This teaches the perfect shuffle tables about lane inserts, that can
help reduce the cost of many entries. Many of the shuffle masks are
one-away from being correct, and a simple lane move can be a lot simpler
than trying to use ext/zip/etc. Because they are not exactly like the
other masks handled in the perfect shuffle tables, they require special
casing to generate them, with a special InsOp Operator.
The lane to insert into is encoded as the RHSID, and the move from is
grabbed from the original mask. This helps reduce the maximum perfect
shuffle entry cost to 3, with many more shuffles being generatable in a
single instruction.
Differential Revision: https://reviews.llvm.org/D123386
A brief introduction to perfect shuffles - AArch64 NEON has a number of
shuffle operations - dups, zips, exts, movs etc that can in some way
shuffle around the lanes of a vector. Given a shuffle of size 4 with 2
inputs, some shuffle masks can be easily codegen'd to a single
instruction. A <0,0,1,1> mask for example is a zip LHS, LHS. This is
great, but some masks are not so simple, like a <0,0,1,2>. It turns out
we can generate that from zip LHS, <0,2,0,2>, having generated
<0,2,0,2> from uzp LHS, LHS, producing the result in 2 instructions.
It is not obvious from a given mask how to get there though. So we have
a simple program (PerfectShuffle.cpp in the util folder) that can scan
through all combinations of 4-element vectors and generate the perfect
combination of results needed for each shuffle mask (for some definition
of perfect). This is run offline to generate a table that is queried for
generating shuffle instructions. (Because the table could get quite big,
it is limited to 4 element vectors).
In the perfect shuffle tables zip, unz and trn shuffles were being cost
as 2, which is higher than needed and skews the perfect shuffle tables
to create inefficient combinations. This sets them to 1 and regenerates
the tables. The codegen will usually be better and the costs should be
more precise (but it can get less second-order re-use of values from
multiple shuffles, these cases should be fixed up in subsequent patches.
Differential Revision: https://reviews.llvm.org/D123379
While working on D122986, noticed that indentation size varies even within
one file. Fixed that - now indentation is 2 spaces everywhere. This indentation
Differential Revision: https://reviews.llvm.org/D123859
Subj, or on other words, we have a lot of tests that are driven by
the LoopVectorizer's debug output, but we don't have
any meaningful way to autogenerate checklines in them,
which means that an insurmountable amount of manual work
is required when modifying the appropriate cost models.
That is not sustainable, so this presents a solution.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D121133
This patch makes possible generating NVPTX assembly check lines with
update_llc_test_checks.py utility.
Differential Revision: https://reviews.llvm.org/D122986
This helps lit unit test performance by a lot, especially on windows. The performance gain comes from launching one gtest executable for many subtests instead of one (this is the current situation).
The shards are executed by the test runner and the results are stored in the
json format supported by the GoogleTest. Later in the test reporting stage,
all test results in the json file are retrieved to continue the test results
summary etc.
On my Win10 desktop, before this patch: `check-clang-unit`: 177s, `check-llvm-unit`: 38s; after this patch: `check-clang-unit`: 37s, `check-llvm-unit`: 11s.
On my Linux machine, before this patch: `check-clang-unit`: 46s, `check-llvm-unit`: 8s; after this patch: `check-clang-unit`: 7s, `check-llvm-unit`: 4s.
Reviewed By: yln, rnk, abrachet
Differential Revision: https://reviews.llvm.org/D122251
This reverts the functional changes of D103427 but keeps its tests, and
and reimplements the functionality by reusing the existing 32-bit
MASKMOVDQU and VMASKMOVDQU instructions as suggested by skan in review.
These instructions were previously predicated on Not64BitMode. This
reimplementation restores the disassembly of a class of instructions,
which will see a test added in followup patch D122449.
These instructions are in 64-bit mode special cased in
X86MCInstLower::Lower, because we use flags with one meaning for subtly
different things: we have an AdSize32 class which indicates both that
the instruction needs a 0x67 prefix and that the text form of the
instruction implies a 0x67 prefix. These instructions are special in
needing a 0x67 prefix but having a text form that does *not* imply a
0x67 prefix, so we encode this in MCInst as an instruction that has an
explicit address size override.
Note that originally VMASKMOVDQU64 was special cased to be excluded from
disassembly, as we cannot distinguish between VMASKMOVDQU and
VMASKMOVDQU64 and rely on the fact that these are indistinguishable, or
close enough to it, at the MCInst level that it does not matter which we
use. Because VMASKMOVDQU now receives special casing, even though it
does not make a difference in the current implementation, as a
precaution VMASKMOVDQU is excluded from disassembly rather than
VMASKMOVDQU64.
Reviewed By: RKSimon, skan
Differential Revision: https://reviews.llvm.org/D122540
This commit contains a refactoring that merges AVRRelaxMemOperations
into AVRExpandPseudoInsts, so that we have a single place in code that
expands the STDWPtrQRr opcode.
Seizing the day, I've also fixed a couple of potential bugs with our
previous implementation (e.g. when the destination register was killed,
the previous implementation would try to .addDef() that killed
register, crashing LLVM in the process - that's fixed now, as proved by
the test).
Reviewed By: benshi001
Differential Revision: https://reviews.llvm.org/D122533
(With C++ exceptions, `clang++ --target=mips64{,el}-linux-gnu -fpie -pie
-fuse-ld=lld` has link errors (lld does not implement some strange R_MIPS_64
.eh_frame handling in GNU ld). However, sanitizer-x86_64-linux-qemu used this to
build ScudoUnitTests. Pined ScudoUnitTests to -no-pie.)
Default the option introduced in D113372 to ON to match all(?) major Linux
distros. This matches GCC and improves consistency with Android and linux-musl
which always default to PIE.
Note: CLANG_DEFAULT_PIE_ON_LINUX may be removed in the future.
Differential Revision: https://reviews.llvm.org/D120305
This reverts commit 3f0587d0c6.
Not all tests pass after a few rounds of fixes.
I spot one failure that std::shuffle (potentially different results with
different STL implementations) was misused and replaced it with llvm::shuffle,
but there appears to be another failure in a Windows build.
The latest failure is reported on https://reviews.llvm.org/D121556#3440383
LLVM GN Syncbot