We lower to a sequence consisting of:
- MOVi 0 into a register
- VCMPS to do the actual comparison and set the VFP flags
- FMSTAT to move the flags out of the VFP unit
- MOVCCi to either use the "zero register" that we have previously set
with the MOVi, or move 1 into the result register, based on the values
of the flags
As was the case with soft-float, for some predicates (one, ueq) we
actually need two comparisons instead of just one. When that happens, we
generate two VCMPS-FMSTAT-MOVCCi sequences and chain them by means of
using the result of the first MOVCCi as the "zero register" for the
second one. This is a bit overkill, since one comparison followed by
two non-flag-setting conditional moves should be enough. In any case,
the backend manages to CSE one of the comparisons away so it doesn't
matter much.
Note that unlike SelectionDAG and FastISel, we always use VCMPS, and not
VCMPES. This makes the code a lot simpler, and it also seems correct
since the LLVM Lang Ref defines simple true/false returns if the
operands are QNaN's. For SNaN's, even VCMPS throws an Invalid Operand
exception, so they won't be slipping through unnoticed.
Implementation-wise, this introduces a template so we can share the same
code that we use for handling integer comparisons, since the only
differences are in the details (exact opcodes to be used etc). Hopefully
this will be easy to extend to s64 G_FCMP.
llvm-svn: 307365
When scavenging for a use in instruction MI, we will reload after
that instruction and hence cannot spill uses/defs of this instruction.
This fixes http://llvm.org/PR33687
llvm-svn: 307352
Adds loop expansions for known-size and unknown-sized memcpy calls, allowing the
target to provide the operand types through TTI callbacks. The default values
for the TTI callbacks use int8 operand types and matches the existing behaviour
if they aren't overridden by the target.
Differential revision: https://reviews.llvm.org/D32536
llvm-svn: 307346
The patch is to adjust the strategy of frequency based consthoisting:
Previously when the candidate block has the same frequency with the existing
blocks containing a const, it will not hoist the const to the candidate block.
For that case, now we change the strategy to hoist the const if only existing
blocks have more than one block member. This is helpful for reducing code size.
Differential Revision: https://reviews.llvm.org/D35084
llvm-svn: 307328
The patch adds support of i128 params lowering. The changes are quite trivial to
support i128 as a "special case" of integer type. With this patch, we lower i128
params the same way as aggregates of size 16 bytes: .param .b8 _ [16].
Currently, NVPTX can't deal with the 128 bit integers:
* in some cases because of failed assertions like
ValVTs.size() == OutVals.size() && "Bad return value decomposition"
* in other cases emitting PTX with .i128 or .u128 types (which are not valid [1])
[1] http://docs.nvidia.com/cuda/parallel-thread-execution/index.html#fundamental-types
Differential Revision: https://reviews.llvm.org/D34555
Patch by: Denys Zariaiev (denys.zariaiev@gmail.com)
llvm-svn: 307326
Regardless of relaxation options such as -cl-fast-relaxed-math
we are producing rather long code for fdiv via amdgcn_fdiv_fast
intrinsic. This intrinsic is used to replace fdiv with 2.5ulp
metadata and does not handle denormals, thus believed to be fast.
An fdiv instruction can also have fast math flag either by itself
or together with fpmath metadata. Clang used with a relaxation flag
always produces both metadata and fast flag:
%div = fdiv fast float %v, %0, !fpmath !12!12 = !{float 2.500000e+00}
Current implementation ignores fast flag and favors metadata. An
instruction with just fast flag would be lowered to a fastest rcp +
mul, but that never happen on practice because of described mutual
clang and BE behavior.
This change allows an "fdiv fast" to be always lowered as rcp + mul.
Differential Revision: https://reviews.llvm.org/D34844
llvm-svn: 307308
When the formulae search space is huge, LSR uses a series of heuristic to keep
pruning the search space until the number of possible solutions are within
certain limit.
The big hammer of the series of heuristics is NarrowSearchSpaceByPickingWinnerRegs,
which picks the register which is used by the most LSRUses and deletes the other
formulae which don't use the register. This is a effective way to prune the search
space, but quite often not a good way to keep the best solution. We saw cases before
that the heuristic pruned the best formula candidate out of search space.
To relieve the problem, we introduce a new heuristic called
NarrowSearchSpaceByFilterFormulaWithSameScaledReg. The basic idea is in order to
reduce the search space while keeping the best formula, we want to keep as many
formulae with different Scale and ScaledReg as possible. That is because the central
idea of LSR is to choose a group of loop induction variables and use those induction
variables to represent LSRUses. An induction variable candidate is often represented
by the Scale and ScaledReg in a formula. If we have more formulae with different
ScaledReg and Scale to choose, we have better opportunity to find the best solution.
That is why we believe pruning search space by only keeping the best formula with the
same Scale and ScaledReg should be more effective than PickingWinnerReg. And we use
two criteria to choose the best formula with the same Scale and ScaledReg. The first
criteria is to select the formula using less non shared registers, and the second
criteria is to select the formula with less cost got from RateFormula. The patch
implements the heuristic before NarrowSearchSpaceByPickingWinnerRegs, which is the
last resort.
Testing shows we get 1.8% and 2% on two internal benchmarks on x86. llvm nightly
testsuite performance is neutral. We also tried lsr-exp-narrow and it didn't help
on the two improved internal cases we saw.
Differential Revision: https://reviews.llvm.org/D34583
llvm-svn: 307269
Summary: Added MachineVerifier code to check register ties more thoroughly, especially so that physical registers that are tied are the same. This may help e.g. when creating MIR files.
Original patch by Jesper Antonsson
Reviewers: stoklund, sanjoy, qcolombet
Reviewed By: qcolombet
Subscribers: qcolombet, llvm-commits
Differential Revision: https://reviews.llvm.org/D34394
llvm-svn: 307259
Summary:
During remat, some subranges might end up having invalid segments which caused problems for later
coalescing.
Added in a check to remove segments that are invalidated as part of the remat.
See http://llvm.org/PR33524
Subscribers: MatzeB, qcolombet
Differential Revision: https://reviews.llvm.org/D34391
llvm-svn: 307247
This covers both hard and soft float.
Hard float is easy, since it's just Legal.
Soft float is more involved, because there are several different ways to
handle it based on the predicate: one and ueq need not only one, but two
libcalls to get a result. Furthermore, we have large differences between
the values returned by the AEABI and GNU functions.
AEABI functions return a nice 1 or 0 representing true and respectively
false. GNU functions generally return a value that needs to be compared
against 0 (e.g. for ogt, the value returned by the libcall is > 0 for
true). We could introduce redundant comparisons for AEABI as well, but
they don't seem easy to remove afterwards, so we do different processing
based on whether or not the result really needs to be compared against
something (and just truncate if it doesn't).
llvm-svn: 307243
If we are lowering a libcall after legalization, we'll split the return type into a pair of legal values.
Patch by Jatin Bhateja and Eli Friedman.
Differential Revision: https://reviews.llvm.org/D34240
llvm-svn: 307207
For two ROTR operations with shifts C1, C2; combined shift operand will be (C1 + C2) % bitsize.
Differential revision: https://reviews.llvm.org/D12833
llvm-svn: 307179
This patch adds the exploitation for new power 9 instructions which extract
variable elements from vectors:
VEXTUBLX
VEXTUBRX
VEXTUHLX
VEXTUHRX
VEXTUWLX
VEXTUWRX
Differential Revision: https://reviews.llvm.org/D34032
Commit on behalf of Zaara Syeda (syzaara@ca.ibm.com)
llvm-svn: 307174
This patch adds on to the exploitation added by https://reviews.llvm.org/D33510.
This now catches build vector nodes where the inputs are coming from sign
extended vector extract elements where the indices used by the vector extract
are not correct. We can still use the new hardware instructions by adding a
shuffle to move the elements to the correct indices. I introduced a new PPCISD
node here because adding a vector_shuffle and changing the elements of the
vector_extracts was getting undone by another DAG combine.
Commit on behalf of Zaara Syeda (syzaara@ca.ibm.com)
Differential Revision: https://reviews.llvm.org/D34009
llvm-svn: 307169
Relanding after rewriting undef.ll test to avoid host-dependant
endianness.
As discussed in D34087, rewrite areNonVolatileConsecutiveLoads using
generic checks. Also, propagate missing local handling from there to
BaseIndexOffset checks.
Tests of note:
* test/CodeGen/X86/build-vector* - Improved.
* test/CodeGen/BPF/undef.ll - Improved store alignment allows an
additional store merge
* test/CodeGen/X86/clear_upper_vector_element_bits.ll - This is a
case we already do not handle well. Here, the DAG is improved, but
scheduling causes a code size degradation.
Reviewers: RKSimon, craig.topper, spatel, andreadb, filcab
Subscribers: nemanjai, llvm-commits
Differential Revision: https://reviews.llvm.org/D34472
llvm-svn: 307114
We should rewrite this using the generic branch relaxation pass, but for
the moment having this pass is better than hitting an assertion error.
llvm-svn: 307109
Made some updates to the half.ll test under CodeGen to make it friendly to the update_llc_test_checks .py tool as follows:
1.Removing the llc flag -asm-verbose=false
2.Grouping the multiple check-prefix directives
3.Apply update_llc_test_checks.py tool on the test
This change is needed to easily update scheduling changes in an upcoming patch.
Reviewers: zvi, RKSimon, craig.topper
Differential Revision: https://reviews.llvm.org/D34934
llvm-svn: 307108
Move from generic to X86 directory since gc intrinsics only supposed in
X86 64 bit.
Add target triple as well.
Fixes build failure in i686-linux-RA caused by rL307084.
llvm-svn: 307086
Summary:
We are crashing in LLC at O0 when gc intrinsics are present in the block.
The reason being FastISel performs basic block ISel by modifying GC.relocates
to be the first instruction in the block. This can cause us to visit the GC
relocate before it's corresponding GC.statepoint is visited, which is incorrect.
When we lower the statepoint, we record the base and derived pointers, along
with the gc.relocates. After this we can visit the gc.relocate.
This patch avoids fastISel from incorrectly creating the block with gc.relocate
as the first instruction.
Reviewers: qcolombet, skatkov, qikon, reames
Reviewed by: skatkov
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34421
llvm-svn: 307084
Converting the Codegen test "extractelement-legalization-store-ordering.ll" to be "update_llc_test_checks" friendly.
The changes to the test are needed for an upcoming scheduling patch.
Reviewers: zvi, RKSimon
Differential Revision: https://reviews.llvm.org/D34935
llvm-svn: 307066
Summary:
When broadcasting from the constant pool its useful to print out the final vector similar to what we do for normal moves from the constant pool.
I changed only a couple tests that were broadcast focused. One of them had been previously hand tweaked after running the script so that it could check the constant pool declaration. But I think this patch makes that unnecessary now since we can check the comment instead.
Reviewers: spatel, RKSimon, zvi
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34923
llvm-svn: 307062
Previously, if a basic block ended with a FRMIDX instruction, we would
end up doing something like this.
*std::next(MBB.end())
Which would hit an error:
"Assertion `!NodePtr->isKnownSentinel()' failed."
llvm-svn: 307057
The patch makes SoftenFloatResult/Operand logic just the same as all other legalization routines have: SoftenFloatResult() now fills the SoftenFloats map and SoftenFloatOperand() perform all needed replacements. This prevents softening mashinery from leaving stale entries in SoftenFloats map (that resulted in errors during the legalize type checking) and clarifies softening. The patch replaces https://reviews.llvm.org/D29265.
Differential Revision: https://reviews.llvm.org/D31946
llvm-svn: 307053
Florian Hahn