Many vector operations never had itineraries. Since the new machine
model was a mapping from existing itinerary classes, we don't have a
model for these. We still want to migrate A9 even though no one has
invested in a complete model, so mark it incomplete to avoid the
scheduler asserting.
llvm-svn: 198123
vector shift by immedate count (VSHLI/VSRLI/VSRAI) into a build_vector when
the vector in input to the shift is a build_vector of all constants or UNDEFs.
Target specific nodes for packed shifts by immediate count are in
general introduced by function 'getTargetVShiftByConstNode' (in
X86ISelLowering.cpp) when lowering shift operations, SSE/AVX immediate
shift intrinsics and (only in very few cases) SIGN_EXTEND_INREG dag
nodes.
This patch adds extra rules for simplifying vector shifts inside
function 'getTargetVShiftByConstNode'.
Added file test/CodeGen/X86/vec_shift5.ll to verify that packed
shifts by immediate are correctly folded into a build_vector when the
input vector to the shift dag node is a vector of constants or undefs.
llvm-svn: 198113
widespread glibc bugs.
The glibc implementation of exp10 has a very serious precision bug in
version 2.15 (and older versions). This is still very widely used (the
current Ubuntu LTS for example uses it) and so it isn't reasonable to
make transforms that produce these functions. This fixes many
miscompiles introduced when we started transforming pow(10.0, ...) into
exp10, and it may have fixed other latent miscompiles where exp10
provided sufficient precision but exp10f did not.
This is all really horrible. The primary bug has been fixed for over
a year and glibc 2.18 works correctly for the test cases I have, but it
will be 2017 before the LTS using 2.15 is no longer supported by Ubuntu
(and thus reasonable for folks to be relying on). =[ We're either going
to need to live without these optimizations, or find a way to switch
behavior more dynamically than using simply the fact that the OS is
"Linux".
To make matters worse, there appears to be significant testing and
fixing of numerous other bugs in the exp10 family of functions right now
in glibc. While those haven't been causing problems I've seen in the
wild, it gives me concerns that we may need to wait until an even later
release of glibc before we can reliably transform code into exp10.
llvm-svn: 198093
...namely LOAD AND ADD, LOAD AND AND, LOAD AND OR and LOAD AND EXCLUSIVE OR.
LOAD AND ADD LOGICAL isn't really separately useful for LLVM.
I'll look at adding reusing the CC results in new year.
llvm-svn: 197985
DAG.getVectorShuffle() doesn't always return a vector_shuffle node.
If mask is the exact sequence of it's operand(For example, operand_0
is v8i8, and the mask is 0, 1, 2, 3, 4, 5, 6, 7), it will directly
return that operand. So a check is added here.
llvm-svn: 197967
This failure caused by improper condition when lowering shuffle_vector
to scalar_to_vector. After this patch NEON_VDUP with v1i64 will not
be generated.
llvm-svn: 197966
Check for single use of fmul node in fused multiply patterns
to allow generation of fused multiply add/sub instructions.
Otherwise fmul operation ends up being repeated more than
once which does not help peformance on targets with
only one MAC unit, as for example cortex-a53.
llvm-svn: 197929
The correct pattern matching should be:
- fnmadd is (-Ra) + (-Rn)*Rm which should be matched as:
fma (fneg node:$Rn), node:$Rm, (fneg node:$Ra) and as
(f32 (fsub (f32 (fneg FPR32:$Ra)), (f32 (fmul FPR32:$Rn, FPR32:$Rm))))
- fnmsub is (-Ra) + Rn*Rm which should be matched as
fma node:$Rn, node:$Rm, (fneg node:$Ra) and as
(f32 (fsub (f32 (fmul FPR32:$Rn, FPR32:$Rm)), FPR32:$Ra))))
llvm-svn: 197928
The bkpt mnemonic has an implicit immediate constant of 0 unless otherwise
specified. Add an instruction alias for the unvalued breakpoint mnemonic to
treat it as a 0. This improves compatibility with GNU AS.
Signed-off-by: Saleem Abdulrasool <compnerd@compnerd.org>
llvm-svn: 197913
If the extension of a loaded value is compared against zero and used in
other arithmetic, InstCombine will change the comparison to use the
unextended load. It's also possible that the comparison could be against
the unextended load from the outset.
In DAG form this becomes a truncation of an extending load. We want to
strip the truncation if possible so that we can use load-and-test instructions.
llvm-svn: 197804
The handling of ANY_EXTEND and ZERO_EXTEND was too strict. In this context
we can treat ZERO_EXTEND in much the same way as an AND and then also handle
outermost ZERO_EXTENDs.
I couldn't find a test that benefited from the ANY_EXTEND change, but it's
more obvious to write it this way once SIGN_EXTEND and ZERO_EXTEND are
handled differently.
llvm-svn: 197802
v2: Add ftrunc->TRUNC pattern instead of replacing int_AMDGPU_trunc
v3: move ftrunc pattern next to TRUNC definition, it's available since R600
Patch By: Jan Vesely
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 197783
That's what it actually means, and with 16-bit support it's going to be
a little more relevant since in a few corner cases we may actually want
to distinguish between 16-bit and 32-bit mode (for example the bare 'push'
aliases to pushw/pushl etc.)
Patch by David Woodhouse
llvm-svn: 197768
this commit as the only one on the Blamelist so I quickly reverted this.
However it was actually Nick's change who has since fixed that issue.
Original commit message:
Changed the X86 assembler for intel syntax to work with directional labels.
The X86 assembler as a separate code to parser the intel assembly syntax
in X86AsmParser::ParseIntelOperand(). This did not parse directional labels.
And if something like 1f was used as a branch target it would get an
"Unexpected token" error.
The fix starts in X86AsmParser::ParseIntelExpression() in the case for
AsmToken::Integer, it needs to grab the IntVal from the current token
then look for a 'b' or 'f' following an Integer. Then it basically needs to
do what is done in AsmParser::parsePrimaryExpr() for directional
labels. It saves the MCExpr it creates in the IntelExprStateMachine
in the Sym field.
When it returns to X86AsmParser::ParseIntelOperand() it looks
for a non-zero Sym field in the IntelExprStateMachine and if
set it creates a memory operand not an immediate operand
it would normally do for the Integer.
rdar://14961158
llvm-svn: 197744
We dump any non-empty assembler constant pools after a successful
parse of an assembly file that uses the ldr pseudo opcode. These
per-section constant pools should be output in a deterministic order
to ensure that we always generate the same output when printing the
output with an AsmStreamer.
This patch changes the map data struture used to associate a section
with its constant pool to a MapVector to ensure deterministic
output. Because this map type does not support deletion, we now
check that the constant pool is not empty before dumping its entries
and clear the entries after emitting them with the streamer.
llvm-svn: 197735
The X86 assembler has a separate code to parser the intel assembly syntax
in X86AsmParser::ParseIntelOperand(). This did not parse directional labels.
And if something like 1f was used as a branch target it would get an
"Unexpected token" error.
The fix starts in X86AsmParser::ParseIntelExpression() in the case for
AsmToken::Integer, it needs to grab the IntVal from the current token
then look for a 'b' or 'f' following the Integer. Then it basically needs to
do what is done in AsmParser::parsePrimaryExpr() for directional
labels. It saves the MCExpr it creates in the IntelExprStateMachine
in the Sym field.
When it returns to X86AsmParser::ParseIntelOperand() it looks
for a non-zero Sym field in the IntelExprStateMachine and if
set it creates a memory operand not an immediate operand
it would normally do for the Integer.
rdar://14961158
llvm-svn: 197728
The condition in selects is supposed to be i1.
Make sure we are just reading the less significant bit
of the 8 bits width value to match this constraint.
<rdar://problem/15651765>
llvm-svn: 197712
This directive will write out the assembler-maintained constant
pool for the current section. These constant pools are created to
support the ldr-pseudo instruction (e.g. ldr r0, =val).
The directive can be used by the programmer to place the constant
pool in a location that can be reached by a pc-relative offset in
the ldr instruction.
llvm-svn: 197711
The ldr-pseudo opcode is a convenience for loading 32-bit constants.
It is converted into a pc-relative load from a constant pool. For
example,
ldr r0, =0x10001
ldr r1, =bar
will generate this output in the final assembly
ldr r0, .Ltmp0
ldr r1, .Ltmp1
...
.Ltmp0: .long 0x10001
.Ltmp1: .long bar
Sketch of the LDR pseudo implementation:
Keep a map from Section => ConstantPool
When parsing ldr r0, =val
parse val as an MCExpr
get ConstantPool for current Section
Label = CreateTempSymbol()
remember val in ConstantPool at next free slot
add operand to ldr that is MCSymbolRef of Label
On finishParse() callback
Write out all non-empty constant pools
for each Entry in ConstantPool
Emit Entry.Label
Emit Entry.Value
Possible improvements to be added in a later patch:
1. Does not convert load of small constants to mov
(e.g. ldr r0, =0x1 => mov r0, 0x1)
2. Does reuse constant pool entries for same constant
The implementation was tested for ARM, Thumb1, and Thumb2 targets on
linux and darwin.
llvm-svn: 197708
The tests for the disassembler were adapted from the encoder tests, and for the
most part, the output from the disassembler matches that encoder-test inputs.
There are some places where more-informative mnemonics could be produced
(notably for the branch instructions), and those cases are noted in the tests
with FIXMEs.
Future work includes:
- Generating more-informative mnemonics when possible (this may also be done
in the printer).
- Remove the dependence on positional "numbered" operand-to-variable mapping
(for both encoding and decoding).
- Internally using 64-bit instruction variants in 64-bit mode (if this turns
out to matter).
llvm-svn: 197693
Different sized address spaces should theoretically work
most of the time now, and since 64-bit add is currently
disabled, using more 32-bit pointers fixes some cases.
llvm-svn: 197659
This adds support for the .inst directive. This is an ARM specific directive to
indicate an instruction encoded as a constant expression. The major difference
between .word, .short, or .byte and .inst is that the latter will be
disassembled as an instruction since it does not get flagged as data.
llvm-svn: 197657
This changes the MachineFrameInfo API to use the new SSPLayoutKind information
produced by the StackProtector pass (instead of a boolean flag) and updates a
few pass dependencies (to preserve the SSP analysis).
The stack layout follows the same approach used prior to this change - i.e.,
only LargeArray stack objects will be placed near the canary and everything
else will be laid out normally. After this change, structures containing large
arrays will also be placed near the canary - a case previously missed by the
old implementation.
Out of tree targets will need to update their usage of
MachineFrameInfo::CreateStackObject to remove the MayNeedSP argument.
The next patch will implement the rules for sspstrong and sspreq. The end goal
is to support ssp-strong stack layout rules.
WIP.
Differential Revision: http://llvm-reviews.chandlerc.com/D2158
llvm-svn: 197653
This matches the data in clang which was added by Jakob Stoklund Olesen in
r179596.
Thanks for erikjv on irc for pointing me to the relevant documents:
http://sparc.com/standards/64.psabi.1.35.ps.Z
page 25: Every stack frame must be 16-byte aligned.
http://sparc.com/standards/psABI3rd.pdf
page 3-10: Although the architecture requires only word alignment, software convention and the operating system require every stack frame to be doubleword aligned.
I tried to add a test, but it looks like sparc doesn't implement dynamic stack
realignment. This will be tested in clang shortly.
llvm-svn: 197646
The inalloca attribute is designed to support passing C++ objects by
value in the Microsoft C++ ABI. It behaves the same as byval, except
that it always implies that the argument is in memory and that the bytes
are never copied. This attribute allows the caller to take the address
of an outgoing argument's memory and execute arbitrary code to store
into it.
This patch adds basic IR support, docs, and verification. It does not
attempt to implement any lowering or fix any possibly broken transforms.
When this patch lands, a complete description of this feature should
appear at http://llvm.org/docs/InAlloca.html .
Differential Revision: http://llvm-reviews.chandlerc.com/D2173
llvm-svn: 197645
tail call optimization. Some more work may be needed for indirect
calls but this patch fixes the current regression in Prolangc++/trees.
S2 optimization as part of the general cleanup and optimization
of prolog and epilog was not saving S2 in this case and needed to.
llvm-svn: 197630
Given vsel_cc, op1, op2, since vsel has no LE/LT, to generate vsel for
such selection, it needs to inverse cc and swap op1 and op2. To inverse
cc, both L/G and E bits should be flipped.
llvm-svn: 197615
According to "Addenda to ABI for ARM architecture", Tag_FP_arch is the
new name for the equivalent Tag_VFP_arch. This commit renames
Tag_VFP_arch to Tag_FP_arch.
llvm-svn: 197587
This patch adds -f64:32:64 to 32 bit ppc darwin since a f64 inside a
structure are only 32 bit aligned.
The patch also drop -f128:64:128 from all ppc darwin, since f128 is
128 bit aligned.
llvm-svn: 197574
Clang sets the float-abi target option manually, but no longer
annotates each function with its ABI. This can lead to confusing
mistmatch between "clang -emit-llvm | llc" and normal clang
invocations.
Besides which, gnueabihf actually *is* hard-float. Defaulting to soft
was just perverse.
llvm-svn: 197554
The instruction definitions in the PPC backend have a number of variants
defined for the same instruction to represent differences between 64-bit and
32-bit semantics. In order to generate a disassembler for the PPC backend, we
need to mark all but one of these as CodeGen only.
No functionality change intended; this is prep work for PPC disassembly
support.
llvm-svn: 197535
This reverts commit r197481, recommiting r197469 with an extra fix.
The vastart_save_xmm_regs pseudo-instruction expands to a test and a
branch, so it modifies EFLAGS. Mark it so, or else the scheduler might
place it in the middle of another test+branch.
This fixes a bug exposed by r192750, which changed the initial scheduler
to source-order as part of enabling the MI Scheduler for X86.
This re-commit changes the VASTART_SAVE_XMM_REGS custom inserter not to
try to save %flags, and adds a test that catches the bad behavior of
r197469.
<rdar://problem/15627766>
llvm-svn: 197503
http://llvm.org/bugs/show_bug.cgi?id=18045
Short issue description:
For X86 machines with sse < sse4.1 we got failures for some
particular load/store vector sequences:
$ clang-trunk -m32 -O2 test-case.c
fatal error: error in backend: Cannot select: 0x4200920: v4i32,ch = load 0x41d6ab0, 0x4205850,
0x41dcb10<LD16[getelementptr inbounds ([4 x i32]* @e, i32 0, i32 0)](align=4)> [ORD=82]
[ID=58]
0x4205850: i32 = X86ISD::Wrapper 0x41d5490 [ORD=26] [ID=43]
0x41d5490: i32 = TargetGlobalAddress<[4 x i32]* @e> 0 [ORD=26] [ID=23]
0x41dcb10: i32 = undef [ID=2]
The reason is that EltsFromConsecutiveLoads could emit such load instruction
both before and after legalize stage. Though this instruction is not legal for
machines with SSSE3 and lower.
The fix: In EltsFromConsecutiveLoads, if we have passed legalize stage, we
check whether nodes it emits are legal.
P.S.: If you get failure in time from 12:00 and till 22:00 (UTC-8),
perhaps I'll slow with response, so you better reject this commit. Thanks!
llvm-svn: 197492
This reverts commit r197469.
The sanitizer and dragonegg buildbots are failing, I think because of
this change. Reverting until I figure out why.
llvm-svn: 197481
The vastart_save_xmm_regs pseudo-instruction expands to a test and a
branch, so it modifies EFLAGS. Mark it so, or else the scheduler might
place it in the middle of another test+branch.
This fixes a bug exposed by r192750, which turned on the MI Scheduler
for X86.
<rdar://problem/15627766>
llvm-svn: 197469
Without this, MachineCSE is powerless to handle redundant operations with truncated source operands.
This required fixing the 2-addr pass to handle tied subregisters. It isn't clear what combinations of subregisters can legally be tied, but the simple case of truncated source operands is now safely handled:
%vreg11<def> = COPY %vreg1:sub_32bit; GR32:%vreg11 GR64:%vreg1
%vreg12<def> = COPY %vreg2:sub_32bit; GR32:%vreg12 GR64:%vreg2
%vreg13<def,tied1> = ADD32rr %vreg11<tied0>, %vreg12<kill>, %EFLAGS<imp-def>
Test case: cse-add-with-overflow.ll.
This exposed an existing bug in
PPCInstrInfo::commuteInstruction. Thanks to Rafael for the test case:
PowerPC/crash.ll.
llvm-svn: 197465
Added scalar compare VCMPSS, VCMPSD.
Implemented LowerSELECT for scalar FP operations.
I replaced FSETCCss, FSETCCsd with one node type FSETCCs.
Node extract_vector_elt(v16i1/v8i1, idx) returns an element of type i1.
llvm-svn: 197384
Currently we have such types as legal vector types. The DAG combiner may generate some DAG nodes having such types but we don't have patterns to match them.
E.g. a load i32 and a bitcast i32 to v1i32 will be combined into a load v1i32:
bitcast (load i32) to v1i32 -> load v1i32.
So this patch fixes such problems for load/dup instructions.
If v1i8/v1i16/v1i32 are not legal any more, the code in this patch can be deleted. So I also add some FIXME.
llvm-svn: 197361
Some tiny cosmetic code changes to follow. Because of the wide
ranging nature of the patch a full 24 test cycle was needed to
check against regression. This was the smallest patch I could
make to progress from the earlier ones in the series.
llvm-svn: 197350
This is a base implementation of the powerpc-apple-darwin asm parser dialect.
* Enables infrastructure (essentially isDarwin()) and fixes up the parsing of asm directives to separate out ELF and MachO/Darwin additions.
* Enables parsing of {r,f,v}XX as register identifiers.
* Enables parsing of lo16() hi16() and ha16() as modifiers.
The changes to the test case are from David Fang (fangism).
llvm-svn: 197324
were falling into the cases for 24-bit branch kinds which are not 24-bit
branches. The routine is to return false for fixups are expected to always
be resolvable at assembly time. Which these three fixups are as they have
limited displacement and are for local references within a function.
rdar://15586725
llvm-svn: 197282
The cpp backend is not a reasonable fallback for a missing target. It is a
very special backend, so it is reasonable to use it only if explicitly
requested.
While at it, simplify the interface a bit.
llvm-svn: 197241
This originally came about after noticing that InstCombine turns
some of the TMHH (icmp (and...), ...) tests into plain comparisons.
Since there is no instruction to compare with a 64-bit immediate,
TMHH is generally better than an ordered comparison for the cases
that it can handle.
llvm-svn: 197238
This patch makes more use of LPGFR and LNGFR. It builds on top of
the LTGFR selection from r197234. Most of the tests are motivated
by what InstCombine would produce.
llvm-svn: 197236
...in an attempt to rein back the increasingly complex selection code.
A knock-on effect is that ICmpType is exposed from the outset, which
slightly simplifies adjustSubwordCmp.
The code is no piece of art even after this change, but at least it should
be slightly better. No behavioral change intended.
llvm-svn: 197235
InstCombine turns (sext (trunc)) into (ashr (shl)), then converts any
comparison of the ashr against zero into a comparison of the shl against zero.
This makes sense in itself, but we want to undo it for z, since the sign-
extension instruction has a CC-setting form.
I've included tests for both the original and InstCombined variants,
but the former already worked. The patch fixes the latter.
llvm-svn: 197234
While it's safe for the X86-specific shift nodes, dag combining will
kill generic nodes. Insert an AND to make it safe, isel will nuke it
as x86's shift instructions have an implicit AND.
Fixes PR16108, which contains a contraption to hit this case in between
constant folders.
llvm-svn: 197228
branch instructions for mips and micromips instruction sets thus avoiding
the situation of generating branches to undesired locations if offsets
cannot be encoded.
This patch also checks if a fixup cannot be applied and returns a fatal error
if that's the case.
llvm-svn: 197223
Since gcc 4.6 the compiler uses ___chkstk_ms which has the same semantics as the
MS CRT function __chkstk. This simplifies the prologue generation a bit.
Reviewed by Rafael Espíndola.
llvm-svn: 197205
- Copy patterns with float/double types are enough.
- Fix typos in test case names that were using v1fx.
- There is no ACLE intrinsic that uses v1f32 type. And there is no conflict of
neon and non-neon ovelapped operations with this type, so there is no need to
support operations with this type.
- Remove v1f32 from FPR32 register and disallow v1f32 as a legal type for
operations.
Patch by Ana Pazos!
llvm-svn: 197159
a vector packed single/double fp operation followed by a vector insert.
The effect is that the backend coverts the packed fp instruction
followed by a vectro insert into a SSE or AVX scalar fp instruction.
For example, given the following code:
__m128 foo(__m128 A, __m128 B) {
__m128 C = A + B;
return (__m128) {c[0], a[1], a[2], a[3]};
}
previously we generated:
addps %xmm0, %xmm1
movss %xmm1, %xmm0
we now generate:
addss %xmm1, %xmm0
llvm-svn: 197145
Aside from a few minor latency corrections, the major change here is a new
hazard recognizer which focuses on better dispatch-group formation on the
POWER7. As with the PPC970's hazard recognizer, the most important thing it
does is avoid load-after-store hazards within the same dispatch group. It uses
the POWER7's special dispatch-group-terminating nop instruction (instead of
inserting multiple regular nop instructions). This new hazard recognizer makes
use of the scheduling dependency graph itself, built using AA information, to
robustly detect the possibility of load-after-store hazards.
significant test-suite performance changes (the error bars are 99.5% confidence
intervals based on 5 test-suite runs both with and without the change --
speedups are negative):
speedups:
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
-0.55171% +/- 0.333168%
MultiSource/Benchmarks/TSVC/CrossingThresholds-dbl/CrossingThresholds-dbl
-17.5576% +/- 14.598%
MultiSource/Benchmarks/TSVC/Reductions-dbl/Reductions-dbl
-29.5708% +/- 7.09058%
MultiSource/Benchmarks/TSVC/Reductions-flt/Reductions-flt
-34.9471% +/- 11.4391%
SingleSource/Benchmarks/BenchmarkGame/puzzle
-25.1347% +/- 11.0104%
SingleSource/Benchmarks/Misc/flops-8
-17.7297% +/- 9.79061%
SingleSource/Benchmarks/Shootout-C++/ary3
-35.5018% +/- 23.9458%
SingleSource/Regression/C/uint64_to_float
-56.3165% +/- 25.4234%
SingleSource/UnitTests/Vectorizer/gcc-loops
-18.5309% +/- 6.8496%
regressions:
MultiSource/Benchmarks/ASCI_Purple/SMG2000/smg2000
18.351% +/- 12.156%
SingleSource/Benchmarks/Shootout-C++/methcall
27.3086% +/- 14.4733%
llvm-svn: 197099
For one predicate to subsume another, they must both check the same condition
register. Failure to check this prerequisite was causing miscompiles.
Fixes PR18003.
llvm-svn: 197089
point reciprocal exponent, and floating-point reciprocal square root estimate
LLVM AArch64 intrinsics to use f32/f64 types, rather than their vector
equivalents.
llvm-svn: 197066
The tests were no longer using fast-isel at all (MachO needs an "ios" rather
than "darwin" triple at the moment and Linux needs ARM mode). Once that was
corrected, the verifier complained about a t2ADDri created for the alloca.
llvm-svn: 197046
I moved a test from avx512-vbroadcast-crash.ll to avx512-vbroadcast.ll
I defined HasAVX512 predicate as AssemblerPredicate. It means that you should invoke llvm-mc with "-mcpu=knl" to get encoding for AVX-512 instructions. I need this to let AsmMatcher to set different encoding for AVX and AVX-512 instructions that have the same mnemonic and operands (all scalar instructions).
llvm-svn: 197041
The combination of inline asm, stack realignment, and dynamic allocas
turns out to be too common to reject out of hand.
ASan inserts empy inline asm fragments and uses aligned allocas.
Compiling any trivial function containing a dynamic alloca with ASan is
enough to trigger the check.
XFAIL the test cases that would be miscompiled and add one that uses the
relevant functionality.
llvm-svn: 196986
This re-lands commit r196876, which was reverted in r196879.
The tests have been fixed to pass on platforms with a stack alignment
larger than 4.
Update to clang side tests will land shortly.
llvm-svn: 196939
Most users would be surprised if "isCOFF" and "isMachO" were simultaneously
true, unless they'd put the compiler in a box with a gun attached to a photon
detector.
This makes sure precisely one of the three formats is true for any triple and
simplifies some target logic based on that.
llvm-svn: 196934
immediately after SSE scalar fp instructions like addss or mulss.
Added patterns to select SSE scalar fp arithmetic instructions from a scalar
fp operation followed by a blend.
For example, given the following code:
__m128 foo(__m128 A, __m128 B) {
A[0] += B[0];
return A;
}
previously we generated:
addss %xmm0, %xmm1
movss %xmm1, %xmm0
now we generate:
addss %xmm1, %xmm0
llvm-svn: 196925
Save S2(reg 18) only when we are calling floating point stubs that
have a return value of float or complex. Some more work to make this
better but this is the first step.
llvm-svn: 196921
One unusual feature of the z architecture is that the result of a
previous load can be reused indefinitely for subsequent loads, even if
a cache-coherent store to that location is performed by another CPU.
A special serializing instruction must be used if you want to force
a load to be reattempted.
Since volatile loads are not supposed to be omitted in this way,
we should insert a serializing instruction before each such load.
The same goes for atomic loads.
The patch implements this at the IR->DAG boundary, in a similar way
to atomic fences. It is a no-op for targets other than SystemZ.
llvm-svn: 196906
One unusual feature of the z architecture is that the result of a
previous load can be reused indefinitely for subsequent loads, even if
a cache-coherent store to that location is performed by another CPU.
A special serializing instruction must be used if you want to force
a load to be reattempted.
Since volatile loads are not supposed to be omitted in this way,
we should insert a serializing instruction before each such load.
The same goes for atomic loads.
The patch implements this at the IR->DAG boundary, in a similar way
to atomic fences. It is a no-op for targets other than SystemZ.
llvm-svn: 196905
For stack frames requiring realignment, three pointers may be needed:
- ebp to address incoming arguments
- esi (could be any callee-saved register) to address locals
- esp to address outgoing arguments
We would use esi unconditionally without verifying that it did not
conflict with inline assembly.
This change doesn't do the verification, it simply emits a fatal error
on functions that use stack realignment, dynamic SP adjustments, and
inline assembly.
Because stack realignment is common on Windows, we also no longer assume
that MS inline assembly clobbers esp. Instead, we analyze the inline
instructions for implicit definitions and check if esp is there. If so,
we require the use of a base pointer and consider it in the condition
above.
Mostly fixes PR16830, but we could try harder to find a non-conflicting
base pointer.
Reviewers: sunfish
Differential Revision: http://llvm-reviews.chandlerc.com/D1317
llvm-svn: 196876
Patch by Jiangning Liu.
With some test case changes:
- intrinsic test added to the existing /test/CodeGen/AArch64/neon-aba-abd.ll.
- New test cases to cover movi 1D scenario without using the intrinsic in
test/CodeGen/AArch64/neon-mov.ll.
llvm-svn: 196806
Summary:
The MSA ld.[bhwd] and st.[bhwd] instructions scale the immediate by the
element size before use as an offset. The offset must therefore be a
multiple of the element size to be valid in these instructions. However,
an unaligned base address is valid in MSA.
This commit causes the compiler to emit valid code when the calculated
offset is not a multiple of the element size by accounting for the offset
using addiu and using a zero offset in the load/store.
Depends on D2338
Reviewers: matheusalmeida
Reviewed By: matheusalmeida
Differential Revision: http://llvm-reviews.chandlerc.com/D2339
llvm-svn: 196777
Summary:
The immediate in these instructions is scaled before use as an offset.
They therefore have a wider reach than ld.b/st.b.
Reviewers: matheusalmeida
Reviewed By: matheusalmeida
Differential Revision: http://llvm-reviews.chandlerc.com/D2338
llvm-svn: 196775
As we can't make a complete solution now it has been decided to enable .set directive to handle long jump expressions. This will cause parser to report errors when parsing integer based register assignments, for example:
.set r3, will be reported as error. Still, the need for expressions is higher priority as the integer based register assignments are Mips specific and can be avoided using register names.
llvm-svn: 196773
When trying to eliminate an "sub sp, sp, #N" instruction by folding
it into an existing push/pop using dummy registers, we need to account
for the fact that this might affect precisely how "fp" gets set in the
prologue.
We were attempting this, but assuming that *whenever* we performed a
fold it would make a difference. This is false, for example, in:
push {r4, r7, lr}
add fp, sp, #4
vpush {d8}
sub sp, sp, #8
we can fold the "sub" into the "vpush", forming "vpush {d7, d8}".
However, in that case the "add fp" instruction mustn't change, which
we were getting wrong before.
Should fix PR18160.
llvm-svn: 196725
They were out of place since the introduction of arbitrary precision integer
types.
This also synchronizes the documentation to Types.h, so it refers to first class
types and single value types.
llvm-svn: 196661
- krait processor currently modeled with the same features as A9.
- Krait processor additionally has VFP4 (fused multiply add/sub)
and hardware division features enabled.
- krait has currently the same Schedule model as A9
- krait cpu flag is not recognized by the GNU assembler yet,
it is replaced with march=armv7-a to avoid a lower march
from being used.
llvm-svn: 196619
The current peephole optimizing for compare inst assumes an instr that
uses CPSR has an MO for ARM Cond code.However, for VSEL instructions
(vseqeq, vselgt, vselgt, vselvs), there is no such operand nor do
they support the modification of Cond Code.
llvm-svn: 196588
Since z has no setcc instruction as such, the choice of setBooleanContents
is a bit arbitrary. Currently it's set to ZeroOrOneBooleanContent,
so we produced a branch-free form when selecting between 0 and 1,
but not when selecting between 0 and -1. This patch handles the latter
case too.
At some point I'd like to measure whether it's better to use conditional
moves for constant selects on z196, but that's future work.
llvm-svn: 196578
in case the operands are constants and its difference is |1|.
It should be possible in those cases to rematerialize the result using
MIPS's slt and similar instructions.
The small update to some of the tests in cmov.ll, sel1c.ll and sel2c.ll was needed
otherwise the optimization implemented in this patch would have been triggered
(difference between the operands was 1) and that would have changed the semantic
of the tests.
llvm-svn: 196498
not being correctly encoded/decoded.
In more detail, immediate fields of LD/ST instructions should be
divided/multiplied by the size of the data format before encoding and
after decoding, respectively.
llvm-svn: 196494
We were trying to fold the stack adjustment into the wrong instruction in the
situation where the entire basic-block was epilogue code. Really, it can only
ever be valid to do the folding precisely where the "add sp, ..." would be
placed so there's no need for a separate iterator to track that.
Should fix PR18136.
llvm-svn: 196493
getSymbolWithGlobalValueBase use is to create a name of a new symbol based
on the name of an existing GV. Assert that and then remove the last call
to pass true to isImplicitlyPrivate.
This gives the mangler API a 1:1 mapping from GV to names, which is what we
need to drop the mangler dependency on the target (and use an extended
datalayout instead).
llvm-svn: 196472
given
declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1)
declare void @foo()
define void @bar() {
call void @foo()
call void @llvm.memset.p0i8.i32(i8* null, i8 0, i32 188, i32 1, i1 false)
ret void
}
We used to produce
L_foo$stub:
.indirect_symbol _foo
.ascii "\364\364\364\364\364"
_memset$stub:
.indirect_symbol _memset
.ascii "\364\364\364\364\364"
We not produce a private stub for memset too.
Stubs are not needed with recent linkers, but we still produce them for darwin8.
Thanks to David Fang for confirming that gcc used to do this too.
llvm-svn: 196468
Where it would use a scattered relocation entry but falls back to a
normal relocation entry because the FixupOffset is more than 24-bits.
The bug is in the X86MachObjectWriter::RecordScatteredRelocation() where
it changes reference parameter FixedValue but then returns false to indicate
it did not create a scattered relocation entry. The fix is simply to save the
original value of the parameter FixedValue at the start of the method and
restore it if we are returning false in that case.
rdar://15526046
llvm-svn: 196432
ARM symbol variants are written with parens instead of @ like this:
.word __GLOBAL_I_a(target1)
This commit adds support for parsing these symbol variants in
expressions. We introduce a new flag to MCAsmInfo that indicates the
parser should use parens to parse the symbol variant. The expression
parser is modified to look for symbol variants using parens instead
of @ when the corresponding MCAsmInfo flag is true.
The MCAsmInfo parens flag is enabled only for ARM on ELF.
By adding this flag to MCAsmInfo, we are able to get rid of
redundant ARM-specific symbol variants and use the generic variants
instead (e.g. VK_GOT instead of VK_ARM_GOT). We use the new
UseParensForSymbolVariant attribute in MCAsmInfo to correctly print
the symbol variants for arm.
To achive this we need to keep a handle to the MCAsmInfo in the
MCSymbolRefExpr class that we can check when printing the symbol
variant.
Updated Tests:
Changed case of symbol variant to match the generic kind.
test/CodeGen/ARM/tls-models.ll
test/CodeGen/ARM/tls1.ll
test/CodeGen/ARM/tls2.ll
test/CodeGen/Thumb2/tls1.ll
test/CodeGen/Thumb2/tls2.ll
PR18080
llvm-svn: 196424
this completes the basic port of ARM constant islands to Mips16.
More testing, code review, cleanup is in order but basically everything
seems to be working. A bug in gas is preventing some of the runtime
testing but I hope to resolve this soon.
llvm-svn: 196331
Unlike msvc, when handling a thiscall + sret gcc will
* Put the sret in %ecx
* Put the this pointer is (%esp)
This fixes, for example, calling stringstream::str.
llvm-svn: 196312
The backend converts 64-bit ORs into subreg moves if the upper 32 bits
of one operand and the low 32 bits of the other are known to be zero.
It then tries to peel away redundant ANDs from the upper 32 bits.
Since AND masks are canonicalized to exclude known-zero bits,
the test ORs the mask and the known-zero bits together before
checking for redundancy. The problem was that it was using the
wrong node when checking for known-zero bits, so could drop ANDs
that were still needed.
llvm-svn: 196267
- The fix to PR17631 fixes part of the cases where 'vzeroupper' should
not be issued before 'call' insn. There're other cases where helper
calls will be inserted not limited to epilog. These helper calls do
not follow the standard calling convention and won't clobber any YMM
registers. (So far, all call conventions will clobber any or part of
YMM registers.)
This patch enhances the previous fix to cover more cases 'vzerosupper' should
not be inserted by checking if that function call won't clobber any YMM
registers and skipping it if so.
llvm-svn: 196261
PPCScoreboardHazardRecognizer was a subclass of ScoreboardHazardRecognizer
which did only one thing: filtered out nodes in EmitInstruction for which
DAG->getInstrDesc(SU) returned NULL. This used to be the case for PPC pseudo
instructions. As far as I can tell, this is no longer true, and so we can use
ScoreboardHazardRecognizer directly.
llvm-svn: 196171
MO_JumpTableIndex and MO_ExternalSymbol don't show up on inline asm.
Keeping parts of the old asm printer just to print inline asm to a string that
we then parse back looks like a hack.
llvm-svn: 196111
eliminateFrameIndex() has been reworked to handle both small & large frames
with either a FP or SP.
An additional Slot is required for Scavenging spills when not using FP for large frames.
Reworked the handling of Register Scavenging.
Whether we are using an FP or not, whether it is a large frame or not,
and whether we are using a large code model or not are now independent.
llvm-svn: 196091
These are used by MachO only at the moment, and (much like the existing
MOVW/MOVT set) work around the fact that the labels used in the actual
instructions often contain PC-dependent components, which means that repeatedly
materialising the same global can't be CSEed.
With small modifications, it could be adapted to how ELF finds the address of
_GLOBAL_OFFSET_TABLE_, which would give similar benefits in PIC mode there.
llvm-svn: 196090
When using large code model:
Global objects larger than 'CodeModelLargeSize' bytes are placed in sections named with a trailing ".large"
The folded global address of such objects are lowered into the const pool.
During inspection it was noted that LowerConstantPool() was using a default offset of zero.
A fix was made, but due to only offsets of zero being generated, testing only verifies the change is not detrimental.
Correct the flags emitted for explicitly specified sections.
We assume the size of the object queried by getSectionForConstant() is never greater than CodeModelLargeSize.
To handle greater than CodeModelLargeSize, changes to AsmPrinter would be required.
llvm-svn: 196087
Large frame offsets are loaded from the ConstantPool.
Where possible, offsets are encoded using the smaller MKMSK instruction.
Large frame offsets can only be used when there is a frame-pointer.
llvm-svn: 196085
Previously, we clobbered callee-saved registers when folding an "add
sp, #N" into a "pop {rD, ...}" instruction. This change checks whether
a register we're going to add to the "pop" could actually be live
outside the function before doing so and should fix the issue.
This should fix PR18081.
llvm-svn: 196046
- Actually abort when an error occurred.
- Check that the frontend lookup worked when parsing length/size/type operators.
Tested by a clang test. PR18096.
llvm-svn: 196044
This adds a scheduling model for the POWER7 (P7) core, and enables the
machine-instruction scheduler when targeting the P7. Scheduling for the P7,
like earlier ooo PPC cores, requires considering both dispatch group hazards,
and functional unit resources and latencies. These are both modeled in a
combined itinerary. Dispatch group formation is still handled by the post-RA
scheduler (which still needs to be updated for the P7, but nevertheless does a
pretty good job).
One interesting aspect of this change is that I've also enabled to use of AA
duing CodeGen for the P7 (just as it is for the embedded cores). The benchmark
results seem to support this decision (see below), and while this is normally
useful for in-order cores, and not for ooo cores like the P7, I think that the
dispatch slot hazards are enough like in-order resources to make the AA useful.
Test suite significant performance differences (where negative is a speedup,
and positive is a regression) vs. the current situation:
MultiSource/Benchmarks/BitBench/drop3/drop3
with AA: N/A
without AA: -28.7614% +/- 19.8356%
(significantly against AA)
MultiSource/Benchmarks/FreeBench/neural/neural
with AA: -17.7406% +/- 11.2712%
without AA: N/A
(significantly in favor of AA)
MultiSource/Benchmarks/SciMark2-C/scimark2
with AA: -11.2079% +/- 1.80543%
without AA: -11.3263% +/- 2.79651%
MultiSource/Benchmarks/TSVC/Symbolics-flt/Symbolics-flt
with AA: -41.8649% +/- 17.0053%
without AA: -34.5256% +/- 23.7072%
MultiSource/Benchmarks/mafft/pairlocalalign
with AA: 25.3016% +/- 17.8614%
without AA: 38.6629% +/- 14.9391%
(significantly in favor of AA)
MultiSource/Benchmarks/sim/sim
with AA: N/A
without AA: 13.4844% +/- 7.18195%
(significantly in favor of AA)
SingleSource/Benchmarks/BenchmarkGame/Large/fasta
with AA: 15.0664% +/- 6.70216%
without AA: 12.7747% +/- 8.43043%
SingleSource/Benchmarks/BenchmarkGame/puzzle
with AA: 82.2713% +/- 26.3567%
without AA: 75.7525% +/- 41.1842%
SingleSource/Benchmarks/Misc/flops-2
with AA: -37.1621% +/- 20.7964%
without AA: -35.2342% +/- 20.2999%
(significantly in favor of AA)
These are 99.5% confidence intervals from 5 runs per configuration. Regarding
the choice to turn on AA during CodeGen, of these results, four seem
significantly in favor of using AA, and one seems significantly against. I'm
not making this decision based on these numbers alone, but these results
seem consistent with results I have from other tests, and so I think that, on
balance, using AA is a win.
llvm-svn: 195981
In preparation for adding scheduling definitions for the POWER7, split some PPC
itinerary classes so that the P7's latencies and hazards can be better
described. For the most part, this means differentiating indexed from non-index
pre-increment loads and stores. Also, differentiate single from
double-precision sqrt.
No functionality change intended (except for a more-specific latency for
single-precision sqrt on the A2).
llvm-svn: 195980
This prevents the compiler from emitting invalid ld.[bhwd]'s and st.[bhwd]'s
when the stack frame is between 512 and 32,768 bytes in size.
llvm-svn: 195973
in constant islands for Mips16. We introdcuce JalB16 as a synomnym
for Jal16. It makes it easier to read and is also necessary because
Jal16 is a call instruction but JalB16 is being used as a branch.
Various parts of LLVM will not work properly even in this late stage of
the backend if we use what was declared as a call instruction to function
as a branch. For one, basic block labels may not get emitted in some
situations.
llvm-svn: 195968
The operand latencies for loads and stores in the PPC440 itinerary were wrong
(the store operands are all inputs, and the "with update" (pre-increment)
instructions need a latency for the additional output).
llvm-svn: 195948
The operand latencies for the PPC440 should be specified relative to dispatch,
not relative to the initial fetch-and-decode stages. Because most instructions
(ignoring bypass) wait in dispatch until their operands are ready, this is
modeled as reading input operands "at dispatch" (0 cycles after issue), and so
every input and output operand has 4 cycles subtracted from it.
This could alter scheduling slightly, but I don't expect a large effect.
llvm-svn: 195947
Modeling the fetch and decode units in the PPC440 itinerary does not add
anything to the hazard detection capability (and so modeling them just wastes
compile time).
No functionality change intended.
llvm-svn: 195946
target independent.
Most of the x86 specific stackmap/patchpoint handling was necessitated by the
use of the native address-mode format for frame index operands. PEI has now
been modified to treat stackmap/patchpoint similarly to DEBUG_INFO, allowing
us to use a simple, platform independent register/offset pair for frame
indexes on stackmap/patchpoints.
Notes:
- Folding is now platform independent and automatically supported.
- Emiting patchpoints with direct memory references now just involves calling
the TargetLoweringBase::emitPatchPoint utility method from the target's
XXXTargetLowering::EmitInstrWithCustomInserter method. (See
X86TargetLowering for an example).
- No more ugly platform-specific operand parsers.
This patch shouldn't change the generated output for X86.
llvm-svn: 195944
I think, in principle, intrinsics_gen may be added explicitly.
That said, it can be added incidentally, since each target already has dependencies to llvm-tblgen.
Almost all source files depend on both CommonTaleGen and intrinsics_gen.
Explicit add_dependencies() have been pruned under lib/Target.
llvm-svn: 195929
add_public_tablegen_target adds *CommonTableGen to LLVM_COMMON_DEPENDS.
LLVM_COMMON_DEPENDS affects add_llvm_library (and other add_target stuff) within its scope.
llvm-svn: 195927
Instead of sharing functional unit names between the various PPC itineraries,
give each core its own unit names prefixed with the core name. This follows
the convention used by other backends (such as ARM), and removes a non-obvious
ordering dependency between the various PPCSchedule*.td files.
No functionality change intended.
llvm-svn: 195908
conditional branches for very large targets. That will be the next small
patch. Everything now should in principle work as good (functionality
wise) as without constant islands so we decided at Mips/Imagination to
make constant islands the default for Mips16 now so that it will get
excercised a lot and this port is still experimentatl though hopefully soon
we will change the status. Some more cleanup and code review is in order
but things are converging fast.
llvm-svn: 195902
make PIC calls a little more efficient:
1. Remove instructions setting up $gp if it is known that a function has been
called at least once.
2. Save the address of a called function in a register instead of loading
it from the GOT at every call site.
llvm-svn: 195892
This adds the IIC_ prefix to the instruction itinerary class names, giving the
PPC backend a naming convention for itinerary classes that is more consistent
with that used by the X86 and ARM backends.
Instruction scheduling in the PPC backend needs a bunch of cleanup and
improvement (especially for the ooo cores). This is just a preliminary step.
No functionality change intended.
llvm-svn: 195890
SGPRs are spilled into VGPRs using the {READ,WRITE}LANE_B32 instructions.
v2:
- Fix encoding of Lane Mask
- Use correct register flags, so we don't overwrite the low dword
when restoring multi-dword registers.
v3:
- Register spilling seems to hang the GPU, so replace all shaders
that need spilling with a dummy shader.
v4:
- Fix *LANE definitions
- Change destination reg class for 32-bit SMRD instructions
v5:
- Remove small optimization that was crashing Serious Sam 3.
https://bugs.freedesktop.org/show_bug.cgi?id=68224https://bugs.freedesktop.org/show_bug.cgi?id=71285
NOTE: This is a candidate for the 3.4 branch.
llvm-svn: 195880
Writing to the M0 register from an SMRD instruction hangs the GPU, so
we need to use the SGPR_32 register class, which does not include M0.
NOTE: This is a candidate for the 3.4 branch.
llvm-svn: 195879
It is only used for asm printing.
On X86 we put basic block addresses on register before passing them to inline
asm, so the MO_MachineBasicBlock case was dead.
MO_ExternalSymbol was dead since any symbol being passed to inline asm
is represented as MO_GlobalAddress.
The MO_GlobalAddress and MO_Register cases were not tested.
llvm-svn: 195824
- Fix bug in (vsext (vzext x)) -> (vsext x) in SIGN_EXTEND_IN_REG
lowering where we need to check whether x is a vector type (in-reg
type) of i8, i16 or i32; otherwise, that optimization is not valid.
llvm-svn: 195779
We would wrongly transform the testcase into the equivalent of an AND with 1.
The problem was that, when testing whether the shifted-in bits of the right
shift were significant, we used the width of the final zero-extended result
rather than the width of the shifted value.
llvm-svn: 195731
A Direct stack map location records the address of frame index. This
address is itself the value that the runtime requested. This differs
from IndirectMemRefOp locations, which refer to a stack locations from
which the requested values must be loaded. Direct locations can
directly communicate the address if an alloca, while IndirectMemRefOp
handle register spills.
For example:
entry:
%a = alloca i64...
llvm.experimental.stackmap(i32 <ID>, i32 <shadowBytes>, i64* %a)
Since both the alloca and stackmap intrinsic are in the entry block,
and the intrinsic takes the address of the alloca, the runtime can
assume that LLVM will not substitute alloca with any intervening
value. This must be verified by the runtime by checking that the stack
map's location is a Direct location type. The runtime can then
determine the alloca's relative location on the stack immediately after
compilation, or at any time thereafter. This differs from Register and
Indirect locations, because the runtime can only read the values in
those locations when execution reaches the instruction address of the
stack map.
llvm-svn: 195712
Patch by Mikulas Patocka. I added the test. I checked that for cpu names that
gas knows about, it also doesn't generate nopl.
The modified cpus:
i686 - there are i686-class CPUs that don't have nopl: Via c3, Transmeta
Crusoe, Microsoft VirtualBox - see
https://bbs.archlinux.org/viewtopic.php?pid=775414
k6, k6-2, k6-3, winchip-c6, winchip2 - these are 586-class CPUs
via c3 c3-2 - see https://bugs.archlinux.org/task/19733 as a proof that
Via c3 and c3-Nehemiah don't have nopl
llvm-svn: 195679
These are handled almost identically to static mode (and ELF's global address
materialisation), except that a symbol may have "$non_lazy_ptr" appended. This
can be handled by passing appropriate flags along with the instruction instead
of using entirely separate pseudo-instructions.
llvm-svn: 195655
There is no sane way for an LEApcrel (= single ADR) instruction to generate a
global address on any ARM target I know of. Fortunately, no-one was trying to
any more, but there were vestigial patterns.
llvm-svn: 195644
Andrew Trick