| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
| |
Whether it is legal or not needs to check for the instruction
it will be replaced with.
llvm-svn: 291711
|
| |
|
|
|
|
|
|
|
| |
This reverts commit ada6595a526d71df04988eb0a4b4fe84df398ded.
This needs a simple probability check because there are some cases where it is
not profitable.
llvm-svn: 291695
|
| |
|
|
|
|
|
|
|
| |
The new matchers work after legalization to make them simpler, and to avoid
blocking other optimizations.
Differential Revision: https://reviews.llvm.org/D27779
llvm-svn: 291693
|
| |
|
|
| |
llvm-svn: 291690
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Commit rL290616 (https://reviews.llvm.org/rL290616) changed a checking command
for the triple arm-apple-darwin in LLVM::CodeGen/ARM/fpcmp_ueq.ll. As a result
of the changes the test could fail for the valid generated code.
These changes fixes the test to check only instructions we would expect.
Differential Revision: https://reviews.llvm.org/D28159
llvm-svn: 291678
|
| |
|
|
|
|
|
|
|
| |
DAG patterns optimization: truncate + unsigned saturation supported by VPMOVUS* instructions in AVX-512.
And VPACKUS* instructions on SEE* targets.
Differential Revision: https://reviews.llvm.org/D28216
llvm-svn: 291670
|
| |
|
|
|
|
| |
Differential Revision: https://reviews.llvm.org/D28447
llvm-svn: 291665
|
| |
|
|
|
|
|
|
|
|
|
| |
The code emiited by Clang's intrinsics for (v)cvtsi2ss, (v)cvtsi2sd,
(v)cvtsd2ss and (v)cvtss2sd is lowered to a code sequence that includes
redundant (v)movss/(v)movsd instructions. This patch adds patterns for
optimizing these sequences.
Differential revision: https://reviews.llvm.org/D28455
llvm-svn: 291660
|
| |
|
|
|
|
|
|
| |
AllOnes), N1, N2) -> (vselect N0, N2, N1). Only do this if the target indicates its vector boolean type is ZeroOrNegativeOneBooleanContent."
Some test appears to be hanging on the build bots.
llvm-svn: 291650
|
| |
|
|
|
|
| |
-> (vselect N0, N2, N1). Only do this if the target indicates its vector boolean type is ZeroOrNegativeOneBooleanContent.
llvm-svn: 291645
|
| |
|
|
|
|
|
|
| |
Even with aggressive fusion enabled, this requires duplicating
the fmul, or increases an fadd to another fma which is not an
improvement.
llvm-svn: 291642
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
to (setcc (LADD x, -C), COND) (PR31367)
This was reverted because it would miscompile code where the cmp had
multiple uses. That was due to a deficiency in the existing code, which
was fixed in r291630 (see the PR for details).
This re-commit includes an extra test for the kind of code that got
miscompiled: @test_sub_1_setcc_jcc.
llvm-svn: 291640
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
We would miscompile the following:
void g(int);
int f(volatile long long *p) {
bool b = __atomic_fetch_add(p, 1, __ATOMIC_SEQ_CST) < 0;
g(b ? 12 : 34);
return b ? 56 : 78;
}
into
pushq %rax
lock incq (%rdi)
movl $12, %eax
movl $34, %edi
cmovlel %eax, %edi
callq g(int)
testq %rax, %rax <---- Bad.
movl $56, %ecx
movl $78, %eax
cmovsl %ecx, %eax
popq %rcx
retq
because the code failed to take into account that the cmp has multiple
uses, replaced one of them, and left the other one comparing garbage.
llvm-svn: 291630
|
| |
|
|
|
|
| |
Differential Revision: https://reviews.llvm.org/D28164
llvm-svn: 291622
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Previously if you had
* a function with the fast-math-enabled attr, followed by
* a function without the fast-math attr,
the second function would inherit the first function's fast-math-ness.
This means that mixing fast-math and non-fast-math functions in a module
was completely broken unless you explicitly annotated every
non-fast-math function with "unsafe-fp-math"="false". This appears to
have been broken since r176986 (March 2013), when the resetTargetOptions
function was introduced.
This patch tests the correct behavior as best we can. I don't think I
can test FPDenormalMode and NoTrappingFPMath, because they aren't used
in any backends during function lowering. Surprisingly, I also can't
find any uses at all of LessPreciseFPMAD affecting generated code.
The NVPTX/fast-math.ll test changes are an expected result of fixing
this bug. When FMA is disabled, we emit add as "add.rn.f32", which
prevents fma combining. Before this patch, fast-math was enabled in all
functions following the one which explicitly enabled it on itself, so we
were emitting plain "add.f32" where we should have generated
"add.rn.f32".
Reviewers: mkuper
Subscribers: hfinkel, majnemer, jholewinski, nemanjai, llvm-commits
Differential Revision: https://reviews.llvm.org/D28507
llvm-svn: 291618
|
| |
|
|
|
|
|
|
| |
Also fix up whitespace.
Test-only change.
llvm-svn: 291617
|
| |
|
|
|
|
| |
In future commits these patterns will appear after moveToVALU changes.
llvm-svn: 291615
|
| |
|
|
|
|
|
|
|
|
|
| |
When choosing the best successor for a block, ordinarily we would have preferred
a block that preserves the CFG unless there is a strong probability the other
direction. For small blocks that can be duplicated we now skip that requirement
as well.
Differential revision: https://reviews.llvm.org/D27742
llvm-svn: 291609
|
| |
|
|
|
|
|
|
| |
about the value.
Differential Revision: https://reviews.llvm.org/D28487
llvm-svn: 291605
|
| |
|
|
|
|
|
|
|
| |
If a vector index is out of bounds, the result is supposed to be
undefined but is not undefined behavior. Change the legalization
for indexing the vector on the stack so that an out of bounds
index does not create an out of bounds memory access.
llvm-svn: 291604
|
| |
|
|
|
|
|
|
|
|
|
|
| |
When we collect 2 uses of a function in FindUses and then RAUW when we
visit the first, we end up visiting the wrapper (because the second was
RAUW'd). We still want to use RAUW instead of just Use->set() because
it has special handling for Constants, so this patch just ensures that
only one use of each constant is added to the work list.
Differential Revision: https://reviews.llvm.org/D28504
llvm-svn: 291603
|
| |
|
|
|
|
| |
This was enabled without many specific tests or the comment.
llvm-svn: 291586
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch fix PR31351: https://llvm.org/bugs/show_bug.cgi?id=31351
1. This patch adds new type of shuffle lowering
2. We can use the expand instruction, When the shuffle pattern is as following:
{ 0*a[0]0*a[1]...0*a[n] , n >=0 where a[] elements in a ascending order}.
Reviewers: 1. igorb
2. guyblank
3. craig.topper
4. RKSimon
Differential Revision: https://reviews.llvm.org/D28352
llvm-svn: 291584
|
| |
|
|
|
|
| |
Differential Revision: https://reviews.llvm.org/D28379
llvm-svn: 291575
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The usage of some MIPS MSA instrinsics that took immediates could crash LLVM
during lowering. This patch addresses that behaviour. Crucially this patch
also makes the use of intrinsics with out of range immediates as producing an
internal error.
The ld,st instrinsics would trigger an assertion failure for MIPS64 as their
lowering would attempt to add an i32 offset to a i64 pointer.
Reviewers: vkalintiris, slthakur
Differential Revision: https://reviews.llvm.org/D25438
llvm-svn: 291571
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Previous the lowering of FILL_FW would use the MSA128W register class when
performing a vector splat. Instead it should be honouring -mno-odd-spreg and
only use the even registers when performing a splat from word to vector
register.
Logical follow-on from r230235.
This fixes PR/31369.
A previous commit was missing the test case and had another differential
in it.
Reviewers: slthakur
Differential Revision: https://reviews.llvm.org/D28373
llvm-svn: 291566
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
This patch enables the following
1. AMD family 17h architecture using "znver1" tune flag (-march, -mcpu).
2. ISAs that are enabled for "znver1" architecture.
3. Checks ADX isa from cpuid to identify "znver1" flag when -march=native is used.
4. ISAs FMA4, XOP are disabled as they are dropped from amdfam17.
5. For the time being, it uses the btver2 scheduler model.
6. Test file is updated to check this flag.
This item is linked to clang review item https://reviews.llvm.org/D28018
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, RKSimon, ashutosh.nema, llvm-commits
Differential Revision: https://reviews.llvm.org/D28017
llvm-svn: 291543
|
| |
|
|
| |
llvm-svn: 291488
|
| |
|
|
|
|
|
|
|
|
|
| |
While we can usually replace bitcast like instructions
(MachineInstr::isBitcast()) with a COPY this is not legal if any of the
users uses SUBREG_TO_REG to assert the upper bits of the result are
zero.
Differential Revision: https://reviews.llvm.org/D28474
llvm-svn: 291483
|
| |
|
|
|
|
| |
See PR31589 for details.
llvm-svn: 291478
|
| |
|
|
|
|
| |
Differential Revision: https://reviews.llvm.org/D28087
llvm-svn: 291473
|
| |
|
|
|
|
|
|
|
|
|
| |
For i16 zeroext arguments when i16 was a legal type, the
known bits information from the truncate was lost. Insert
a zeroext so the known bits optimizations work with the 32-bit
loads.
Fixes code quality regressions vs. SI in min.ll test.
llvm-svn: 291461
|
| |
|
|
|
|
|
|
|
|
| |
extend+shift+truncate pattern.
Use the existing AVX2 v8i16 vector shift lowering for v16i8 (extending to v16i32) on AVX512 targets and v32i8 (extending to v32i16) on AVX512BW targets.
Cost model updates to follow.
llvm-svn: 291451
|
| |
|
|
|
|
|
|
|
|
| |
pattern.
Use the existing AVX2 v8i16 vector shift lowering for v16i16 on AVX512 targets (AVX512BW will have already have lowered with vpsravw).
Cost model updates to follow.
llvm-svn: 291445
|
| |
|
|
| |
llvm-svn: 291444
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Originally
i64 = umax t8, Constant:i64<4>
was expanded into
i32,i32 = umax Constant:i32<0>, Constant:i32<0>
i32,i32 = umax t7, Constant:i32<4>
Now instead the two produced umax:es return i32 instead of i32, i32.
Thanks to Jan Vesely for help with the test case.
Patch by mikael.holmen at ericsson.com
Reviewers: bogner, jvesely, tstellarAMD, arsenm
Subscribers: test, wdng, RKSimon, arsenm, nhaehnle, llvm-commits
Differential Revision: https://reviews.llvm.org/D28135
llvm-svn: 291441
|
| |
|
|
|
|
| |
A future patch will conver it back to BLENDM if its beneficial to register allocation.
llvm-svn: 291419
|
| |
|
|
|
|
|
|
| |
vselects of all ones and all zeros.
Previously we emitted a VPTERNLOG and a separate masked move.
llvm-svn: 291415
|
| |
|
|
|
|
| |
of zeroes/ones when handling sign extends of i1 without VLX.
llvm-svn: 291402
|
| |
|
|
|
|
|
|
| |
test.
This is preparation for improving a case with avx512dq.
llvm-svn: 291401
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
I noticed this problem as part of the ongoing attempt to canonicalize min/max ops in IR.
The debug output shows nodes like this:
t4: i32 = xor t2, Constant:i32<-1>
t21: i8 = setcc t4, Constant:i32<0>, setlt:ch
t14: i32 = select t21, t4, Constant:i32<-1>
And because the select is holding onto the t4 (xor) node while EmitTest creates a new
x86-specific xor node, the lowering results in:
t4: i32 = xor t2, Constant:i32<-1>
t25: i32,i32 = X86ISD::XOR t2, Constant:i32<-1>
t28: i32,glue = X86ISD::CMOV Constant:i32<-1>, t4, Constant:i8<15>, t25:1
Differential Revision: https://reviews.llvm.org/D28374
llvm-svn: 291392
|
| |
|
|
|
|
|
| |
This allows the use of the 'read_register' intrinsics used by clang's
named register globals features.
llvm-svn: 291375
|
| |
|
|
|
|
|
|
| |
redundant with masked move instructions.
We should probably teach the two address instruction pass to turn masked moves into BLENDM when its beneficial to the register allocator.
llvm-svn: 291371
|
| |
|
|
| |
llvm-svn: 291370
|
| |
|
|
|
|
| |
I'm not too sure how to get isel to select even all of the unmasked forms, but at least we have a consistent set now.
llvm-svn: 291368
|
| |
|
|
|
|
| |
Fixed missing checks for tests that used a '-' in the name, which was messing with update_llc_test_checks.py
llvm-svn: 291363
|
| |
|
|
|
|
| |
v64i8 shuffles (PR31470)
llvm-svn: 291347
|
| |
|
|
|
|
|
|
| |
Gracefully leave code that performs function-pointer bitcasts implying
non-trivial pointer conversions alone, rather than aborting, since it's
just undefined behavior.
llvm-svn: 291326
|
| |
|
|
|
|
|
|
|
|
|
|
| |
WebAssembly requires caller and callee signatures to match exactly. In LLVM,
there are a variety of circumstances where signatures may be mismatched in
practice, and one can bitcast a function address to another type to call it
as that type. This patch adds a pass which replaces bitcasted function
addresses with wrappers to replace the bitcasts.
This doesn't catch everything, but it does match many common cases.
llvm-svn: 291315
|
| |
|
|
|
|
|
|
| |
This will make transition to SCRATCH_MEMORY easier
Differential Revision: https://reviews.llvm.org/D24746
llvm-svn: 291279
|