This commit makes the following changes:
- Stop issuing a warning when the triples' string representations do not match
exactly if the Triple objects generated from the strings compare equal.
- On Apple platforms, choose the triple that has the larger minimum version
number.
rdar://problem/16743513
Differential Revision: http://reviews.llvm.org/D7591
llvm-svn: 228999
Using this in combination with -ffunction-sections allows LLVM to output a .o
file with mulitple sections named .text. This saves space by avoiding long
unique names of the form .text.<C++ mangled name>.
llvm-svn: 228980
Constant pool entries are uniqued by their contents regardless of their
type. This means that a pshufb can have a shuffle mask which isn't a
simple array of bytes.
The code path which attempts to decode the mask didn't check for
failure, causing PR22559.
llvm-svn: 228979
I'd modify my migration tool to account for this, but this is the only
instance of a typedef'd pointer type to a gep I found in the whole test
suite, so it didn't seem worthwhile.
llvm-svn: 228970
The PowerPC backend has long promoted some floating-point vector operations
(such as select) to integer vector operations. Unfortunately, this behavior was
broken by r216555. When using FP_EXTEND/FP_ROUND for promotions, we must check
that both the old and new types are floating-point types. Otherwise, we must
use BITCAST as we did prior to r216555 for everything.
llvm-svn: 228969
Summary:
Implement the bulk of returning values in Mips fast-isel
Test Plan:
reatabi.ll
Passes test-suite at -O0,-O2 and with mips32r2 and mips32r1.
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: llvm-commits, aemerson, rfuhler
Differential Revision: http://reviews.llvm.org/D5920
llvm-svn: 228958
Summary:
Instances of the AssumptionCache are per function, so we can't re-use
the same AssumptionCache instance when recursing in the CallAnalyzer to
analyze a different function. Instead we have to pass the
AssumptionCacheTracker to the CallAnalyzer so it can get the right
AssumptionCache on demand.
Reviewers: hfinkel
Subscribers: llvm-commits, hans
Differential Revision: http://reviews.llvm.org/D7533
llvm-svn: 228957
We can't solve the full subgraph isomorphism problem. But we can
allow obvious cases, where for example two instructions of different
types are out of order. Due to them having different types/opcodes,
there is no ambiguity.
llvm-svn: 228931
Now that SimplifyCFG uses TTI for the cost heuristic, we can teach BasicTTIImpl
how to query TLI in order to get a more accurate cost for truncates and
zero-extends.
Before this patch, the basic cost heuristic in TargetTransformInfoImplCRTPBase
would have conservatively returned a 'default' TCC_Basic for all zero-extends,
and TCC_Free for truncates on native types.
This patch improves the heuristic so that we query TLI (if available) to get
more accurate answers. If TLI is available, then methods 'isZExtFree' and
'isTruncateFree' can be used to check if a zext/trunc is free for the target.
Added more test cases to SimplifyCFG/X86/speculate-cttz-ctlz.ll.
With this change, SimplifyCFG is now able to speculate a 'cheap' cttz/ctlz
immediately followed by a free zext/trunc.
Differential Revision: http://reviews.llvm.org/D7585
llvm-svn: 228923
The changes in r223113 (ARM modified-immediate syntax) have broken
instructions like:
mov r0, #~0xffffff00
The problem is that I've added a spurious range check on the immediate
operand to ensure that it lies between INT32_MIN and UINT32_MAX. While
this range check is correct in theory, it causes problems because the
operand is stored in an int64_t (by MC). So valid 32-bit constants like
\#~0xffffff00 become out of range. The solution is to simply remove this
range check. It is not possible to validate the range of the immediate
operand with the current setup because: 1) The operand is stored in an
int64_t by MC, 2) The immediate can be of the forms #imm, #-imm, #~imm
or even #((~imm)) etc. So we just chop the value to 32 bits and use it.
Also noted that the original range check was note tested by any of the
unit tests. I've added a new test to cover #~imm kind of operands.
Change-Id: I411e90d84312a2eff01b732bb238af536c4a7599
llvm-svn: 228920
I've built some tests in WebRTC with and without this change. With this change number of __tsan_read/write calls is reduced by 20-40%, binary size decreases by 5-10% and execution time drops by ~5%. For example:
$ ls -l old/modules_unittests new/modules_unittests
-rwxr-x--- 1 dvyukov 41708976 Jan 20 18:35 old/modules_unittests
-rwxr-x--- 1 dvyukov 38294008 Jan 20 18:29 new/modules_unittests
$ objdump -d old/modules_unittests | egrep "callq.*__tsan_(read|write|unaligned)" | wc -l
239871
$ objdump -d new/modules_unittests | egrep "callq.*__tsan_(read|write|unaligned)" | wc -l
148365
http://reviews.llvm.org/D7069
llvm-svn: 228917
Using KORTESTW for comparison i1 value with zero was wrong since the instruction tests 16 bits.
KORTESTW may be used with KSHIFTL+KSHIFTR that clean the 15 upper bits.
I removed (X86cmp i1, 0) pattern and zero-extend i1 to i8 and then use TESTB.
There are some cases where i1 is in the mask register and the upper bits are already zeroed.
Then KORTESTW is the better solution, but it is subject for optimization.
Meanwhile, I'm fixing the correctness issue.
llvm-svn: 228916
This gives a rough estimate of whether using pushes instead of movs is profitable, in terms of size.
We go over all calls in the MachineFunction and compute:
a) For each callsite that can not use pushes, the penalty of not having a reserved call frame.
b) For each callsite that can use pushes, the gain of actually replacing the movs with pushes (and the potential penalty of having to readjust the stack).
Differential Revision: http://reviews.llvm.org/D7561
llvm-svn: 228915
We used to do this DAG combine, but it's not always correct:
If the first fp_round isn't a value preserving truncation, it might
introduce a tie in the second fp_round, that wouldn't occur in the
single-step fp_round we want to fold to.
In other words, double rounding isn't the same as rounding.
Differential Revision: http://reviews.llvm.org/D7571
llvm-svn: 228911
We would crash if we couldn't locate a Function that either Location's
Value belonged to. Now we just print out a debug message and return
conservatively.
llvm-svn: 228901
Apparently some code finally started to tickle this after my
canonicalization changes to instcombine.
The bug stems from trying to form a vector type out of scalars that
aren't compatible at all. In this example, from x86_mmx values. The code
in the vectorizer that checks for reasonable types whas checking for
aggregates or vectors, but there are lots of other types that should
just never reach the vectorizer.
Debugging this was made more confusing by the lie in an assert in
VectorType::get() -- it isn't that the types are *primitive*. The types
must be integer, pointer, or floating point types. No other types are
allowed.
I've improved the assert and added a helper to the vectorizer to handle
the element type validity checks. It now re-uses the VectorType static
function and then further excludes weird target-specific types that we
probably shouldn't be touching here (x86_fp80 and ppc_fp128). Neither of
these are really reachable anyways (neither 80-bit nor 128-bit things
will get vectorized) but it seems better to just eagerly exclude such
nonesense.
I've added a test case, but while it definitely covers two of the paths
through this code there may be more paths that would benefit from test
coverage. I'm not familiar enough with the SLP vectorizer to synthesize
test cases for all of these, but was able to update the code itself by
inspection.
llvm-svn: 228899
On PowerPC, which has a full set of logical operations on (its multiple sets
of) condition-register bits, it is not profitable to break of complex
conditions feeding a jump into multiple jumps. We can turn off this feature of
CGP/SDAGBuilder by marking jumps as "expensive".
P7 test-suite speedups (no regressions):
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
-0.626647% +/- 0.323583%
MultiSource/Benchmarks/Olden/power/power
-18.2821% +/- 8.06481%
llvm-svn: 228895
I mistakenly thought the liveness of each "RetVal(F, i)" depended only on F. It
actually depends on the index too, which means we need to be careful about how
the results are combined before return. In particular if a single Use returns
Live, that counts for the entire object, at the granularity we're considering.
llvm-svn: 228885
Summary:
When trying to canonicalize negative constants out of
multiplication expressions, we need to check that the
constant is not INT_MIN which cannot be negated.
Reviewers: mcrosier
Reviewed By: mcrosier
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D7286
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 228872
Summary:
Move calls to get_input_file and release_input_file out of
getModuleForFile(). Otherwise release_input_file may end up
unmapping a view of the file while the view is still being
used by the Module (on 32-bit hosts).
Fix for PR22482.
Test Plan: Add test using --no-map-whole-files.
Reviewers: rafael, nlewycky
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D7539
llvm-svn: 228842
This is a union of these commits:
* R600/SI: Enable more tests for VI which need no changes
* R600/SI: Enable V_BCNT tests for VI
Differences:
- v_bcnt_..._e32 -> _e64
- s_load_dword* inline offset is in bytes instead of dwords
* R600/SI: Enable all tests for VI which use S_LOAD_DWORD
The inline offset is changed from dwords to bytes.
* R600/SI: Enable LDS tests for VI
Differences:
- the s_load_dword inline offset changed from dwords to bytes
- the tests checked very little on CI, so they have been fixed to check all
instructions that "SI" checked
* R600/SI: Enable lshr tests for VI
* R600/SI: Fix divrem64 tests
- "v_lshl_64" was missing "b" before "64"
- added VI-NOT checks
* R600/SI: Enable the SI.tid test for VI
* R600/SI: Enable the frem test for VI
Also, the frem_f64 checking is added for CI-VI.
* R600/SI: Add VI tests for rsq.clamped
llvm-svn: 228830
This patch is a follow-up of r228826 (see code-review: D7506).
Now that SimplifyCFG uses TargetTransformInfo for cost analysis, we
have to fix the cost heuristic for intrinsic calls to cttz/ctlz.
This patch defines method 'getIntrinsicCost' in BasicTTIImpl: now, BasicTTIImpl
queries TLI to check if a call to cttz/ctlz is cheap for the target.
Added test cases in Transforms/SimplifyCFG/X86 to verify that on x86,
SimplifyCFG only speculates a call to cttz/ctlz if it is cheap.
Differential Revision: http://reviews.llvm.org/D7554
llvm-svn: 228829
analysis.
We're already using TTI in SimplifyCFG, so remove the hard-baked "cheapness"
heuristic and use TTI directly. Generally NFC intended, but we're using a slightly
different heuristic now so there is a slight test churn.
Test changes:
* combine-comparisons-by-cse.ll: Removed unneeded branch check.
* 2014-08-04-muls-it.ll: Test now doesn't branch but emits muleq.
* coalesce-subregs.ll: Superfluous block check.
* 2008-01-02-hoist-fp-add.ll: fadd is safe to speculate. Change to udiv.
* PhiBlockMerge.ll: Superfluous CFG checking code. Main checks still present.
* select-gep.ll: A variable GEP is not expensive, just TCC_Basic, according to the TTI.
llvm-svn: 228826
Summary:
Currently we have Mips32 and Mips64 disassemblers and this causes the target
triple to affect the disassembly despite all the relevant information being in
the ELF header. These implementations do not need to be separate.
This patch merges them together such that the appropriate tables are checked
for the subtarget (e.g. Mips64 is checked when GP64 is enabled).
Reviewers: vmedic
Reviewed By: vmedic
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D7498
llvm-svn: 228825
A DAGRootSet models an induction variable being used in a rerollable
loop. For example:
x[i*3+0] = y1
x[i*3+1] = y2
x[i*3+2] = y3
Base instruction -> i*3
+---+----+
/ | \
ST[y1] +1 +2 <-- Roots
| |
ST[y2] ST[y3]
There may be multiple DAGRootSets, for example:
x[i*2+0] = ... (1)
x[i*2+1] = ... (1)
x[i*2+4] = ... (2)
x[i*2+5] = ... (2)
x[(i+1234)*2+5678] = ... (3)
x[(i+1234)*2+5679] = ... (3)
This concept is similar to the "Scale" member used previously, but allows
multiple independent sets of roots based off the same induction variable.
llvm-svn: 228821
If the landingpad of the invoke is using a personality function that
catches asynch exceptions, then it can catch a trap.
Also add some landingpads to invalid LLVM IR test cases that lack them.
Over-the-shoulder reviewed by David Majnemer.
llvm-svn: 228782
The isSigned argument of makeLibCall function was hard-coded to false
(unsigned). This caused zero extension on MIPS64 soft float.
As the result SingleSource/Benchmarks/Stanford/FloatMM test and
SingleSource/UnitTests/2005-07-17-INT-To-FP test failed.
The solution was to use the proper argument.
Patch by Strahinja Petrovic.
Differential Revision: http://reviews.llvm.org/D7292
llvm-svn: 228765
Simply loading or storing the frame pointer is not sufficient for
Windows targets. Instead, create a synthetic frame object that we will
lower later. References to this synthetic object will be replaced with
the correct reference to the frame address.
llvm-svn: 228748
Unless we meet an insertvalue on a path from some value to a return, that value
will be live if *any* of the return's components are live, so all of those
components must be added to the MaybeLiveUses.
Previously we were deleting arguments if sub-value 0 turned out to be dead.
llvm-svn: 228731
See full discussion in http://reviews.llvm.org/D7491.
We now hide the add-immediate and call instructions together in a
separate pseudo-op, which is tagged to define GPR3 and clobber the
call-killed registers. The PPCTLSDynamicCall pass prior to RA now
expands this op into the two separate addi and call ops, with explicit
definitions of GPR3 on both instructions, and explicit clobbers on the
call instruction. The pass is now marked as requiring and preserving
the LiveIntervals and SlotIndexes analyses, and fixes these up after
the replacement sequences are introduced.
Self-hosting has been verified on LE P8 and BE P7 with various
optimization levels, etc. It has also been verified with the
--no-tls-optimize flag workaround removed.
llvm-svn: 228725
Walk the instructions marked FrameSetup and consider any stores of XMM
registers to the stack as needing a SaveXMM opcode.
This fixes PR22521.
Differential Revision: http://reviews.llvm.org/D7527
llvm-svn: 228724
Added most of the missing vector folding patterns for AVX2 (as well as fixing the vpermpd and verpmq patterns)
Differential Revision: http://reviews.llvm.org/D7492
llvm-svn: 228688
This patch adds the complete AMD Bulldozer XOP instruction set to the memory folding pattern tables for stack folding, etc.
Note: Many of the XOP instructions have multiple table entries as it can fold loads from different sources.
Differential Revision: http://reviews.llvm.org/D7484
llvm-svn: 228685
This patch teaches X86FastISel how to select AVX instructions for scalar
float/double convert operations.
Before this patch, X86FastISel always selected legacy SSE instructions
for FPExt (from float to double) and FPTrunc (from double to float).
For example:
\code
define double @foo(float %f) {
%conv = fpext float %f to double
ret double %conv
}
\end code
Before (with -mattr=+avx -fast-isel) X86FastIsel selected a CVTSS2SDrr which is
legacy SSE:
cvtss2sd %xmm0, %xmm0
With this patch, X86FastIsel selects a VCVTSS2SDrr instead:
vcvtss2sd %xmm0, %xmm0, %xmm0
Added test fast-isel-fptrunc-fpext.ll to check both the register-register and
the register-memory float/double conversion variants.
Differential Revision: http://reviews.llvm.org/D7438
llvm-svn: 228682
This commit isn't using the correct context, and is transfoming calls
that are operands to loads rather than calls that are operands to an
icmp feeding into an assume. I've replied on the original review thread
with a very reduced test case and some thoughts on how to rework this.
llvm-svn: 228677
nodes when folding bitcasts of constants.
We can't fold things and then check after-the-fact whether it was legal.
Once we have formed the DAG node, arbitrary other nodes may have been
collapsed to it. There is no easy way to go back. Instead, we need to
test for the specific folding cases we're interested in and ensure those
are legal first.
This could in theory make this less powerful for bitcasting from an
integer to some vector type, but AFAICT, that can't actually happen in
the SDAG so its fine. Now, we *only* whitelist specific int->fp and
fp->int bitcasts for post-legalization folding. I've added the test case
from the PR.
(Also as a note, this does not appear to be in 3.6, no backport needed)
llvm-svn: 228656
Win64 has specific contraints on what valid prologues and epilogues look
like. This constraint is born from the flexibility and descriptiveness
of Win64's unwind opcodes.
Prologues previously emitted by LLVM could not be represented by the
unwind opcodes, preventing operations powered by stack unwinding to
successfully work.
Differential Revision: http://reviews.llvm.org/D7520
llvm-svn: 228641
for any padding introduced by SROA. In particular, do not emit debug info
for an alloca that represents only the padding introduced by a previous
iteration.
Fixes PR22495.
llvm-svn: 228632
intermediate representation. This
- increases consistency by using the same granularity everywhere
- allows for pieces < 1 byte
- DW_OP_piece didn't actually allow storing an offset.
Part of PR22495.
llvm-svn: 228631
Remove handling for DW_TAG_constant. We started producing it in
r110656, but reverted that in r110876 without dropping the support.
Finish the job.
llvm-svn: 228623
These tests the two optimizations for backedge insertion currently implemented and the split backedge flag which is currently off by default.
llvm-svn: 228617
Without a valid data layout, deferenceable(N) doesn't get parsed or
propagated. Since this is the key item we are testing, add a dependency
on the pass.
Differential Revision: http://reviews.llvm.org/D7508
llvm-svn: 228611
This is just adding really simple tests which should have been part of the original submission. When doing so, I discovered that I'd mistakenly removed required pieces when preparing the patch for upstream submission. I fixed two such bugs in this submission.
llvm-svn: 228610
While a theoretical GC might change dereferenceability on collection,
there is no such known collector and no need to account for the case
with a flag yet.
Differential Revision: http://reviews.llvm.org/D7454
llvm-svn: 228606
When creating a scev for sext({X,+,Y}), scev checks if the expression
is equivalent to {sext X,+,zext Y}. If it can prove that, it also
tags the original {X,+,Y} as <nsw>, which is not correct.
In the test case I run `-scalar-evolution` twice because the bug
manifests only once SCEV has run through and seen the `sext`
expressions (and then does a in-place mutation on {X,+,Y}).
Differential Revision: http://reviews.llvm.org/D7495
llvm-svn: 228586
veqv (vector equivalence)
vnand
vorc
I increased the AddedComplexity for these instructions to 500 to ensure they are generated instead of issuing other VSX instructions.
Phabricator review: http://reviews.llvm.org/D7469
llvm-svn: 228580
For the attached test case different types are used in the ICmpInst
and SelectInst that represent the min/max expressions. However, if the
ICmpInst type is smaller a comparison with the sign/zero extended
operands would have yielded the same result. This situation might
arise after the instruction combination pass was applied.
Differential Revision: http://reviews.llvm.org/D7338
llvm-svn: 228572
wrong basic block.
This would happen when the result of an invoke was used by a phi instruction
in the invoke's normal destination block. An instruction to reload the invoke's
value would get inserted before the critical edge was split and a new basic
block (which is the correct insertion point for the reload) was created. This
commit fixes the bug by splitting the critical edge before all the reload
instructions are inserted.
Also, hoist up the code which computes the insertion point to the only place
that need that computation.
rdar://problem/15978721
llvm-svn: 228566
Some parts of DeadArgElim were only considering the individual fields
of StructTypes separately, but others (where insertvalue &
extractvalue instructions occur) also looked into ArrayTypes.
This one is an actual bug; the mismatch can lead to an argument being
considered used by a return sub-value that isn't being tracked (and
hence is dead by default). It then gets incorrectly eliminated.
llvm-svn: 228559
Previously, a non-extractvalue use of an aggregate return value meant
the entire return was considered live (the algorithm gave up
entirely). This was correct, but conservative. It's better to actually
look at that Use, making the analysis results apply to all sub-values
under consideration.
E.g.
%val = call { i32, i32 } @whatever()
[...]
ret { i32, i32 } %val
The return is using the entire aggregate (sub-values 0 and 1). We can
still simplify @whatever if we can prove that this return is itself
unused.
Also unifies the logic slightly between aggregate and non-aggregate
cases..
llvm-svn: 228558
Make assume (load (call|invoke) != null) set nonNull return attribute
for the call and invoke. Also include tests.
Differential Revision: http://reviews.llvm.org/D7107
llvm-svn: 228556
add recurrences don't overflow.
This change makes the optimization more restrictive. It still assumes
that an overflowing `add nsw` is undefined behavior; and this change
will need revisiting once we have a consistent semantics for poison
values.
Differential Revision: http://reviews.llvm.org/D7331
llvm-svn: 228552
Summary:
The alias.scope metadata represents sets of things an instruction might
alias with. When generically combining the metadata from two
instructions the result must be the union of the original sets, because
the new instruction might alias with anything any of the original
instructions aliased with.
Reviewers: hfinkel
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D7490
llvm-svn: 228525
While various DAG combines try to guarantee that a vector SETCC
operation will have the same output size as input, there's nothing
intrinsic to either creation or LegalizeTypes that actually guarantees
it, so the function needs to be ready to handle a mismatch.
Fortunately this is easy enough, just extend or truncate the naturally
compared result.
I couldn't reproduce the failure in other backends that I know have
SIMD, so it's probably only an issue for these two due to shared
heritage.
Should fix PR21645.
llvm-svn: 228518
different fields.
We can show that two GEPs off of the same (possibly multidimensional)
array of structs, into different fields, can't alias. Quoting:
For two GEPOperators GEP1 and GEP2, if we find that:
- both GEPs begin indexing from the exact same pointer;
- the last indices in both GEPs are constants, indexing into a struct;
- said indices are different, hence,the pointed-to fields are different;
- and both GEPs only index through arrays prior to that;
this lets us determine that the struct that GEP1 indexes into and the
struct that GEP2 indexes into must either precisely overlap or be
completely disjoint. Because they cannot partially overlap, indexing
into different non-overlapping fields of the struct will never alias.
The other BasicAA::aliasGEP rules worked in some cases, but not all
(for example, the i32x3 struct in the testcase).
We can add this simple ad-hoc rule to complement them.
rdar://19717375
Differential Revision: http://reviews.llvm.org/D7453
llvm-svn: 228498
COFF section flags are not idempotent:
'rd' will make a read-write section because 'd' implies write
'dr' will make a read-only section because 'r' disables write
llvm-svn: 228490
If a loop predecessor has an invoke as its terminator, and the return value
from that invoke is used to determine the loop iteration space, then we can't
insert a computation based on that value in the loop predecessor prior to the
terminator (oops). If there's such an invoke, or just no predecessor for that
matter, insert a new loop preheader.
llvm-svn: 228488
Unfortunately, even with the workaround of disabling the linker TLS
optimizations in Clang restored (which has already been done), this still
breaks self-hosting on my P7 machine (-O3 -DNDEBUG -mcpu=native).
Bill is currently working on an alternate implementation to address the TLS
issue in a way that also fully elides the linker bug (which, unfortunately,
this approach did not fully), so I'm reverting this now.
llvm-svn: 228460
Remove unnecessary restriction of 24-bits for line numbers in
`MDLocation`.
The rest of the debug info schema (with the exception of local
variables) uses 32-bits for line numbers. As I introduce the
specialized nodes, it makes sense to canonicalize on one size or the
other.
llvm-svn: 228455
An atomic store always make the target location fully initialized (in the
current implementation). It should not store origin. Initialized memory can't
have meaningful origin, and, due to origin granularity (4 bytes) there is a
chance that this extra store would overwrite meaningfull origin for an adjacent
location.
llvm-svn: 228444
Normalize
select(C0, select(C1, a, b), b) -> select((C0 & C1), a, b)
select(C0, a, select(C1, a, b)) -> select((C0 | C1), a, b)
This normal form may enable further combines on the And/Or and shortens
paths for the values. Many targets prefer the other but can go back
easily in CodeGen.
Differential Revision: http://reviews.llvm.org/D7399
llvm-svn: 228409
Doesn't seem necessary anymore. I think this was mostly compensating for
not enabling WQM for texture sampling instructions.
v2: Add test coverage
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 228373
If whole quad mode isn't enabled for these, the level of detail is
calculated incorrectly for pixels along diagonal triangle edges, causing
artifacts.
v2: Use a TSFlag instead of lots of switch cases
v3: Add test coverage
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=88642
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 228372
Since testing the function indirectly is tricky, introduce a direct
print-memderefs pass, in the same spirit as print-memdeps, which prints
dereferenceability information matched by FileCheck.
Differential Revision: http://reviews.llvm.org/D7075
llvm-svn: 228369
Avoid the creation of select instructions which can result in different
scheduling of the selects.
I also added a bunch of additional store volatiles. Those avoid A
CodeGen problem (bug?) where normalizes and denomarlizing the control
moves all shift instructions into the first block where ISel can't match
them together with the cmps.
llvm-svn: 228362
Fixes PR22462: two of the tests have regressed for a while,
but were using CHECK-NOT to match "May:". The actual output
was changed to "MayAlias:" at some point, which made the tests
useless.
Two others return MayAlias only because of a lack of analysis;
BasicAA returns PartialAlias in those cases, when a datalayout
is present.
llvm-svn: 228346
PowerPC supports pre-increment load/store instructions (except for Altivec/VSX
vector load/stores). Using these on embedded cores can be very important, but
most loops are not naturally set up to use them. We can often change that,
however, by placing loops into a non-canonical form. Generically, this means
transforming loops like this:
for (int i = 0; i < n; ++i)
array[i] = c;
to look like this:
T *p = array[-1];
for (int i = 0; i < n; ++i)
*++p = c;
the key point is that addresses accessed are pulled into dedicated PHIs and
"pre-decremented" in the loop preheader. This allows the use of pre-increment
load/store instructions without loop peeling.
A target-specific late IR-level pass (running post-LSR), PPCLoopPreIncPrep, is
introduced to perform this transformation. I've used this code out-of-tree for
generating code for the PPC A2 for over a year. Somewhat to my surprise,
running the test suite + externals on a P7 with this transformation enabled
showed no performance regressions, and one speedup:
External/SPEC/CINT2006/483.xalancbmk/483.xalancbmk
-2.32514% +/- 1.03736%
So I'm going to enable it on everything for now. I was surprised by this
because, on the POWER cores, these pre-increment load/store instructions are
cracked (and, thus, harder to schedule effectively). But seeing no regressions,
and feeling that it is generally easier to split instructions apart late than
it is to combine them late, this might be the better approach regardless.
In the future, we might want to integrate this functionality into LSR (but
currently LSR does not create new PHI nodes, so (for that and other reasons)
significant work would need to be done).
llvm-svn: 228328
PowerPC supports pre-increment floating-point load/store instructions, both r+r
and r+i, and we had patterns for them, but they were not marked as legal. Mark
them as legal (and add a test case).
llvm-svn: 228327
The combine that forms extloads used to be disabled on vector types,
because "None of the supported targets knows how to perform load and
sign extend on vectors in one instruction."
That's not entirely true, since at least SSE4.1 X86 knows how to do
those sextloads/zextloads (with PMOVS/ZX).
But there are several aspects to getting this right.
First, vector extloads are controlled by a profitability callback.
For instance, on ARM, several instructions have folded extload forms,
so it's not always beneficial to create an extload node (and trying to
match extloads is a whole 'nother can of worms).
The interesting optimization enables folding of s/zextloads to illegal
(splittable) vector types, expanding them into smaller legal extloads.
It's not ideal (it introduces some legalization-like behavior in the
combine) but it's better than the obvious alternative: form illegal
extloads, and later try to split them up. If you do that, you might
generate extloads that can't be split up, but have a valid ext+load
expansion. At vector-op legalization time, it's too late to generate
this kind of code, so you end up forced to scalarize. It's better to
just avoid creating egregiously illegal nodes.
This optimization is enabled unconditionally on X86.
Note that the splitting combine is happy with "custom" extloads. As
is, this bypasses the actual custom lowering, and just unrolls the
extload. But from what I've seen, this is still much better than the
current custom lowering, which does some kind of unrolling at the end
anyway (see for instance load_sext_4i8_to_4i64 on SSE2, and the added
FIXME).
Also note that the existing combine that forms extloads is now also
enabled on legal vectors. This doesn't have a big effect on X86
(because sext+load is usually combined to sext_inreg+aextload).
On ARM it fires on some rare occasions; that's for a separate commit.
Differential Revision: http://reviews.llvm.org/D6904
llvm-svn: 228325
The return value's address must be returned in %rax.
i.e. the callee needs to copy the sret argument (%rdi)
into the return value (%rax).
This probably won't manifest as a bug when the caller is LLVM-compiled
code. But it is an ABI guarantee and tools expect it.
llvm-svn: 228321
We should be setting UnrollingPreferences::MaxCount to MAX_UINT instead
of UnrollingPreferences::Count.
Count is a 'forced unrolling factor', while MaxCount sets an upper
limit to the unrolling factor.
Setting Count to MAX_UINT was causing the loop in the testcase to be
unrolled 15 times, when it only had a maximum of 4 iterations.
llvm-svn: 228303
The llvm.SI.end.cf intrinsic is used to mark the end of if-then blocks,
if-then-else blocks, and loops. It is responsible for updating the
exec mask to re-enable threads that had been masked during the preceding
control flow block. For example:
s_mov_b64 exec, 0x3 ; Initial exec mask
s_mov_b64 s[0:1], exec ; Saved exec mask
v_cmpx_gt_u32 exec, s[2:3], v0, 0 ; llvm.SI.if
do_stuff()
s_or_b64 exec, exec, s[0:1] ; llvm.SI.end.cf
The bug fixed by this patch was one where the llvm.SI.end.cf intrinsic
was being inserted into the header of loops. This would happen when
an if block terminated in a loop header and we would end up with
code like this:
s_mov_b64 exec, 0x3 ; Initial exec mask
s_mov_b64 s[0:1], exec ; Saved exec mask
v_cmpx_gt_u32 exec, s[2:3], v0, 0 ; llvm.SI.if
do_stuff()
LOOP: ; Start of loop header
s_or_b64 exec, exec, s[0:1] ; llvm.SI.end.cf <-BUG: The exec mask has the
same value at the beginning of each loop
iteration.
do_stuff();
s_cbranch_execnz LOOP
The fix is to create a new basic block before the loop and insert the
llvm.SI.end.cf there. This way the exec mask is restored before the
start of the loop instead of at the beginning of each iteration.
llvm-svn: 228302
Patch by Kit Barton.
Add the vector count leading zeros instruction for byte, halfword,
word, and doubleword sizes. This is a fairly straightforward addition
after the changes made for vpopcnt:
1. Add the correct definitions for the various instructions in
PPCInstrAltivec.td
2. Make the CTLZ operation legal on vector types when using P8Altivec
in PPCISelLowering.cpp
Test Plan
Created new test case in test/CodeGen/PowerPC/vec_clz.ll to check the
instructions are being generated when the CTLZ operation is used in
LLVM.
Check the encoding and decoding in test/MC/PowerPC/ppc_encoding_vmx.s
and test/Disassembler/PowerPC/ppc_encoding_vmx.txt respectively.
llvm-svn: 228301
Implement a BITCAST dag combine to transform i32->mmx conversion patterns
into a X86 specific node (MMX_MOVW2D) and guarantee that moves between
i32 and x86mmx are better handled, i.e., don't use store-load to do the
conversion..
llvm-svn: 228293
Avoid regression in previously supported MMX code by adding different
combinations of tests which exercise MMX bitcasts. Small improvements
to these patterns should come next.
llvm-svn: 228292
Summary: When evaluating floating point instructions in the inliner, ask the TTI whether it is an expensive operation. By default, it's not an expensive operation. This keeps the default behavior the same as before. The ARM TTI has been updated to return back TCC_Expensive for targets which don't have hardware floating point.
Reviewers: chandlerc, echristo
Reviewed By: echristo
Subscribers: t.p.northover, aemerson, llvm-commits
Differential Revision: http://reviews.llvm.org/D6936
llvm-svn: 228263
Parts of llvm were not expecting it and we wouldn't print
the entity size of the section.
Given what comdats are used for, having SHF_MERGE sections would be
just a small improvement, so just disable it for now.
Fixes pr22463.
llvm-svn: 228196
v2i32, i32, trunc i32 to i16, and truc i32 to i8 stores are legal for
all address spaces. We had marked them as custom in order to lower
them for the private address space, but this is no longer necessary.
This enables lowering of misaligned stores of these types in the
DAGLegalizer.
llvm-svn: 228189
We were previously doing a post-order traversal and operating on the
list in reverse, however this would occasionaly cause backedges for
loops to be visited before some of the other blocks in the loop.
We know use a reverse post-order traversal, which avoids this issue.
The reverse post-order traversal is not completely ideal, so we need
to manually fixup the list to ensure that inner loop backedges are
visited before outer loop backedges.
llvm-svn: 228186
Track unresolved nodes under distinct `MDNode`s during `MapMetadata()`,
and resolve them at the end. Previously, these cycles wouldn't get
resolved.
llvm-svn: 228180
In case CSE reuses a previoulsy unused register the dead-def flag has to
be cleared on the def operand, as exposed by the arm64-cse.ll test.
This fixes PR22439 and the corresponding rdar://19694987
Differential Revision: http://reviews.llvm.org/D7395
llvm-svn: 228178
This is a bug that was caused due to storing the feature bitset in a 32-bit
variable when it is a 64-bit mask, discarding the top half of the feature set.
llvm-svn: 228151
Currently, Cortex-A72 is modelled as an Cortex-A57 except the fp
load balancing pass isn't enabled for Cortex-A72 as it's not
profitable to have it enabled for this core.
Patch by Ranjeet Singh.
llvm-svn: 228140
This associates movss and movsd with the packed single and packed double
execution domains (resp.). While this is largely cosmetic, as we now
don't have weird ping-pong-ing between single and double precision, it
is also useful because it avoids the domain fixing algorithm from seeing
domain breaks that don't actually exist. It will also be much more
important if we have an execution domain default other than packed
single, as that would cause us to mix movss and movsd with integer
vector code on a regular basis, a very bad mixture.
llvm-svn: 228135
version of the script.
Changes include:
- Using the VEX prefix
- Skipping more detail when we have useful shuffle comments to match
- Matching more shuffle comments that have been added to the printer
(yay!)
- Matching the destination registers of some AVX instructions
- Stripping trailing whitespace that crept in
- Fixing indentation issues
Nothing interesting going on here. I'm just trying really hard to ensure
these changes don't show up in the diffs with actual changes to the
backend.
llvm-svn: 228132
This reverts patches 223862, 224198, 224203, and 224754, which were all
related to the vector load/store combining and were reverted/reaplied
a few times due to the same alignment problems we're seeing now.
Further tests, mainly self-hosting Clang, will be needed to reapply this
patch in the future.
llvm-svn: 228129
zero for v8i16 as well.
These exhibit the same domain badness, but also exhibit other weaknesses
in our blend lowering. More fixes to come.
llvm-svn: 228126
This is the simplest form of bit-math based blending which only fires
when we are blending with zero and is relatively profitable. I've only
enabled this path on very specific lowering strategies. I'm planning to
widen its applicability in subsequent patches, but so far you'll notice
that even though we get fewer shufps instructions, we *still* do the bit
math in the FP execution port. I'm looking into why this is still
happening.
llvm-svn: 228124
The ARM assembler allows register alias redefinitions as long as it
targets the same register. r222319 broke that. In the AArch64 case
it would just produce a new warning, but in the ARM case it would
error out on previously accepted assembler.
llvm-svn: 228109
update_llc_test_checks.py.
The exact format of the checks has changed over time. This includes
different indenting rules, new shuffle comments that have been added,
and more operand hiding behind regular expressions.
No functional change to the tests are expected here, but this will make
subsequent patches have a clean diff as they change shuffle lowering.
llvm-svn: 228097
update_llc_test_checks.py script uses, and refresh the checks in this
test.
No functionality changed here, just bringing this test up to work with
automated updates using the python script.
llvm-svn: 228096
This will make it easy to update as I change some parts of the X86
backend, makes it more clear what instruction differences are
introduced, and I find it makes it a bit easier to read as well.
llvm-svn: 228095
This preserves the handy functionality of force-enabling the MachineVerifier, without the need to embed usage of environment variables in LLVM client applications.
llvm-svn: 228079
Patch to match cases where shuffle masks can be reduced to bit shifts. Similar to byte shift shuffle matching from D5699.
Differential Revision: http://reviews.llvm.org/D6649
llvm-svn: 228047
Patch by Kit Barton.
Add the vector population count instructions for byte, halfword, word,
and doubleword sizes. There are two major changes here:
PPCISelLowering.cpp: Make CTPOP legal for vector types.
PPCRegisterInfo.td: Added v2i64 to the VRRC register
definition. This is needed for the doubleword variations of the
integer ops that were added in P8.
Test Plan
Test the instruction vpcnt* encoding/decoding in ppc64-encoding-vmx.s
Test the generation of the vpopcnt instructions for various vector
data types. When adding the v2i64 type to the Vector Register set, I
also needed to add the appropriate bit conversion patterns between
v2i64 and the existing vector types. Testing for these conversions
were also added in the test case by passing a different vector type as
a parameter into the test functions. There is also a run step that
will ensure the vpopcnt instructions are generated when the vsx
feature is disabled.
llvm-svn: 228046
with 'stress' to indicate that the specific output isn't interesting and
relax them to only check the last instruction (a ret).
I've updated the one test case that really uses this to name the one
'stress_test' which was actually producing output we can directly check.
With this, the script doesn't introduce noise when run over the v16 test
file.
llvm-svn: 228033
This patch adds general shuffle pattern matching for the MOVQ zero-extend instruction (copy lower 64bits, zero upper) for all 128-bit integer vectors, it is added as a fallback test in lowerVectorShuffleAsZeroOrAnyExtend.
llvm-svn: 228022
Summary:
Straight-line strength reduction (SLSR) is implemented in GCC but not yet in
LLVM. It has proven to effectively simplify statements derived from an unrolled
loop, and can potentially benefit many other cases too. For example,
LLVM unrolls
#pragma unroll
foo (int i = 0; i < 3; ++i) {
sum += foo((b + i) * s);
}
into
sum += foo(b * s);
sum += foo((b + 1) * s);
sum += foo((b + 2) * s);
However, no optimizations yet reduce the internal redundancy of the three
expressions:
b * s
(b + 1) * s
(b + 2) * s
With SLSR, LLVM can optimize these three expressions into:
t1 = b * s
t2 = t1 + s
t3 = t2 + s
This commit is only an initial step towards implementing a series of such
optimizations. I will implement more (see TODO in the file commentary) in the
near future. This optimization is enabled for the NVPTX backend for now.
However, I am more than happy to push it to the standard optimization pipeline
after more thorough performance tests.
Test Plan: test/StraightLineStrengthReduce/slsr.ll
Reviewers: eliben, HaoLiu, meheff, hfinkel, jholewinski, atrick
Reviewed By: jholewinski, atrick
Subscribers: karthikthecool, jholewinski, llvm-commits
Differential Revision: http://reviews.llvm.org/D7310
llvm-svn: 228016
This patch detects consecutive vector loads using the existing
EltsFromConsecutiveLoads() logic. This fixes:
http://llvm.org/bugs/show_bug.cgi?id=22329
This patch effectively reverts the tablegen additions of D6492 /
http://reviews.llvm.org/rL224344 ...which in hindsight were a horrible hack.
The test cases that were added with that patch are simply modified to load
from varying offsets of a base pointer. These loads did not match the existing
tablegen patterns.
A happy side effect of doing this optimization earlier is that we can now fold
the load into a math op where possible; this is shown in some of the updated
checks in the test file.
Differential Revision: http://reviews.llvm.org/D7303
llvm-svn: 228006
This can happen when a REV instruction is commuted.
The trick is not to define the _vi versions of instructions, which has these
consequences:
- code generation will always fail if a pseudo cannot be lowered
(very useful to catch bugs where an unsupported instruction somehow makes
it to the printer)
- ability to query if a pseudo can be lowered, which is done in commuteOpcode
to prevent REV from commuting to non-REV on VI
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 227990
This fixes a hang when using an empty geometry shader.
v2: - don't add s_nop when followed by s_waitcnt
- comestic changes
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 227986
r224330 introduced a bug by misinterpreting the "FeatureVectorUAMem" bit.
The commit log says that change did not affect anything, but that's not correct.
That change allowed SSE instructions to have unaligned mem operands folded into
math ops, and that's not allowed in the default specification for any SSE variant.
The bug is exposed when compiling for an AVX-capable CPU that had this feature
flag but without enabling AVX codegen. Another mistake in r224330 was not adding
the feature flag to all AVX CPUs; the AMD chips were excluded.
This is part of the fix for PR22371 ( http://llvm.org/bugs/show_bug.cgi?id=22371 ).
This feature bit is SSE-specific, so I've renamed it to "FeatureSSEUnalignedMem".
Changed the existing test case for the feature bit to reflect the new name and
renamed the test file itself to better reflect the feature.
Added runs to fold-vex.ll to check for the failing codegen.
Note that the feature bit is not set by default on any CPU because it may require a
configuration register setting to enable the enhanced unaligned behavior.
llvm-svn: 227983
This patch is a third attempt to properly handle the local-dynamic and
global-dynamic TLS models.
In my original implementation, calls to __tls_get_addr were hidden
from view until the asm-printer phase, at which point the underlying
branch-and-link instruction was created with proper relocations. This
mostly worked well, but I used some repellent techniques to ensure
that the TLS_GET_ADDR nodes at the SD and MI levels correctly received
input from GPR3 and produced output into GPR3. This proved to work
badly in the presence of multiple TLS variable accesses, with the
copies to and from GPR3 being scheduled incorrectly and generally
creating havoc.
In r221703, I addressed that problem by representing the calls to
__tls_get_addr as true calls during instruction lowering. This had
the advantage of removing all of the bad hacks and relying on the
existing call machinery to properly glue the copies in place. It
looked like this was going to be the right way to go.
However, as a side effect of the recent discovery of problems with
linker optimizations for TLS, we discovered cases of suboptimal code
generation with this strategy. The problem comes when tls_get_addr is
called for the same address, and there is a resulting CSE
opportunity. It turns out that in such cases MachineCSE will common
the addis/addi instructions that set up the input value to
tls_get_addr, but will not common the calls themselves. MachineCSE
does not have any machinery to common idempotent calls. This is
perfectly sensible, since presumably this would be done at the IR
level, and introducing calls in the back end isn't commonplace. In
any case, we end up with two calls to __tls_get_addr when one would
suffice, and that isn't good.
I presumed that the original design would have allowed commoning of
the machine-specific nodes that hid the __tls_get_addr calls, so as
suggested by Ulrich Weigand, I went back to that design and cleaned it
up so that the copies were properly held together by glue
nodes. However, it turned out that this didn't work either...the
presence of copies to physical registers kept the machine-specific
nodes from being commoned also.
All of which leads to the design presented here. This is a return to
the original design, except that no attempt is made to introduce
copies to and from GPR3 during instruction lowering. Virtual registers
are used until prior to register allocation. At that point, a special
pass is run that identifies the machine-specific nodes that hide the
tls_get_addr calls and introduces the copies to and from GPR3 around
them. The register allocator then coalesces these copies away. With
this design, MachineCSE succeeds in commoning tls_get_addr calls where
possible, and we get nice optimal code generation (better than GCC at
the moment, which does not common these calls).
One additional problem must be dealt with: After introducing the
mentions of the physical register GPR3, the aggressive anti-dependence
breaker sees opportunities to improve scheduling by selecting a
different register instead. Flags must be used on the instruction
descriptions to tell the anti-dependence breaker to keep its hands in
its pockets.
One thing missing from the original design was recording a definition
of the link register on the GET_TLS_ADDR nodes. Doing this was found
to be insufficient to force a stack frame to be created, which led to
looping behavior because two different LR values were stored at the
same address. This appears to have been an oversight in
PPCFrameLowering::determineFrameLayout(), which is repaired here.
Because MustSaveLR() returns true for calls to builtin_return_address,
this changed the expected behavior of
test/CodeGen/PowerPC/retaddr2.ll, which now stacks a frame but
formerly did not. I've fixed the test case to reflect this.
There are existing TLS tests to catch regressions; the checks in
test/CodeGen/PowerPC/tls-store2.ll proved to be too restrictive in the
face of instruction scheduling with these changes, so I fixed that
up.
I've added a new test case based on the PrettyStackTrace module that
demonstrated the original problem. This checks that we get correct
code generation and that CSE of the calls to __get_tls_addr has taken
place.
llvm-svn: 227976
This test was checking for lack of a "movaps" (an aligned load)
rather than a "movups" (an unaligned load). It also included
a store which complicated the checking.
Add specific CPU runs to prevent subtarget feature flag overrides
from inhibiting this optimization.
llvm-svn: 227972
Improve EXTRACT_VECTOR_ELT DAG combine to catch conversion patterns
between x86mmx and i32 with more layers of indirection.
Before:
movq2dq %mm0, %xmm0
movd %xmm0, %eax
After:
movd %mm0, %eax
llvm-svn: 227969
LLVM ToT produces poor MMX code compared to 3.5. However, part of the previous
functionality can be achieved by using -x86-experimental-vector-widening-legalization.
Add tests to be sure we don't regress again.
llvm-svn: 227869
ObjectLinkingLayer.
There are a two of overloads for addObject, one of which transfers ownership of
the underlying buffer to OrcMCJITReplacement. This commit makes the ownership
transfering version pass ownership down to the ObjectLinkingLayer in order to
prevent the issue described in r227778.
I think this commit will fix the sanitizer bot failures that necessitated the
removal of the load-object-a.ll regression test in r227785, so I'm reinstating
that test.
llvm-svn: 227845
described by integer constants. This is a bit ugly, but if the source
language allows arbitrary type casting, the debug info must follow suit.
For example:
void foo() {
float a;
*(int *)&a = 0;
}
For the curious: SROA replaces the float alloca with an i32 alloca, which
is then optimized away and described via dbg.value(i32 0, ...).
llvm-svn: 227827
This is true for SI only. CI+ supports unaligned memory accesses,
but this requires driver support, so for now we disallow unaligned
accesses for all GCN targets.
llvm-svn: 227822
This avoids a partial false dependency on the previous content of
the upper lanes of the destination vector register.
Differential Revision: http://reviews.llvm.org/D7307
llvm-svn: 227820
Summary:
Previously it only avoided optimizing signed comparisons to 0.
Sometimes the DAGCombiner will optimize the unsigned comparisons
to 0 before it gets to the peephole pass, but sometimes it doesn't.
Fix for PR22373.
Test Plan: test/CodeGen/ARM/sub-cmp-peephole.ll
Reviewers: jfb, manmanren
Subscribers: aemerson, llvm-commits
Differential Revision: http://reviews.llvm.org/D7274
llvm-svn: 227809
The commit r225977 uncovered this bug. The problem was that the vectorizer tried to
read the second operand of an already deleted instruction.
The bug didn't show up before r225977 because the freed memory still contained a non-null pointer.
With r225977 deletion of instructions is delayed and the read operand pointer is always null.
llvm-svn: 227800
