With && at the top level of an expression, the last thing done when
emitting the expression was an unconditional jump to the cleanup block.
To reduce the amount of stepping, the DebugLoc is omitted from the
unconditional jump. This is done by clearing the IRBuilder's
"CurrentDebugLocation"*. If this is not set to some non-empty value
before the cleanup block is emitted, the cleanups don't get a location
either. If a call without a location is emitted in a function with debug
info, and that call is then inlined - bad things happen. (without a
location for the call site, the inliner would just leave the inlined
DebugLocs as they were - pointing to roots in the original function, not
inlined into the current function)
Follow up commit to LLVM will ensure that breaking the invariants of the
DebugLoc chains by having chains that don't lead to the current function
will fail assertions, so we shouldn't accidentally slip any of these
cases in anymore. Those assertions may reveal further cases that need to
be fixed in clang, though I've tried to test heavily to avoid that.
* See r128471, r128513 for the code that clears the
CurrentDebugLocation. Simply removing this code or moving the code
into IRBuilder to apply to all unconditional branches would regress
desired behavior, unfortunately.
llvm-svn: 211722
This patch teaches method 'LowerVECTOR_SHUFFLE' to give higher precedence to
the check for 'isBlendMask'; the idea is that, when possible, we should firstly
check if a shuffle performs a blend, and in case, try to lower it into a BLENDI
instead of selecting a SHUFP or (worse) a VPERM2X128.
In general:
- AVX VBLENDPS/D always have better latency and throughput than VPERM2F128;
- BLENDPS/D instructions tend to always have better 'reciprocal throughput'
than the equivalent SHUFPS/D;
- Both BLENDPS/D and SHUFPS/D are often decoded into the same number of
m-ops; however, a m-op obtained from a BLENDPS/D can be scheduled to more
than one execution port.
This patch:
- Moves the check for 'isBlendMask' immediately before the check for
'isSHUFPMask' within method 'LowerVECTOR_SHUFFLE';
- Updates existing tests for sse/avx shuffle/blend instructions to verify
that we select (v)blendps/d when possible (instead of (v)shufps/d or
vperm2f128).
llvm-svn: 211720
Types defined in function prototype are diagnosed earlier in C++ compilation.
They are put into declaration context where the prototype is introduced. Later on,
when FunctionDecl object is created, these types are moved into the function context.
This patch fixes PR19018 and PR18963.
Differential Revision: http://reviews.llvm.org/D4145
llvm-svn: 211718
Conditionally include x86intrin.h if we are building for x86 or x86_64.
Conditionalise definition of inline assembly routines which use x86 or x86_64
inline assembly. This is needed as clang can target Windows on ARM where these
definitions may be included into user code.
llvm-svn: 211716
[Clang part]
These patches rename the loop unrolling and loop vectorizer metadata
such that they have a common 'llvm.loop.' prefix. Metadata name
changes:
llvm.vectorizer.* => llvm.loop.vectorizer.*
llvm.loopunroll.* => llvm.loop.unroll.*
This was a suggestion from an earlier review
(http://reviews.llvm.org/D4090) which added the loop unrolling
metadata.
Patch by Mark Heffernan.
llvm-svn: 211712
[LLVM part]
These patches rename the loop unrolling and loop vectorizer metadata
such that they have a common 'llvm.loop.' prefix. Metadata name
changes:
llvm.vectorizer.* => llvm.loop.vectorizer.*
llvm.loopunroll.* => llvm.loop.unroll.*
This was a suggestion from an earlier review
(http://reviews.llvm.org/D4090) which added the loop unrolling
metadata.
Patch by Mark Heffernan.
llvm-svn: 211710
Provides an abstraction for a random number generator (RNG) that produces a stream of pseudo-random numbers.
The current implementation uses C++11 facilities and is therefore not cryptographically secure.
The RNG is salted with the text of the current command line invocation.
In addition, a user may specify a seed (reproducible builds).
In clang, the seed can be set via
-frandom-seed=X
In the back end, the seed can be set via
-rng-seed=X
This is the llvm part of the patch.
clang part: D3391
URL: http://reviews.llvm.org/D3390
Author: yln
I'm landing this for the second time, it broke Windows bots the first time around.
llvm-svn: 211705
The previous function returned true for "s < s", which could completely mess up
the sorting of symbols within a section.
Unfortunately, I don't think there's a robust way to write a test for this.
Anything I come up with will be making assumptions about the particular
implementation of std::sort.
llvm-svn: 211704
Origin history should only be recorded for uninitialized values, because it is
meaningless otherwise. This change moves __msan_chain_origin to the runtime
library side and makes it conditional on the corresponding shadow value.
Previous code was correct, but _very_ inefficient.
llvm-svn: 211700
v2 Changes:
- use __builtin_signbit instead of shifting by hand
- significantly improve vector shuffling
- Works correctly now for signbit(float16) on radeonsi
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 211696
--
This patch enables LLVM to emit Win64-native unwind info rather than
DWARF CFI. It handles all corner cases (I hope), including stack
realignment.
Because the unwind info is not flexible enough to describe stack frames
with a gap of unknown size in the middle, such as the one caused by
stack realignment, I modified register spilling code to place all spills
into the fixed frame slots, so that they can be accessed relative to the
frame pointer.
Patch by Vadim Chugunov!
Reviewed By: rnk
Differential Revision: http://reviews.llvm.org/D4081
llvm-svn: 211691
The < 8 instead of <= 8 meant that a bunch of vreinterprets were not available on v8 AArch32. Simplify the guard to just !defined(aarch64) while we're at it, and enable some v8 AArch32 testing.
llvm-svn: 211686
When looking through sections with zero-terminated string-literals (__cstring
or __ustring) we were constantly rechecking the first few bytes of the string
for '\0' rather than advancing along. This obviously failed unless all strings
within the section had the same length as that first one.
llvm-svn: 211682
We were trying to examine the first symbol in a section that we wanted to
atomize by symbols, even when there wasn't one. Instead, we should make the
initial anonymous symbol cover the entire section in that situation.
llvm-svn: 211681
This patch teaches the backend how to combine a build_vector that implements
an 'addsub' between packed float vectors into a sequence of vector add
and vector sub followed by a VSELECT.
The new VSELECT is expected to be lowered into a BLENDI.
At ISel stage, the sequence 'vector add + vector sub + BLENDI' is
pattern-matched against ISel patterns added at r211427 to select
'addsub' instructions.
Added three more ISel patterns for ADDSUB.
Added test sse3-avx-addsub-2.ll to verify that we correctly emit 'addsub'
instructions.
llvm-svn: 211679
The C++ language requires that the address of a function be the same
across all translation units. To make __declspec(dllimport) useful,
this means that a dllimported function must also obey this rule. MSVC
implements this by dynamically querying the import address table located
in the linked executable. This means that the address of such a
function in C++ is not constant (which violates other rules).
However, the C language has no notion of ODR nor does it permit dynamic
initialization whatsoever. This requires implementations to _not_
dynamically query the import address table and instead utilize a wrapper
function that will be synthesized by the linker which will eventually
query the import address table. The effect this has is, to say the
least, perplexing.
Consider the following C program:
__declspec(dllimport) void f(void);
typedef void (*fp)(void);
static const fp var = &f;
const fp fun() { return &f; }
int main() { return fun() == var; }
MSVC will statically initialize "var" with the address of the wrapper
function and "fun" returns the address of the actual imported function.
This means that "main" will return false!
Note that LLVM's optimizers are strong enough to figure out that "main"
should return true. However, this result is dependent on having
optimizations enabled!
N.B. This change also permits the usage of dllimport declarators inside
of template arguments; they are sufficiently constant for such a
purpose. Add tests to make sure we don't regress here.
llvm-svn: 211677
dynamic symbol table populating and DT_NEEDED tag creation.
The `isDynSymEntryRequired` function returns true if the specified shared
library atom requires a dynamic symbol table entry. The `isNeededTagRequired`
function returns true if we need to create DT_NEEDED tag for the shared
library defined specified shared atom.
By default the both functions return true. So there is no functional changes
for all targets except MIPS. Probably we need to spread the same modifications
on other ELF targets but I want to implement and fully tested complete set of
changes for MIPS target first.
For MIPS we create a dynamic symbol table entry for a shared library atom iif
this atom is referenced by a regular defined atom. For example, if library L1
defines symbol T1, library L2 defines symbol T2 and uses symbol T1
and executable file E1 uses symbol T2 but does not use symbol T1 we create
an entry in the E1 dynamic symbol table for symbol T2 and do not create
an entry for T1.
The patch creates DT_NEEDED tags for shared libraries contain shared library
atoms which a) referenced by regular defined atoms; b) have corresponding
copy dynamic relocations (R_MIPS_COPY).
Now the patch does not take in account --as-needed / --no-as-needed command
line options. So it is too restrictive and create DT_NEEDED tags for really
needed shared libraries only. I plan to fix that by subsequent patches.
llvm-svn: 211674
Fixes exponential compilation complexity in PR19835, caused by
LICM::sink not handling the following pattern well:
f = op g
e = op f, g
d = op e
c = op d, e
b = op c
a = op b, c
When an instruction with N uses is sunk, each of its operands gets N
new uses (all of them - phi nodes). In the example above, if a had 1
use, c would have 2, e would have 4, and g would have 8.
llvm-svn: 211673
Due to bad habit we sometimes used a variable %defaultOpts that listed
a set of passes commonly run to prepare for Polly. None of these test cases
actually needs special preparation and only two of them need the 'basicaa' to
be scheduled. Scheduling the required alias analysis explicitly makes the test
cases clearer.
llvm-svn: 211671
David Blaikie