Same as the VPERMILPS/VPERMILPD approach for v8f32/v4f64 cases, rely on PSHUFB using bits[3:0] for indexing - we can ignore the sign bit (zero element) as those index vector values are considered undefined. The select between the lo/hi permute results based on the index size.
llvm-svn: 327242
As VPERMILPS/VPERMILPD only selects elements based on the bits[1:0]/bit[1] then we can permute both the (repeated) lo/hi 128-bit vectors in each case and then select between these results based on whether the index was for for lo/hi.
For v4i64/v4f64 this avoids some rather nasty v4i64 multiples on the AVX2 implementation, which seems to be worse than the extra port5 pressure from the additional shuffles/blends.
llvm-svn: 327239
Helper function to insert a subvector into the bottom elements of a larger zero/undef vector with the same scalar type.
I've converted a couple of INSERT_SUBVECTOR calls to use it, there are plenty more although in some cases I was worried it might make the code more ambiguous.
llvm-svn: 327236
Else, the test fails in LLVM_TARGETS_TO_BUILD=X86 builds like so:
bin/llvm-mc: : error: unable to get target for 'arm64-apple-ios7.0.0'
llvm-svn: 327233
The intent of revision r300311 was to add a check for invalid scheduling class
descriptors. However, it ended up adding a redundant call in a basic block that
should not be reachable.
llvm-svn: 327231
In C, we'll wait until the end of the scope to clean up aggregate
temporaries used for returns from calls. This means in cases like:
{
// Assuming that `Bar` is large enough to warrant indirect returns
struct Bar b = {};
b = foo(&b);
b = foo(&b);
b = foo(&b);
b = foo(&b);
}
...We'll allocate space for 5 Bars on the stack (`b`, and 4
temporaries). This becomes painful in things like large switch
statements.
If cleaning up sooner is trivial, we should do it.
llvm-svn: 327229
Summary:
There are 3 different operand orders for FMA instructions so figuring out the exact operation being performed requires a lot of thought.
This patch adds a comment to the end of the assembly line to print the exact operation.
I think I've got all the instructions in here except the ones with builtin rounding.
I didn't update all tests, but I assume we can get them as we regenerate tests in the future.
Reviewers: spatel, v_klochkov, RKSimon
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D44345
llvm-svn: 327225
Summary:
r327219 adds wrappers to sort which shuffle the container before sorting.
This causes lldb bots to break as the call to sort is now ambiguous:
http://lab.llvm.org:8011/builders/lldb-x86_64-ubuntu-14.04-buildserver/builds/20725/steps/ninja%20build%20local/logs/stdio
So we need use llvm::sort instead of sort to avoid ambiguity with std::sort.
Note: This patch is just to unbreak the bots. I plan to have subsequent patches which will convert all
calls to std::sort to llvm::sort.
Reviewers: RKSimon, k8stone, jingham, labath, zturner
Subscribers: andreadb, lldb-commits
Tags: #lldb
Differential Revision: https://reviews.llvm.org/D44354
llvm-svn: 327224
Summary:
std::sort and array_pod_sort both use non-stable sorting algorithms.
This means that the relative order of elements with the same key is
undefined. This patch is an attempt to uncover such scenarios by
randomly shuffling all containers before sorting, if EXPENSIVE_CHECKS
is enabled.
Here's the bugzilla for this: https://bugs.llvm.org/show_bug.cgi?id=35135
Reviewers: dblaikie, dexonsmith, chandlerc, efriedma, RKSimon
Reviewed By: RKSimon
Subscribers: fhahn, davide, RKSimon, vsk, mgorny, llvm-commits
Differential Revision: https://reviews.llvm.org/D39245
llvm-svn: 327219
Piecewise affine expressions have directly corresponding mathematical
operators. Introduce these operators as overloads as this makes writing
code with isl::pw_aff expressions more directly readable.
We can now write:
A = B + C instead of A = B.add(C)
llvm-svn: 327216
This change removes method Backend::getProcResourceMasks() and simplifies some
logic in the Views. This effectively removes yet another dependency between the
views and the Backend.
No functional change intended.
llvm-svn: 327214
With the updated LangRef ( D44216 / rL327138 ) in place, we can proceed with more constant folding.
I'm intentionally taking the conservative path here: no matter what the constant or the FMF, we can
always fold to NaN. This is because the undef operand can be chosen as NaN, and in our simplified
default FP env, nothing else happens - NaN just propagates to the result. If we find some way/need
to propagate undef instead, that can be added subsequently.
The tests show that we always choose the same quiet NaN constant (0x7FF8000000000000 in IR text).
There were suggestions to improve that with a 'NaN' string token or not always print a 64-bit hex
value, but those are independent changes. We might also consider setting/propagating the payload of
NaN constants as an enhancement.
Differential Revision: https://reviews.llvm.org/D44308
llvm-svn: 327208
Use isInlineViable to prevent inlining of functions with non-inlinable
constructs, in case cost analysis is skipped.
Reviewers: efriedma, sfertile, davide, davidxl
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D42846
llvm-svn: 327207
This patch uses the infrastructure added in r326307 for enabling
non-trivial fields to be declared in C structs to allow __weak fields in
C structs in ARC.
rdar://problem/33599681
Differential Revision: https://reviews.llvm.org/D44095
llvm-svn: 327206
X86InstComments.h is used by tools that only have the MC layer. We shouldn't be importing a file from CodeGen into this.
X86InstrInfo.h isn't a great place, but I couldn't find a better one.
llvm-svn: 327202
We're persisting AliasResults in some places in MemorySSA, so the size
of these now matters a little bit (well, 8 regular-sized bits, to be
precise).
Do the same for ModRefInfo for consistency.
llvm-svn: 327201
r327100 made us stop producing vecreduce-propagate-sd-flags.s, but it's
still sticking around on some bots. This makes the bots unhappy.
I'll revert this tomorrow.
llvm-svn: 327199
This fixes pr36674.
While it is valid for shouldAssumeDSOLocal to return false anytime,
always returning false for intrinsics is not optimal on i386 and also
hits a bug in the backend.
To use a plt, the caller must first setup ebx to handle the case of
that file being linked into a PIE executable or shared library. In
those cases the generated PLT uses ebx.
Currently we can produce "calll expf@plt" without setting ebx. We
could fix that by correctly setting ebx, but this would produce worse
code for the case where the runtime library is statically linked. It
would also required other tools to handle R_386_PLT32.
llvm-svn: 327198
r327171 "Improve Dependency analysis when doing multi-node Instruction Selection"
r328170 "[DAG] Enforce stricter NodeId invariant during Instruction selection"
Reverting patch as NodeId invariant change is causing pathological
increases in compile time on PPC
llvm-svn: 327197
Simon Pilgrim