The triple parser should only accept existing architecture names
when the triple starts with armv, armebv, thumbv or thumbebv.
Patch by Gabor Ballabas.
llvm-svn: 222129
This was motivated by a bug which caused code like this to be
miscompiled:
declare void @take_ptr(i8*)
define void @test() {
%addr1.32 = alloca i8
%addr2.32 = alloca i32, i32 1028
call void @take_ptr(i8* %addr1)
ret void
}
This was emitting the following assembly to get the value of %addr1:
add r0, sp, #1020
add r0, r0, #8
However, "add r0, r0, #8" is not a valid Thumb1 instruction, and this
could not be assembled. The generated object file contained this,
resulting in r0 holding SP+8 rather tha SP+1028:
add r0, sp, #1020
add r0, sp, #8
This function looked like it could have caused miscompilations for
other combinations of registers and offsets (though I don't think it is
currently called with these), and the heuristic it used did not match
the emitted code in all cases.
llvm-svn: 222125
Some optimisations in DAGCombiner cause miscompilations for targets that use
TargetLowering::UndefinedBooleanContent, because they assume that the results
of a SELECT_CC node are boolean values, and can be safely ANDed, ORed and
XORed. These optimisations are only valid for targets that use
ZeroOrOneBooleanContent or ZeroOrNegativeOneBooleanContent.
This is a follow-up to D6210/r221693.
llvm-svn: 222123
This patch teaches the DAGCombiner how to combine shuffles according to rules:
shuffle(shuffle(A, Undef, M0), B, M1) -> shuffle(B, A, M2)
shuffle(shuffle(A, B, M0), B, M1) -> shuffle(B, A, M2)
shuffle(shuffle(A, B, M0), A, M1) -> shuffle(B, A, M2)
llvm-svn: 222090
Updated X86TargetLowering::isShuffleMaskLegal to match SHUFP masks with commuted inputs and PSHUFD masks that reference the second input.
As part of this I've refactored isPSHUFDMask to work in a more general manner and allow it to match against either the first or second input vector.
Differential Revision: http://reviews.llvm.org/D6287
llvm-svn: 222087
This gets the correct NaN behavior based on the compare type
the hardware uses. This now passes the new piglit test I have
for this on SI.
Add stricter tests for the operand order.
llvm-svn: 222079
We use to track quite a few "adjusted" offsets through the FrameLowering code
to account for changes in the prologue instructions as we went and allow the
emission of correct CFA annotations. However, we were missing a couple of cases
and the code was almost impenetrable.
It's easier to just add any stack-adjusting instruction to a list and emit them
together.
llvm-svn: 222057
When we folded the DPR alignment gap into a push, we weren't noting the extra
distance from the beginning of the push to the FP, and so FP ended up pointing
at an incorrect offset.
The .cfi_def_cfa_offset directives are still wrong in this case, but I think
that can be improved by refactoring.
llvm-svn: 222056
The test's DWARF stubs were there just to trigger the emission of .cfi
directives. Fortunately, the NetBSD ABI already demands proper DWARF unwind
info, so it's easier to just use that triple.
llvm-svn: 222055
If we have spilled the value of the m0 register, then we need to restore
it with v_readlane_b32 to a regular sgpr, because v_readlane_b32 can't
write to m0.
v_readlane_b32 can't write to m0, so
llvm-svn: 222036
This patch adds builtin support for xvdivdp and xvdivsp, along with a
test case. Straightforward stuff.
There's a companion patch for Clang.
llvm-svn: 221983
getTargetConstant should only be used when you can guarantee the instruction
selected will be able to cope with the raw value. BUILD_VECTOR is rather too
generic for this so we should use getConstant instead. In that case, an
instruction can still consume the constant, but if it doesn't it'll be
materialised through its own round of ISel.
Should fix PR21352.
llvm-svn: 221961
Summary:
This has most of what is needed for mips fast-isel call lowering for O32.
What is missing I will add on the next patch because this patch is already too large.
It should not be doing anything wrong but it will punt on some cases that it is basically
capable of doing.
The mechanism is there for parameters to be passed on the stack but I have not enabled it because it serves as a way for now to prevent some of the strange cases of O32 register passing that I have not fully checked yet and have some issues.
The Mips O32 abi rules are very complicated as far how data is passed in floating and integer registers.
However there is a way to think about this all very simply and this implementation reflects that.
Basically, the ABI rules are written as if everything is passed on the stack and aligned as such.
Once that is conceptually done, it is nearly trivial to reassign those locations to registers and
then all the complexity disappears.
So I have told tablegen that all the data is passed on the stack and during the lowering I fix
this by assigning to registers as per the ABI doc.
This has been my approach and you can line up what I did with the ABI document and see 1 to 1 what
is going on.
Test Plan: callabi.ll
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: jholewinski, echristo, ahatanak, llvm-commits, rfuhler
Differential Revision: http://reviews.llvm.org/D5714
llvm-svn: 221948
in-lane shuffles that aren't always handled well by the current vector
shuffle lowering.
No functionality change yet, that will follow in a subsequent commit.
llvm-svn: 221938
The generic FastISel code would bail, because it can't emit a sign-extend for
AArch64. This copies the code over and uses AArch64 specific emit functions.
This is not ideal and 'computeAddress' should handles this, so it can fold the
address computation into the memory operation.
I plan to clean up 'computeAddress' anyways, so I will add that in a future
commit.
Related to rdar://problem/18962471.
llvm-svn: 221923
If a function is just an unreachable, this would hit a
"this is not a MachO target" assertion because of setting
HasSubsectionViaSymbols.
llvm-svn: 221920
e.g. v_mad_f32 a, b, c -> v_mad_f32 b, a, c
This simplifies matching v_madmk_f32.
This looks somewhat surprising, but it appears to be
OK to do this. We can commute src0 and src1 in all
of these instructions, and that's all that appears
to matter.
llvm-svn: 221910
Normally entries can only move to a lower address, but when that wasn't viable,
the user's block was considered anyway. Unfortunately, it went via
createNewWater which wasn't designed to handle the case where there's already
an island after the block.
Unfortunately, the test we have is slow and fragile, and I couldn't reduce it
to anything sane even with the @llvm.arm.space intrinsic. The test change here
is recreating the previous one after the change.
rdar://problem/18545506
llvm-svn: 221905
We were using a naive heuristic to determine whether a basic block already had
an unconditional branch at the end. This mostly corresponded to reality
(assuming branches got optimised) because there's not much point in a branch to
the next block, but could go wrong.
llvm-svn: 221904
Creating tests for the ConstantIslands pass is very difficult, since it depends
on precise layout details. Having the ability to precisely inject a number of
bytes into the stream helps greatly.
llvm-svn: 221903
between splitting a vector into 128-bit lanes and recombining them vs.
decomposing things into single-input shuffles and a final blend.
This handles a large number of cases in AVX1 where the cross-lane
shuffles would be much more expensive to represent even though we end up
with a fast blend at the root. Instead, we can do a better job of
shuffling in a single lane and then inserting it into the other lanes.
This fixes the remaining bits of Halide's regression captured in PR21281
for AVX1. However, the bug persists in AVX2 because I've made this
change reasonably conservative. The cases where it makes sense in AVX2
to split into 128-bit lanes are much more rare because we can often do
full permutations across all elements of the 256-bit vector. However,
the particular test case in PR21281 is an example of one of the rare
cases where it is *always* better to work in a single 128-bit lane. I'm
going to try to teach the logic to detect and form the good code even in
AVX2 next, but it will need to use a separate heuristic.
Finally, there is one pesky regression here where we previously would
craftily use vpermilps in AVX1 to shuffle both high and low halves at
the same time. We no longer pull that off, and not for any really good
reason. Ultimately, I think this is just another missing nuance to the
selection heuristic that I'll try to add in afterward, but this change
already seems strictly worth doing considering the magnitude of the
improvements in common matrix math shuffle patterns.
As always, please let me know if this causes a surprising regression for
you.
llvm-svn: 221861
re-combining shuffles because nothing was available in the wider vector
type.
The key observation (which I've put in the comments for future
maintainers) is that at this point, no further combining is really
possible. And so even though these shuffles trivially could be combined,
we need to actually do that as we produce them when producing them this
late in the lowering.
This fixes another (huge) part of the Halide vector shuffle regressions.
As it happens, this was already well covered by the tests, but I hadn't
noticed how bad some of these got. The specific patterns that turn
directly into unpckl/h patterns were occurring *many* times in common
vector processing code.
There are still more problems here sadly, but trying to incrementally
tease them apart and it looks like this is the core of the problem in
the splitting logic.
There is some chance of regression here, you can see it in the test
changes. Specifically, where we stop forming pshufb in some cases, it is
possible that pshufb was in fact faster. Intel "says" that pshufb is
slower than the instruction sequences replacing it.
llvm-svn: 221852
Prior to this patch the TypePromotionHelper was promoting only sign extensions.
Supporting zero extensions changes:
- How constants are extended.
- How sign extensions, zero extensions, and truncate are composed together.
- How the type of the extended operation is recorded. Now we need to know the
kind of the extension as well as its type.
Each change is fairly small, unlike the diff.
Most of the diff are comments/variable renaming to say "extension" instead of
"sign extension".
The performance improvements on the test suite are within the noise.
Related to <rdar://problem/18310086>.
llvm-svn: 221851
This folds the compare emission into the select emission when possible, so we
can directly use the flags and don't have to emit a separate compare.
Related to rdar://problem/18960150.
llvm-svn: 221847
This is a follow-on to r221706 and r221731 and discussed in more detail in PR21385.
This patch also loosens the testcase checking for btver2. We know that the "1.0" will be loaded, but
we can't tell exactly when, so replace the CHECK-NEXT specifiers with plain CHECKs. The CHECK-NEXT
sequence relied on a quirk of post-RA-scheduling that may change independently of anything in these tests.
llvm-svn: 221819
Summary:
Large-model was added first. With the addition of support for multiple PIC
models in LLVM, now add small-model PIC for 32-bit PowerPC, SysV4 ABI. This
generates more optimal code, for shared libraries with less than about 16380
data objects.
Test Plan: Test cases added or updated
Reviewers: joerg, hfinkel
Reviewed By: hfinkel
Subscribers: jholewinski, mcrosier, emaste, llvm-commits
Differential Revision: http://reviews.llvm.org/D5399
llvm-svn: 221791
cases from Halide folks. This initial step was extracted from
a prototype change by Clay Wood to try and address regressions found
with Halide and the new vector shuffle lowering.
llvm-svn: 221779
This patch enables the vec_vsx_ld and vec_vsx_st intrinsics for
PowerPC, which provide programmer access to the lxvd2x, lxvw4x,
stxvd2x, and stxvw4x instructions.
New LLVM intrinsics are provided to represent these four instructions
in IntrinsicsPowerPC.td. These are patterned after the similar
intrinsics for lvx and stvx (Altivec). In PPCInstrVSX.td, these
intrinsics are tied to the code gen patterns, with additional patterns
to allow plain vanilla loads and stores to still generate these
instructions.
At -O1 and higher the intrinsics are immediately converted to loads
and stores in InstCombineCalls.cpp. This will open up more
optimization opportunities while still allowing the correct
instructions to be generated. (Similar code exists for aligned
Altivec loads and stores.)
The new intrinsics are added to the code that checks for consecutive
loads and stores in PPCISelLowering.cpp, as well as to
PPCTargetLowering::getTgtMemIntrinsic().
There's a new test to verify the correct instructions are generated.
The loads and stores tend to be reordered, so the test just counts
their number. It runs at -O2, as it's not very effective to test this
at -O0, when many unnecessary loads and stores are generated.
I ended up having to modify vsx-fma-m.ll. It turns out this test case
is slightly unreliable, but I don't know a good way to prevent
problems with it. The xvmaddmdp instructions read and write the same
register, which is one of the multiplicands. Commutativity allows
either to be chosen. If the FMAs are reordered differently than
expected by the test, the register assignment can be different as a
result. Hopefully this doesn't change often.
There is a companion patch for Clang.
llvm-svn: 221767
This commit adds a new pass that can inject checks before indirect calls to
make sure that these calls target known locations. It supports three types of
checks and, at compile time, it can take the name of a custom function to call
when an indirect call check fails. The default failure function ignores the
error and continues.
This pass incidentally moves the function JumpInstrTables::transformType from
private to public and makes it static (with a new argument that specifies the
table type to use); this is so that the CFI code can transform function types
at call sites to determine which jump-instruction table to use for the check at
that site.
Also, this removes support for jumptables in ARM, pending further performance
analysis and discussion.
Review: http://reviews.llvm.org/D4167
llvm-svn: 221708
This is a first step for generating SSE rcp instructions for reciprocal
calcs when fast-math allows it. This is very similar to the rsqrt optimization
enabled in D5658 ( http://reviews.llvm.org/rL220570 ).
For now, be conservative and only enable this for AMD btver2 where performance
improves significantly both in terms of latency and throughput.
We may never enable this codegen for Intel Core* chips because the divider circuits
are just too fast. On SandyBridge, divss can be as fast as 10 cycles versus the 21
cycle critical path for the rcp + mul + sub + mul + add estimate.
Follow-on patches may allow configuration of the number of Newton-Raphson refinement
steps, add AVX512 support, and enable the optimization for more chips.
More background here: http://llvm.org/bugs/show_bug.cgi?id=21385
Differential Revision: http://reviews.llvm.org/D6175
llvm-svn: 221706
My original support for the general dynamic and local dynamic TLS
models contained some fairly obtuse hacks to generate calls to
__tls_get_addr when lowering a TargetGlobalAddress. Rather than
generating real calls, special GET_TLS_ADDR nodes were used to wrap
the calls and only reveal them at assembly time. I attempted to
provide correct parameter and return values by chaining CopyToReg and
CopyFromReg nodes onto the GET_TLS_ADDR nodes, but this was also not
fully correct. Problems were seen with two back-to-back stores to TLS
variables, where the call sequences ended up overlapping with unhappy
results. Additionally, since these weren't real calls, the proper
register side effects of a call were not recorded, so clobbered values
were kept live across the calls.
The proper thing to do is to lower these into calls in the first
place. This is relatively straightforward; see the changes to
PPCTargetLowering::LowerGlobalTLSAddress() in PPCISelLowering.cpp.
The changes here are standard call lowering, except that we need to
track the fact that these calls will require a relocation. This is
done by adding a machine operand flag of MO_TLSLD or MO_TLSGD to the
TargetGlobalAddress operand that appears earlier in the sequence.
The calls to LowerCallTo() eventually find their way to
LowerCall_64SVR4() or LowerCall_32SVR4(), which call FinishCall(),
which calls PrepareCall(). In PrepareCall(), we detect the calls to
__tls_get_addr and immediately snag the TargetGlobalTLSAddress with
the annotated relocation information. This becomes an extra operand
on the call following the callee, which is expected for nodes of type
tlscall. We change the call opcode to CALL_TLS for this case. Back
in FinishCall(), we change it again to CALL_NOP_TLS for 64-bit only,
since we require a TOC-restore nop following the call for the 64-bit
ABIs.
During selection, patterns in PPCInstrInfo.td and PPCInstr64Bit.td
convert the CALL_TLS nodes into BL_TLS nodes, and convert the
CALL_NOP_TLS nodes into BL8_NOP_TLS nodes. This replaces the code
removed from PPCAsmPrinter.cpp, as the BL_TLS or BL8_NOP_TLS
nodes can now be emitted normally using their patterns and the
associated printTLSCall print method.
Finally, as a result of these changes, all references to get-tls-addr
in its various guises are no longer used, so they have been removed.
There are existing TLS tests to verify the changes haven't messed
anything up). I've added one new test that verifies that the problem
with the original code has been fixed.
llvm-svn: 221703
The ISel lowering for global TLS access in PIC mode was creating a pseudo
instruction that is later expanded to a call, but the code was not
setting the hasCalls flag in the MachineFrameInfo alongside the adjustsStack
flag. This caused some functions to be mistakenly recognized as leaf functions,
and this in turn affected the decision to eliminate the frame pointer.
With the fix, hasCalls is properly set and the leaf frame pointer is correctly
preserved.
llvm-svn: 221695
LLVM replaces the SelectionDAG pattern (xor (set_cc cc x y) 1) with
(set_cc !cc x y), which is only correct when the xor has type i1.
Instead, we should check that the constant operand to the xor is all
ones.
llvm-svn: 221693
Summary:
This patch enables code generation for the MIPS II target. Pre-Mips32
targets don't have the MUL instruction, so we add the correspondent
pattern that uses the MULT/MFLO combination in order to retrieve the
product.
This is WIP as we don't support code generation for select nodes due to
the lack of conditional-move instructions.
Reviewers: dsanders
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D6150
llvm-svn: 221686
This fixes an issue with matching trunc -> assertsext -> zext on x86-64, which would not zero the high 32-bits. See PR20494 for details.
Recommitting - This time, with a hopefully working test.
Differential Revision: http://reviews.llvm.org/D6128
llvm-svn: 221672
AVX2 is available.
According to IACA, the new lowering has a throughput of 8 cycles instead of 13
with the previous one.
Althought this lowering kicks in some SPECs benchmarks, the performance
improvement was within the noise.
Correctness testing has been done for the whole range of uint32_t with the
following program:
uint4 v = (uint4) {0,1,2,3};
uint32_t i;
//Check correctness over entire range for uint4 -> float4 conversion
for( i = 0; i < 1U << (32-2); i++ )
{
float4 t = test(v);
float4 c = correct(v);
if( 0xf != _mm_movemask_ps( t == c ))
{
printf( "Error @ %vx: %vf vs. %vf\n", v, c, t);
return -1;
}
v += 4;
}
Where "correct" is the old lowering and "test" the new one.
The patch adds a test case for the two custom lowering instruction.
It also modifies the vector cost model, which is why cast.ll and uitofp.ll are
modified.
2009-02-26-MachineLICMBug.ll is also modified because we now hoist 7
instructions instead of 4 (3 more constant loads).
rdar://problem/18153096>
llvm-svn: 221657
In the case we optimize an integer extend away and replace it directly with the
source register, we also have to clear all kill flags at all its uses.
This is necessary, because the orignal IR instruction might be trivially dead,
but we replaced it with a nop at MI level.
llvm-svn: 221628
This fixes an issue with matching trunc -> assertsext -> zext on x86-64, which would not zero the high 32-bits.
See PR20494 for details.
Differential Revision: http://reviews.llvm.org/D6128
llvm-svn: 221626
Summary:
... and after all that refactoring, it's possible to distinguish softfloat
floating point values from integers so this patch no longer breaks softfloat to
do it.
Remove direct handling of i32's in the N32/N64 ABI by promoting them to
i64. This more closely reflects the ABI documentation and also fixes
problems with stack arguments on big-endian targets.
We now rely on signext/zeroext annotations (already generated by clang) and
the Assert[SZ]ext nodes to avoid the introduction of unnecessary sign/zero
extends.
It was not possible to convert three tests to use signext/zeroext. These tests
are bswap.ll, ctlz-v.ll, ctlz-v.ll. It's not possible to put signext on a
vector type so we just accept the sign extends here for now. These tests don't
pass the vectors the same way clang does (clang puts multiple elements in the
same argument, these map 1 element to 1 argument) so we don't need to worry too
much about it.
With this patch, all known N32/N64 bugs should be fixed and we now pass the
first 10,000 tests generated by ABITest.py.
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D6117
llvm-svn: 221534
Reversing a CB* instruction used to drop the flags on the condition. On the
included testcase, this lead to a read from an undefined vreg.
Using addOperand keeps the flags, here <undef>.
Differential Revision: http://reviews.llvm.org/D6159
llvm-svn: 221507
Fixed an issue with the (v)cvttps2dq and (v)cvttpd2dq instructions being incorrectly put in the 2 source operand folding tables instead of the 1 source operand and added the missing SSE/AVX versions.
Also added missing (v)cvtps2dq and (v)cvtpd2dq instructions to the folding tables.
Differential Revision: http://reviews.llvm.org/D6001
llvm-svn: 221489
On 32 bit windows we use label differences and .set does not suppress
rolocations, a combination that was not used before r220256.
This fixes PR21497.
llvm-svn: 221456
Example:
define <4 x i32> @test(<4 x i32> %a, <4 x i32> %b) {
%shuffle = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 4, i32 5, i32 6, i32 3>
ret <4 x i32> %shuffle
}
Before llc (-mattr=+sse4.1), produced the following assembly instruction:
pblendw $4294967103, %xmm1, %xmm0
After
pblendw $63, %xmm1, %xmm0
llvm-svn: 221455
Summary:
Currently, we give an error if %z is used with non-immediates, instead of continuing as if the %z isn't there.
For example, you use the %z operand modifier along with the "Jr" constraints ("r" makes the operand a register, and "J" makes it an immediate, but only if its value is 0).
In this case, you want the compiler to print "$0" if the inline asm input operand turns out to be an immediate zero and you want it to print the register containing the operand, if it's not.
We give an error in the latter case, and we shouldn't (GCC also doesn't).
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D6023
llvm-svn: 221453
condition to match a blend.
This prevents optimizations that work on VSELECT to perform invalid
transformations. Indeed, the optimized condition does not match the vector
boolean content that is expected and bad things may happen.
This patch yields the exact same code on the whole test-suite + specs (-O3 and
-O3 -march=core-avx2), it improves one test case (vector-blend.ll) and fixes a
bug reduced in vselect-avx.ll.
<rdar://problem/18819506>
llvm-svn: 221429
Remove dynamic relocations of __gxx_personality_v0 from the .eh_frame.
The MIPS64 follow-up of the MIPS32 fix (rL209907).
Patch by Vladimir Stefanovic.
Differential Revision: http://reviews.llvm.org/D6141
llvm-svn: 221408
Added missing memory folding for the (V)CVTDQ2PS instructions - we can safely fold these (but not the (V)CVTDQ2PD versions which have a register/memory size discrepancy in the source operand). I've added a test case demonstrating that stack folding now works.
Differential Revision: http://reviews.llvm.org/D5981
llvm-svn: 221407
Summary:
X86FastISel::fastMaterializeAlloca was incorrectly conditioning its
opcode selection on subtarget bitness rather than pointer size.
Differential Revision: http://reviews.llvm.org/D6136
llvm-svn: 221386
This works around the limitation that PTX does not allow .param space
loads/stores with arbitrary pointers.
If a function has a by-val struct ptr arg, say foo(%struct.x *byval %d), then
add the following instructions to the first basic block :
%temp = alloca %struct.x, align 8
%tt1 = bitcast %struct.x * %d to i8 *
%tt2 = llvm.nvvm.cvt.gen.to.param %tt2
%tempd = bitcast i8 addrspace(101) * to %struct.x addrspace(101) *
%tv = load %struct.x addrspace(101) * %tempd
store %struct.x %tv, %struct.x * %temp, align 8
The above code allocates some space in the stack and copies the incoming
struct from param space to local space. Then replace all occurences of %d
by %temp.
Fixes PR21465.
llvm-svn: 221377
This matches the format produced by the AMD proprietary driver.
//==================================================================//
// Shell script for converting .ll test cases: (Pass the .ll files
you want to convert to this script as arguments).
//==================================================================//
; This was necessary on my system so that A-Z in sed would match only
; upper case. I'm not sure why.
export LC_ALL='C'
TEST_FILES="$*"
MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r`
for f in $TEST_FILES; do
# Check that there are SI tests:
grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f
if [ $? -eq 0 ]; then
for match in $MATCHES; do
sed -i -e "s/\([ :]$match\)/\L\1/" $f
done
# Try to get check lines with partial instruction names
sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f
fi
done
sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll
sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll
sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll
sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll
sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll
//==================================================================//
// Shell script for converting .td files (run this last)
//==================================================================//
export LC_ALL='C'
sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td
sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td
llvm-svn: 221350
This patch improves the folding of vector AND nodes into blend operations for
targets that feature SSE4.1. A vector AND node where one of the operands is
a constant build_vector with elements that are either zero or all-ones can be
converted into a blend.
This allows for example to simplify the following code:
define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) {
%1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1>
%2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0>
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
Before this patch llc (-mcpu=corei7) generated:
andps LCPI1_0(%rip), %xmm0, %xmm0
andps LCPI1_1(%rip), %xmm1, %xmm1
orps %xmm1, %xmm0, %xmm0
retq
With this patch we generate a single 'vpblendw'.
llvm-svn: 221343
We currently try to push an even number of registers to preserve 8-byte
alignment during a function's prologue, but only when the stack alignment is
prcisely 8. Many of the reasons for doing it apply also when that alignment > 8
(the extra store is often free, and can save another stack adjustment, though
less frequently for 16-byte stack alignment).
llvm-svn: 221321
We were making an attempt to do this by adding an extra callee-saved GPR (so
that there was an even number in the list), but when that failed we went ahead
and pushed anyway.
This had a couple of potential issues:
+ The .cfi directives we emit misplaced dN because they were based on
PrologEpilogInserter's calculation.
+ Unaligned stores can be less efficient.
+ Unaligned stores can actually fault (likely only an issue in niche cases,
but possible).
This adds a final explicit stack adjustment if all other options fail, so that
the actual locations of the registers match up with where they should be.
llvm-svn: 221320
Patch to allow (v)blendps, (v)blendpd, (v)pblendw and vpblendd instructions to be commuted - swaps the src registers and inverts the blend mask.
This is primarily to improve memory folding (see new tests), but it also improves the quality of shuffles (see modified tests).
Differential Revision: http://reviews.llvm.org/D6015
llvm-svn: 221313
While fixing up the register classes in the machine combiner in a previous
commit I missed one.
This fixes the last one and adds a test case.
llvm-svn: 221308
Registers are not all equal. Some are not allocatable (infinite cost),
some have to be preserved but can be used, and some others are just free
to use.
Ensure there is a cost hierarchy reflecting this fact, so that the
allocator will favor scratch registers over callee-saved registers.
llvm-svn: 221293
register class tGPRRegClass if the target is thumb1.
This commit fixes a crash that occurs during register allocation which was
triggered when a virtual register defined by an inline-asm instruction had to
be spilled.
rdar://problem/18740489
llvm-svn: 221178
For 8-bit divrems where the remainder is used, we used to generate:
divb %sil
shrw $8, %ax
movzbl %al, %eax
That was to avoid an H-reg access, which is problematic mainly because
it isn't possible in REX-prefixed instructions.
This patch optimizes that to:
divb %sil
movzbl %ah, %eax
To do that, we explicitly extend AH, and extract the L-subreg in the
resulting register. The extension is done using the NOREX variants of
MOVZX. To support signed operations, MOVSX_NOREX is also added.
Further, this introduces a new SDNode type, [us]divrem_ext_hreg, which is
then lowered to a sequence containing a single zext (rather than 2).
Differential Revision: http://reviews.llvm.org/D6064
llvm-svn: 221176
call DAGCombiner. But we ran into a case (on Windows) where the
calling convention causes argument lowering to bail out of fast-isel,
and we end up in CodeGenAndEmitDAG() which does run DAGCombiner.
So, we need to make DAGCombiner check for 'optnone' after all.
Commit includes the test that found this, plus another one that got
missed in the original optnone work.
llvm-svn: 221168
This CPU definition is redundant. The Cortex-A9 is defined as
supporting multiprocessing extensions. Remove its definition and
update appropriate tests.
LLVM defines both a cortex-a9 CPU and a cortex-a9-mp CPU. The only
difference between the two CPU definitions in ARM.td is that
cortex-a9-mp contains the feature FeatureMP for multiprocessing
extensions.
This is redundant since the Cortex-A9 is defined as having
multiprocessing extensions in the TRMs. armcc also defines the
Cortex-A9 as having multiprocessing extensions by default.
Change-Id: Ifcadaa6c322be0a33d9d2a39cfdd7da1d75981a7
llvm-svn: 221166
Some literals in the AArch64 backend had 15 'f's rather than 16, causing
comparisons with a constant 0xffffffffffffffff to be miscompiled.
llvm-svn: 221157
Hexagon was not calling InitializeELF and could not select between
ctors and init_array.
Phabricator revision: http://reviews.llvm.org/D6061
llvm-svn: 221156
"[x86] Simplify vector selection if condition value type matches vselect value type and true value is all ones or false value is all zeros."
llvm-svn: 221028
We need to figure out how to track ptrtoint values all the
way until result is converted back to a pointer in order
to correctly rewrite the pointer type.
llvm-svn: 220997
Now that we have initial support for VSX, we can begin adding
intrinsics for programmer access to VSX instructions. This patch adds
basic support for VSX intrinsics in general, and tests it by
implementing intrinsics for minimum and maximum for the vector double
data type.
The LLVM portion of this is quite straightforward. There is a
companion patch for Clang.
llvm-svn: 220988
This patch adds an optimization in CodeGenPrepare to move an extractelement
right before a store when the target can combine them.
The optimization may promote any scalar operations to vector operations in the
way to make that possible.
** Context **
Some targets use different register files for both vector and scalar operations.
This means that transitioning from one domain to another may incur copy from one
register file to another. These copies are not coalescable and may be expensive.
For example, according to the scheduling model, on cortex-A8 a vector to GPR
move is 20 cycles.
** Motivating Example **
Let us consider an example:
define void @foo(<2 x i32>* %addr1, i32* %dest) {
%in1 = load <2 x i32>* %addr1, align 8
%extract = extractelement <2 x i32> %in1, i32 1
%out = or i32 %extract, 1
store i32 %out, i32* %dest, align 4
ret void
}
As it is, this IR generates the following assembly on armv7:
vldr d16, [r0] @vector load
vmov.32 r0, d16[1] @ cross-register-file copy: 20 cycles
orr r0, r0, #1 @ scalar bitwise or
str r0, [r1] @ scalar store
bx lr
Whereas we could generate much faster code:
vldr d16, [r0] @ vector load
vorr.i32 d16, #0x1 @ vector bitwise or
vst1.32 {d16[1]}, [r1:32] @ vector extract + store
bx lr
Half of the computation made in the vector is useless, but this allows to get
rid of the expensive cross-register-file copy.
** Proposed Solution **
To avoid this cross-register-copy penalty, we promote the scalar operations to
vector operations. The penalty will be removed if we manage to promote the whole
chain of computation in the vector domain.
Currently, we do that only when the chain of computation ends by a store and the
target is able to combine an extract with a store.
Stores are the most likely candidates, because other instructions produce values
that would need to be promoted and so, extracted as some point[1]. Moreover,
this is customary that targets feature stores that perform a vector extract (see
AArch64 and X86 for instance).
The proposed implementation relies on the TargetTransformInfo to decide whether
or not it is beneficial to promote a chain of computation in the vector domain.
Unfortunately, this interface is rather inaccurate for this level of details and
although this optimization may be beneficial for X86 and AArch64, the inaccuracy
will lead to the optimization being too aggressive.
Basically in TargetTransformInfo, everything that is legal has a cost of 1,
whereas, even if a vector type is legal, usually a vector operation is slightly
more expensive than its scalar counterpart. That will lead to too many
promotions that may not be counter balanced by the saving of the
cross-register-file copy. For instance, on AArch64 this penalty is just 4
cycles.
For now, the optimization is just enabled for ARM prior than v8, since those
processors have a larger penalty on cross-register-file copies, and the scope is
limited to basic blocks. Because of these two factors, we limit the effects of
the inaccuracy. Indeed, I did not want to build up a fancy cost model with block
frequency and everything on top of that.
[1] We can imagine targets that can combine an extractelement with other
instructions than just stores. If we want to go into that direction, the current
interfaces must be augmented and, moreover, I think this becomes a global isel
problem.
Differential Revision: http://reviews.llvm.org/D5921
<rdar://problem/14170854>
llvm-svn: 220978
Since block address values can be larger than 2GB in 64-bit code, they
cannot be loaded simply using an @l / @ha pair, but instead must be
loaded from the TOC, just like GlobalAddress, ConstantPool, and
JumpTable values are.
The commit also fixes a bug in PPCLinuxAsmPrinter::doFinalization where
temporary labels could not be used as TOC values, since code would
attempt (and fail) to use GetOrCreateSymbol to create a symbol of the
same name as the temporary label.
llvm-svn: 220959
r212242 introduced a legalizer hook, originally to let AArch64 widen
v1i{32,16,8} rather than scalarize, because the legalizer expected, when
scalarizing the result of a conversion operation, to already have
scalarized the operands. On AArch64, v1i64 is legal, so that commit
ensured operations such as v1i32 = trunc v1i64 wouldn't assert.
It did that by choosing to widen v1 types whenever possible. However,
v1i1 types, for which there's no legal widened type, would still trigger
the assert.
This commit fixes that, by only scalarizing a trunc's result when the
operand has already been scalarized, and introducing an extract_elt
otherwise.
This is similar to r205625.
Fixes PR20777.
llvm-svn: 220937
Earlier this summer I fixed an issue where we were incorrectly combining
multiple loads that had different constraints such alignment, invariance,
temporality, etc. Apparently in one case I made copt paste error and swapped
alignment and invariance.
Tests included.
rdar://18816719
llvm-svn: 220933
This transformation worked if selector is produced by SETCC, however SETCC is needed only if we consider to swap operands. So I replaced SETCC check for this case.
Added tests for vselect of <X x i1> values.
llvm-svn: 220777
Ffter commit at rev219046 512-bit broadcasts lowering become non-optimal. Most of tests on broadcasting and embedded broadcasting were changed and they doesn’t produce efficient code.
Example below is from commit changes (it’s the first test from test/CodeGen/X86/avx512-vbroadcast.ll):
define <16 x i32> @_inreg16xi32(i32 %a) {
; CHECK-LABEL: _inreg16xi32:
; CHECK: ## BB#0:
-; CHECK-NEXT: vpbroadcastd %edi, %zmm0
+; CHECK-NEXT: vmovd %edi, %xmm0
+; CHECK-NEXT: vpbroadcastd %xmm0, %ymm0
+; CHECK-NEXT: vinserti64x4 $1, %ymm0, %zmm0, %zmm0
; CHECK-NEXT: retq
%b = insertelement <16 x i32> undef, i32 %a, i32 0
%c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
ret <16 x i32> %c
}
Here, 256-bit broadcast was generated instead of 512-bit one.
In this patch
1) I added vector-shuffle lowering through broadcasts
2) Removed asserts and branches likes because this is incorrect
- assert(Subtarget->hasDQI() && "We can only lower v8i64 with AVX-512-DQI");
3) Fixed lowering tests
llvm-svn: 220774
This is a Microsoft calling convention that supports both x86 and x86_64
subtargets. It passes vector and floating point arguments in XMM0-XMM5,
and passes them indirectly once they are consumed.
Homogenous vector aggregates of up to four elements can be passed in
sequential vector registers, but this part is not implemented in LLVM
and will be handled in Clang.
On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as
integer register parameters and is callee cleanup. On x86_64, it
delegates to the normal win64 calling convention.
Reviewers: majnemer
Differential Revision: http://reviews.llvm.org/D5943
llvm-svn: 220745
Benchmarks have shown that it's harmless to the performance there, and having a
unified set of passes between the two cores where possible helps big.LITTLE
deployment.
Patch by Z. Zheng.
llvm-svn: 220744
For a call to not return in to the stackmap shadow, the shadow must end with the call.
To do this, we must insert any required nops *before* the call, and not after it.
llvm-svn: 220728
This is a minor change to use the immediate version when the operand is a null
value. This should get rid of an unnecessary 'mov' instruction in debug
builds and align the code more with the one generated by SelectionDAG.
This fixes rdar://problem/18785125.
llvm-svn: 220713
To avoid emitting too many nops, a stackmap shadow can include emitted instructions in the shadow, but these must not include branch targets.
A return from a call should count as a branch target as patching over the instructions after the call would lead to incorrect behaviour for threads currently making that call, when they return.
llvm-svn: 220710
The pattern matching for a 'ConstantInt' value was too restrictive. Checking for
a 'Constant' with a bull value is sufficient for using an 'cbz/cbnz' instruction.
This fixes rdar://problem/18784732.
llvm-svn: 220709
This fixes a bug where the input register was not defined for the 'tbz/tbnz'
instruction. This happened, because we folded the 'and' instruction from a
different basic block.
This fixes rdar://problem/18784013.
llvm-svn: 220704
At higher optimization levels the LLVM IR may contain more complex patterns for
loads/stores from/to frame indices. The 'computeAddress' function wasn't able to
handle this and triggered an assertion.
This fix extends the possible addressing modes for frame indices.
This fixes rdar://problem/18783298.
llvm-svn: 220700
Currently, the ARM backend will select the VMAXNM and VMINNM for these C
expressions:
(a < b) ? a : b
(a > b) ? a : b
but not these expressions:
(a > b) ? b : a
(a < b) ? b : a
This patch allows all of these expressions to be matched.
llvm-svn: 220671
Summary:
Fixes PR21100 which is caused by inconsistency between the declared return type
and the expected return type at the call site. The new behavior is consistent
with nvcc and the NVPTXTargetLowering::getPrototype function.
Test Plan: test/Codegen/NVPTX/vector-return.ll
Reviewers: jholewinski
Reviewed By: jholewinski
Subscribers: llvm-commits, meheff, eliben, jholewinski
Differential Revision: http://reviews.llvm.org/D5612
llvm-svn: 220607
Minor patch to fix an issue in XFormVExtractWithShuffleIntoLoad where a load is unary shuffled, then bitcast (to a type with the same number of elements) before extracting an element.
An undef was created for the second shuffle operand using the original (post-bitcasted) vector type instead of the pre-bitcasted type like the rest of the shuffle node - this was then causing an assertion on the different types later on inside SelectionDAG::getVectorShuffle.
Differential Revision: http://reviews.llvm.org/D5917
llvm-svn: 220592
This is a first step for generating SSE rsqrt instructions for
reciprocal square root calcs when fast-math is allowed.
For now, be conservative and only enable this for AMD btver2
where performance improves significantly - for example, 29%
on llvm/projects/test-suite/SingleSource/Benchmarks/BenchmarkGame/n-body.c
(if we convert the data type to single-precision float).
This patch adds a two constant version of the Newton-Raphson
refinement algorithm to DAGCombiner that can be selected by any target
via a parameter returned by getRsqrtEstimate()..
See PR20900 for more details:
http://llvm.org/bugs/show_bug.cgi?id=20900
Differential Revision: http://reviews.llvm.org/D5658
llvm-svn: 220570
Summary:
Most structs were fixed by r218451 but those of between >32-bits and
<64-bits remained broken since they were not marked with [ASZ]ExtUpper.
This patch fixes the remaining cases by using
CCPromoteToUpperBitsInType<i64> on i64's in addition to i32 and smaller.
Reviewers: vmedic
Reviewed By: vmedic
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D5963
llvm-svn: 220556
This fixes a miscompilation in the AArch64 fast-isel which was
triggered when a branch is based on an icmp with condition eq or ne,
and type i1, i8 or i16. The cbz instruction compares the whole 32-bit
register, so values with the bottom 1, 8 or 16 bits clear would cause
the wrong branch to be taken.
llvm-svn: 220553
This adds support for legalization of instructions of the form:
[fp_conv] <1 x i1> %op to <1 x double>
where fp_conv is one of fpto[us]i, [us]itofp. This used to assert
because they were simply missing from the vector operand scalarizer.
A similar problem arose in r190830, with trunc instead.
Fixes PR20778.
Differential Revision: http://reviews.llvm.org/D5810
llvm-svn: 220533
x86's CMPXCHG -> EFLAGS consumer wasn't being recorded as a real EFLAGS
dependency because it was represented by a pair of CopyFromReg(EFLAGS) ->
CopyToReg(EFLAGS) nodes. ScheduleDAG was expecting the source to be an
implicit-def on the instruction, where the result numbers in the DAG and the
Uses list in TableGen matched up precisely.
The Copy notation seems much more robust, so this patch extends ScheduleDAG
rather than refactoring x86.
Should fix PR20376.
llvm-svn: 220529
Currently, @llvm.smul.with.overflow.i8 expands to 9 instructions, where
3 are really needed.
This adds X86ISD::UMUL8/SMUL8 SD nodes, and custom lowers them to
MUL8/IMUL8 + SETO.
i8 is a special case because there is no two/three operand variants of
(I)MUL8, so the first operand and return value need to go in AL/AX.
Also, we can't write patterns for these instructions: TableGen refuses
patterns where output operands don't match SDNode results. In this case,
instructions where the output operand is an implicitly defined register.
A related special case (and FIXME) exists for MUL8 (X86InstrArith.td):
// FIXME: Used for 8-bit mul, ignore result upper 8 bits.
// This probably ought to be moved to a def : Pat<> if the
// syntax can be accepted.
[(set AL, (mul AL, GR8:$src)), (implicit EFLAGS)]
Ideally, these go away with UMUL8, but we still need to improve TableGen
support of implicit operands in patterns.
Before this change:
movsbl %sil, %eax
movsbl %dil, %ecx
imull %eax, %ecx
movb %cl, %al
sarb $7, %al
movzbl %al, %eax
movzbl %ch, %esi
cmpl %eax, %esi
setne %al
After:
movb %dil, %al
imulb %sil
seto %al
Also, remove a made-redundant testcase for PR19858, and enable more FastISel
ALU-overflow tests for SelectionDAG too.
Differential Revision: http://reviews.llvm.org/D5809
llvm-svn: 220516
This reverts commit r214981.
I'm not sure what I was thinking when I wrote this. Testing with MSVC
shows that this function is mangled to '@f@8':
int __fastcall f(int a, int b);
llvm-svn: 220492
This updates check for double precision zero floating point constant to allow
use of instruction with immediate value rather than temporary register.
Currently "a == 0.0", where "a" is of "double" type generates:
vmov.i32 d16, #0x0
vcmpe.f64 d0, d16
With this change it becomes:
vcmpe.f64 d0, #0
Patch by Sergey Dmitrouk.
llvm-svn: 220486
A previous patch enabled SELECT_VSRC and SELECT_CC_VSRC for VSX to
handle <2 x double> cases. This patch adds SELECT_VSFRC and
SELECT_CC_VSFRC to allow use of all 64 vector-scalar registers for the
f64 type when VSX is enabled. The changes are analogous to those in
the previous patch. I've added a new variant to vsx.ll to test the
code generation.
(I also cleaned up a little formatting in PPCInstrVSX.td from the
previous patch.)
llvm-svn: 220395
This enables targets to adapt their pass pipeline to the register
allocator in use. For example, with the AArch64 backend, using PBQP
with the cortex-a57, the FPLoadBalancing pass is no longer necessary.
llvm-svn: 220321
With VSX enabled, test/CodeGen/PowerPC/recipest.ll exposes a bug in
the FMA mutation pass. If we have a situation where a killed product
register is the same register as the FMA target, such as:
%vreg5<def,tied1> = XSNMSUBADP %vreg5<tied0>, %vreg11, %vreg5,
%RM<imp-use>; VSFRC:%vreg5 F8RC:%vreg11
then the substitution makes no sense. We end up getting a crash when
we try to extend the interval associated with the killed product
register, as there is already a live range for %vreg5 there. This
patch just disables the mutation under those circumstances.
Since recipest.ll generates different code with VMX enabled, I've
modified that test to use -mattr=-vsx. I've borrowed the code from
that test that exposed the bug and placed it in fma-mutate.ll, where
it tests several mutation opportunities including the "bad" one.
llvm-svn: 220290
Every target we support has support for assembly that looks like
a = b - c
.long a
What is special about MachO is that the above combination suppresses the
production of a relocation.
With this change we avoid producing the intermediary labels when they don't
add any value.
llvm-svn: 220256
X86 code to lower VSELECT messed a bit with the bits set in the mask of VSELECT
when it knows it can be lowered into BLEND. Indeed, only the high bits need to be
set for those and it optimizes those accordingly.
However, when the mask is a compile time constant, the lowering will be handled
by the generic optimizer and those modifications will generate bad code in the
generic optimizer.
This patch fixes that by preventing the optimization if the VSELECT will be
handled by the generic optimizer.
<rdar://problem/18675020>
llvm-svn: 220242
This patch improves support for commutative instructions in the x86 memory folding implementation by attempting to fold a commuted version of the instruction if the original folding fails - if that folding fails as well the instruction is 're-commuted' back to its original order before returning.
Updated version of r219584 (reverted in r219595) - the commutation attempt now explicitly ensures that neither of the commuted source operands are tied to the destination operand / register, which was the source of all the regressions that occurred with the original patch attempt.
Added additional regression test case provided by Joerg Sonnenberger.
Differential Revision: http://reviews.llvm.org/D5818
llvm-svn: 220239
The previous code had a few problems, motivating the choices here.
1. It could create instructions clobbering CPSR, but the incoming MachineInstr
didn't reflect this. A potential source of corruption. This is why the patch
has a new PseudoInst for before lowering.
2. Similarly, there was some code to handle the incoming instruction not being
ARMCC::AL, but this would have caused massive problems if it was actually
invoked when a complex offset needing more than one instruction was requested.
3. It wasn't designed to handle unaligned pointers (or offsets). These should
probably be minimised anyway, but the code needs to deal with them properly
regardless.
4. It had some rather dubious ad-hoc code to avoid calling
emitThumbRegPlusImmediate, a function which should be designed to do precisely
this job.
We seem to cover the common cases correctly now, and hopefully can enhance
emitThumbRegPlusImmediate to handle any extra optimisations we need to add in
future.
llvm-svn: 220236
The current instruction selection patterns for SMULW[BT] and SMLAW[BT]
are incorrect. These instructions multiply a 32-bit and a 16-bit value
(both signed) and return the top 32 bits of the 48-bit result. This
preserves the 16 bits of overflow, whereas the patterns they currently
match truncate the result to 16 bits then sign extend.
To select these instructions, we would need to match an ISD::SMUL_LOHI,
a sign extend, two shifts and an or. There is no way to match SMUL_LOHI
in an instruction pattern as it defines multiple values, so this would
have to be done in C++. I have raised
http://llvm.org/bugs/show_bug.cgi?id=21297 to cover allowing correct
selection of these instructions.
This fixes http://llvm.org/bugs/show_bug.cgi?id=19396
llvm-svn: 220196
This function can, for some offsets from the SP, split one instruction
into two. Since it re-uses the original instruction as the first
instruction of the result, we need ensure its result register is not
marked as dead before we use it in the second instruction.
llvm-svn: 220194
We recently discovered an issue that reinforces what a good idea it is
to always specify -mcpu in our code generation tests, particularly for
-mattr=+vsx. This patch ensures that all tests that specify
-mattr=+vsx also specify -mcpu=pwr7 or -mcpu=pwr8, as appropriate.
Some of the uses of -mattr=+vsx added recently don't make much sense
(when specified for -mtriple=powerpc-apple-darwin8 or -march=ppc32,
for example). For cases like this I've just removed the extra VSX
test commands; there's enough coverage without them.
llvm-svn: 220173
Patch by Bill Seurer; some comment formatting changes by me.
There are a few PowerPC test cases for FastISel support that currently
fail with VSX support enabled. The temporary workaround under
discussion in http://reviews.llvm.org/D5362 helps, but the tests still
fail because they specify -fast-isel-abort, and the VSX workaround
punts back to SelectionDAG. We have plans to fix FastISel permanently
for VSX, but until that's in place these tests are preventing us from
enabling VSX by default. Therefore we are adding -mattr=-vsx to these
tests until the full support is ready.
llvm-svn: 220172
The VSX testing variant in test/CodeGen/PowerPC/fma.ll had to be
disabled because of unexpected behavior on many of the builders. I
tracked this down to a situation that occurs when the VSX attribute is
enabled for a target that disables the MI early scheduling pass. This
patch adds -mcpu=pwr7 to make this predictable. The other issue will
be addressed separately.
llvm-svn: 220171
The previous tests claimed to test constant offsets in the function name,
but the tests weren't actually testing them.
Clone the tests, and do testing of all combinations of the following:
1) with/without constant pointer offset
2) 32/64-bit addressing modes
3) Usage and non-usage of the return value from the atomicrmw
Reviewed-by: Matt Arsenault <matthew.arsenault@amd.com>
llvm-svn: 220103
The function name now matches what it's actually testing.
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Matt Arsenault <matthew.arsenault@amd.com>
llvm-svn: 220102
TL;DR: Indexing maps with [] creates missing entries.
The long version:
When selecting lifetime intrinsics, we index the *static* alloca map with the AllocaInst we find for that lifetime. Trouble is, we don't first check to see if this is a dynamic alloca.
On the attached example, this causes a dynamic alloca to create an entry in the static map, and returns 0 (the default) as the frame index for that lifetime. 0 was used for the frame index of the stack protector, which given that it now has a lifetime, is coloured, and merged with other stack slots.
PEI would later trigger an assert because it expects the stack protector to not be dead.
This fix ensures that we only get frame indices for static allocas, ie, those in the map. Dynamic ones are effectively dropped, which is suboptimal, but at least isn't completely broken.
rdar://problem/18672951
llvm-svn: 220099
With VSX enabled, LLVM crashes when compiling
test/CodeGen/PowerPC/fma.ll. I traced this to the liveness test
that's revised in this patch. The interval test is designed to only
work for virtual registers, but in this case the AddendSrcReg is
physical. Since there is already a walk of the MIs between the
AddendMI and the FMA, I added a check for def/kill of the AddendSrcReg
in that loop. At Hal Finkel's request, I converted the liveness test
to an assert restricted to virtual registers.
I've changed the fma.ll test to have VSX and non-VSX variants so we
can test both kinds of multiply-adds.
llvm-svn: 220090
When the input to a store instruction was a zero vector, the backend
always selected a normal vector store regardless of the non-temporal
hint. This is fixed by this patch.
This fixes PR19370.
llvm-svn: 220054
We should be talking about the number of source elements, not the number of destination elements, given we know at this point that the source and dest element numbers are not the same.
While we're at it, avoid writing to std::vector::end()...
Bug found with random testing and a lot of coffee.
llvm-svn: 220051
Currently the VSX support enables use of lxvd2x and stxvd2x for 2x64
types, but does not yet use lxvw4x and stxvw4x for 4x32 types. This
patch adds that support.
As with lxvd2x/stxvd2x, this involves straightforward overriding of
the patterns normally recognized for lvx/stvx, with preference given
to the VSX patterns when VSX is enabled.
In addition, the logic for permitting misaligned memory accesses is
modified so that v4r32 and v4i32 are treated the same as v2f64 and
v2i64 when VSX is enabled. Finally, the DAG generation for unaligned
loads is changed to just use a normal LOAD (which will become lxvw4x)
on P8 and later hardware, where unaligned loads are preferred over
lvsl/lvx/lvx/vperm.
A number of tests now generate the VSX loads/stores instead of
lvx/stvx, so this patch adds VSX variants to those tests. I've also
added <4 x float> tests to the vsx.ll test case, and created a
vsx-p8.ll test case to be used for testing code generation for the
P8Vector feature. For now, that simply tests the unaligned load/store
behavior.
This has been tested along with a temporary patch to enable the VSX
and P8Vector features, with no new regressions encountered with or
without the temporary patch applied.
llvm-svn: 220047
v2: use dyn_cast
fixup comments
v3: use cast
Reviewed-by: Matt Arsenault <arsenm2@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 220044
Patch by Bill Seurer; committed on his behalf.
These test cases generate slightly different code sequences when VSX
is activated and thus fail. The update turns off VSX explicitly for
the existing checks and then adds a second set of checks for most of
them that test the VSX instruction output.
llvm-svn: 220019
The bug is in ARMConstantIslands::createNewWater where the upper bound of the
new water split point is computed:
// This could point off the end of the block if we've already got constant
// pool entries following this block; only the last one is in the water list.
// Back past any possible branches (allow for a conditional and a maximally
// long unconditional).
if (BaseInsertOffset + 8 >= UserBBI.postOffset()) {
BaseInsertOffset = UserBBI.postOffset() - UPad - 8;
DEBUG(dbgs() << format("Move inside block: %#x\n", BaseInsertOffset));
}
The split point is supposed to be somewhere between the machine instruction that
loads from the constant pool entry and the end of the basic block, before branch
instructions. The code above is fine if the basic block is large enough and
there are a sufficient number of instructions following the machine instruction.
However, if the machine instruction is near the end of the basic block,
BaseInsertOffset can point to the machine instruction or another instruction
that precedes it, and this can lead to convergence failure.
This commit fixes this bug by ensuring BaseInsertOffset is larger than the
offset of the instruction following the constant-loading instruction.
rdar://problem/18581150
llvm-svn: 220015
Summary:
Backends can use setInsertFencesForAtomic to signal to the middle-end that
montonic is the only memory ordering they can accept for
stores/loads/rmws/cmpxchg. The code lowering those accesses with a stronger
ordering to fences + monotonic accesses is currently living in
SelectionDAGBuilder.cpp. In this patch I propose moving this logic out of it
for several reasons:
- There is lots of redundancy to avoid: extremely similar logic already
exists in AtomicExpand.
- The current code in SelectionDAGBuilder does not use any target-hooks, it
does the same transformation for every backend that requires it
- As a result it is plain *unsound*, as it was apparently designed for ARM.
It happens to mostly work for the other targets because they are extremely
conservative, but Power for example had to switch to AtomicExpand to be
able to use lwsync safely (see r218331).
- Because it produces IR-level fences, it cannot be made sound ! This is noted
in the C++11 standard (section 29.3, page 1140):
```
Fences cannot, in general, be used to restore sequential consistency for atomic
operations with weaker ordering semantics.
```
It can also be seen by the following example (called IRIW in the litterature):
```
atomic<int> x = y = 0;
int r1, r2, r3, r4;
Thread 0:
x.store(1);
Thread 1:
y.store(1);
Thread 2:
r1 = x.load();
r2 = y.load();
Thread 3:
r3 = y.load();
r4 = x.load();
```
r1 = r3 = 1 and r2 = r4 = 0 is impossible as long as the accesses are all seq_cst.
But if they are lowered to monotonic accesses, no amount of fences can prevent it..
This patch does three things (I could cut it into parts, but then some of them
would not be tested/testable, please tell me if you would prefer that):
- it provides a default implementation for emitLeadingFence/emitTrailingFence in
terms of IR-level fences, that mimic the original logic of SelectionDAGBuilder.
As we saw above, this is unsound, but the best that can be done without knowing
the targets well (and there is a comment warning about this risk).
- it then switches Mips/Sparc/XCore to use AtomicExpand, relying on this default
implementation (that exactly replicates the logic of SelectionDAGBuilder, so no
functional change)
- it finally erase this logic from SelectionDAGBuilder as it is dead-code.
Ideally, each target would define its own override for emitLeading/TrailingFence
using target-specific fences, but I do not know the Sparc/Mips/XCore memory model
well enough to do this, and they appear to be dealing fine with the ARM-inspired
default expansion for now (probably because they are overly conservative, as
Power was). If anyone wants to compile fences more agressively on these
platforms, the long comment should make it clear why he should first override
emitLeading/TrailingFence.
Test Plan: make check-all, no functional change
Reviewers: jfb, t.p.northover
Subscribers: aemerson, llvm-commits
Differential Revision: http://reviews.llvm.org/D5474
llvm-svn: 219957
When the constant divisor was larger than 32bits, then the optimized code
generated for the AArch64 backend would emit the wrong code, because the shift
was defined as a shift of a 32bit constant '(1<<Lg2(divisor))' and we would
loose the upper 32bits.
This fixes rdar://problem/18678801.
llvm-svn: 219934
Summary:
In order to support big endian targets for the BuildPairF64 nodes we
just need to swap the low/high pair registers. Additionally, for the
ExtractElementF64 nodes we have to calculate the correct stack offset
with respect to the node's register/operand that we want to extract.
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D5753
llvm-svn: 219931
In AVX512f we support 64x2 and 32x8 inserts via matching them to 32x4 and 64x4
respectively. These are matched by "Alt" Pat<>'s (Alt stands for alternative
VTs).
Since DQ has native support for these intructions, I peeled off the non-"Alt"
part of the baseclass into vinsert_for_size_no_alt. The DQ instructions are
derived from this multiclass. The "Alt" Pat<>'s are disabled with DQ.
Fixes <rdar://problem/18426089>
llvm-svn: 219874
The SelectDS1Addr1Offset complex pattern always tries to store constant
lds pointers in the offset operand and store a zero value in the addr operand.
Since the addr operand does not accept immediates, the zero value
needs to first be copied to a register.
This newly created zero value will not go through normal instruction
selection, so we need to manually insert a V_MOV_B32_e32 in the complex
pattern.
This bug was hidden by the fact that if there was another zero value
in the DAG that had not been selected yet, then the CSE done by the DAG
would use the unselected node for the addr operand rather than the one
that was just created. This would lead to the zero value being selected
and the DAG automatically inserting a V_MOV_B32_e32 instruction.
llvm-svn: 219848
This is mostly a copy of the existing FastISel GEP code, but we have to
duplicate it for AArch64, because otherwise we would bail out even for simple
cases. This is because the standard fastEmit functions don't cover MUL at all
and ADD is lowered very inefficientily.
The original commit had a bug in the add emit logic, which has been fixed.
llvm-svn: 219831
Summary:
Fixes a FIXME in MachineSinking. Instead of using the simple heuristics in
isPostDominatedBy, use the real MachinePostDominatorTree and MachineLoopInfo.
The old heuristics caused instructions to sink unnecessarily, and might create
register pressure.
This is the second try of the fix. The first one (D4814) caused a performance
regression due to failing to sink instructions out of loops (PR21115). This
patch fixes PR21115 by sinking an instruction from a deeper loop to a shallower
one regardless of whether the target block post-dominates the source.
Thanks Alexey Volkov for reporting PR21115!
Test Plan:
Added a NVPTX codegen test to verify that our change prevents the backend from
over-sinking. It also shows the unnecessary register pressure caused by
over-sinking.
Added an X86 test to verify we can sink instructions out of loops regardless of
the dominance relationship. This test is reduced from Alexey's test in PR21115.
Updated an affected test in X86.
Also ran SPEC CINT2006 and llvm-test-suite for compilation time and runtime
performance. Results are attached separately in the review thread.
Reviewers: Jiangning, resistor, hfinkel
Reviewed By: hfinkel
Subscribers: hfinkel, bruno, volkalexey, llvm-commits, meheff, eliben, jholewinski
Differential Revision: http://reviews.llvm.org/D5633
llvm-svn: 219773
Peephole optimization that generates a single conditional branch
for csinc-branch sequences like in the examples below. This is
possible when the csinc sets or clears a register based on a condition
code and the branch checks that register. Also the condition
code may not be modified between the csinc and the original branch.
Examples:
1. Convert csinc w9, wzr, wzr, <CC>;tbnz w9, #0, 0x44
to b.<invCC>
2. Convert csinc w9, wzr, wzr, <CC>; tbz w9, #0, 0x44
to b.<CC>
rdar://problem/18506500
llvm-svn: 219742
Patch to provide shuffle decodes and asm comments for the sse pslldq/psrldq SSE2/AVX2 byte shift instructions.
Differential Revision: http://reviews.llvm.org/D5598
llvm-svn: 219738
Thumb1 has legitimate reasons for preferring 32-bit alignment of types
i1/i8/i16, since the 16-bit encoding of "add rD, sp, #imm" requires #imm to be
a multiple of 4. However, this is a trade-off betweem code size and RAM usage;
the DataLayout string is not the best place to represent it even if desired.
So this patch removes the extra Thumb requirements, hopefully making ARM and
Thumb completely compatible in this respect.
llvm-svn: 219734
There's no hard requirement on LLVM to align local variable to 32-bits, so the
Thumb1 frame handling needs to be able to deal with variables that are only
naturally aligned without falling over.
llvm-svn: 219733
This is mostly a copy of the existing FastISel GEP code, but on AArch64 we bail
out even for simple cases, because the standard fastEmit functions don't cover
MUL and ADD is lowered inefficientily.
llvm-svn: 219726
Before, ARM and Thumb mode code had different preferred alignments, which could
lead to some rather unexpected results. There's justification for reducing it
from the default 64-bits (wasted space), but I don't think there is for going
below 32-bits.
There's no actual ABI change here, just to reassure people.
llvm-svn: 219719
Sign-/zero-extend folding depended on the load and the integer extend to be
both selected by FastISel. This cannot always be garantueed and SelectionDAG
might interfer. This commit adds additonal checks to load and integer extend
lowering to catch this.
Related to rdar://problem/18495928.
llvm-svn: 219716
This effectively reverts revert 219707. After fixing the test to work with
new function name format and renamed intrinsic.
Reviewed-by: Tom Stellard <tom@stellard.net>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 219710
v2: Add SI lowering
Add test
v3: Place work dimensions after the kernel arguments.
v4: Calculate offset while lowering arguments
v5: rebase
v6: change prefix to AMDGPU
Reviewed-by: Tom Stellard <tom@stellard.net>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 219705
e.g Currently we'll generate following instructions if the immediate is too wide:
MOV X0, WideImmediate
ADD X1, BaseReg, X0
LDR X2, [X1, 0]
Using [Base+XReg] addressing mode can save one ADD as following:
MOV X0, WideImmediate
LDR X2, [BaseReg, X0]
Differential Revision: http://reviews.llvm.org/D5477
llvm-svn: 219665
Some early revisions of the Cortex-A53 have an erratum (835769) whereby it is
possible for a 64-bit multiply-accumulate instruction in AArch64 state to
generate an incorrect result. The details are quite complex and hard to
determine statically, since branches in the code may exist in some
circumstances, but all cases end with a memory (load, store, or prefetch)
instruction followed immediately by the multiply-accumulate operation.
The safest work-around for this issue is to make the compiler avoid emitting
multiply-accumulate instructions immediately after memory instructions and the
simplest way to do this is to insert a NOP.
This patch implements such work-around in the backend, enabled via the option
-aarch64-fix-cortex-a53-835769.
The work-around code generation is not enabled by default.
llvm-svn: 219603
This patch improves support for commutative instructions in the x86 memory folding implementation by attempting to fold a commuted version of the instruction if the original folding fails - if that folding fails as well the instruction is 're-commuted' back to its original order before returning.
This mainly helps the stack inliner better fold reloads of 3 (or more) operand instructions (VEX encoded SSE etc.) but by performing this in the lowest foldMemoryOperandImpl implementation it also replaces the X86InstrInfo::optimizeLoadInstr version and is now used by FastISel too.
Differential Revision: http://reviews.llvm.org/D5701
llvm-svn: 219584
Summary: Implement the most basic form of conditional branches in Mips fast-isel.
Test Plan:
br1.ll
run 4 flavors of test-suite. mips32 r1/r2 and at -O0/O2
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: llvm-commits, rfuhler
Differential Revision: http://reviews.llvm.org/D5583
llvm-svn: 219556
Currently this only functions to match simple cases
where ds_read2_* / ds_write2_* instructions can be used.
In the future it might match some of the other weird
load patterns, such as direct to LDS loads.
Currently enabled only with a subtarget feature to enable
easier testing.
llvm-svn: 219533
Fixes a logic error in the MachineScheduler found by Steve Montgomery (and
confirmed by Andy). This has gone unfixed for months because the fix has been
found to introduce some small performance regressions. However, Andy has
recommended that, at this point, we fix this to avoid further dependence on the
incorrect behavior (and then follow-up separately on any regressions), and I
agree.
Fixes PR18883.
llvm-svn: 219512
Summary: Add the ability to convert 64 or 32 bit floating point values to integer in mips fast-isel
Test Plan:
fpintconv.ll
ran 4 flavors of test-suite with no errors, misp32 r1/r2 O0/O2
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: llvm-commits, rfuhler, mcrosier
Differential Revision: http://reviews.llvm.org/D5562
llvm-svn: 219511
This patch changes the fast-math implementation for calculating sqrt(x) from:
y = 1 / (1 / sqrt(x))
to:
y = x * (1 / sqrt(x))
This has 2 benefits: less code / faster code and one less estimate instruction
that may lose precision.
The only target that will be affected (until http://reviews.llvm.org/D5658 is approved)
is PPC. The difference in codegen for PPC is 2 less flops for a single-precision sqrtf
or vector sqrtf and 4 less flops for a double-precision sqrt.
We also eliminate a constant load and extra register usage.
Differential Revision: http://reviews.llvm.org/D5682
llvm-svn: 219445
The current implementation of GPR->FPR register moves uses a stack slot. This mechanism writes a double word and reads a word. In big-endian the load address must be displaced by 4-bytes in order to get the right value. In little endian this is no longer required. This patch fixes the issue and adds LE regression tests to fast-isel-conversion which currently expose this problem.
llvm-svn: 219441
LLVM assumes INSERT_SUBREG will always have register operands, so
we need to legalize non-register operands, like FrameIndexes, to
avoid random assertion failures.
llvm-svn: 219420
This adds the Pat<>'s for the intrinsics. These are necessary because we
don't lower these intrinsics to SDNodes but match them directly. See the
rational in the previous commit.
llvm-svn: 219362
Summary:
I had forgotten to check for NotSlowIncDec in the patterns that can generate
inc/dec for the above pattern (added in D4796).
This currently applies to Atom Silvermont, KNL and SKX.
Test Plan: New checks on atomic_mi.ll
Reviewers: jfb, nadav
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D5677
llvm-svn: 219336
Summary:
Fix pr21099
The pseudocode of what we were doing (spread through two functions) was:
if (operand.doesNotFitIn32Bits())
Opc.initializeWithFoo();
if (operand < 0)
operand = -operand;
if (operand.doesFitIn8Bits())
Opc.initializeWithBar();
else if (operand.doesFitIn32Bits())
Opc.initializeWithBlah();
doStuff(Opc);
So for operand == INT32_MIN, Opc was never initialized because the operand changes
from fitting in 32 bits to not fitting, causing the various bugs/error messages
noted by pr21099.
This patch adds an extra test at the beginning for this case, and an
llvm_unreachable to have better error message if the operand ends up
not fitting in 32-bits at the end.
Test Plan: new test + make check
Reviewers: jfb
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D5655
llvm-svn: 219257
Added a FIXME coment instead, we need to handle the case where the
two DS instructions being compared have different numbers of operands.
llvm-svn: 219236
Summary:
According to the ABI documentation, f128 and {f128} should both be returned
in $f0 and $f2. However, this doesn't match GCC's behaviour which is to
return f128 in $f0 and $f2, but {f128} in $f0 and $f1.
Reviewers: vmedic
Reviewed By: vmedic
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D5578
llvm-svn: 219196
The code already folds sign-/zero-extends, but only if they are arguments to
mul and shift instructions. This extends the code to also fold them when they
are direct inputs.
llvm-svn: 219187
Tiny enhancement to the address computation code to also fold sub instructions
if the rhs is constant and can be folded into the offset.
llvm-svn: 219186
This commit fixes an issue with sign-/zero-extending loads that was discovered
by Richard Barton.
We use now the correct load instructions for sign-extending loads to 64bit. Also
updated and added more unit tests.
llvm-svn: 219185
The patch's author points out that, despite the function's documentation,
getSetCCResultType is only used to get the SETCC result type (with one
here-removed problematic exception). In one case, getSetCCResultType was being
used to get the predicate type to use for a SELECT node, and then
SIGN_EXTENDing (or truncating) to get the input predicate to match that type.
Unfortunately, this was happening inside visitSIGN_EXTEND, and creating new
SIGN_EXTEND nodes was causing an infinite loop. In addition, this behavior was
wrong if a target was not using ZeroOrNegativeOneBooleanContent. Lastly, the
extension/truncation seems unnecessary here: SELECT is defined as:
Select(COND, TRUEVAL, FALSEVAL). If the type of the boolean COND is not i1
then the high bits must conform to getBooleanContents.
So here we remove this use of getSetCCResultType and update
getSetCCResultType's documentation to reflect its actual uses.
Patch by deadal nix!
llvm-svn: 219141
This trades a (register-renamer-friendly) movaps for a floating point
/ integer domain cross. That is a very bad trade, even on architectures
where domain crossing is relatively fast. On any chip where there is
even a cycle stall, this is a Very Bad Idea. It doesn't even seem likely
to cause a spill to be introduced because the reason for the copy is to
destructively shuffle in place.
Thanks to Ben Kramer for fixing a bug in this code that my new shuffle
lowering exposed and highlighting that perhaps it should just go away.
=]
llvm-svn: 219090
that are unused.
This allows the combiner to delete math feeding shuffles where the math
isn't actually necessary. This improves some of the vperm2x128 tests
that regressed when the vector shuffle lowering started actually
generating vperm instructions rather than forcibly decomposing them.
Sadly, this isn't enough to get this *really* right because we still
form a completely unnecessary permutation. To fix that, we also need to
fold shuffles which just rearrange concatenated or inserted subvectors.
llvm-svn: 219086
new vector shuffle lowering.
This is loosely based on a patch by Marius Wachtler to the PR (thanks!).
I refactored it a bi to use std::count_if and a mutable array ref but
the core idea was exactly right. I also added some direct testing of
this case.
I believe PR21137 is now the only remaining regression.
llvm-svn: 219081
shuffles using AVX and AVX2 instructions. This fixes PR21138, one of the
few remaining regressions impacting benchmarks from the new vector
shuffle lowering.
You may note that it "regresses" many of the vperm2x128 test cases --
these were actually "improved" by the naive lowering that the new
shuffle lowering previously did. This regression gave me fits. I had
this patch ready-to-go about an hour after flipping the switch but
wasn't sure how to have the best of both worlds here and thought the
correct solution might be a completely different approach to lowering
these vector shuffles.
I'm now convinced this is the correct lowering and the missed
optimizations shown in vperm2x128 are actually due to missing
target-independent DAG combines. I've even written most of the needed
DAG combine and will submit it shortly, but this part is ready and
should help some real-world benchmarks out.
llvm-svn: 219079
Update the entire regression test suite for the new shuffles. Remove
most of the old testing which was devoted to the old shuffle lowering
path and is no longer relevant really. Also remove a few other random
tests that only really exercised shuffles and only incidently or without
any interesting aspects to them.
Benchmarking that I have done shows a few small regressions with this on
LNT, zero measurable regressions on real, large applications, and for
several benchmarks where the loop vectorizer fires in the hot path it
shows 5% to 40% improvements for SSE2 and SSE3 code running on Sandy
Bridge machines. Running on AMD machines shows even more dramatic
improvements.
When using newer ISA vector extensions the gains are much more modest,
but the code is still better on the whole. There are a few regressions
being tracked (PR21137, PR21138, PR21139) but by and large this is
expected to be a win for x86 generated code performance.
It is also more correct than the code it replaces. I have fuzz tested
this extensively with ISA extensions up through AVX2 and found no
crashes or miscompiles (yet...). The old lowering had a few miscompiles
and crashers after a somewhat smaller amount of fuzz testing.
There is one significant area where the new code path lags behind and
that is in AVX-512 support. However, there was *extremely little*
support for that already and so this isn't a significant step backwards
and the new framework will probably make it easier to implement lowering
that uses the full power of AVX-512's table-based shuffle+blend (IMO).
Many thanks to Quentin, Andrea, Robert, and others for benchmarking
assistance. Thanks to Adam and others for help with AVX-512. Thanks to
Hal, Eric, and *many* others for answering my incessant questions about
how the backend actually works. =]
I will leave the old code path in the tree until the 3 PRs above are at
least resolved to folks' satisfaction. Then I will rip it (and 1000s of
lines of code) out. =] I don't expect this flag to stay around for very
long. It may not survive next week.
llvm-svn: 219046
the various ways in which blends can be used to do vector element
insertion for lowering with the scalar math instruction forms that
effectively re-blend with the high elements after performing the
operation.
This then allows me to bail on the element insertion lowering path when
we have SSE4.1 and are going to be doing a normal blend, which in turn
restores the last of the blends lost from the new vector shuffle
lowering when I got it to prioritize insertion in other cases (for
example when we don't *have* a blend instruction).
Without the patterns, using blends here would have regressed
sse-scalar-fp-arith.ll *completely* with the new vector shuffle
lowering. For completeness, I've added RUN-lines with the new lowering
here. This is somewhat superfluous as I'm about to flip the default, but
hey, it shows that this actually significantly changed behavior.
The patterns I've added are just ridiculously repetative. Suggestions on
making them better very much welcome. In particular, handling the
commuted form of the v2f64 patterns is somewhat obnoxious.
llvm-svn: 219033
perform a load to use blendps rather than movss when it is available.
For non-loads, blendps is *much* faster. It can execute on two ports in
Sandy Bridge and Ivy Bridge, and *three* ports on Haswell. This fixes
one of the "regressions" from aggressively taking the "insertion" path
in the new vector shuffle lowering.
This does highlight one problem with blendps -- it isn't commuted as
heavily as it should be. That's future work though.
llvm-svn: 219022
This reverts commit r218918, effectively reapplying r218914 after fixing
an Ocaml bindings test and an Asan crash. The root cause of the latter
was a tightened-up check in `DILexicalBlock::Verify()`, so I'll file a
PR to investigate who requires the loose check (and why).
Original commit message follows.
--
This patch addresses the first stage of PR17891 by folding constant
arguments together into a single MDString. Integers are stringified and
a `\0` character is used as a separator.
Part of PR17891.
Note: I've attached my testcases upgrade scripts to the PR. If I've
just broken your out-of-tree testcases, they might help.
llvm-svn: 219010
In the X86 backend, matching an address is initiated by the 'addr' complex
pattern and its friends. During this process we may reassociate and-of-shift
into shift-of-and (FoldMaskedShiftToScaledMask) to allow folding of the
shift into the scale of the address.
However as demonstrated by the testcase, this can trigger CSE of not only the
shift and the AND which the code is prepared for but also the underlying load
node. In the testcase this node is sitting in the RecordedNode and MatchScope
data structures of the matcher and becomes a deleted node upon CSE. Returning
from the complex pattern function, we try to access it again hitting an assert
because the node is no longer a load even though this was checked before.
Now obviously changing the DAG this late is bending the rules but I think it
makes sense somewhat. Outside of addresses we prefer and-of-shift because it
may lead to smaller immediates (FoldMaskAndShiftToScale is an even better
example because it create a non-canonical node). We currently don't recognize
addresses during DAGCombiner where arguably this canonicalization should be
performed. On the other hand, having this in the matcher allows us to cover
all the cases where an address can be used in an instruction.
I've also talked a little bit to Dan Gohman on llvm-dev who added the RAUW for
the new shift node in FoldMaskedShiftToScaledMask. This RAUW is responsible
for initiating the recursive CSE on users
(http://lists.cs.uiuc.edu/pipermail/llvmdev/2014-September/076903.html) but it
is not strictly necessary since the shift is hooked into the visited user. Of
course it's safer to keep the DAG consistent at all times (e.g. for accurate
number of uses, etc.).
So rather than changing the fundamentals, I've decided to continue along the
previous patches and detect the CSE. This patch installs a very targeted
DAGUpdateListener for the duration of a complex-pattern match and updates the
matching state accordingly. (Previous patches used HandleSDNode to detect the
CSE but that's not practical here). The listener is only installed on X86.
I tested that there is no measurable overhead due to this while running
through the spec2k BC files with llc. The only thing we pay for is the
creation of the listener. The callback never ever triggers in spec2k since
this is a corner case.
Fixes rdar://problem/18206171
llvm-svn: 219009
The test Atomics-32.ll was both redundant (all operations are also checked by
atomics.ll at least) and not actually checking correctness (it was not using
FileCheck, just verifying that the compiler does not crash).
llvm-svn: 218997
Summary:
hwsync is only required for seq_cst fences, acquire and release one can use
the cheaper lwsync.
Test Plan: Added some cases to atomics.ll + make check-all
Reviewers: jfb, wschmidt
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D5317
llvm-svn: 218995
and MOVSD nodes for single element vector inserts.
This is particularly important because a number of patterns in the
backend detect these patterns and leverage them to simplify things. It
also fixes quite a few of the insertion bad code examples. However, it
regresses a specific area: when available, blendps and blendpd are
*dramatically* faster than movss and movsd respectively. But it doesn't
really work to form the blend logic first because the blends *aren't* as
crazy efficient when the data is coming from memory anyways, and thus
will have a movss or movsd regardless. Also, doing that would block
a bunch of the patterns that this is designed to hit.
So my plan is to go into the patterns for lowering MOVSS and MOVSD and
lower them via blends when available. However that's a pretty invasive
restructuring so it will need to be a follow-up patch.
I have already gone into the patterns to lower MOVSS and MOVSD from
memory using MOVLPD, etc. Without that, several of the test cases
I already have regress.
llvm-svn: 218985
That commit was introduced in order to help investigate a problem in ARM
codegen breaking from commit 202304 (Add a limit to the heuristic that register
allocates instructions in local order). Recent analisys indicated that the
problem no longer exists, so I'm reverting this change.
See PR18996.
llvm-svn: 218981
I got them quite wrong when updating it and had the SSE4.1 run checked
for SSE2 and the SSE2 run checked for SSE4.1. I think everything was
actually generic SSE, but this still seems good to fix. While here,
hoist the triple into the IR and make the flag set a bit more direct in
what it is trying to test.
llvm-svn: 218978
lowering to match VZEXT_MOVL patterns.
I hadn't realized that these had sufficient pattern smarts in the
backend to lower zext-ing from the low element of a vector without it
being a scalar_to_vector node. They do, and this is how to match a bunch
of patterns for movq, movss, etc.
There is a weird propensity to end up using pshufd to place the element
afterward even though it means domain crossing (or rather, to use
xorps+movss to zext the element rather than movq) but that's an
orthogonal problem with VZEXT_MOVL that someone should probably look at.
llvm-svn: 218977
vector to a zero vector for the v2 cases and fix the v4 integer cases to
actually blend from a vector.
There are already seprate tests for the case of inserting from a scalar.
These cases cover a lot of the regressions I've seen in the regression
test suite for the new vector shuffle lowering and specifically cover
the reported lack of using various zext-ing instruction patterns. My
next patch should fix a big chunk of this, but wanted to get a nice
baseline for these patterns in the test cases first.
llvm-svn: 218976
element types to form illegal vector types.
I've added a special SSE1 test case here that makes sure we don't break
this going forward.
llvm-svn: 218974
testing that we generated divps and divss but not in a very systematic
way. There are other tests for widening binary operations already that
make these unnecessary.
The second one seems mostly about testing Atom as well as normal X86,
but despite the comment claiming it is testing a different instruction
sequence, it then tests for exactly the same div instruction sequence!
(The sequence of instructions is actually quite different on Atom, but
not the sequence of div instructions....)
And then it has an "execution" test that simply isn't run? Very strange.
Anyways, none of this is really needed so clean this up.
llvm-svn: 218972
intergrated much more fully into some logical part of the backend to
really understand what it is trying to accomplish and how to update it.
I suspect it no longer holds enough value to be worth having.
llvm-svn: 218950
shufle switch.
I nuked a win64 config from one test as it doesn't really make sense to
cover that ABI specially for generic v2f32 tests...
llvm-svn: 218948
test cases that will change with the new vector shuffle lowering. This
gives us a nice baseline for deltas against. I've checked and removed
the cases where there were weird register usage being pinned down, and
all of these are extremely pin-pointed tests so fully checking them
seems very appropriate.
llvm-svn: 218941
tighter, more strict FileCheck assertions. Some of these I really like
as they show case exactly what instruction sequences come out of these
microscopic functionality tests.
llvm-svn: 218936
baseline for updates from the new vector shuffle lowering.
I've inspected the results here, and I couldn't find any register
allocation decisions where there should be any realistic way to register
allocate things differently. The closest was the imul test case. If you
see something here you'd like register number variables on, just shout
and I'll add them.
llvm-svn: 218935
need to be updated for the new vector shuffle lowering.
After talking to Adam Nemet, Tim Northover, etc., it seems that testing
MC encodings in the same suite as the basic codegen isn't the right
approach. Instead, we're going to want dedicated MC tests for the
encodings. These encodings are starting to get in my way so I wanted to
cut them out early. The total set of instructions that should have
encoding tests added is:
vpaddd
vsqrtss
vsqrtsd
vmovlhps
vmovhlps
valignq
vbroadcastss
Not too many parts of these tests were even using this. =]
llvm-svn: 218932
Older Book-E cores, such as the PPC 440, support only msync (which has the same
encoding as sync 0), but not any of the other sync forms. Newer Book-E cores,
however, do support sync, and for performance reasons we should allow the use
of the more-general form.
This refactors msync use into its own feature group so that it applies by
default only to older Book-E cores (of the relevant cores, we only have
definitions for the PPC440/450 currently).
llvm-svn: 218923
Summary:
Atomic loads and store of up to the native size (32 bits, or 64 for PPC64)
can be lowered to a simple load or store instruction (as the synchronization
is already handled by AtomicExpand, and the atomicity is guaranteed thanks to
the alignment requirements of atomic accesses). This is exactly what this patch
does. Previously, these were implemented by complex
load-linked/store-conditional loops.. an obvious performance problem.
For example, this patch turns
```
define void @store_i8_unordered(i8* %mem) {
store atomic i8 42, i8* %mem unordered, align 1
ret void
}
```
from
```
_store_i8_unordered: ; @store_i8_unordered
; BB#0:
rlwinm r2, r3, 3, 27, 28
li r4, 42
xori r5, r2, 24
rlwinm r2, r3, 0, 0, 29
li r3, 255
slw r4, r4, r5
slw r3, r3, r5
and r4, r4, r3
LBB4_1: ; =>This Inner Loop Header: Depth=1
lwarx r5, 0, r2
andc r5, r5, r3
or r5, r4, r5
stwcx. r5, 0, r2
bne cr0, LBB4_1
; BB#2:
blr
```
into
```
_store_i8_unordered: ; @store_i8_unordered
; BB#0:
li r2, 42
stb r2, 0(r3)
blr
```
which looks like a pretty clear win to me.
Test Plan:
fixed the tests + new test for indexed accesses + make check-all
Reviewers: jfb, wschmidt, hfinkel
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D5587
llvm-svn: 218922
Do not eliminate the frame pointer if there is a stackmap or patchpoint in the
function. All stackmap references should be FP relative.
This fixes PR21107.
llvm-svn: 218920
This patch addresses the first stage of PR17891 by folding constant
arguments together into a single MDString. Integers are stringified and
a `\0` character is used as a separator.
Part of PR17891.
Note: I've attached my testcases upgrade scripts to the PR. If I've
just broken your out-of-tree testcases, they might help.
llvm-svn: 218914
elements as well as integer elements in order to form simpler shuffle
patterns.
This is the primary reason why we were failing to match some of the
2-and-2 floating point shuffles such as PR21140. Even after fixing this
we need to support some extra patterns in the backend in order to match
the resulting X86ISD::UNPCKL nodes into the correct instructions. This
commit should fix PR21140 and includes more comprehensive testing of
insertion patterns in v4 shuffles.
Not all of the added tests are beautiful. For example, we don't have
clever instructions to insert-via-load in the integer domain. There are
also some places where we aren't sufficiently cunning with our use of
movq and movd, but that's future work.
llvm-svn: 218911
floating point and integer domains.
Merge the AVX2 test into it and add an extra RUN line. Generate clean
FileCheck statements with my script. Remove the now merged AVX2 tests.
llvm-svn: 218903
This file isn't really doing anything useful. Many of the tests that
seem to be combined are also repeats from other test files. Many of the
other tests, despite the comment that they should be combined into
a single shuffle... well... aren't combined into a single shuffle.
=/
llvm-svn: 218862
least seem *slightly* more interesting test wise, although given how
spotily we actually combine anything, I remain somewhat suspicious.
llvm-svn: 218861
checks for all the ISA variants.
If the SSE2 checks here terrify you, good. This is (in large part) the
kind of amazingly bad code that is holding LLVM back when vectorizing on
older ISAs.
At the same time, these tests seem increasingly dubious to me. There are
a very large number of tests and it isn't clear that they are
systematically covering a specific set of functionality. Anyways,
I don't want to reduce testing during the transition, I just want to
consolidate it to where it is easier to manage.
llvm-svn: 218860
file.
Some of these really don't make sense to test -- we're testing for the
*lack* of combining two shuffles into one, presumably because the two
would generate better shuffles in the end. But if you look at the
generated code shown here, in many cases the generated code is, frankly,
terrible. Or we combine any two generated shuffles back into a single
instruction! I've left a FIXME to revisit these decisions.
llvm-svn: 218859
and use the new grouped FileCheck patterns to match them.
No interesting changes yet, but this test is now in proper form to have
the other shuffle combining tests merged into it.
llvm-svn: 218857
The test has to do with DAG combines, and so it doesn't need the new
vector shuffle lowering to be effective. Also, it has a nice in-IR
triple string which we should really be using rather than command line
flags (unless it varies form RUN-line to RUN-line). Finally, I much
prefer letting LLVM synthesize the correct datalayout string from the
triple rather than baking one in here that will just become stale.
llvm-svn: 218856
generic DAG combining of shuffles relevant to x86.
My plan is to fold a bunch of the other DAG combining test cases into
this one, while converting them to use the nice new FileCheck assertion
syntax.
llvm-svn: 218855
a bare-metal triple and have nice BB labels, etc.
No significant change here, just tidying up to have a consistent set of
OS-agnostic vector functionality here.
llvm-svn: 218854
matching and lowering 64-bit insertions.
The first problem was that we weren't looking through bitcasts to
discover that we *could* lower as insertions. Once fixed, we in turn
weren't looking through bitcasts to discover that we could fold a load
into the lowering. Once fixed, we weren't forming a SCALAR_TO_VECTOR
node around the inserted element and instead were passing a scalar to
a DAG node that expected a vector. It turns out there are some patterns
that will "lower" this into the correct asm, but the rest of the X86
backend is very unhappy with such antics.
This should fix a few more edge case regressions I've spotted going
through the regression test suite to enable the new vector shuffle
lowering.
llvm-svn: 218839
Negative FABS of either a scalar or vector should be handled the same way
on x86 with SSE/AVX: a single OR instruction of the FP operand with a
constant to light up the sign bit(s).
http://llvm.org/bugs/show_bug.cgi?id=20578
Differential Revision: http://reviews.llvm.org/D5201
llvm-svn: 218822
test file.
This old test had a bunch of functions that were never even checked. =/
The only thing it really did was to make sure that we did something
reasonable in 32-bit mode with SSE4.1. Adding another run line to the
main vector-sext.ll test seems a better way to do that.
llvm-svn: 218810
of architectures: SSE2, SSSE3, SSE4.1, AVX, and AVX2.
Unfortunately, this exposses the absolute horror of the code we generate
for many of these patterns. Anyone wanting to familiarize themselves
with the x86 backend and improve performance could do a lot of good
sitting down and making these test cases not look so terrible. While the
new vector shuffle code I'm working on well help some, it won't fix all
of the crimes here.
llvm-svn: 218807
These tests are far and away the best sext and zext tests we have for
vectors. I'm going to merge the other similar tests into them and expand
the ISA coverage.
llvm-svn: 218800
script to make them nice and predictable. This will ease updating them
for the new vector shuffle lowering and seeing the delta if any.
llvm-svn: 218795
avx-sext.ll using my new script.
Also add an AVX2 mode to this test.
Part of cleaning up the test suite before enabling the new vector
shuffle lowering. This also highlights some of the abysmal failures of
the old shuffle lowering. Check out those 'pinsrw' and 'pextrw'
sequences!
llvm-svn: 218794
As with x86 and AArch64, certain situations can arise where we need to spill
CPSR in the middle of a calculation. These should be avoided where possible
(MRS/MSR is rather expensive), which ARM is actually better at than the other
two since it tries to Glue defs to uses, but as a last ditch effort, copying is
better than crashing.
rdar://problem/18011155
llvm-svn: 218789
argument of the llvm.dbg.declare/llvm.dbg.value intrinsics.
Previously, DIVariable was a variable-length field that has an optional
reference to a Metadata array consisting of a variable number of
complex address expressions. In the case of OpPiece expressions this is
wasting a lot of storage in IR, because when an aggregate type is, e.g.,
SROA'd into all of its n individual members, the IR will contain n copies
of the DIVariable, all alike, only differing in the complex address
reference at the end.
By making the complex address into an extra argument of the
dbg.value/dbg.declare intrinsics, all of the pieces can reference the
same variable and the complex address expressions can be uniqued across
the CU, too.
Down the road, this will allow us to move other flags, such as
"indirection" out of the DIVariable, too.
The new intrinsics look like this:
declare void @llvm.dbg.declare(metadata %storage, metadata %var, metadata %expr)
declare void @llvm.dbg.value(metadata %storage, i64 %offset, metadata %var, metadata %expr)
This patch adds a new LLVM-local tag to DIExpressions, so we can detect
and pretty-print DIExpression metadata nodes.
What this patch doesn't do:
This patch does not touch the "Indirect" field in DIVariable; but moving
that into the expression would be a natural next step.
http://reviews.llvm.org/D4919
rdar://problem/17994491
Thanks to dblaikie and dexonsmith for reviewing this patch!
Note: I accidentally committed a bogus older version of this patch previously.
llvm-svn: 218787
Summary: Implement conversion of 64 to 32 bit floating point numbers (fptrunc) in mips fast-isel
Test Plan:
fptrunc.ll
checked also with 4 internal mips build bot flavors mip32r1/miprs32r2 and at -O0 and -O2
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: rfuhler
Differential Revision: http://reviews.llvm.org/D5553
llvm-svn: 218785
argument of the llvm.dbg.declare/llvm.dbg.value intrinsics.
Previously, DIVariable was a variable-length field that has an optional
reference to a Metadata array consisting of a variable number of
complex address expressions. In the case of OpPiece expressions this is
wasting a lot of storage in IR, because when an aggregate type is, e.g.,
SROA'd into all of its n individual members, the IR will contain n copies
of the DIVariable, all alike, only differing in the complex address
reference at the end.
By making the complex address into an extra argument of the
dbg.value/dbg.declare intrinsics, all of the pieces can reference the
same variable and the complex address expressions can be uniqued across
the CU, too.
Down the road, this will allow us to move other flags, such as
"indirection" out of the DIVariable, too.
The new intrinsics look like this:
declare void @llvm.dbg.declare(metadata %storage, metadata %var, metadata %expr)
declare void @llvm.dbg.value(metadata %storage, i64 %offset, metadata %var, metadata %expr)
This patch adds a new LLVM-local tag to DIExpressions, so we can detect
and pretty-print DIExpression metadata nodes.
What this patch doesn't do:
This patch does not touch the "Indirect" field in DIVariable; but moving
that into the expression would be a natural next step.
http://reviews.llvm.org/D4919
rdar://problem/17994491
Thanks to dblaikie and dexonsmith for reviewing this patch!
llvm-svn: 218778
Currently, we only codegen the VRINT[APMXZR] and VCVT[BT] instructions
when targeting ARMv8, but they are actually present on any target with
FP-ARMv8. Note that FP-ARMv8 is called FPv5 when is is part of an
M-profile core, but they have the same instructions so we model them
both as FPARMv8 in the ARM backend.
llvm-svn: 218763
that keep cropping up in the regression test suite.
This also addresses one of the issues raised on the mailing list with
failing to form 'movsd' in as many cases as we realistically should.
There will be corresponding patches forthcoming for v4f32 at least. This
was a lot of fuss for a relatively small gain, but all the fuss was on
my end trying different ways of holding the pieces of the x86 fragment
patterns *just right*. Now that it works, the code is reasonably simple.
In the new test cases I'm adding here, v2i64 sticks out as just plain
horrible. I've not come up with any great ideas here other than that it
would be nice to recognize when we're *going* to take a domain crossing
hit and cross earlier to get the decent instructions. At least with AVX
it is slightly less silly....
llvm-svn: 218756
Summary: The natual vector cast node (similar to bitcast) AArch64ISD::NVCAST
was introduced in r217159 and r217138. This patch adds a missing cast from
v2f32 to v1i64 which is causing some compilation failures. Also added test
cases to cover various modimm types and BUILD_VECTORs with i64 elements.
llvm-svn: 218751
The Cortex-M7 has 3 options for its FPU: none, FPv5-SP-D16 and
FPv5-DP-D16. FPv5 has the same instructions as FP-ARMv8, so it can be
modelled using the same target feature, and all double-precision
operations are already disabled by the fp-only-sp target features.
llvm-svn: 218747
doesn't generate lazy binding stub for a function whose address is taken in
the program.
Differential Revision: http://reviews.llvm.org/D5067
llvm-svn: 218744
in exposing the scalar value to the broadcast DAG fragment so that we
can catch even reloads and fold them into the broadcast.
This is somewhat magical I'm afraid but seems to work. It is also what
the old lowering did, and I've switched an old test to run both
lowerings demonstrating that we get the same result.
Unlike the old code, I'm not lowering f32 or f64 scalars through this
path when we only have AVX1. The target patterns include pretty heinous
code to re-cast those as shuffles when the scalar happens to not be
spilled because AVX1 provides no broadcast mechanism from registers
what-so-ever. This is terribly brittle. I'd much rather go through our
generic lowering code to get this. If needed, we can add a peephole to
get even more opportunities to broadcast-from-spill-slots that are
exposed post-RA, but my suspicion is this just doesn't matter that much.
llvm-svn: 218734
the same speed as pshufd but we can fold loads into the pmovzx
instructions.
This fixes some regressions that came up in the regression test suite
for the new vector shuffle lowering.
llvm-svn: 218733
VPBROADCAST.
This has the somewhat expected pervasive impact. I don't know why
I forgot about this. Everything seems good with lots of significant
improvements in the tests.
llvm-svn: 218724
cases.
While clearly we don't need the AVX vector width, these ISA extensions
often cause us to select different instructions and we should cover them
even with the narrow vector width.
Also, while here, nuke the stress_test2 contents. There is no reason to
try to FileCheck this entire body when it is mostly a test for
successfully surviving the code generator.
llvm-svn: 218710
shuffle tests to match that used in the script I posted and now used
consistently in 128-bit tests.
Nothing interesting changing here, just using the label name as the
FileCheck label and a slightly more general comment marker consumption
strategy.
llvm-svn: 218709
updating script so that they are more thorough and consistent.
Specific fixes here include:
- Actually test VEX-encoded AVX mnemonics.
- Actually use an SSE 4.1 run to test SSE 4.1 features!
- Correctly check instructions sequences from the start of the function.
- Elide the shuffle operands and comment designator in a consistent way.
- Test all of the architectures instead of just the ones I was motivated
to manually author.
I've gone back through and fixed up any egregious issues I spotted. Let
me know if I missed something you really dislike.
One downside to this is that we're now not as diligently using FileCheck
variables for registers. I would be much more concerned with this if we
had larger register usage, but there just aren't that interesting of
register choices here and most of the registers are constrained by the
ABI. Ultimately, I don't think this is likely to be the maintenance
burden for these tests and updating them again should be staright
forward.
llvm-svn: 218707
Note: This version fixed an issue with the TBZ/TBNZ instructions that were
generated in FastISel. The issue was that the 64bit version of TBZ (TBZX)
automagically sets the upper bit of the immediate field that is used to specify
the bit we want to test. To test for any of the lower 32bits we have to first
extract the subregister and use the 32bit version of the TBZ instruction (TBZW).
Original commit message:
Teach selectBranch to fold bit test and branch into a single instruction (TBZ or
TBNZ).
llvm-svn: 218693
Renato Golin