Explanation: This function is in TargetLowering because it uses
RegClassForVT which would need to be moved to TargetRegisterInfo
and would necessitate moving isTypeLegal over as well - a massive
change that would just require TargetLowering having a TargetRegisterInfo
class member that it would use.
llvm-svn: 230585
This required plumbing a TargetRegisterInfo through computeRegisterProperties
and into findRepresentativeClass which uses it for register class
iteration. This required passing a subtarget into a few target specific
initializations of TargetLowering.
llvm-svn: 230583
LDtocL, and other loads that roughly correspond to the TOC_ENTRY SDAG node,
represent loads from the TOC, which is invariant. As a result, these loads can
be hoisted out of loops, etc. In order to do this, we need to generate
GOT-style MMOs for TOC_ENTRY, which requires treating it as a legitimate memory
intrinsic node type. Once this is done, the MMO transfer is automatically
handled for TableGen-driven instruction selection, and for nodes generated
directly in PPCISelDAGToDAG, we need to transfer the MMOs manually.
Also, we were not transferring MMOs associated with pre-increment loads, so do
that too.
Lastly, this fixes an exposed bug where R30 was not added as a defined operand of
UpdateGBR.
This problem was highlighted by an example (used to generate the test case)
posted to llvmdev by Francois Pichet.
llvm-svn: 230553
The Win64 epilogue structure is very restrictive, it permits a very
small number of opcodes and none of them are 'mov'.
This means that given:
mov %rbp, %rsp
pop %rbp
The mov isn't the epilogue, only the pop is. This is problematic unless
a frame pointer is present in which case we are free to do whatever we'd
like in the "body" of the function. If a frame pointer is present,
unwinding will undo the prologue operations in reverse order regardless
of the fact that we are at an instruction which is reseting the stack
pointer.
llvm-svn: 230543
We had somehow accumulated a few target-specific SDAG nodes dealing with PPC64
TOC access that were referenced only in TableGen patterns. The associated
(pseudo-)instructions are used, but are being generated directly. NFC.
llvm-svn: 230518
Reapply r230248.
Teach the peephole optimizer to work with MMX instructions by adding
entries into the foldable tables. This covers folding opportunities not
handled during isel.
llvm-svn: 230499
MMX_MOVD64rm zero-extends i32 load results into i64 registers.
The peephole optimizer will try to fold it in other MMX foldable
instructions, the wrong thing to do, since there's no MMX memory
instruction that loads from i32 and does implict zero extension.
Remove 'canFoldAsLoad' from MOVD64rm in order to prevent such folding.
The current MMX tests already test this, but since there are no MMX
instructions in the foldable tables yet, this did not trigger. This
commit prepares the addition of those instructions.
llvm-svn: 230498
Thumb-1 only allows SP-based LDR and STR to be word-sized, and SP-base LDR,
STR, and ADD only allow offsets that are a multiple of 4. Make some changes
to better make use of these instructions:
* Use word loads for anyext byte and halfword loads from the stack.
* Enforce 4-byte alignment on objects accessed in this way, to ensure that
the offset is valid.
* Do the same for objects whose frame index is used, in order to avoid having
to use more than one ADD to generate the frame index.
* Correct how many bits of offset we think AddrModeT1_s has.
Patch by John Brawn.
llvm-svn: 230496
Gather and scatter instructions additionally write to one of the source operands - mask register.
In this case Gather has 2 destination values - the loaded value and the mask.
Till now we did not support code gen pattern for gather - the instruction was generated from
intrinsic only and machine node was hardcoded.
When we introduce the masked_gather node, we need to select instruction automatically,
in the standard way.
I added a flag "hasTwoExplicitDefs" that allows to handle 2 destination operands.
(Some code in the X86InstrFragmentsSIMD.td is commented out, just to split one big
patch in many small patches)
llvm-svn: 230471
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).
I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).
The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.
llvm-svn: 230413
The reason why these large shift sizes happen is because OpaqueConstants
currently inhibit alot of DAG combining, but that has to be addressed in
another commit (like the proposal in D6946).
Differential Revision: http://reviews.llvm.org/D6940
llvm-svn: 230355
The logic is almost there already, with our special homogeneous aggregate
handling. Tweaking it like this allows front-ends to emit AAPCS compliant code
without ever having to count registers or add discarded padding arguments.
Only arrays of i32 and i64 are needed to model AAPCS rules, but I decided to
apply the logic to all integer arrays for more consistency.
llvm-svn: 230348
Summary: Separated some instruction and pseudo-instruction definitions from InstAlias definitions, added banner for pseudo-instructions and removed a redundant whitespace from a pseudo-instruction definition. No functional change.
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D7552
llvm-svn: 230327
Summary: Begin to add various address modes; including alloca.
Test Plan: Make sure there are no regressions in test-suite at O0/02 in mips32r1/r2
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: echristo, rfuhler, llvm-commits
Differential Revision: http://reviews.llvm.org/D6426
llvm-svn: 230300
This is a follow up to r230233 to fix something that I noticed by
inspection. The AddrModeT2_i8s4 addressing mode does not support
negative offsets. I spent a good chunk of the day trying to come up with
a testcase for this but was not successful. This addressing mode is used
to spill and restore GPRPair registers in Thumb2 code and that does not
happen often. We also make very limited used of negative offsets when
lowering frame indexes. I am going ahead with the change anyway, because
I am pretty confident that it is correct. I also added a missing assertion
to check that the low bits of the scaled offset are zero.
llvm-svn: 230297
Prologue emission, in some cases, requires calls to a stack probe helper
function. The amount of stack to probe is passed as a register
argument in the Win64 ABI but the instruction sequence used is
pessimistic: it assumes that the number of bytes to probe is greater
than 4 GB.
Instead, select a more appropriate opcode depending on the number of
bytes we are going to probe.
llvm-svn: 230270
Front-ends could use global unnamed_addr to hold pointers to other
symbols, like @gotequivalent below:
@foo = global i32 42
@gotequivalent = private unnamed_addr constant i32* @foo
@delta = global i32 trunc (i64 sub (i64 ptrtoint (i32** @gotequivalent to i64),
i64 ptrtoint (i32* @delta to i64))
to i32)
The global @delta holds a data "PC"-relative offset to @gotequivalent,
an unnamed pointer to @foo. The darwin/x86-64 assembly output for this follows:
.globl _foo
_foo:
.long 42
.globl _gotequivalent
_gotequivalent:
.quad _foo
.globl _delta
_delta:
.long _gotequivalent-_delta
Since unnamed_addr indicates that the address is not significant, only
the content, we can optimize the case above by replacing pc-relative
accesses to "GOT equivalent" globals, by a PC relative access to the GOT
entry of the final symbol instead. Therefore, "delta" can contain a pc
relative relocation to foo's GOT entry and we avoid the emission of
"gotequivalent", yielding the assembly code below:
.globl _foo
_foo:
.long 42
.globl _delta
_delta:
.long _foo@GOTPCREL+4
There are a couple of advantages of doing this: (1) Front-ends that need
to emit a great deal of data to store pointers to external symbols could
save space by not emitting such "got equivalent" globals and (2) IR
constructs combined with this opt opens a way to represent GOT pcrel
relocations by using the LLVM IR, which is something we previously had
no way to express.
Differential Revision: http://reviews.llvm.org/D6922
rdar://problem/18534217
llvm-svn: 230264
It was previously using the subtarget to get values for the global
offset without actually checking each function as it was generating
code. Go ahead and solidify the current behavior and make the
existing FIXMEs more prominent.
As a note the ARM backend previously had a thumb1 and non-thumb1
set of defaults. Only the former was tested so I've changed the
behavior to only use that for now.
llvm-svn: 230245
This patch adds the isProfitableToHoist API. For AArch64, we want to prevent a
fmul from being hoisted in cases where it is more profitable to form a
fmsub/fmadd.
Phabricator Review: http://reviews.llvm.org/D7299
Patch by Lawrence Hu <lawrence@codeaurora.org>
llvm-svn: 230241
Summary:
-mno-odd-spreg prohibits the use of odd-numbered single-precision floating
point registers. However, vector insert/extract was still using them when
manipulating the subregisters of an MSA register. Fixed this by ensuring
that insertion/extraction is only performed on even-numbered vector
registers when -mno-odd-spreg is given.
Reviewers: vmedic, sstankovic
Reviewed By: sstankovic
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D7672
llvm-svn: 230235
The natural way to handle this addressing mode would be to say that it has
8 bits and gets scaled by 4, but since the MC layer is expecting the scaling
to be already reflected in the immediate value, we have been setting the
Scale to 1. That's fine, but then NumBits needs to be adjusted to reflect
the effective increase in the range of the immediate. That adjustment was
missing.
The consequence is that the register scavenger can fail.
The estimateRSStackSizeLimit() function in ARMFrameLowering.cpp correctly
assumes that the AddrModeT2_i8s4 address mode can handle scaled offsets up to
1020. Under just the right circumstances, we fail to reserve space for the
scavenger because it thinks that nothing will be needed. However, the overly
pessimistic behavior in rewriteT2FrameIndex causes some frame indexes to be
out of range and require scavenged registers, and so the scavenger asserts.
Unfortunately I have not been able to come up with a testcase for this. I
can only reproduce it on an internal branch where the frame layout and
register allocation is slightly different than trunk. We really need a
way to serialize MachineInstr-level IR to write reasonable tests for things
like this.
rdar://problem/19909005
llvm-svn: 230233
Teach the peephole optimizer to work with MMX instructions by adding
entries into the foldable tables. This covers folding opportunities not
handled during isel.
llvm-svn: 230226
I made the templates general, no need to define pattern separately for each instruction/intrinsic.
Now only need to add r_Int pattern for AVX.
llvm-svn: 230221
Synthesizing a call directly using the MI layer would confuse the frame
lowering code. This is problematic as frame lowering is highly
sensitive the particularities of calls, etc.
llvm-svn: 230129
Everyone except R600 was manually passing the length of a static array
at each callsite, calculated in a variety of interesting ways. Far
easier to let ArrayRef handle that.
There should be no functional change, but out of tree targets may have
to tweak their calls as with these examples.
llvm-svn: 230118
Stack realignment occurs after the prolog, not during, for Win64.
Because of this, don't factor in the maximum stack alignment when
establishing a frame pointer.
This fixes PR22572.
llvm-svn: 230113
The expansion code does the same thing. Since
the operands were not defined with the correct
types, this has the side effect of fixing operand
folding since the expanded pseudo would never use
SGPRs or inline immediates.
llvm-svn: 230072
This enables a few useful combines that used to only
use fma.
Also since v_mad_f32 apparently does not support denormals,
disable the existing cases that are custom handled if they are
requested.
llvm-svn: 230071
usage of instruction ADDU16 by CodeGen. For this instruction an improper
register is allocated, i.e. the register that is not from register set defined
for the instruction.
llvm-svn: 230053
changes to remove non-Function based subtargets out of the asm
printer. For module level emission we'll need to construct up
an MCSubtargetInfo so that we can encode instructions for
emission.
llvm-svn: 230050
This patch teaches X86FastISel how to select intrinsic 'convert_from_fp16' and
intrinsic 'convert_to_fp16'.
If the target has F16C, we can select VCVTPS2PHrr for a float-half conversion,
and VCVTPH2PSrr for a half-float conversion.
Differential Revision: http://reviews.llvm.org/D7673
llvm-svn: 230043
EmitFunctionStubs is called from doFinalization and so can't
depend on the Subtarget existing. It's also irrelevant as
we know we're darwin since we're in the darwin asm printer.
llvm-svn: 230039
This canonicalization step saves us 3 pattern matching possibilities * 4 math ops
for scalar FP math that uses xmm regs. The backend can re-commute the operands
post-instruction-selection if that makes register allocation better.
The tests in llvm/test/CodeGen/X86/sse-scalar-fp-arith.ll cover this scenario already,
so there are no new tests with this patch.
Differential Revision: http://reviews.llvm.org/D7777
llvm-svn: 230024
the wrong answer. We also got initializer lists which are *way* cleaner
for this kind of thing. Let's use those and make this a normal, boring
functionn accepting ArrayRef.
llvm-svn: 230004
The IBM BG/Q supercomputer's A2 cores have a hardware prefetching unit, the
L1P, but it does not prefetch directly into the A2's L1 cache. Instead, it
prefetches into its own L1P buffer, and the latency to access that buffer is
significantly higher than that to the L1 cache (although smaller than the
latency to the L2 cache). As a result, especially when multiple hardware
threads are not actively busy, explicitly prefetching data into the L1 cache is
advantageous.
I've been using this pass out-of-tree for data prefetching on the BG/Q for well
over a year, and it has worked quite well. It is enabled by default only for
the BG/Q, but can be enabled for other cores as well via a command-line option.
Eventually, we might want to add some TTI interfaces and move this into
Transforms/Scalar (there is nothing particularly target dependent about it,
although only machines like the BG/Q will benefit from its simplistic
strategy).
llvm-svn: 229966
The new shuffle lowering has been the default for some time. I've
enabled the new legality testing by default with no really blocking
regressions. I've fuzz tested this very heavily (many millions of fuzz
test cases have passed at this point). And this cleans up a ton of code.
=]
Thanks again to the many folks that helped with this transition. There
was a lot of work by others that went into the new shuffle lowering to
make it really excellent.
In case you aren't using a diff algorithm that can handle this:
X86ISelLowering.cpp: 22 insertions(+), 2940 deletions(-)
llvm-svn: 229964
is going well, remove the flag and the code for the old legality tests.
This is the first step toward removing the entire old vector shuffle
lowering. *Much* more code to delete coming up next.
llvm-svn: 229963
reflects the fact that the x86 backend can in fact lower any shuffle you
want it to with reasonably high code quality.
My recent work on the new vector shuffle has made this regress *very*
little. The diff in the test cases makes me very, very happy.
llvm-svn: 229958
This re-applies r223862, r224198, r224203, and r224754, which were
reverted in r228129 because they exposed Clang misalignment problems
when self-hosting.
The combine caused the crashes because we turned ISD::LOAD/STORE nodes
to ARMISD::VLD1/VST1_UPD nodes. When selecting addressing modes, we
were very lax for the former, and only emitted the alignment operand
(as in "[r1:128]") when it was larger than the standard alignment of
the memory type.
However, for ARMISD nodes, we just used the MMO alignment, no matter
what. In our case, we turned ISD nodes to ARMISD nodes, and this
caused the alignment operands to start being emitted.
And that's how we exposed alignment problems that were ignored before
(but I believe would have been caught with SCTRL.A==1?).
To fix this, we can just mirror the hack done for ISD nodes: only
take into account the MMO alignment when the access is overaligned.
Original commit message:
We used to only combine intrinsics, and turn them into VLD1_UPD/VST1_UPD
when the base pointer is incremented after the load/store.
We can do the same thing for generic load/stores.
Note that we can only combine the first load/store+adds pair in
a sequence (as might be generated for a v16f32 load for instance),
because other combines turn the base pointer addition chain (each
computing the address of the next load, from the address of the last
load) into independent additions (common base pointer + this load's
offset).
rdar://19717869, rdar://14062261.
llvm-svn: 229932
In preparation for a future patch:
- rename isLoad to isLoadOp: the former is confusing, and can be taken
to refer to the fact that the node is an ISD::LOAD. (it isn't, yet.)
- change formatting here and there.
- add some comments.
- const-ify bools.
llvm-svn: 229929
systematic lowering of v8i16.
This required a slight strategy shift to prefer unpack lowerings in more
places. While this isn't a cut-and-dry win in every case, it is in the
overwhelming majority. There are only a few places where the old
lowering would probably be a touch faster, and then only by a small
margin.
In some cases, this is yet another significant improvement.
llvm-svn: 229859
addition to lowering to trees rooted in an unpack.
This saves shuffles and or registers in many various ways, lets us
handle another class of v4i32 shuffles pre SSE4.1 without domain
crosses, etc.
llvm-svn: 229856
terribly complex partial blend logic.
This code path was one of the more complex and bug prone when it first
went in and it hasn't faired much better. Ultimately, with the simpler
basis for unpack lowering and support bit-math blending, this is
completely obsolete. In the worst case without this we generate
different but equivalent instructions. However, in many cases we
generate much better code. This is especially true when blends or pshufb
is available.
This does expose one (minor) weakness of the unpack lowering that I'll
try to address.
In case you were wondering, this is actually a big part of what I've
been trying to pull off in the recent string of commits.
llvm-svn: 229853
needed, and significantly improve the SSSE3 path.
This makes the new strategy much more clear. If we can blend, we just go
with that. If we can't blend, we try to permute into an unpack so
that we handle cases where the unpack doing the blend also simplifies
the shuffle. If that fails and we've got SSSE3, we now call into
factored-out pshufb lowering code so that we leverage the fact that
pshufb can set up a blend for us while shuffling. This generates great
code, especially because we *know* we don't have a fast blend at this
point. Finally, we fall back on decomposing into permutes and blends
because we do at least have a bit-math-based blend if we need to use
that.
This pretty significantly improves some of the v8i16 code paths. We
never need to form pshufb for the single-input shuffles because we have
effective target-specific combines to form it there, but we were missing
its effectiveness in the blends.
llvm-svn: 229851
them into permutes and a blend with the generic decomposition logic.
This works really well in almost every case and lets the code only
manage the expansion of a single input into two v8i16 vectors to perform
the actual shuffle. The blend-based merging is often much nicer than the
pack based merging that this replaces. The only place where it isn't we
end up blending between two packs when we could do a single pack. To
handle that case, just teach the v2i64 lowering to handle these blends
by digging out the operands.
With this we're down to only really random permutations that cause an
explosion of instructions.
llvm-svn: 229849
v16i8 shuffles, and replace it with new facilities.
This uses precise patterns to match exact unpacks, and the new
generalized unpack lowering only when we detect a case where we will
have to shuffle both inputs anyways and they terminate in exactly
a blend.
This fixes all of the blend horrors that I uncovered by always lowering
blends through the vector shuffle lowering. It also removes *sooooo*
much of the crazy instruction sequences required for v16i8 lowering
previously. Much cleaner now.
The only "meh" aspect is that we sometimes use pshufb+pshufb+unpck when
it would be marginally nicer to use pshufb+pshufb+por. However, the
difference there is *tiny*. In many cases its a win because we re-use
the pshufb mask. In others, we get to avoid the pshufb entirely. I've
left a FIXME, but I'm dubious we can really do better than this. I'm
actually pretty happy with this lowering now.
For SSE2 this exposes some horrors that were really already there. Those
will have to fixed by changing a different path through the v16i8
lowering.
llvm-svn: 229846
on things not being marked as either custom or legal, but we now do
custom lowering of more VSELECT nodes. To cope with this, manually
replicate the legality tests here. These have to stay in sync with the
set of tests used in the custom lowering of VSELECT.
Ideally, we wouldn't do any of this combine-based-legalization when we
have an actual custom legalization step for VSELECT, but I'm not going
to be able to rewrite all of that today.
I don't have a test case for this currently, but it was found when
compiling a number of the test-suite benchmarks. I'll try to reduce
a test case and add it.
This should at least fix the test-suite fallout on build bots.
llvm-svn: 229844
lowering paths. I'm going to be leveraging this to simplify a lot of the
overly complex lowering of v8 and v16 shuffles in pre-SSSE3 modes.
Sadly, this isn't profitable on v4i32 and v2i64. There, the float and
double blending instructions for pre-SSE4.1 are actually pretty good,
and we can't beat them with bit math. And once SSE4.1 comes around we
have direct blending support and this ceases to be relevant.
Also, some of the test cases look odd because the domain fixer
canonicalizes these to floating point domain. That's OK, it'll use the
integer domain when it matters and some day I may be able to update
enough of LLVM to canonicalize the other way.
This restores almost all of the regressions from teaching x86's vselect
lowering to always use vector shuffle lowering for blends. The remaining
problems are because the v16 lowering path is still doing crazy things.
I'll be re-arranging that strategy in more detail in subsequent commits
to finish recovering the performance here.
llvm-svn: 229836
First, don't combine bit masking into vector shuffles (even ones the
target can handle) once operation legalization has taken place. Custom
legalization of vector shuffles may exist for these patterns (making the
predicate return true) but that custom legalization may in some cases
produce the exact bit math this matches. We only really want to handle
this prior to operation legalization.
However, the x86 backend, in a fit of awesome, relied on this. What it
would do is mark VSELECTs as expand, which would turn them into
arithmetic, which this would then match back into vector shuffles, which
we would then lower properly. Amazing.
Instead, the second change is to teach the x86 backend to directly form
vector shuffles from VSELECT nodes with constant conditions, and to mark
all of the vector types we support lowering blends as shuffles as custom
VSELECT lowering. We still mark the forms which actually support
variable blends as *legal* so that the custom lowering is bypassed, and
the legal lowering can even be used by the vector shuffle legalization
(yes, i know, this is confusing. but that's how the patterns are
written).
This makes the VSELECT lowering much more sensible, and in fact should
fix a bunch of bugs with it. However, as you'll see in the test cases,
right now what it does is point out the *hilarious* deficiency of the
new vector shuffle lowering when it comes to blends. Fortunately, my
very next patch fixes that. I can't submit it yet, because that patch,
somewhat obviously, forms the exact and/or pattern that the DAG combine
is matching here! Without this patch, teaching the vector shuffle
lowering to produce the right code infloops in the DAG combiner. With
this patch alone, we produce terrible code but at least lower through
the right paths. With both patches, all the regressions here should be
fixed, and a bunch of the improvements (like using 2 shufps with no
memory loads instead of 2 andps with memory loads and an orps) will
stay. Win!
There is one other change worth noting here. We had hilariously wrong
vectorization cost estimates for vselect because we fell through to the
code path that assumed all "expand" vector operations are scalarized.
However, the "expand" lowering of VSELECT is vector bit math, most
definitely not scalarized. So now we go back to the correct if horribly
naive cost of "1" for "not scalarized". If anyone wants to add actual
modeling of shuffle costs, that would be cool, but this seems an
improvement on its own. Note the removal of 16 and 32 "costs" for doing
a blend. Even in SSE2 we can blend in fewer than 16 instructions. ;] Of
course, we don't right now because of OMG bad code, but I'm going to fix
that. Next patch. I promise.
llvm-svn: 229835
Previously, subtarget features were a bitfield with the underlying type being uint64_t.
Since several targets (X86 and ARM, in particular) have hit or were very close to hitting this bound, switching the features to use a bitset.
No functional change.
Differential Revision: http://reviews.llvm.org/D7065
llvm-svn: 229831
A null MCTargetStreamer allows IRObjectFile to ignore target-specific
directives. Previously we were crashing.
Differential Revision: http://reviews.llvm.org/D7711
llvm-svn: 229797
This involved moving two non-subtarget dependent features (64-bitness
and the driver interface) to the NVPTX target machine and updating
the uses (or migrating around the subtarget use for ease of review).
Otherwise use the cached subtarget or create a default subtarget
based on the TargetMachine cpu and feature string for the module
level assembler emission.
llvm-svn: 229785
VOP2 declares vsrc1, but VOP3 declares src1.
We can't use the same "ins" if the operands have different names in VOP2
and VOP3 encodings.
This fixes a hang in geometry shaders which spill M0 on VI.
(BTW it doesn't look like M0 needs spilling and the spilling seems
duplicated 3 times)
llvm-svn: 229752
Summary:
These ISA's didn't add any instructions so they are almost identical to
Mips32r2 and Mips64r2. Even the ELF e_flags are the same, However the ISA
revision in .MIPS.abiflags is 3 or 5 respectively instead of 2.
Reviewers: vmedic
Reviewed By: vmedic
Subscribers: tomatabacu, llvm-commits, atanasyan
Differential Revision: http://reviews.llvm.org/D7381
llvm-svn: 229695
Summary:
Parse for an MCExpr instead of an Identifier and use the symbol for relocations, not just the symbol's name.
This fixes errors when using local labels in .cpsetup (PR22518).
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: seanbruno, emaste, llvm-commits
Differential Revision: http://reviews.llvm.org/D7697
llvm-svn: 229671
quite literally the same work, we just need to special case the >64-bit
element shift code emission to emit the byte shift instructions and
offsets. This also makes reasoning about each of the vector lowering
strategies easier as we don't have to remember to use both forms.
llvm-svn: 229662
Add some of the missing M and R class Cortex CPUs, namely:
Cortex-M0+ (called Cortex-M0plus for GCC compatibility)
Cortex-M1
SC000
SC300
Cortex-R5
llvm-svn: 229660
Removed (unreachable) default case in switch to clean up warning:
lib/Target/SystemZ/SystemZISelLowering.cpp:1974:5:
error: default label in switch which covers all enumeration values
[-Werror,-Wcovered-switch-default]
llvm-svn: 229658
code.
While this didn't have the miscompile (it used MatchLeft consistently)
it missed some cases where it could use right shifts. I've added a test
case Craig Topper came up with to exercise the right shift matching.
This code is really identical between the two. I'm going to merge them
next so that we don't keep two copies of all of this logic.
llvm-svn: 229655
The current SystemZ back-end only supports the local-exec TLS access model.
This patch adds all required CodeGen support for the other TLS models, which
means in particular:
- Expand initial-exec TLS accesses by loading TLS offsets from the GOT
using @indntpoff relocations.
- Expand general-dynamic and local-dynamic accesses by generating the
appropriate calls to __tls_get_offset. Note that this routine has
a non-standard ABI and requires loading the GOT pointer into %r12,
so the patch also adds support for the GLOBAL_OFFSET_TABLE ISD node.
- Add a new platform-specific optimization pass to remove redundant
__tls_get_offset calls in the local-dynamic model (modeled after
the corresponding X86 pass).
- Add test cases verifying all access models and optimizations.
llvm-svn: 229654
The current SystemZ back-end only supports the local-exec TLS access model.
This patch adds all required MC support for the other TLS models, which
means in particular:
- Support additional relocation types for
Initial-exec model: R_390_TLS_IEENT
Local-dynamic-model: R_390_TLS_LDO32, R_390_TLS_LDO64,
R_390_TLS_LDM32, R_390_TLS_LDM64, R_390_TLS_LDCALL
General-dynamic model: R_390_TLS_GD32, R_390_TLS_GD64, R_390_TLS_GDCALL
- Support assembler syntax to generate additional relocations
for use with __tls_get_offset calls:
:tls_gdcall:
:tls_ldcall:
The patch also adds a new test to verify fixups and relocations,
and removes the (already unused) FK_390_PLT16DBL/FK_390_PLT32DBL
fixup kinds.
llvm-svn: 229652
track state.
I didn't like this in the code review because the pattern tends to be
error prone, but I didn't see a clear way to rewrite it. Turns out that
there were bugs here, I found them when fuzz testing our shuffle
lowering for correctness on x86.
The core of the problem is that we need to consistently test all our
preconditions for the same directionality of shift and the same input
vector. Instead, formulate this as two predicates (one doesn't depend on
the input in any way), pass things like the directionality and input
vector as inputs, and loop over the alternatives.
This fixes a pattern of very rare miscompiles coming out of this code.
Turned up roughly 4 out of every 1 million v8 shuffles in my fuzz
testing. The new code is over half a million test runs with no failures
yet. I've also fuzzed every other function in the lowering code with
over 3.5 million test cases and not discovered any other miscompiles.
llvm-svn: 229642
Some formats capitalized these, but most didn't. Change
them all to be consistently lowercase.
Now, non-encoding fields and convenience bits are capitalized.
Also remove weird looking empty line in some of the formats.
llvm-svn: 229613
initialization. Initialize the subtarget once per function and
migrate EmitStartOfAsmFile to either use calls on the
TargetMachine or get information from the subtarget we'd use
for assembling.
The top-level-ness of the MIPS attribute output for assembly is,
by nature, contrary to how we'd want to do this for an LTO
situation where we have multiple cpu architectures so this
solution is good enough for now.
llvm-svn: 229596
This patch teaches fast-isel how to select a (V)CVTSI2SSrr for an integer to
float conversion, and how to select a (V)CVTSI2SDrr for an integer to double
conversion.
Added test 'fast-isel-int-float-conversion.ll'.
Differential Revision: http://reviews.llvm.org/D7698
llvm-svn: 229589
The problem in the original patch was not switching back to .text after printing
an eh table.
Original message:
On ELF, put PIC jump tables in a non executable section.
Fixes PR22558.
llvm-svn: 229586
Change the memory operands in sse12_fp_packed_scalar_logical_alias from scalars to vectors.
That's what the hardware packed logical FP instructions define: 128-bit memory operands.
There are no scalar versions of these instructions...because this is x86.
Generating the wrong code (folding a scalar load into a 128-bit load) is still possible
using the peephole optimization pass and the load folding tables. We won't completely
solve this bug until we either fix the lowering in fabs/fneg/fcopysign and any other
places where scalar FP logic is created or fix the load folding in foldMemoryOperandImpl()
to make sure it isn't changing the size of the load.
Differential Revision: http://reviews.llvm.org/D7474
llvm-svn: 229531
initialization. Initialize the subtarget once per function and
migrate Emit{Start|End}OfAsmFile to either use attributes on the
TargetMachine or get information from the subtarget we'd use
for assembling. One bit (getISAEncoding) touched the general
AsmPrinter and the debug output. Handle this one by passing
the function for the subprogram down and updating all callers
and users.
The top-level-ness of the ARM attribute output for assembly is,
by nature, contrary to how we'd want to do this for an LTO
situation where we have multiple cpu architectures so this
solution is good enough for now.
llvm-svn: 229528
GCC 4.8 reported two new warnings due to comparisons
between signed and unsigned integer expressions. The new warnings were
accidentally introduced by revision 229480.
Added explicit casts to silence the warnings. No functional change intended.
llvm-svn: 229488
- added mask types v8i1 and v16i1 to possible function parameters
- enabled passing 512-bit vectors in standard CC
- added a test for KNL intel_ocl_bi conventions
llvm-svn: 229482
Vector zext tends to get legalized into a vector anyext, represented as a vector shuffle with an undef vector + a bitcast, that gets ANDed with a mask that zeroes the undef elements.
Combine this into an explicit shuffle with a zero vector instead. This allows shuffle lowering to match it as a zext, instead of matching it as an anyext and emitting an explicit AND.
This combine only covers a subset of the cases, but it's a start.
Differential Revision: http://reviews.llvm.org/D7666
llvm-svn: 229480
initialization. Initialize the subtarget once per function and
migrate EmitStartOfAsmFile to either use attributes on the
TargetMachine or get information from all of the various
subtargets.
llvm-svn: 229475
This allows it to match still more places where previously we would have
to fall back on floating point shuffles or other more complex lowering
strategies.
I'm hoping to replace some of the hand-rolled unpack matching with this
routine is it gets more and more clever.
llvm-svn: 229463
Our register allocation has become better recently, it seems, and is now
starting to generate cross-block copies into inflated register classes. These
copies are not transformed into subregister insertions/extractions by the
PPCVSXCopy class, and so need to be handled directly by
PPCInstrInfo::copyPhysReg. The code to do this was *almost* there, but not
quite (it was unnecessarily restricting itself to only the direct
sub/super-register-class case (not copying between, for example, something in
VRRC and the lower-half of VSRC which are super-registers of F8RC).
Triggering this behavior manually is difficult; I'm including two
bugpoint-reduced test cases from the test suite.
llvm-svn: 229457
Patch to explicitly add the SSE MOVQ (rr,mr,rm) instructions to SSEPackedInt domain - prevents a number of costly domain switches.
Differential Revision: http://reviews.llvm.org/D7600
llvm-svn: 229439
This adds a safe interface to the machine independent InputArg struct
for accessing the index of the original (IR-level) argument. When a
non-native return type is lowered, we generate the hidden
machine-level sret argument on-the-fly. Before this fix, we were
representing this argument as OrigArgIndex == 0, which is an outright
lie. In particular this crashed in the AArch64 backend where we
actually try to access the type of the original argument.
Now we use a sentinel value for machine arguments that have no
original argument index. AArch64, ARM, Mips, and PPC now check for this
case before accessing the original argument.
Fixes <rdar://19792160> Null pointer assertion in AArch64TargetLowering
llvm-svn: 229413
to generically lower blends and is particularly nice because it is
available frome SSE2 onward. This removes a lot of the remaining domain
crossing blends in SSE2 code.
I'm hoping to replace some of the "interleaved" lowering hacks with
something closer to this which should be more principled. First, this
needs to learn how to detect and use other interleavings besides that of
the natural type provided. That will be a follow-up patch though.
llvm-svn: 229378
This blend instruction is ... really lame. The register usage is insane.
As a consequence this is probably only *barely* better than 2 pshufbs
followed by a por, and that mostly because it only has to read from
a single memory location.
However, this doesn't fix as much as I kind of expected, so more to go.
Pretty sure that the ordering and delegation of v16i8 is just really,
really bad.
llvm-svn: 229373
template now that we can use them.
This is, of course, horribly ugly because of the required recursive
formulation. Suggestions for making it less ugly welcome.
llvm-svn: 229367
advantage of the existence of a reasonable blend instruction.
The 256-bit vector shuffle lowering has leveraged the general technique
of decomposed shuffles and blends for quite some time, but this never
made it back into the 128-bit code, and there are a large number of
patterns where this is substantially better. For example, this removes
almost all domain crossing in vector shuffles that involve some blend
and some permutation with SSE4.1 and later. See the massive reduction
in 'shufps' for integer test cases in this commit.
This isn't perfect yet for a few reasons:
1) The v8i16 shuffle lowering continues to plague me. We don't always
form an unpack-based blend when that would be better. But the wins
pretty drastically outstrip the losses here.
2) The v16i8 shuffle lowering is just a disaster here. I never went and
implemented blend support here for some terrible reason. I'll do
that next probably. I've not updated it for now.
More variations on this technique are coming as well -- we don't
shuffle-into-unpack or shuffle-into-palignr, both of which would also be
profitable.
Note that some test cases grow significantly in the number of
instructions, but I expect to actually be faster. We use
pshufd+pshufd+blendw instead of a single shufps, but the pshufd's are
very likely to pipeline well (two ports on most modern intel chips) and
the blend is a *very* fast instruction. The domain switch penalty will
essentially always be more than a blend instruction, which is the only
increase in tree height.
llvm-svn: 229350
This patch refactors the existing lowerVectorShuffleAsByteShift function to add support for 256-bit vectors on AVX2 targets.
It also fixes a tablegen issue that prevented the lowering of vpslldq/vpsrldq vec256 instructions.
Differential Revision: http://reviews.llvm.org/D7596
llvm-svn: 229311
when that will allow it to lower with a single permute instead of
multiple permutes.
It tries to detect when it will only have to do a single permute in
either case to maximize folding of loads and such.
This cuts a *lot* of the avx2 shuffle permute counts in half. =]
llvm-svn: 229309
vectors and detect equivalent inputs.
This lets the code match unpck-style instructions when only one of the
inputs are lined up but the other input is a splat and so which lanes we
pull from doesn't matter. Today, this doesn't really happen, but just by
accident. I have a patch that normalizes how we shuffle splats, and with
that patch this will be necessary for a lot of the mask equivalence
tests to work.
I don't really know how to write a test case for this specific change
until the other change lands though.
llvm-svn: 229307
don't try to do element insertion for non-zero-index floating point
vectors.
We don't have any useful patterns or lowering for element insertion into
high elements of a floating point vector, and the generic shuffle
lowering will end up being better -- namely it will fall back to unpck.
But we should try to handle other forms of element insertion before
matching unpck patterns.
While this doesn't matter much right now, I'm working on a patch that
makes unpck matching much more powerful, and that patch will break
without this re-ordering.
llvm-svn: 229306
I was somewhat surprised this pattern really came up, but it does. It
seems better to just directly handle it than try to special case every
place where we end up forming a shuffle that devolves to a shuffle of
a zero vector.
llvm-svn: 229301
subvectors from buildvectors. That doesn't really make any sense and it
breaks all of the down-stream matching of buildvectors to cleverly lower
shuffles.
With this, we now get the shift-based lowering of 256-bit vector
shuffles with AVX1 when we split them into 128-bit vectors. We also do
much better on the zero-extension patterns, although there remains quite
a bit of room for improvement here.
llvm-svn: 229299
least in theory.
I don't actually have a test case that benefits from this, but
theoretically, it could come up, and I don't want to try to think about
whether this is the culprit or something else is, so I'd rather just
make this code powerful. =/ Makes me sad that I can't really test it
though.
llvm-svn: 229298
lowerings -- one which decomposes into an initial blend followed by
a permute.
Particularly on newer chips, blends are handled independently of
shuffles and so this is much less bottlenecked on the single port that
floating point shuffles are executed with on Intel.
I'll be adding this lowering to a bunch of other code paths in
subsequent commits to handle still more places where we can effectively
leverage blends when they're available in the ISA.
llvm-svn: 229292
Patch to allow XOP instructions (integer comparison and integer multiply-add) to be commuted. The comparison instructions sometimes require the compare mode to be flipped but the remaining instructions can use default commutation modes.
This patch also sets the SSE domains of all the XOP instructions.
Differential Revision: http://reviews.llvm.org/D7646
llvm-svn: 229267
Canonicalize access to function attributes to use the simpler API.
getAttributes().getAttribute(AttributeSet::FunctionIndex, Kind)
=> getFnAttribute(Kind)
getAttributes().hasAttribute(AttributeSet::FunctionIndex, Kind)
=> hasFnAttribute(Kind)
llvm-svn: 229261
Canonicalize access to function attributes to use the simpler API.
getAttributes().getAttribute(AttributeSet::FunctionIndex, Kind)
=> getFnAttribute(Kind)
getAttributes().hasAttribute(AttributeSet::FunctionIndex, Kind)
=> hasFnAttribute(Kind)
llvm-svn: 229260
This should allow finally fixing the f64 fdiv implementation.
Test is disabled for VI since there seems to be a problem with one
of the buffer load instructions on it.
llvm-svn: 229236
Canonicalize access to function attributes to use the simpler API.
getAttributes().getAttribute(AttributeSet::FunctionIndex, Kind)
=> getFnAttribute(Kind)
getAttributes().hasAttribute(AttributeSet::FunctionIndex, Kind)
=> hasFnAttribute(Kind)
llvm-svn: 229224
Canonicalize access to function attributes to use the simpler API.
getAttributes().getAttribute(AttributeSet::FunctionIndex, Kind)
=> getFnAttribute(Kind)
getAttributes().hasAttribute(AttributeSet::FunctionIndex, Kind)
=> hasFnAttribute(Kind)
llvm-svn: 229222
Canonicalize access to function attributes to use the simpler API.
getAttributes().getAttribute(AttributeSet::FunctionIndex, Kind)
=> getFnAttribute(Kind)
getAttributes().hasAttribute(AttributeSet::FunctionIndex, Kind)
=> hasFnAttribute(Kind)
llvm-svn: 229221
Canonicalize access to function attributes to use the simpler API.
getAttributes().getAttribute(AttributeSet::FunctionIndex, Kind)
=> getFnAttribute(Kind)
getAttributes().hasAttribute(AttributeSet::FunctionIndex, Kind)
=> hasFnAttribute(Kind)
llvm-svn: 229220
Canonicalize access to function attributes to use the simpler API.
getAttributes().getAttribute(AttributeSet::FunctionIndex, Kind)
=> getFnAttribute(Kind)
getAttributes().hasAttribute(AttributeSet::FunctionIndex, Kind)
=> hasFnAttribute(Kind)
llvm-svn: 229218
Canonicalize access to function attributes to use the simpler API.
getAttributes().getAttribute(AttributeSet::FunctionIndex, Kind)
=> getFnAttribute(Kind)
getAttributes().hasAttribute(AttributeSet::FunctionIndex, Kind)
=> hasFnAttribute(Kind)
llvm-svn: 229214
This takes the preposterous number of patterns in this section
that were last added to in r219033 down to just plain obnoxious.
With a little more work, we might get this down to just comical.
I've added more test cases to the existing file that checks these
patterns, but it seems that some of these patterns simply don't
exist with today's shuffle lowering.
llvm-svn: 229158
This patch adds functionality in MIPS delay slot filler such as if delay slot
filler have to put NOP instruction into the delay slot of microMIPS JR
instruction, then instead of emitting NOP this instruction is replaced by
compact jump instruction JRC.
Differential Revision: http://reviews.llvm.org/D7522
llvm-svn: 229128
Summary:
Made the following changes:
Added calls to emitDirectiveSetNoAt() and emitDirectiveSetAt().
Added special emit function for .set at=$reg, emitDirectiveSetAtWithArg(unsigned RegNo).
Improved parsing error checks for .set at.
Refactored parser code for .set at.
Improved testing of both directives.
Improved code readability and comments.
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D7176
llvm-svn: 229097
LLVM's include tree and the use of using declarations to hide the
'legacy' namespace for the old pass manager.
This undoes the primary modules-hostile change I made to keep
out-of-tree targets building. I sent an email inquiring about whether
this would be reasonable to do at this phase and people seemed fine with
it, so making it a reality. This should allow us to start bootstrapping
with modules to a certain extent along with making it easier to mix and
match headers in general.
The updates to any code for users of LLVM are very mechanical. Switch
from including "llvm/PassManager.h" to "llvm/IR/LegacyPassManager.h".
Qualify the types which now produce compile errors with "legacy::". The
most common ones are "PassManager", "PassManagerBase", and
"FunctionPassManager".
llvm-svn: 229094
Constant pool entries are uniqued by their contents regardless of their
type. This means that a pshufb can have a shuffle mask which isn't a
simple array of bytes.
The code path which attempts to decode the mask didn't check for
failure, causing PR22559.
llvm-svn: 228979
Summary:
Implement the bulk of returning values in Mips fast-isel
Test Plan:
reatabi.ll
Passes test-suite at -O0,-O2 and with mips32r2 and mips32r1.
Reviewers: dsanders
Reviewed By: dsanders
Subscribers: llvm-commits, aemerson, rfuhler
Differential Revision: http://reviews.llvm.org/D5920
llvm-svn: 228958
The changes in r223113 (ARM modified-immediate syntax) have broken
instructions like:
mov r0, #~0xffffff00
The problem is that I've added a spurious range check on the immediate
operand to ensure that it lies between INT32_MIN and UINT32_MAX. While
this range check is correct in theory, it causes problems because the
operand is stored in an int64_t (by MC). So valid 32-bit constants like
\#~0xffffff00 become out of range. The solution is to simply remove this
range check. It is not possible to validate the range of the immediate
operand with the current setup because: 1) The operand is stored in an
int64_t by MC, 2) The immediate can be of the forms #imm, #-imm, #~imm
or even #((~imm)) etc. So we just chop the value to 32 bits and use it.
Also noted that the original range check was note tested by any of the
unit tests. I've added a new test to cover #~imm kind of operands.
Change-Id: I411e90d84312a2eff01b732bb238af536c4a7599
llvm-svn: 228920
Using KORTESTW for comparison i1 value with zero was wrong since the instruction tests 16 bits.
KORTESTW may be used with KSHIFTL+KSHIFTR that clean the 15 upper bits.
I removed (X86cmp i1, 0) pattern and zero-extend i1 to i8 and then use TESTB.
There are some cases where i1 is in the mask register and the upper bits are already zeroed.
Then KORTESTW is the better solution, but it is subject for optimization.
Meanwhile, I'm fixing the correctness issue.
llvm-svn: 228916
This gives a rough estimate of whether using pushes instead of movs is profitable, in terms of size.
We go over all calls in the MachineFunction and compute:
a) For each callsite that can not use pushes, the penalty of not having a reserved call frame.
b) For each callsite that can use pushes, the gain of actually replacing the movs with pushes (and the potential penalty of having to readjust the stack).
Differential Revision: http://reviews.llvm.org/D7561
llvm-svn: 228915
On PowerPC, which has a full set of logical operations on (its multiple sets
of) condition-register bits, it is not profitable to break of complex
conditions feeding a jump into multiple jumps. We can turn off this feature of
CGP/SDAGBuilder by marking jumps as "expensive".
P7 test-suite speedups (no regressions):
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
-0.626647% +/- 0.323583%
MultiSource/Benchmarks/Olden/power/power
-18.2821% +/- 8.06481%
llvm-svn: 228895
Summary:
Currently we have Mips32 and Mips64 disassemblers and this causes the target
triple to affect the disassembly despite all the relevant information being in
the ELF header. These implementations do not need to be separate.
This patch merges them together such that the appropriate tables are checked
for the subtarget (e.g. Mips64 is checked when GP64 is enabled).
Reviewers: vmedic
Reviewed By: vmedic
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D7498
llvm-svn: 228825
This splits collecting information from actually performing the transformation, so that we can add a heuristic in between the two.
NFC.
Differential Revision: http://reviews.llvm.org/D7497
llvm-svn: 228817
The NodeMetadata are maintained in an incremental way. When an edge between
2 nodes has its cost updated, in the course of graph reduction for example,
the NodeMetadata need first to have the old edge cost removed, then the new
edge cost added. Only once the NodeMetadata have been fully updated, it
becomes safe to consider promoting the nodes to the
ConservativelyAllocatable or OptimallyReducible sets. Previously, this
promotion was occuring right after the removing the old cost, and this was
breaking the assumption that a ConservativelyAllocatable should not be
spilled.
This patch also adds asserts to:
- enforces the invariant that a node's reduction can not be downgraded,
- only not provably allocatable or optimally reducible nodes can be spilled.
llvm-svn: 228816
This allows IDEs to recognize the entire set of header files for
each of the core LLVM projects.
Differential Revision: http://reviews.llvm.org/D7526
Reviewed By: Chris Bieneman
llvm-svn: 228798
Simply loading or storing the frame pointer is not sufficient for
Windows targets. Instead, create a synthetic frame object that we will
lower later. References to this synthetic object will be replaced with
the correct reference to the frame address.
llvm-svn: 228748
See full discussion in http://reviews.llvm.org/D7491.
We now hide the add-immediate and call instructions together in a
separate pseudo-op, which is tagged to define GPR3 and clobber the
call-killed registers. The PPCTLSDynamicCall pass prior to RA now
expands this op into the two separate addi and call ops, with explicit
definitions of GPR3 on both instructions, and explicit clobbers on the
call instruction. The pass is now marked as requiring and preserving
the LiveIntervals and SlotIndexes analyses, and fixes these up after
the replacement sequences are introduced.
Self-hosting has been verified on LE P8 and BE P7 with various
optimization levels, etc. It has also been verified with the
--no-tls-optimize flag workaround removed.
llvm-svn: 228725
Walk the instructions marked FrameSetup and consider any stores of XMM
registers to the stack as needing a SaveXMM opcode.
This fixes PR22521.
Differential Revision: http://reviews.llvm.org/D7527
llvm-svn: 228724
Added most of the missing vector folding patterns for AVX2 (as well as fixing the vpermpd and verpmq patterns)
Differential Revision: http://reviews.llvm.org/D7492
llvm-svn: 228688
This patch adds the complete AMD Bulldozer XOP instruction set to the memory folding pattern tables for stack folding, etc.
Note: Many of the XOP instructions have multiple table entries as it can fold loads from different sources.
Differential Revision: http://reviews.llvm.org/D7484
llvm-svn: 228685
This patch teaches X86FastISel how to select AVX instructions for scalar
float/double convert operations.
Before this patch, X86FastISel always selected legacy SSE instructions
for FPExt (from float to double) and FPTrunc (from double to float).
For example:
\code
define double @foo(float %f) {
%conv = fpext float %f to double
ret double %conv
}
\end code
Before (with -mattr=+avx -fast-isel) X86FastIsel selected a CVTSS2SDrr which is
legacy SSE:
cvtss2sd %xmm0, %xmm0
With this patch, X86FastIsel selects a VCVTSS2SDrr instead:
vcvtss2sd %xmm0, %xmm0, %xmm0
Added test fast-isel-fptrunc-fpext.ll to check both the register-register and
the register-memory float/double conversion variants.
Differential Revision: http://reviews.llvm.org/D7438
llvm-svn: 228682
Win64 has specific contraints on what valid prologues and epilogues look
like. This constraint is born from the flexibility and descriptiveness
of Win64's unwind opcodes.
Prologues previously emitted by LLVM could not be represented by the
unwind opcodes, preventing operations powered by stack unwinding to
successfully work.
Differential Revision: http://reviews.llvm.org/D7520
llvm-svn: 228641
veqv (vector equivalence)
vnand
vorc
I increased the AddedComplexity for these instructions to 500 to ensure they are generated instead of issuing other VSX instructions.
Phabricator review: http://reviews.llvm.org/D7469
llvm-svn: 228580
While various DAG combines try to guarantee that a vector SETCC
operation will have the same output size as input, there's nothing
intrinsic to either creation or LegalizeTypes that actually guarantees
it, so the function needs to be ready to handle a mismatch.
Fortunately this is easy enough, just extend or truncate the naturally
compared result.
I couldn't reproduce the failure in other backends that I know have
SIMD, so it's probably only an issue for these two due to shared
heritage.
Should fix PR21645.
llvm-svn: 228518
If a loop predecessor has an invoke as its terminator, and the return value
from that invoke is used to determine the loop iteration space, then we can't
insert a computation based on that value in the loop predecessor prior to the
terminator (oops). If there's such an invoke, or just no predecessor for that
matter, insert a new loop preheader.
llvm-svn: 228488
from a conditional branch fed by an add/sub/mul-with-overflow node.
We previously used the SDLoc of the overflow node, for no good reason.
In some cases, this led to the Bcc and B terminators having different
source orders, and DBG_VALUEs being inserted between them.
The real issue is with the code that can't handle DBG_VALUEs between
terminators: the few places affected by this will be fixed soon.
In the meantime, fixing the SDLoc is a positive change no matter what.
No tests, as I have no idea how to get .loc emitted for branches?
rdar://19347133
llvm-svn: 228463
Unfortunately, even with the workaround of disabling the linker TLS
optimizations in Clang restored (which has already been done), this still
breaks self-hosting on my P7 machine (-O3 -DNDEBUG -mcpu=native).
Bill is currently working on an alternate implementation to address the TLS
issue in a way that also fully elides the linker bug (which, unfortunately,
this approach did not fully), so I'm reverting this now.
llvm-svn: 228460
Doesn't seem necessary anymore. I think this was mostly compensating for
not enabling WQM for texture sampling instructions.
v2: Add test coverage
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 228373
If whole quad mode isn't enabled for these, the level of detail is
calculated incorrectly for pixels along diagonal triangle edges, causing
artifacts.
v2: Use a TSFlag instead of lots of switch cases
v3: Add test coverage
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=88642
Reviewed-by: Tom Stellard <tom@stellard.net>
llvm-svn: 228372
PassManager instance. In one case we can make the determination
from the Triple, in the other (execution dependency pass) the
pass will avoid running if we don't have any code that uses that
register class so go ahead and add it to the pipeline.
llvm-svn: 228334
dealing with module level emission. Currently this is using
the Triple to determine, but eventually the logic should
probably migrate to TLOF.
llvm-svn: 228332
PowerPC supports pre-increment load/store instructions (except for Altivec/VSX
vector load/stores). Using these on embedded cores can be very important, but
most loops are not naturally set up to use them. We can often change that,
however, by placing loops into a non-canonical form. Generically, this means
transforming loops like this:
for (int i = 0; i < n; ++i)
array[i] = c;
to look like this:
T *p = array[-1];
for (int i = 0; i < n; ++i)
*++p = c;
the key point is that addresses accessed are pulled into dedicated PHIs and
"pre-decremented" in the loop preheader. This allows the use of pre-increment
load/store instructions without loop peeling.
A target-specific late IR-level pass (running post-LSR), PPCLoopPreIncPrep, is
introduced to perform this transformation. I've used this code out-of-tree for
generating code for the PPC A2 for over a year. Somewhat to my surprise,
running the test suite + externals on a P7 with this transformation enabled
showed no performance regressions, and one speedup:
External/SPEC/CINT2006/483.xalancbmk/483.xalancbmk
-2.32514% +/- 1.03736%
So I'm going to enable it on everything for now. I was surprised by this
because, on the POWER cores, these pre-increment load/store instructions are
cracked (and, thus, harder to schedule effectively). But seeing no regressions,
and feeling that it is generally easier to split instructions apart late than
it is to combine them late, this might be the better approach regardless.
In the future, we might want to integrate this functionality into LSR (but
currently LSR does not create new PHI nodes, so (for that and other reasons)
significant work would need to be done).
llvm-svn: 228328
PowerPC supports pre-increment floating-point load/store instructions, both r+r
and r+i, and we had patterns for them, but they were not marked as legal. Mark
them as legal (and add a test case).
llvm-svn: 228327
The combine that forms extloads used to be disabled on vector types,
because "None of the supported targets knows how to perform load and
sign extend on vectors in one instruction."
That's not entirely true, since at least SSE4.1 X86 knows how to do
those sextloads/zextloads (with PMOVS/ZX).
But there are several aspects to getting this right.
First, vector extloads are controlled by a profitability callback.
For instance, on ARM, several instructions have folded extload forms,
so it's not always beneficial to create an extload node (and trying to
match extloads is a whole 'nother can of worms).
The interesting optimization enables folding of s/zextloads to illegal
(splittable) vector types, expanding them into smaller legal extloads.
It's not ideal (it introduces some legalization-like behavior in the
combine) but it's better than the obvious alternative: form illegal
extloads, and later try to split them up. If you do that, you might
generate extloads that can't be split up, but have a valid ext+load
expansion. At vector-op legalization time, it's too late to generate
this kind of code, so you end up forced to scalarize. It's better to
just avoid creating egregiously illegal nodes.
This optimization is enabled unconditionally on X86.
Note that the splitting combine is happy with "custom" extloads. As
is, this bypasses the actual custom lowering, and just unrolls the
extload. But from what I've seen, this is still much better than the
current custom lowering, which does some kind of unrolling at the end
anyway (see for instance load_sext_4i8_to_4i64 on SSE2, and the added
FIXME).
Also note that the existing combine that forms extloads is now also
enabled on legal vectors. This doesn't have a big effect on X86
(because sext+load is usually combined to sext_inreg+aextload).
On ARM it fires on some rare occasions; that's for a separate commit.
Differential Revision: http://reviews.llvm.org/D6904
llvm-svn: 228325
The return value's address must be returned in %rax.
i.e. the callee needs to copy the sret argument (%rdi)
into the return value (%rax).
This probably won't manifest as a bug when the caller is LLVM-compiled
code. But it is an ABI guarantee and tools expect it.
llvm-svn: 228321
We should be setting UnrollingPreferences::MaxCount to MAX_UINT instead
of UnrollingPreferences::Count.
Count is a 'forced unrolling factor', while MaxCount sets an upper
limit to the unrolling factor.
Setting Count to MAX_UINT was causing the loop in the testcase to be
unrolled 15 times, when it only had a maximum of 4 iterations.
llvm-svn: 228303
The llvm.SI.end.cf intrinsic is used to mark the end of if-then blocks,
if-then-else blocks, and loops. It is responsible for updating the
exec mask to re-enable threads that had been masked during the preceding
control flow block. For example:
s_mov_b64 exec, 0x3 ; Initial exec mask
s_mov_b64 s[0:1], exec ; Saved exec mask
v_cmpx_gt_u32 exec, s[2:3], v0, 0 ; llvm.SI.if
do_stuff()
s_or_b64 exec, exec, s[0:1] ; llvm.SI.end.cf
The bug fixed by this patch was one where the llvm.SI.end.cf intrinsic
was being inserted into the header of loops. This would happen when
an if block terminated in a loop header and we would end up with
code like this:
s_mov_b64 exec, 0x3 ; Initial exec mask
s_mov_b64 s[0:1], exec ; Saved exec mask
v_cmpx_gt_u32 exec, s[2:3], v0, 0 ; llvm.SI.if
do_stuff()
LOOP: ; Start of loop header
s_or_b64 exec, exec, s[0:1] ; llvm.SI.end.cf <-BUG: The exec mask has the
same value at the beginning of each loop
iteration.
do_stuff();
s_cbranch_execnz LOOP
The fix is to create a new basic block before the loop and insert the
llvm.SI.end.cf there. This way the exec mask is restored before the
start of the loop instead of at the beginning of each iteration.
llvm-svn: 228302
Patch by Kit Barton.
Add the vector count leading zeros instruction for byte, halfword,
word, and doubleword sizes. This is a fairly straightforward addition
after the changes made for vpopcnt:
1. Add the correct definitions for the various instructions in
PPCInstrAltivec.td
2. Make the CTLZ operation legal on vector types when using P8Altivec
in PPCISelLowering.cpp
Test Plan
Created new test case in test/CodeGen/PowerPC/vec_clz.ll to check the
instructions are being generated when the CTLZ operation is used in
LLVM.
Check the encoding and decoding in test/MC/PowerPC/ppc_encoding_vmx.s
and test/Disassembler/PowerPC/ppc_encoding_vmx.txt respectively.
llvm-svn: 228301
Implement a BITCAST dag combine to transform i32->mmx conversion patterns
into a X86 specific node (MMX_MOVW2D) and guarantee that moves between
i32 and x86mmx are better handled, i.e., don't use store-load to do the
conversion..
llvm-svn: 228293
Summary: When evaluating floating point instructions in the inliner, ask the TTI whether it is an expensive operation. By default, it's not an expensive operation. This keeps the default behavior the same as before. The ARM TTI has been updated to return back TCC_Expensive for targets which don't have hardware floating point.
Reviewers: chandlerc, echristo
Reviewed By: echristo
Subscribers: t.p.northover, aemerson, llvm-commits
Differential Revision: http://reviews.llvm.org/D6936
llvm-svn: 228263
v2i32, i32, trunc i32 to i16, and truc i32 to i8 stores are legal for
all address spaces. We had marked them as custom in order to lower
them for the private address space, but this is no longer necessary.
This enables lowering of misaligned stores of these types in the
DAGLegalizer.
llvm-svn: 228189
This is a bug that was caused due to storing the feature bitset in a 32-bit
variable when it is a 64-bit mask, discarding the top half of the feature set.
llvm-svn: 228151
Currently, Cortex-A72 is modelled as an Cortex-A57 except the fp
load balancing pass isn't enabled for Cortex-A72 as it's not
profitable to have it enabled for this core.
Patch by Ranjeet Singh.
llvm-svn: 228140
This associates movss and movsd with the packed single and packed double
execution domains (resp.). While this is largely cosmetic, as we now
don't have weird ping-pong-ing between single and double precision, it
is also useful because it avoids the domain fixing algorithm from seeing
domain breaks that don't actually exist. It will also be much more
important if we have an execution domain default other than packed
single, as that would cause us to mix movss and movsd with integer
vector code on a regular basis, a very bad mixture.
llvm-svn: 228135
This reverts patches 223862, 224198, 224203, and 224754, which were all
related to the vector load/store combining and were reverted/reaplied
a few times due to the same alignment problems we're seeing now.
Further tests, mainly self-hosting Clang, will be needed to reapply this
patch in the future.
llvm-svn: 228129
This is the simplest form of bit-math based blending which only fires
when we are blending with zero and is relatively profitable. I've only
enabled this path on very specific lowering strategies. I'm planning to
widen its applicability in subsequent patches, but so far you'll notice
that even though we get fewer shufps instructions, we *still* do the bit
math in the FP execution port. I'm looking into why this is still
happening.
llvm-svn: 228124
Specifically, the existing patterns were scalar-only. These cover the
packed vector bitwise operations when specifically requested with pseudo
instructions. This is particularly important in SSE1 where we can't
actually emit a logical operation on a v2i64 as that isn't a legal type.
This will be tested in subsequent patches which form the floating point
and patterns in more places.
llvm-svn: 228123
The ARM assembler allows register alias redefinitions as long as it
targets the same register. r222319 broke that. In the AArch64 case
it would just produce a new warning, but in the ARM case it would
error out on previously accepted assembler.
llvm-svn: 228109
Patch to match cases where shuffle masks can be reduced to bit shifts. Similar to byte shift shuffle matching from D5699.
Differential Revision: http://reviews.llvm.org/D6649
llvm-svn: 228047
Patch by Kit Barton.
Add the vector population count instructions for byte, halfword, word,
and doubleword sizes. There are two major changes here:
PPCISelLowering.cpp: Make CTPOP legal for vector types.
PPCRegisterInfo.td: Added v2i64 to the VRRC register
definition. This is needed for the doubleword variations of the
integer ops that were added in P8.
Test Plan
Test the instruction vpcnt* encoding/decoding in ppc64-encoding-vmx.s
Test the generation of the vpopcnt instructions for various vector
data types. When adding the v2i64 type to the Vector Register set, I
also needed to add the appropriate bit conversion patterns between
v2i64 and the existing vector types. Testing for these conversions
were also added in the test case by passing a different vector type as
a parameter into the test functions. There is also a run step that
will ensure the vpopcnt instructions are generated when the vsx
feature is disabled.
llvm-svn: 228046
What this does is that if you accidentally select these instructions on VI,
the code generation will fail, because the pseudo -> _vi mapping will be
undefined.
The idea is to be able to catch possible future bugs easily.
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 228038
This patch adds general shuffle pattern matching for the MOVQ zero-extend instruction (copy lower 64bits, zero upper) for all 128-bit integer vectors, it is added as a fallback test in lowerVectorShuffleAsZeroOrAnyExtend.
llvm-svn: 228022
Summary:
Straight-line strength reduction (SLSR) is implemented in GCC but not yet in
LLVM. It has proven to effectively simplify statements derived from an unrolled
loop, and can potentially benefit many other cases too. For example,
LLVM unrolls
#pragma unroll
foo (int i = 0; i < 3; ++i) {
sum += foo((b + i) * s);
}
into
sum += foo(b * s);
sum += foo((b + 1) * s);
sum += foo((b + 2) * s);
However, no optimizations yet reduce the internal redundancy of the three
expressions:
b * s
(b + 1) * s
(b + 2) * s
With SLSR, LLVM can optimize these three expressions into:
t1 = b * s
t2 = t1 + s
t3 = t2 + s
This commit is only an initial step towards implementing a series of such
optimizations. I will implement more (see TODO in the file commentary) in the
near future. This optimization is enabled for the NVPTX backend for now.
However, I am more than happy to push it to the standard optimization pipeline
after more thorough performance tests.
Test Plan: test/StraightLineStrengthReduce/slsr.ll
Reviewers: eliben, HaoLiu, meheff, hfinkel, jholewinski, atrick
Reviewed By: jholewinski, atrick
Subscribers: karthikthecool, jholewinski, llvm-commits
Differential Revision: http://reviews.llvm.org/D7310
llvm-svn: 228016
This patch detects consecutive vector loads using the existing
EltsFromConsecutiveLoads() logic. This fixes:
http://llvm.org/bugs/show_bug.cgi?id=22329
This patch effectively reverts the tablegen additions of D6492 /
http://reviews.llvm.org/rL224344 ...which in hindsight were a horrible hack.
The test cases that were added with that patch are simply modified to load
from varying offsets of a base pointer. These loads did not match the existing
tablegen patterns.
A happy side effect of doing this optimization earlier is that we can now fold
the load into a math op where possible; this is shown in some of the updated
checks in the test file.
Differential Revision: http://reviews.llvm.org/D7303
llvm-svn: 228006
This can happen when a REV instruction is commuted.
The trick is not to define the _vi versions of instructions, which has these
consequences:
- code generation will always fail if a pseudo cannot be lowered
(very useful to catch bugs where an unsupported instruction somehow makes
it to the printer)
- ability to query if a pseudo can be lowered, which is done in commuteOpcode
to prevent REV from commuting to non-REV on VI
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 227990
The getCommute* functions are only used with pseudos, so this commit doesn't
change anything.
The issue with missing non-rev versions of shift instructions on VI will fixed
separately.
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 227989
- V_MAC_LEGACY_F32 exists on VI, but it's VOP3-only.
- Define CVT_PK opcodes which are different between SI and VI. These are
unused. The idea is to define all chip differences.
v2: keep V_MUL_LO_U32
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 227988
These are VOP2 on SI and VOP3 on VI, and their pseudos are neither, which can
be a problem. In order to make isVOP2 and isVOP3 queries behave as expected,
the encoding must be determined first.
This doesn't fix any known issue, but better safe than sorry.
v2: add and use getMCOpcodeFromPseudo
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 227987
This fixes a hang when using an empty geometry shader.
v2: - don't add s_nop when followed by s_waitcnt
- comestic changes
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 227986
r224330 introduced a bug by misinterpreting the "FeatureVectorUAMem" bit.
The commit log says that change did not affect anything, but that's not correct.
That change allowed SSE instructions to have unaligned mem operands folded into
math ops, and that's not allowed in the default specification for any SSE variant.
The bug is exposed when compiling for an AVX-capable CPU that had this feature
flag but without enabling AVX codegen. Another mistake in r224330 was not adding
the feature flag to all AVX CPUs; the AMD chips were excluded.
This is part of the fix for PR22371 ( http://llvm.org/bugs/show_bug.cgi?id=22371 ).
This feature bit is SSE-specific, so I've renamed it to "FeatureSSEUnalignedMem".
Changed the existing test case for the feature bit to reflect the new name and
renamed the test file itself to better reflect the feature.
Added runs to fold-vex.ll to check for the failing codegen.
Note that the feature bit is not set by default on any CPU because it may require a
configuration register setting to enable the enhanced unaligned behavior.
llvm-svn: 227983
This patch is a third attempt to properly handle the local-dynamic and
global-dynamic TLS models.
In my original implementation, calls to __tls_get_addr were hidden
from view until the asm-printer phase, at which point the underlying
branch-and-link instruction was created with proper relocations. This
mostly worked well, but I used some repellent techniques to ensure
that the TLS_GET_ADDR nodes at the SD and MI levels correctly received
input from GPR3 and produced output into GPR3. This proved to work
badly in the presence of multiple TLS variable accesses, with the
copies to and from GPR3 being scheduled incorrectly and generally
creating havoc.
In r221703, I addressed that problem by representing the calls to
__tls_get_addr as true calls during instruction lowering. This had
the advantage of removing all of the bad hacks and relying on the
existing call machinery to properly glue the copies in place. It
looked like this was going to be the right way to go.
However, as a side effect of the recent discovery of problems with
linker optimizations for TLS, we discovered cases of suboptimal code
generation with this strategy. The problem comes when tls_get_addr is
called for the same address, and there is a resulting CSE
opportunity. It turns out that in such cases MachineCSE will common
the addis/addi instructions that set up the input value to
tls_get_addr, but will not common the calls themselves. MachineCSE
does not have any machinery to common idempotent calls. This is
perfectly sensible, since presumably this would be done at the IR
level, and introducing calls in the back end isn't commonplace. In
any case, we end up with two calls to __tls_get_addr when one would
suffice, and that isn't good.
I presumed that the original design would have allowed commoning of
the machine-specific nodes that hid the __tls_get_addr calls, so as
suggested by Ulrich Weigand, I went back to that design and cleaned it
up so that the copies were properly held together by glue
nodes. However, it turned out that this didn't work either...the
presence of copies to physical registers kept the machine-specific
nodes from being commoned also.
All of which leads to the design presented here. This is a return to
the original design, except that no attempt is made to introduce
copies to and from GPR3 during instruction lowering. Virtual registers
are used until prior to register allocation. At that point, a special
pass is run that identifies the machine-specific nodes that hide the
tls_get_addr calls and introduces the copies to and from GPR3 around
them. The register allocator then coalesces these copies away. With
this design, MachineCSE succeeds in commoning tls_get_addr calls where
possible, and we get nice optimal code generation (better than GCC at
the moment, which does not common these calls).
One additional problem must be dealt with: After introducing the
mentions of the physical register GPR3, the aggressive anti-dependence
breaker sees opportunities to improve scheduling by selecting a
different register instead. Flags must be used on the instruction
descriptions to tell the anti-dependence breaker to keep its hands in
its pockets.
One thing missing from the original design was recording a definition
of the link register on the GET_TLS_ADDR nodes. Doing this was found
to be insufficient to force a stack frame to be created, which led to
looping behavior because two different LR values were stored at the
same address. This appears to have been an oversight in
PPCFrameLowering::determineFrameLayout(), which is repaired here.
Because MustSaveLR() returns true for calls to builtin_return_address,
this changed the expected behavior of
test/CodeGen/PowerPC/retaddr2.ll, which now stacks a frame but
formerly did not. I've fixed the test case to reflect this.
There are existing TLS tests to catch regressions; the checks in
test/CodeGen/PowerPC/tls-store2.ll proved to be too restrictive in the
face of instruction scheduling with these changes, so I fixed that
up.
I've added a new test case based on the PrettyStackTrace module that
demonstrated the original problem. This checks that we get correct
code generation and that CSE of the calls to __get_tls_addr has taken
place.
llvm-svn: 227976
Improve EXTRACT_VECTOR_ELT DAG combine to catch conversion patterns
between x86mmx and i32 with more layers of indirection.
Before:
movq2dq %mm0, %xmm0
movd %xmm0, %eax
After:
movd %mm0, %eax
llvm-svn: 227969
Summary:
Hi Eric,
this patch cleans up the layering violation that you're fixing across backends.
Anything else I need to fix on bpf backend side?
Thanks
Reviewers: echristo
Reviewed By: echristo
Differential Revision: http://reviews.llvm.org/D7355
llvm-svn: 227865
Summary: MSVC can compile "LoopID->getOperand(0) == LoopID" when LoopID is MDNode*.
Test Plan: no regression
Reviewers: mkuper
Subscribers: jholewinski, llvm-commits
Differential Revision: http://reviews.llvm.org/D7327
llvm-svn: 227853
This is true for SI only. CI+ supports unaligned memory accesses,
but this requires driver support, so for now we disallow unaligned
accesses for all GCN targets.
llvm-svn: 227822
This avoids a partial false dependency on the previous content of
the upper lanes of the destination vector register.
Differential Revision: http://reviews.llvm.org/D7307
llvm-svn: 227820
Summary:
Previously it only avoided optimizing signed comparisons to 0.
Sometimes the DAGCombiner will optimize the unsigned comparisons
to 0 before it gets to the peephole pass, but sometimes it doesn't.
Fix for PR22373.
Test Plan: test/CodeGen/ARM/sub-cmp-peephole.ll
Reviewers: jfb, manmanren
Subscribers: aemerson, llvm-commits
Differential Revision: http://reviews.llvm.org/D7274
llvm-svn: 227809
PPCInstrInfo.cpp has ended up containing several small MI-level passes, and
this is making the file harder to read than necessary. Split out
PPCEarlyReturn into its own source file. NFC.
Now that PPCInstrInfo.cpp does not also contain pass implementations, I hope
that it will be slightly less unwieldy.
llvm-svn: 227775
PPCInstrInfo.cpp has ended up containing several small MI-level passes, and
this is making the file harder to read than necessary. Split out
PPCVSXCopy into its own source file. NFC.
llvm-svn: 227771
PPCInstrInfo.cpp has ended up containing several small MI-level passes, and
this is making the file harder to read than necessary. Split out
PPCVSXFMAMutate into its own source file. NFC.
llvm-svn: 227770
This MI-level pass was necessary when VSX support was first being developed,
specifically, before the ABI code had been updated to use VSX registers for
arguments (the register assignments did not change, in a physical sense, but
the VSX super-registers are now used). Unfortunately, I never went back and
removed this pass after that was done. I believe this code is now effectively
dead.
llvm-svn: 227767
When PPCEarlyReturn, it should really copy implicit ops from the old return
instruction to the new one. This currently does not matter much, because we run
PPCEarlyReturn very late in the pipeline (there is nothing to do DCE on
definitions of those registers). However, for completeness, we should do it
anyway.
Noticed by inspection (and there should be no functional change); thus, no
test case.
llvm-svn: 227763
The VSX store instructions were also picking up an implicit "may read" from the
default pattern, which was an intrinsic (and we don't currently have a way of
specifying write-only intrinsics).
This was causing MI verification to fail for VSX spill restores.
llvm-svn: 227759
isel is actually a cracked instruction on the P7/P8, and must start a dispatch
group. The scheduling model should reflect this so that we don't bunch too many
of them together when possible.
Thanks to Bill Schmidt and Pat Haugen for helping to sort this out.
llvm-svn: 227758
This moves the transformation introduced in r223757 into a separate MI pass.
This allows it to cover many more cases (not only cases where there must be a
reserved call frame), and perform rudimentary call folding. It still doesn't
have a heuristic, so it is enabled only for optsize/minsize, with stack
alignment <= 8, where it ought to be a fairly clear win.
(Re-commit of r227728)
Differential Revision: http://reviews.llvm.org/D6789
llvm-svn: 227752
The TOC base pointer is passed in r2, and we normally reserve this register so
that we can depend on it being there. However, for leaf functions, and
specifically those leaf functions that don't do any TOC access of their own
(which is generally due to accessing the constant pool, using TLS, etc.),
we can treat r2 as an ordinary callee-saved register (it must be callee-saved
because, for local direct calls, the linker will not insert any save/restore
code).
The allocation order has been changed slightly for PPC64/ELF systems to put r2
at the end of the list (while leaving it near the beginning for Darwin systems
to prevent unnecessary output changes). While r2 is allocatable, using it still
requires spill/restore traffic, and thus comes at the end of the list.
llvm-svn: 227745
now that we have a correct and cached subtarget specific to the
function.
Also, finish providing a cached per-function subtarget in the core
LLVMTargetMachine -- that layer hadn't switched over yet.
The only use of the TargetMachine was to re-lookup a subtarget for
a particular function to work around the fact that TTI was immutable.
Now that it is per-function and we haved a cached subtarget, use it.
This still leaves a few interfaces with real warts on them where we were
passing Function objects through the TTI interface. I'll remove these
and clean their usage up in subsequent commits now that this isn't
necessary.
llvm-svn: 227738
intermediate TTI implementation template and instead query up to the
derived class for both the TargetMachine and the TargetLowering.
Most of the derived types had a TLI cached already and there is no need
to store a less precisely typed target machine pointer.
This will in turn make it much cleaner to look up the TLI via
a per-function subtarget instead of the generic subtarget, and it will
pave the way toward pulling the subtarget used for unroll preferences
into the same form once we are *always* using the function to look up
the correct subtarget.
llvm-svn: 227737
TargetIRAnalysis access path directly rather than implementing getTTI.
This even removes getTTI from the interface. It's more efficient for
each target to just register a precise callback that creates their
specific TTI.
As part of this, all of the targets which are building their subtargets
individually per-function now build their TTI instance with the function
and thus look up the correct subtarget and cache it. NVPTX, R600, and
XCore currently don't leverage this functionality, but its trivial for
them to add it now.
llvm-svn: 227735
null.
For some reason some of the original TTI code supported a null target
machine. This seems to have been legacy, and I made matters worse when
refactoring this code by spreading that pattern further through the
various targets.
The TargetMachine can't actually be null, and it doesn't make sense to
support that use case. I've now consistently removed it and removed all
of the code trying to cope with that situation. This is probably good,
as several targets *didn't* cope with it being null despite the null
default argument in their constructors. =]
llvm-svn: 227734
terms of the new pass manager's TargetIRAnalysis.
Yep, this is one of the nicer bits of the new pass manager's design.
Passes can in many cases operate in a vacuum and so we can just nest
things when convenient. This is particularly convenient here as I can
now consolidate all of the TargetMachine logic on this analysis.
The most important change here is that this pushes the function we need
TTI for all the way into the TargetMachine, and re-creates the TTI
object for each function rather than re-using it for each function.
We're now prepared to teach the targets to produce function-specific TTI
objects with specific subtargets cached, etc.
One piece of feedback I'd love here is whether its worth renaming any of
this stuff. None of the names really seem that awesome to me at this
point, but TargetTransformInfoWrapperPass is particularly ... odd.
TargetIRAnalysisWrapper might make more sense. I would want to do that
rename separately anyways, but let me know what you think.
llvm-svn: 227731
This moves the transformation introduced in r223757 into a separate MI pass.
This allows it to cover many more cases (not only cases where there must be a
reserved call frame), and perform rudimentary call folding. It still doesn't
have a heuristic, so it is enabled only for optsize/minsize, with stack
alignment <= 8, where it ought to be a fairly clear win.
Differential Revision: http://reviews.llvm.org/D6789
llvm-svn: 227728
produce it.
This adds a function to the TargetMachine that produces this analysis
via a callback for each function. This in turn faves the way to produce
a *different* TTI per-function with the correct subtarget cached.
I've also done the necessary wiring in the opt tool to thread the target
machine down and make it available to the pass registry so that we can
construct this analysis from a target machine when available.
llvm-svn: 227721
Summary:
CUDA driver can unroll loops when jit-compiling PTX. To prevent CUDA
driver from unrolling a loop marked with llvm.loop.unroll.disable is not
unrolled by CUDA driver, we need to emit .pragma "nounroll" at the
header of that loop.
This patch also extracts getting unroll metadata from loop ID metadata
into a shared helper function.
Test Plan: test/CodeGen/NVPTX/nounroll.ll
Reviewers: eliben, meheff, jholewinski
Reviewed By: jholewinski
Subscribers: jholewinski, llvm-commits
Differential Revision: http://reviews.llvm.org/D7041
llvm-svn: 227703
GCC 4.9 gives the following warning:
warning: enumeral and non-enumeral type in conditional expression
Cast the enumeral value to an integer within the ternary operation. NFC.
llvm-svn: 227692
Summary:
This variable is only used inside an assert. This breaks builds with
asserts disabled.
OK for trunk?
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D7314
llvm-svn: 227691
This patch adds shuffle mask decodes for integer zero extends (pmovzx** and movq xmm,xmm) and scalar float/double loads/moves (movss/movsd).
Also adds shuffle mask decodes for integer loads (movd/movq).
Differential Revision: http://reviews.llvm.org/D7228
llvm-svn: 227688
base which it adds a single analysis pass to, to instead return the type
erased TargetTransformInfo object constructed for that TargetMachine.
This removes all of the pass variants for TTI. There is now a single TTI
*pass* in the Analysis layer. All of the Analysis <-> Target
communication is through the TTI's type erased interface itself. While
the diff is large here, it is nothing more that code motion to make
types available in a header file for use in a different source file
within each target.
I've tried to keep all the doxygen comments and file boilerplate in line
with this move, but let me know if I missed anything.
With this in place, the next step to making TTI work with the new pass
manager is to introduce a really simple new-style analysis that produces
a TTI object via a callback into this routine on the target machine.
Once we have that, we'll have the building blocks necessary to accept
a function argument as well.
llvm-svn: 227685
This adds some comments and splits the flag calculation on type boundaries to
make the table more readable. Addresses some post-commit review comments to SVN
r227603. NFC.
llvm-svn: 227670
type erased interface and a single analysis pass rather than an
extremely complex analysis group.
The end result is that the TTI analysis can contain a type erased
implementation that supports the polymorphic TTI interface. We can build
one from a target-specific implementation or from a dummy one in the IR.
I've also factored all of the code into "mix-in"-able base classes,
including CRTP base classes to facilitate calling back up to the most
specialized form when delegating horizontally across the surface. These
aren't as clean as I would like and I'm planning to work on cleaning
some of this up, but I wanted to start by putting into the right form.
There are a number of reasons for this change, and this particular
design. The first and foremost reason is that an analysis group is
complete overkill, and the chaining delegation strategy was so opaque,
confusing, and high overhead that TTI was suffering greatly for it.
Several of the TTI functions had failed to be implemented in all places
because of the chaining-based delegation making there be no checking of
this. A few other functions were implemented with incorrect delegation.
The message to me was very clear working on this -- the delegation and
analysis group structure was too confusing to be useful here.
The other reason of course is that this is *much* more natural fit for
the new pass manager. This will lay the ground work for a type-erased
per-function info object that can look up the correct subtarget and even
cache it.
Yet another benefit is that this will significantly simplify the
interaction of the pass managers and the TargetMachine. See the future
work below.
The downside of this change is that it is very, very verbose. I'm going
to work to improve that, but it is somewhat an implementation necessity
in C++ to do type erasure. =/ I discussed this design really extensively
with Eric and Hal prior to going down this path, and afterward showed
them the result. No one was really thrilled with it, but there doesn't
seem to be a substantially better alternative. Using a base class and
virtual method dispatch would make the code much shorter, but as
discussed in the update to the programmer's manual and elsewhere,
a polymorphic interface feels like the more principled approach even if
this is perhaps the least compelling example of it. ;]
Ultimately, there is still a lot more to be done here, but this was the
huge chunk that I couldn't really split things out of because this was
the interface change to TTI. I've tried to minimize all the other parts
of this. The follow up work should include at least:
1) Improving the TargetMachine interface by having it directly return
a TTI object. Because we have a non-pass object with value semantics
and an internal type erasure mechanism, we can narrow the interface
of the TargetMachine to *just* do what we need: build and return
a TTI object that we can then insert into the pass pipeline.
2) Make the TTI object be fully specialized for a particular function.
This will include splitting off a minimal form of it which is
sufficient for the inliner and the old pass manager.
3) Add a new pass manager analysis which produces TTI objects from the
target machine for each function. This may actually be done as part
of #2 in order to use the new analysis to implement #2.
4) Work on narrowing the API between TTI and the targets so that it is
easier to understand and less verbose to type erase.
5) Work on narrowing the API between TTI and its clients so that it is
easier to understand and less verbose to forward.
6) Try to improve the CRTP-based delegation. I feel like this code is
just a bit messy and exacerbating the complexity of implementing
the TTI in each target.
Many thanks to Eric and Hal for their help here. I ended up blocked on
this somewhat more abruptly than I expected, and so I appreciate getting
it sorted out very quickly.
Differential Revision: http://reviews.llvm.org/D7293
llvm-svn: 227669
Now that -mstack-probe-size is piped through to the backend via the function
attribute as on Windows x86, honour the value to permit handling of non-default
values for stack probes. This is needed /Gs with the clang-cl driver or
-mstack-probe-size with the clang driver when targeting Windows on ARM.
llvm-svn: 227667
Also revert r227489 since it didn't actually fix the thing I thought I
was fixing (since the test case was targeting the wrong architecture
initially). The change might be correct & demonstrated by other test
cases, but it's not a priority for me to find those test cases right
now.
Filed PR22417 for the failure.
llvm-svn: 227632
Reid Kleckner