
On x86, the generated code goes from
negl %esi
cmpl %esi, %edi
je .LBB0_2
to
addl %esi, %edi
je .L4
This case is correctly handled for ARM with "cmn".
Patch by Manman Ren.
rdar://11245199
PR12545
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155739 91177308-0d34-0410-b5e6-96231b3b80d8
* Model FPSW (the FPU status word) as a register.
* Add ISel patterns for the FUCOM*, FNSTSW and SAHF instructions.
* During Legalize/Lowering, build a node sequence to transfer the comparison
result from FPSW into EFLAGS. If you're wondering about the right-shift: That's
an implicit sub-register extraction (%ax -> %ah) which is handled later on by
the instruction selector.
Fixes PR6679. Patch by Christoph Erhardt!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155704 91177308-0d34-0410-b5e6-96231b3b80d8
DAGCombine strangeness may result in multiple loads from the same
offset. They both may try to glue themselves to another load. We could
insist that the redundant loads glue themselves to each other, but the
beter fix is to bail out from bad gluing at the time we detect it.
Fixes rdar://11314175: BuildSchedUnits assert.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155668 91177308-0d34-0410-b5e6-96231b3b80d8
On some cores it's a bad idea for performance to mix VFP and NEON instructions
and since these patterns are NEON anyway, the NEON load should be used.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155630 91177308-0d34-0410-b5e6-96231b3b80d8
the feature set of v7a. This comes about if the user specifies something like
-arch armv7 -mcpu=cortex-m3. We shouldn't be generating instructions such as
uxtab in this case.
rdar://11318438
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155601 91177308-0d34-0410-b5e6-96231b3b80d8
using the pattern (vbroadcast (i32load src)). In some cases, after we generate
this pattern new users are added to the load node, which prevent the selection
of the blend pattern. This commit provides fallback patterns which perform
in-vector broadcast (using in-vector vbroadcast in AVX2 and pshufd on AVX1).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155437 91177308-0d34-0410-b5e6-96231b3b80d8
on X86 Atom. Some of our tests failed because the tail merging part of
the BranchFolding pass was creating new basic blocks which did not
contain live-in information. When the anti-dependency code in the Post-RA
scheduler ran, it would sometimes rename the register containing
the function return value because the fact that the return value was
live-in to the subsequent block had been lost. To fix this, it is necessary
to run the RegisterScavenging code in the BranchFolding pass.
This patch makes sure that the register scavenging code is invoked
in the X86 subtarget only when post-RA scheduling is being done.
Post RA scheduling in the X86 subtarget is only done for Atom.
This patch adds a new function to the TargetRegisterClass to control
whether or not live-ins should be preserved during branch folding.
This is necessary in order for the anti-dependency optimizations done
during the PostRASchedulerList pass to work properly when doing
Post-RA scheduling for the X86 in general and for the Intel Atom in particular.
The patch adds and invokes the new function trackLivenessAfterRegAlloc()
instead of using the existing requiresRegisterScavenging().
It changes BranchFolding.cpp to call trackLivenessAfterRegAlloc() instead of
requiresRegisterScavenging(). It changes the all the targets that
implemented requiresRegisterScavenging() to also implement
trackLivenessAfterRegAlloc().
It adds an assertion in the Post RA scheduler to make sure that post RA
liveness information is available when it is needed.
It changes the X86 break-anti-dependencies test to use –mcpu=atom, in order
to avoid running into the added assertion.
Finally, this patch restores the use of anti-dependency checking
(which was turned off temporarily for the 3.1 release) for
Intel Atom in the Post RA scheduler.
Patch by Andy Zhang!
Thanks to Jakob and Anton for their reviews.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155395 91177308-0d34-0410-b5e6-96231b3b80d8
test suite failures. The failures occur at each stage, and only get
worse, so I'm reverting all of them.
Please resubmit these patches, one at a time, after verifying that the
regression test suite passes. Never submit a patch without running the
regression test suite.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155372 91177308-0d34-0410-b5e6-96231b3b80d8
The X86 target is editing the selection DAG while isel is selecting
nodes following a topological ordering. When the DAG hacking triggers
CSE, nodes can be deleted and bad things happen.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155257 91177308-0d34-0410-b5e6-96231b3b80d8
when the set bits aren't the same for both args of the xor.
This transformation is in the function TargetLowering::SimplifyDemandedBits
in the file lib/CodeGen/SelectionDAG/TargetLowering.cpp.
I have tested this test using a previous version of llc which the defect and
the a version of llc which does not. I got the expected fail and pass,
respectively.
This test goes with rdar://11195364 and the check in with the fix: svn r154955
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@155156 91177308-0d34-0410-b5e6-96231b3b80d8
also fix SimplifyLibCalls to use TLI rather than compile-time conditionals to enable optimizations on floor, ceil, round, rint, and nearbyint
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154960 91177308-0d34-0410-b5e6-96231b3b80d8
both fallthrough and a conditional branch target the same successor.
Gracefully delete the conditional branch and introduce any unconditional
branch needed to reach the actual successor. This fixes memory
corruption in 2009-06-15-RegScavengerAssert.ll and possibly other tests.
Also, while I'm here fix a latent bug I spotted by inspection. I never
applied the same fundamental fix to this fallthrough successor finding
logic that I did to the logic used when there are no conditional
branches. As a consequence it would have selected landing pads had they
be aligned in just the right way here. I don't have a test case as
I spotted this by inspection, and the previous time I found this
required have of TableGen's source code to produce it. =/ I hate backend
bugs. ;]
Thanks to Jim Grosbach for helping me reason through this and reviewing
the fix.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154867 91177308-0d34-0410-b5e6-96231b3b80d8
This is mostly to test the waters. I'd like to get results from FNT
build bots and other bots running on non-x86 platforms.
This feature has been pretty heavily tested over the last few months by
me, and it fixes several of the execution time regressions caused by the
inlining work by preventing inlining decisions from radically impacting
block layout.
I've seen very large improvements in yacr2 and ackermann benchmarks,
along with the expected noise across all of the benchmark suite whenever
code layout changes. I've analyzed all of the regressions and fixed
them, or found them to be impossible to fix. See my email to llvmdev for
more details.
I'd like for this to be in 3.1 as it complements the inliner changes,
but if any failures are showing up or anyone has concerns, it is just
a flag flip and so can be easily turned off.
I'm switching it on tonight to try and get at least one run through
various folks' performance suites in case SPEC or something else has
serious issues with it. I'll watch bots and revert if anything shows up.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154816 91177308-0d34-0410-b5e6-96231b3b80d8
once we start changing the block layout, so just nuke it. If anyone has
ideas about how to craft a code layout agnostic form of the test please
let me know.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154815 91177308-0d34-0410-b5e6-96231b3b80d8
rotation. When there is a loop backedge which is an unconditional
branch, we will end up with a branch somewhere no matter what. Try
placing this backedge in a fallthrough position above the loop header as
that will definitely remove at least one branch from the loop iteration,
where whole loop rotation may not.
I haven't seen any benchmarks where this is important but loop-blocks.ll
tests for it, and so this will be covered when I flip the default.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154812 91177308-0d34-0410-b5e6-96231b3b80d8
laid out in a form with a fallthrough into the header and a fallthrough
out of the bottom. In that case, leave the loop alone because any
rotation will introduce unnecessary branches. If either side looks like
it will require an explicit branch, then the rotation won't add any, do
it to ensure the branch occurs outside of the loop (if possible) and
maximize the benefit of the fallthrough in the bottom.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154806 91177308-0d34-0410-b5e6-96231b3b80d8
This is a complex change that resulted from a great deal of
experimentation with several different benchmarks. The one which proved
the most useful is included as a test case, but I don't know that it
captures all of the relevant changes, as I didn't have specific
regression tests for each, they were more the result of reasoning about
what the old algorithm would possibly do wrong. I'm also failing at the
moment to craft more targeted regression tests for these changes, if
anyone has ideas, it would be welcome.
The first big thing broken with the old algorithm is the idea that we
can take a basic block which has a loop-exiting successor and a looping
successor and use the looping successor as the layout top in order to
get that particular block to be the bottom of the loop after layout.
This happens to work in many cases, but not in all.
The second big thing broken was that we didn't try to select the exit
which fell into the nearest enclosing loop (to which we exit at all). As
a consequence, even if the rotation worked perfectly, it would result in
one of two bad layouts. Either the bottom of the loop would get
fallthrough, skipping across a nearer enclosing loop and thereby making
it discontiguous, or it would be forced to take an explicit jump over
the nearest enclosing loop to earch its successor. The point of the
rotation is to get fallthrough, so we need it to fallthrough to the
nearest loop it can.
The fix to the first issue is to actually layout the loop from the loop
header, and then rotate the loop such that the correct exiting edge can
be a fallthrough edge. This is actually much easier than I anticipated
because we can handle all the hard parts of finding a viable rotation
before we do the layout. We just store that, and then rotate after
layout is finished. No inner loops get split across the post-rotation
backedge because we check for them when selecting the rotation.
That fix exposed a latent problem with our exitting block selection --
we should allow the backedge to point into the middle of some inner-loop
chain as there is no real penalty to it, the whole point is that it
*won't* be a fallthrough edge. This may have blocked the rotation at all
in some cases, I have no idea and no test case as I've never seen it in
practice, it was just noticed by inspection.
Finally, all of these fixes, and studying the loops they produce,
highlighted another problem: in rotating loops like this, we sometimes
fail to align the destination of these backwards jumping edges. Fix this
by actually walking the backwards edges rather than relying on loopinfo.
This fixes regressions on heapsort if block placement is enabled as well
as lots of other cases where the previous logic would introduce an
abundance of unnecessary branches into the execution.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154783 91177308-0d34-0410-b5e6-96231b3b80d8
There is an assert at line 558 in ScheduleDAGInstrs::buildSchedGraph(AliasAnalysis *AA).
This assert needs to addressed for post RA scheduler. Until that assert is addressed,
any passes that uses post ra scheduler will fail. So, I am temporarily disabling the
hexagon tests until that fix is in.
The assert is as follows:
assert(!MI->isTerminator() && !MI->isLabel() &&
"Cannot schedule terminators or labels!");
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154617 91177308-0d34-0410-b5e6-96231b3b80d8
- FCOPYSIGN nodes that have operands of different types were not handled.
- Different code was generated depending on the endianness of the target.
Additionally, code is added that emits INS and EXT instructions, if they are
supported by target (they are R2 instructions).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154540 91177308-0d34-0410-b5e6-96231b3b80d8
Original message:
Modify the code that lowers shuffles to blends from using blendvXX to vblendXX.
blendV uses a register for the selection while Vblend uses an immediate.
On sandybridge they still have the same latency and execute on the same execution ports.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154483 91177308-0d34-0410-b5e6-96231b3b80d8
don't elide the branch instruction if it's the only one in the block,
otherwise it's ok.
PR9796 and rdar://11215207
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154417 91177308-0d34-0410-b5e6-96231b3b80d8
blendv uses a register for the selection while vblend uses an immediate.
On sandybridge they still have the same latency and execute on the same execution ports.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154396 91177308-0d34-0410-b5e6-96231b3b80d8
legalizer always use the DAG entry node. This is wrong when the libcall is
emitted as a tail call since it effectively folds the return node. If
the return node's input chain is not the entry (i.e. call, load, or store)
use that as the tail call input chain.
PR12419
rdar://9770785
rdar://11195178
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154370 91177308-0d34-0410-b5e6-96231b3b80d8
in-register, such that we can use a single vector store rather then a
series of scalar stores.
For func_4_8 the generated code
vldr d16, LCPI0_0
vmov d17, r0, r1
vadd.i16 d16, d17, d16
vmov.u16 r0, d16[3]
strb r0, [r2, #3]
vmov.u16 r0, d16[2]
strb r0, [r2, #2]
vmov.u16 r0, d16[1]
strb r0, [r2, #1]
vmov.u16 r0, d16[0]
strb r0, [r2]
bx lr
becomes
vldr d16, LCPI0_0
vmov d17, r0, r1
vadd.i16 d16, d17, d16
vuzp.8 d16, d17
vst1.32 {d16[0]}, [r2, :32]
bx lr
I'm not fond of how this combine pessimizes 2012-03-13-DAGCombineBug.ll,
but I couldn't think of a way to judiciously apply this combine.
This
ldrh r0, [r0, #4]
strh r0, [r1]
becomes
vldr d16, [r0]
vmov.u16 r0, d16[2]
vmov.32 d16[0], r0
vuzp.16 d16, d17
vst1.32 {d16[0]}, [r1, :32]
PR11158
rdar://10703339
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154340 91177308-0d34-0410-b5e6-96231b3b80d8
x86 addressing modes. This allows PIE-based TLS offsets to fit directly
into an addressing mode immediate offset, which is the last remaining
code quality issue from PR12380. With this patch, that PR is completely
fixed.
To understand why this patch is correct to match these offsets into
addressing mode immediates, break it down by cases:
1) 32-bit is trivially correct, and unmodified here.
2) 64-bit non-small mode is unchanged and never matches.
3) 64-bit small PIC code which is RIP-relative is handled specially in
the match to try to fit RIP into the base register. If it fails, it
now early exits. This behavior is unchanged by the patch.
4) 64-bit small non-PIC code which is not RIP-relative continues to work
as it did before. The reason these immediates are safe is because the
ABI ensures they fit in small mode. This behavior is unchanged.
5) 64-bit small PIC code which is *not* using RIP-relative addressing.
This is the only case changed by the patch, and the primary place you
see it is in TLS, either the win64 section offset TLS or Linux
local-exec TLS model in a PIC compilation. Here the ABI again ensures
that the immediates fit because we are in small mode, and any other
operations required due to the PIC relocation model have been handled
externally to the Wrapper node (extra loads etc are made around the
wrapper node in ISelLowering).
I've tested this as much as I can comparing it with GCC's output, and
everything appears safe. I discussed this with Anton and it made sense
to him at least at face value. That said, if there are issues with PIC
code after this patch, yell and we can revert it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154304 91177308-0d34-0410-b5e6-96231b3b80d8
comprehensive testing of TLS codegen for x86. Convert all of the ones
that were still using grep to use FileCheck. Remove some redundancies
between them.
Perhaps most interestingly expand the test cases so that they actually
fully list the instruction snippet being tested. TLS operations are
*very* narrowly defined, and so these seem reasonably stable. More
importantly, the existing test cases already were crazy fine grained,
expecting specific registers to be allocated. This just clarifies that
no *other* instructions are expected, and fills in some crucial gaps
that weren't being tested at all.
This will make any subsequent changes to TLS much more clear during
review.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154303 91177308-0d34-0410-b5e6-96231b3b80d8
when -ffast-math, i.e. don't just always do it if the reciprocal can
be formed exactly. There is already an IR level transform that does
that, and it does it more carefully.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154296 91177308-0d34-0410-b5e6-96231b3b80d8
optimizations which are valid for position independent code being linked
into a single executable, but not for such code being linked into
a shared library.
I discussed the design of this with Eric Christopher, and the decision
was to support an optional bit rather than a completely separate
relocation model. Fundamentally, this is still PIC relocation, its just
that certain optimizations are only valid under a PIC relocation model
when the resulting code won't be in a shared library. The simplest path
to here is to expose a single bit option in the TargetOptions. If folks
have different/better designs, I'm all ears. =]
I've included the first optimization based upon this: changing TLS
models to the *Exec models when PIE is enabled. This is the LLVM
component of PR12380 and is all of the hard work.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154294 91177308-0d34-0410-b5e6-96231b3b80d8
Previously we used three instructions to broadcast an immediate value into a
vector register.
On Sandybridge we continue to load the broadcasted value from the constant pool.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154284 91177308-0d34-0410-b5e6-96231b3b80d8
shuffle node because it could introduce new shuffle nodes that were not
supported efficiently by the target.
2. Add a more restrictive shuffle-of-shuffle optimization for cases where the
second shuffle reverses the transformation of the first shuffle.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154266 91177308-0d34-0410-b5e6-96231b3b80d8
reciprocal if converting to the reciprocal is exact. Do it even if inexact
if -ffast-math. This substantially speeds up ac.f90 from the polyhedron
benchmarks.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154265 91177308-0d34-0410-b5e6-96231b3b80d8
by default.
This is a behaviour configurable in the MCAsmInfo. I've decided to turn
it on by default in (possibly optimistic) hopes that most assemblers are
reasonably sane. If this proves a problem, switching to default seems
reasonable.
I'm not sure if this is the opportune place to test, but it seemed good
to make sure it was tested somewhere.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154235 91177308-0d34-0410-b5e6-96231b3b80d8
ARM and Thumb2 mode can use cmn instructions to compare against negative
immediates. Thumb1 mode can't.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154183 91177308-0d34-0410-b5e6-96231b3b80d8
LSR always tries to make the ICmp in the loop latch use the incremented
induction variable. This allows the induction variable to be kept in a
single register.
When the induction variable limit is equal to the stride,
SimplifySetCC() would break LSR's hard work by transforming:
(icmp (add iv, stride), stride) --> (cmp iv, 0)
This forced us to use lea for the IC update, preventing the simpler
incl+cmp.
<rdar://problem/7643606>
<rdar://problem/11184260>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154119 91177308-0d34-0410-b5e6-96231b3b80d8
LSR can fold three addressing modes into its ICmpZero node:
ICmpZero BaseReg + Offset => ICmp BaseReg, -Offset
ICmpZero -1*ScaleReg + Offset => ICmp ScaleReg, Offset
ICmpZero BaseReg + -1*ScaleReg => ICmp BaseReg, ScaleReg
The first two cases are only used if TLI->isLegalICmpImmediate() likes
the offset.
Make sure the right Offset sign is passed to this method in the second
case. The ARM version is not symmetric.
<rdar://problem/11184260>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154079 91177308-0d34-0410-b5e6-96231b3b80d8
A MOVCCr instruction can be commuted by inverting the condition. This
can help reduce register pressure and remove unnecessary copies in some
cases.
<rdar://problem/11182914>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154033 91177308-0d34-0410-b5e6-96231b3b80d8
This is just the fallback tie-breaker ordering, the main allocation
order is still descending size.
Patch by Shamil Kurmangaleev!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153904 91177308-0d34-0410-b5e6-96231b3b80d8
Do not try to optimize swizzles of shuffles if the source shuffle has more than
a single user, except when the source shuffle is also a swizzle.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153864 91177308-0d34-0410-b5e6-96231b3b80d8
This adds a full itinerary for IBM's PPC64 A2 embedded core. These
cores form the basis for the CPUs in the new IBM BG/Q supercomputer.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153842 91177308-0d34-0410-b5e6-96231b3b80d8
This is the CodeGen equivalent of r153747. I tested that there is not noticeable
performance difference with any combination of -O0/-O2 /-g when compiling
gcc as a single compilation unit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153817 91177308-0d34-0410-b5e6-96231b3b80d8
This is a code change to add support for changing instruction sequences of the form:
load
inc/dec of 8/16/32/64 bits
store
into the appropriate X86 inc/dec through memory instruction:
inc[qlwb] / dec[qlwb]
The checks that were in X86DAGToDAGISel::Select(SDNode *Node)>>ISD::STORE have been extracted to isLoadIncOrDecStore and reworked to use the better
named wrappers for getOperand(unsigned) (e.g. getOffset()) and replaced Chain.getNode() with LoadNode. The comments have also been expanded.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153635 91177308-0d34-0410-b5e6-96231b3b80d8
This is a code change to add support for changing instruction sequences of the form:
load
inc/dec of 8/16/32/64 bits
store
into the appropriate X86 inc/dec through memory instruction:
inc[qlwb] / dec[qlwb]
The checks that were in X86DAGToDAGISel::Select(SDNode *Node)>>ISD::STORE have been extracted to isLoadIncOrDecStore and reworked to use the better
named wrappers for getOperand(unsigned) (e.g. getOffset()) and replaced Chain.getNode() with LoadNode. The comments have also been expanded.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153617 91177308-0d34-0410-b5e6-96231b3b80d8
When an strd instruction doesn't get the registers it wants, it can be
expanded into two str instructions. Make sure the first str doesn't kill
the base register in the case where the base and data registers are
identical:
t2STRi12 %R0<kill>, %R0, 4, pred:14, pred:%noreg
t2STRi12 %R2<kill>, %R0, 8, pred:14, pred:%noreg
<rdar://problem/11101911>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153611 91177308-0d34-0410-b5e6-96231b3b80d8
The arm_neon intrinsics can create virtual registers from the DPair
register class which allows both even-odd and odd-even D-register pairs.
This fixes PR12389.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153603 91177308-0d34-0410-b5e6-96231b3b80d8
produces a 32-bit immediate which is consumed by the use. It tries to
fold the immediate by breaking it into two parts and fold them into the
immmediate fields of two uses. e.g
movw r2, #40885
movt r3, #46540
add r0, r0, r3
=>
add.w r0, r0, #3019898880
add.w r0, r0, #30146560
;
However, this transformation is incorrect if the user produces a flag. e.g.
movw r2, #40885
movt r3, #46540
adds r0, r0, r3
=>
add.w r0, r0, #3019898880
adds.w r0, r0, #30146560
Note the adds.w may not set the carry flag even if the original sequence
would.
rdar://11116189
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153484 91177308-0d34-0410-b5e6-96231b3b80d8
* Removed test/lib/llvm.exp - it is no longer needed
* Deleted the dg.exp reading code from test/lit.cfg. There are no dg.exp files
left in the test suite so this code is no longer required. test/lit.cfg is
now much shorter and clearer
* Removed a lot of duplicate code in lit.local.cfg files that need access to
the root configuration, by adding a "root" attribute to the TestingConfig
object. This attribute is dynamically computed to provide the same
information as was previously provided by the custom getRoot functions.
* Documented the config.root attribute in docs/CommandGuide/lit.pod
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153408 91177308-0d34-0410-b5e6-96231b3b80d8
The PPC64 SVR4 ABI requires integer stack arguments, and thus the var. args., that
are smaller than 64 bits be zero extended to 64 bits.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153373 91177308-0d34-0410-b5e6-96231b3b80d8
execution-time regression for nsieve-bits on the ARMv7 -O0 -g nightly tester.
This may also improve compile-time on architectures that would otherwise
generate a libcall for urem (e.g., ARM) or fall back to the DAG selector.
rdar://10810716
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153230 91177308-0d34-0410-b5e6-96231b3b80d8
This results in things such as
vmovups 16(%rdi), %xmm0
vinsertf128 $1, %xmm0, %ymm0, %ymm0
to be combined to
vinsertf128 $1, 16(%rdi), %ymm0, %ymm0
rdar://11076953
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153092 91177308-0d34-0410-b5e6-96231b3b80d8
i128). In that case, we may not be able to print out the MCExpr as an
expression. For instance, we could have an MCExpr like this:
0xBEEF0000BEEF0000 | (0xBEEF0000BEEF0000 << 64)
The MCExpr printer handles sizes up to 64-bits, but this expression would
require 128-bits. In this situation, try to evaluate the constant expression and
emit that as the value into 64-bit chunks.
<rdar://problem/11070338>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153081 91177308-0d34-0410-b5e6-96231b3b80d8
X86InstrCompiler.td.
It also adds –mcpu-generic to the legalize-shift-64.ll test so the test
will pass if run on an Intel Atom CPU, which would otherwise
produce an instruction schedule which differs from that which the test expects.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153033 91177308-0d34-0410-b5e6-96231b3b80d8
This results in things such as
vmovaps -96(%rbx), %xmm1
vinsertf128 $1, %xmm1, %ymm0, %ymm0
to be combined to
vinsertf128 $1, -96(%rbx), %ymm0, %ymm0
rdar://10643481
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152762 91177308-0d34-0410-b5e6-96231b3b80d8
(i16 load $addr+c*sizeof(i16)) and replace uses of (i32 vextract) with the
i16 load. It should issue an extload instead: (i32 extload $addr+c*sizeof(i16)).
rdar://11035895
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152675 91177308-0d34-0410-b5e6-96231b3b80d8
Original commit message from r147481:
DAGCombine for transforming 128->256 casts into a vmovaps, rather
then a vxorps + vinsertf128 pair if the original vector came from a load.
Fix:
Unaligned loads need to generate a vmovups.
rdar://10974078
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152366 91177308-0d34-0410-b5e6-96231b3b80d8
The test fell back to the C backend, making it useless and it started to fail
on configurations that don't build the C backend.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152342 91177308-0d34-0410-b5e6-96231b3b80d8
When an instruction only writes sub-registers, it is still necessary to
add an <imp-def> operand for the super-register. When reloading into a
virtual register, rewriting will add the operand, but when loading
directly into a virtual register, the <imp-def> operand is still
necessary.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152095 91177308-0d34-0410-b5e6-96231b3b80d8
The fpscr register contains both flags (set by FP operations/comparisons) and
control bits. The control bits (FPSCR) should be reserved, since they're always
available and needn't be defined before use. The flag bits (FPSCR_NZCV) should
like to be unreserved so they can be hoisted by MachineCSE. This fixes PR12165.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152076 91177308-0d34-0410-b5e6-96231b3b80d8
This was testing the handling of sub-register coalescing followed by
remat. The original problem was caused by the extra <imp-def> operands
added by sub-register coalescing. Those <imp-def> operands are not
added any longer, and the test case passes even when the original patch
is reverted.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152040 91177308-0d34-0410-b5e6-96231b3b80d8
In this update:
- I assumed neon2 does not imply vfpv4, but neon and vfpv4 imply neon2.
- I kept setting .fpu=neon-vfpv4 code attribute because that is what the
assembler understands.
Patch by Ana Pazos <apazos@codeaurora.org>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152036 91177308-0d34-0410-b5e6-96231b3b80d8
MachineOperands that define part of a virtual register must have an
<undef> flag if they are not intended as read-modify-write operands.
The old trick of adding an <imp-def> operand doesn't work any longer.
Fixes PR12177.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152008 91177308-0d34-0410-b5e6-96231b3b80d8
Some BBs can become dead after codegen preparation. If we delete them here, it
could help enable tail-call optimizations later on.
<rdar://problem/10256573>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152002 91177308-0d34-0410-b5e6-96231b3b80d8
In this instance we are generating the tail-call during legalizeDAG. The 2nd
floor call can't be a tail call because it clobbers %xmm1, which is defined by
the first floor call. The first floor call can't be a tail-call because it's
not in the tail position. The only reasonable way I could think to fix this
in a target-independent manner was to check for glue logic on the copy reg.
rdar://10930395
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151877 91177308-0d34-0410-b5e6-96231b3b80d8
floating point equality comparisons into integer ones with -ffast-math. The
issue is the optimization causes +0.0 != -0.0.
Now the optimization is only done when one side is known to be 0.0. The other
side's sign bit is masked off for the comparison.
rdar://10964603
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151861 91177308-0d34-0410-b5e6-96231b3b80d8
and stores was added.
- SelectAddr should return false if Parent is an unaligned f32 load or store.
- Only aligned load and store nodes should be matched to select reg+imm
floating point instructions.
- MIPS does not have support for f64 unaligned load or store instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151843 91177308-0d34-0410-b5e6-96231b3b80d8
so that the test will not fail when run on an Intel Atom
processor, due to the Atom scheduler producing an instruction sequence that is
different from that which is normally expected.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151832 91177308-0d34-0410-b5e6-96231b3b80d8
To avoid problems with zero shifts when getting the bits that move between words
we use a trick: first shift the by amount-1, then do another shift by one. When
amount is 0 (and size 32) we first shift by 31, then by one, instead of by 32.
Also fix a latent bug that emitted the low and high words in the wrong order
when shifting right.
Fixes PR12113.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151637 91177308-0d34-0410-b5e6-96231b3b80d8
When the GEP index is a vector of pointers, the code that calculated the size
of the element started from the vector type, and not the contained pointer type.
As a result, instead of looking at the data element pointed by the vector, this
code used the size of the vector. This works for 32bit members (on 32bit
systems), but not for other types. Added code to peel the vector type and
added a test.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151626 91177308-0d34-0410-b5e6-96231b3b80d8
the processor keeps a return addresses stack (RAS) which stores the address
and the instruction execution state of the instruction after a function-call
type branch instruction.
Calling a "noreturn" function with normal call instructions (e.g. bl) can
corrupt RAS and causes 100% return misprediction so LLVM should use a
unconditional branch instead. i.e.
mov lr, pc
b _foo
The "mov lr, pc" is issued in order to get proper backtrace.
rdar://8979299
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151623 91177308-0d34-0410-b5e6-96231b3b80d8
When an outgoing call takes more than 2k of arguments on the stack, we
don't allocate that call frame in the prolog, but adjust the stack
pointer immediately before the call instead.
This causes problems with the emergency spill slot because PEI can't
track stack pointer adjustments on the second pass, and if the outgoing
arguments are too big, SP can't be used to reach the emergency spill
slot at all.
Work around these problems by ensuring there is a base or frame pointer
that can be used to access the emergency spill slot.
<rdar://problem/10917166>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151604 91177308-0d34-0410-b5e6-96231b3b80d8
Reverting this because it breaks static linking on ppc64. Specifically, it may be linkonce_odr functions that are the problem.
With this patch, if you link statically, calls to some functions end up calling their descriptor addresses instead
of calling to their entry points. This causes the execution to fail with SIGILL (b/c the descriptor address just
has some pointers, not code).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151433 91177308-0d34-0410-b5e6-96231b3b80d8
[Joe Groff] Hi everyone. My previous patch applied as r151382 had a few problems:
Clang raised a warning, and X86 LowerOperation would assert out for
fptoui f64 to i32 because it improperly lowered to an illegal
BUILD_PAIR. Here's a patch that addresses these issues. Let me know if
any other changes are necessary. Thanks.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151432 91177308-0d34-0410-b5e6-96231b3b80d8
reserving a physical register ($gp or $28) for that purpose.
This will completely eliminate loads that restore the value of $gp after every
function call, if the register allocator assigns a callee-saved register, or
eliminate unnecessary loads if it assigns a temporary register.
example:
.cpload $25 // set $gp.
...
.cprestore 16 // store $gp to stack slot 16($sp).
...
jalr $25 // function call. clobbers $gp.
lw $gp, 16($sp) // not emitted if callee-saved reg is chosen.
...
lw $2, 4($gp)
...
jalr $25 // function call.
lw $gp, 16($sp) // not emitted if $gp is not live after this instruction.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151402 91177308-0d34-0410-b5e6-96231b3b80d8
The tied source operand of tMUL is the second source operand, not the
first like every other two-address thumb instruction. Special case it
in the size reduction pass to make sure we create the tMUL instruction
properly.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151315 91177308-0d34-0410-b5e6-96231b3b80d8
bits of the value carying the boolean condition, as their contents
are undefined. This fixes rdar://10887484.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151310 91177308-0d34-0410-b5e6-96231b3b80d8
value is zero. Instead of a cmov + op, issue an conditional op instead. e.g.
cmp r9, r4
mov r4, #0
moveq r4, #1
orr lr, lr, r4
should be:
cmp r9, r4
orreq lr, lr, #1
That is, optimize (or x, (cmov 0, y, cond)) to (or.cond x, y). Similarly extend
this to xor as well as (and x, (cmov -1, y, cond)) => (and.cond x, y).
It's possible to extend this to ADD and SUB but I don't think they are common.
rdar://8659097
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151224 91177308-0d34-0410-b5e6-96231b3b80d8
The standard function epilog includes a .size directive, but ppc64 uses
an alternate local symbol to tag the actual start of each function.
Until recently, binutils accepted the .size directive as:
.size test1, .Ltmp0-test1
however, using this directive with recent binutils will result in the error:
.size expression for XXX does not evaluate to a constant
so we must use the label which actually tags the start of the function.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151200 91177308-0d34-0410-b5e6-96231b3b80d8
This test case was way too strict, matching the entire assembly output.
Every non-trivial change to the ppc backend or -O0 pipeline required
the test to be updated.
It should be replaced with a test of the specific vaarg feature.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151105 91177308-0d34-0410-b5e6-96231b3b80d8
ecx = mov eax
al = mov ch
The second copy is not a nop because the sub-indices of ecx,ch is not the
same of that of eax/al.
Re-enabled machine-cp.
PR11940
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151002 91177308-0d34-0410-b5e6-96231b3b80d8
