Same as G_EXP. Add a test, and update legalizer-info-validation.mir and
f16-instructions.ll.
Differential Revision: https://reviews.llvm.org/D60165
llvm-svn: 357605
When performing an add-with-overflow with an immediate in the
range -2G ... -4G, code currently loads the immediate into a
register, which generally takes two instructions.
In this particular case, it is preferable to load the negated
immediate into a register instead, which always only requires
one instruction, and then perform a subtract.
llvm-svn: 357597
There are 3 changes to make this correspond to the same transform in instcombine:
1. Remove the legality check - we can't create anything less legal than we started with.
2. Ease the use restriction, so we only bail out if both operands have >1 use.
3. Ease the use restriction for binops with a repeated operand (eg, mul x, x).
As discussed in D60150, there's a scalarization opportunity that will be made
easier by allowing this transform more generally.
llvm-svn: 357580
Summary:
Given that X86 does not use this currently, this is an NFC. I'll
experiment with enabling and will report numbers.
Reviewers: andreadb, lebedev.ri
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D60185
llvm-svn: 357568
The test should really be checking for the property directly in the
code object headers, but there are problems with this. I don't see
this directly represented in the text form, and for the binary
emission this is depending on a function level subtarget feature to
emit a global flag.
llvm-svn: 357558
In fact we don't even need a loop at all. I backed out the bug fix this was testing for and verified that this new case hit the same issue.
This should stop D59626 from deleting some of this code by realizing it was dead due to the loop.
llvm-svn: 357544
This adds partial instruction selection support for llvm.aarch64.stlxr. It also
factors out selection for G_INTRINSIC_W_SIDE_EFFECTS into its own function. The
new function removes the restriction that the intrinsic ID on the
G_INTRINSIC_W_SIDE_EFFECTS be on operand 0.
Also add a test, and add a GISel line to arm64-ldxr-stxr.ll.
Differential Revision: https://reviews.llvm.org/D60100
llvm-svn: 357518
For shift and rotate instructions that only use the last 6 bits of the shift
amount, a shift amount of (x*64-s) can be substituted with (-s). This saves
one instruction and a register:
lhi %r1, 64
sr %r1, %r3
sllg %r2, %r2, 0(%r1)
=>
lcr %r1, %r3
sllg %r2, %r2, 0(%r1)
Review: Ulrich Weigand
llvm-svn: 357481
To disable using of odd floating-point registers (O32 ABI and
-mno-odd-spreg command line option) such registers and their
super-registers added to the set of reserved registers. In general, it
works. But there is at least one problem - in case of enabled machine
verifier pass some floating-point tests failed because live ranges of
register units that are reserved is not empty and verification pass
failed with "Live segment doesn't end at a valid instruction" error
message.
There is D35985 patch which tries to solve the problem by explicit
removing of register units. This solution did not get approval.
I would like to use another approach for prevent using odd floating
point registers - define `AltOrders` and `AltOrderSelect` for MIPS
floating point register classes. Such `AltOrders` contains reduced set
of registers. At first glance, such solution does not break any test
cases and allows enabling machine instruction verification for all MIPS
test cases.
Differential Revision: http://reviews.llvm.org/D59799
llvm-svn: 357472
There are various places in LLVM where the definition of StackID is not
properly honoured, for example in PEI where objects with a StackID > 0 are
allocated on the default stack (StackID0). This patch enforces that PEI
only considers allocating objects to StackID 0.
Reviewers: arsenm, thegameg, MatzeB
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D60062
llvm-svn: 357460
The code was previously checking that candidates for sinking had exactly
one use or were a store instruction (which can't have uses). This meant
we could sink call instructions only if they had a use.
That limitation seemed a bit arbitrary, so this patch changes it to
"instruction has zero or one use" which seems more natural and removes
the need to special-case stores.
Differential revision: https://reviews.llvm.org/D59936
llvm-svn: 357452
There's an existing optimization for x != C, but somehow it was missing
a special case for 0.
While I'm here, also cleaned up the code/comments a bit: the second
value produced by the MERGE_VALUES was actually dead, since a CMOV only
produces one result.
Differential Revision: https://reviews.llvm.org/D59616
llvm-svn: 357437
It's a little tricky to make this issue show up because
prologue/epilogue emission normally likes to push at least two
registers... but it doesn't when lr is force-spilled due to function
length. Not sure if that really makes sense, but I decided not to touch
it for now.
Differential Revision: https://reviews.llvm.org/D59385
llvm-svn: 357436
This improves selection for vector stores into v2s64s. Before we just
scalarized them, but we can just use a STRQui instead.
Differential Revision: https://reviews.llvm.org/D60083
llvm-svn: 357432
Summary:
Previously, we translate llvm.round to PTX cvt.rni, which rounds to the
even interger when the source is equidistant between two integers. This
is not correct as llvm.round should round away from zero. This change
replaces llvm.round with a round away from zero implementation through
target specific custom lowering.
Modify a few affected tests to not check for cvt.rni. Instead, we check
for the use of a few constants used in implementing round. We are also
adding CUDA runnable tests to check for the values produced by
llvm.round to test-suites/External/CUDA.
Reviewers: tra
Subscribers: jholewinski, sanjoy, jlebar, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59947
llvm-svn: 357407
This change incorporates an effort by Connor Abbot to change how we deal
with WWM operations potentially trashing valid values in inactive lanes.
Previously, the SIFixWWMLiveness pass would work out which registers
were being trashed within WWM regions, and ensure that the register
allocator did not have any values it was depending on resident in those
registers if the WWM section would trash them. This worked perfectly
well, but would cause sometimes severe register pressure when the WWM
section resided before divergent control flow (or at least that is where
I mostly observed it).
This fix instead runs through the WWM sections and pre allocates some
registers for WWM. It then reserves these registers so that the register
allocator cannot use them. This results in a significant register
saving on some WWM shaders I'm working with (130 -> 104 VGPRs, with just
this change!).
Differential Revision: https://reviews.llvm.org/D59295
llvm-svn: 357400
This patch adds an implementation of a PC-relative addressing sequence to be
used when -mcmodel=medium is specified. With absolute addressing, a 'medium'
codemodel may cause addresses to be out of range. This is because while
'medium' implies a 2 GiB addressing range, this 2 GiB can be at any offset as
opposed to 'small', which implies the first 2 GiB only.
Note that LLVM/Clang currently specifies code models differently to GCC, where
small and medium imply the same functionality as GCC's medlow and medany
respectively.
Differential Revision: https://reviews.llvm.org/D54143
Patch by Lewis Revill.
llvm-svn: 357393
Summary:
The missing `<` causes the lld command to override the test file, which fails in
environments marking the test files as readonly.
Reviewers: bkramer
Reviewed By: bkramer
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D60060
llvm-svn: 357380
Adds a `seto` pattern expansion. Without it the lowerings of `fcmp one` and
`fcmp ord` would be inefficient due to an unoptimized double negation.
Differential Revision: https://reviews.llvm.org/D59699
llvm-svn: 357378
One motivation for making this change is that the lack of using movmsk is likely
a main source of perf difference between clang and gcc on the C-Ray benchmark as
shown here:
https://www.phoronix.com/scan.php?page=article&item=gcc-clang-2019&num=5
...but this change alone isn't enough to solve that problem.
The 'all-of' examples show what is likely the worst case trade-off: we end up with
an extra instruction (or 2 if we count the 'xor' register clearing). The 'any-of'
examples look clearly better using movmsk because we've traded 2 vector instructions
for 2 scalar instructions, and movmsk may have better timing than the generic 'movq'.
If we examine the llvm-mca output for these cases, it appears that even though the
'all-of' movmsk variant looks worse on paper, it would perform better on both
Haswell and Jaguar.
$ llvm-mca -mcpu=haswell no_movmsk.s -timeline
Iterations: 100
Instructions: 400
Total Cycles: 504
Total uOps: 400
Dispatch Width: 4
uOps Per Cycle: 0.79
IPC: 0.79
Block RThroughput: 1.0
$ llvm-mca -mcpu=haswell movmsk.s -timeline
Iterations: 100
Instructions: 600
Total Cycles: 358
Total uOps: 600
Dispatch Width: 4
uOps Per Cycle: 1.68
IPC: 1.68
Block RThroughput: 1.5
$ llvm-mca -mcpu=btver2 no_movmsk.s -timeline
Iterations: 100
Instructions: 400
Total Cycles: 407
Total uOps: 400
Dispatch Width: 2
uOps Per Cycle: 0.98
IPC: 0.98
Block RThroughput: 2.0
$ llvm-mca -mcpu=btver2 movmsk.s -timeline
Iterations: 100
Instructions: 600
Total Cycles: 311
Total uOps: 600
Dispatch Width: 2
uOps Per Cycle: 1.93
IPC: 1.93
Block RThroughput: 3.0
Finally, there may be CPUs where movmsk is horribly slow (old AMD small cores?), but if
that's true, then we're also almost certainly making the wrong transform already for
reductions with >2 elements, so that should be fixed independently.
Differential Revision: https://reviews.llvm.org/D59997
llvm-svn: 357367
Negate updates flags like a subtract. We should be able to use the flags from the RMW form of negate when we have (store (X86ISD::SUB 0, load A), A)
Differential Revision: https://reviews.llvm.org/D60007
llvm-svn: 357353
This patch adds support for the RISC-V hard float ABIs, building on top of
rL355771, which added basic target-abi parsing and MC layer support. It also
builds on some re-organisations and expansion of the upstream ABI and calling
convention tests which were recently committed directly upstream.
A number of aspects of the RISC-V float hard float ABIs require frontend
support (e.g. flattening of structs and passing int+fp for fp+fp structs in a
pair of registers), and will be addressed in a Clang patch.
As can be seen from the tests, it would be worthwhile extending
RISCVMergeBaseOffsets to handle constant pool as well as global accesses.
Differential Revision: https://reviews.llvm.org/D59357
llvm-svn: 357352
Fixes PR41316 where the expanded PAVG intrinsic had had one of its ADDs turned into an OR due to its operands having no conflicting bits.
llvm-svn: 357351
vararg.ll previously missed RV64 tests. This patch also prepares for using
vararg.ll to test handling of varargs for the ilp32f/ilp32d/lp64f/lp64d hard
float ABIs. In these ABIs, varargs are passed as in either the ilp32 or lp64
ABI. Due to some slight codegen differences, different check lines are needed
for when RV32D is enabled.
llvm-svn: 357350
Summary:
Linearing the control flow by placing `try`/`end_try` markers can create
mismatches in unwind destinations. This patch resolves these mismatches
by wrapping those instructions with an incorrect unwind destination with
a nested `try`/`catch`/`end_try` and branching to the right destination
within the new catch block.
Reviewers: dschuff
Subscribers: sunfish, sbc100, jgravelle-google, chrib, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D48345
llvm-svn: 357343
Summary:
While this does not change any final output, this will greatly simplify
ixing unwind destination mismatches in CFGStackify (D48345), because we
have to create some new registers there.
Reviewers: dschuff
Subscribers: sunfish, sbc100, jgravelle-google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59652
llvm-svn: 357342
The SplitF64 node is used on RV32D to convert an f64 directly to a pair of i32
(necessary as bitcasting to i64 isn't legal). When performed on a ConstantFP,
this will result in a FP load from the constant pool followed by a store to
the stack and two integer loads from the stack (necessary as there is no way
to directly move between f64 FPRs and i32 GPRs on RV32D). It's always cheaper
to just materialise integers for the lo and hi parts of the FP constant, so do
that instead.
llvm-svn: 357341
This minimises differences in output when compiling with hardware floating
point support, which will be done in a future patch (to demonstrate the same
vararg calling convention is used).
llvm-svn: 357339
Summary:
Currently we create a routing block to the dispatch block for every
predecessor of every entry. So the total number of routing blocks
created will be (# of preds) * (# of entries). But we don't need to do
this: we need at most 2 routing blocks per loop entry, one for when the
predecessor is inside the loop and one for it is outside the loop. (We
can't merge these into one because this will creates another loop cycle
between blocks inside and blocks outside) This patch fixes this and
creates at most 2 routing blocks per entry.
This also renames variable `Split` to `Routing`, which I think is a bit
clearer.
Reviewers: kripken
Subscribers: sunfish, dschuff, sbc100, jgravelle-google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59462
llvm-svn: 357337
Summary:
This feature is not actually used for anything in the WebAssembly
backend, but adding it allows users to get it into the target features
sections of their objects, which makes these objects
future-compatible.
Reviewers: aheejin, dschuff
Subscribers: sbc100, jgravelle-google, hiraditya, sunfish, jdoerfert, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D60013
llvm-svn: 357321
This adds support for v2s32 vector inserts, and updates the selection +
regbankselect tests for G_INSERT_VECTOR_ELT.
Differential Revision: https://reviews.llvm.org/D59910
llvm-svn: 357318
We need XMM registers to handle varargs with the Win64 ABI. Before we would
silently generate bad code resulting in an assertion failure elsewhere in the
backend.
llvm-svn: 357317
Summary:
This fixes crashes when a BB in which an END_LOOP is to be placed is
unreachable and does not have any predecessors. Fixes PR41307.
Reviewers: dschuff
Subscribers: yurydelendik, sbc100, jgravelle-google, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D60004
llvm-svn: 357303
Since this can be set with s_setreg*, it should not be a subtarget
property. Set a default based on the calling convention, and Introduce
a new amdgpu-dx10-clamp attribute to override this if desired.
Also introduce a new amdgpu-ieee attribute to match.
The values need to match to allow inlining. I think it is OK for the
caller's dx10-clamp attribute to override the callee, but there
doesn't appear to be the infrastructure to do this currently without
definining the attribute in the generic Attributes.td.
Eventually the calling convention lowering will need to insert a mode
switch somewhere for these.
llvm-svn: 357302
Summary:
Nodes that have no uses are eventually pruned when they are selected
from the worklist. Record nodes newly added to the worklist or DAG and
perform pruning after every combine attempt.
Reviewers: efriedma, RKSimon, craig.topper, spatel, jyknight
Reviewed By: jyknight
Subscribers: jdoerfert, jyknight, nemanjai, jvesely, nhaehnle, javed.absar, hiraditya, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D58070
llvm-svn: 357283
The `lowerMSASplatImm` function zero-extends `i32` immediates while
building constant. If target type is `i64`, negative immediate loses
the sign. As a result, for example `__builtin_msa_ldi_d(-1)` lowered
to series of instruction loads incorrect value 0xffffffff to the `$w0`
register instead of single `ldi.d $w0, -1` instruction.
The fix zero-extends unsigned immediates and signed-extend signed
immediates.
Differential Revision: http://reviews.llvm.org/D59884
llvm-svn: 357264
After investigating the examples from D59777 targeting an SSE4.1 machine,
it looks like a very different problem due to how we map illegal types (256-bit in these cases).
We're missing a shuffle simplification that maps elements of a vector back to a shuffled operand.
We have a more general version of this transform in DAGCombiner::visitVECTOR_SHUFFLE(), but that
generality means it is limited to patterns with a one-use constraint, and the examples here have
2 uses. We don't need any uses or legality limitations for a simplification (no new value is
created).
It looks like we miss this pattern in IR too.
In one of the zext examples here, we have shuffle masks like this:
Shuf0 = vector_shuffle<0,u,3,7,0,u,3,7>
Shuf = vector_shuffle<4,u,6,7,u,u,u,u>
...so that's moving the high half of the 1st vector into the low half. But the high half of the
1st vector is already identical to the low half.
Differential Revision: https://reviews.llvm.org/D59961
llvm-svn: 357258
This is a sibling to rL357178 that I noticed we'd hit if we chose
an alternate transform in D59818.
%z = zext i8 %x to i32
%dec = add i32 %z, -1
%r = sext i32 %dec to i64
=>
%z2 = zext i8 %x to i64
%r = add i64 %z2, -1
https://rise4fun.com/Alive/kPP
The x86 vector diffs show a slight regression, so there's a chance
that we should limit this and the previous transform to scalars.
But given that we allowed vectors before, I'm matching that behavior
here. We should change both transforms together if that's the right
thing to do.
llvm-svn: 357254
In the example below, we would previously emit two range checks, one for cases
1--3 and one for 4--6. This patch makes us exploit the fact that the
fall-through is unreachable and only one range check is necessary.
switch i32 %i, label %default [
i32 1, label %bb1
i32 2, label %bb1
i32 3, label %bb1
i32 4, label %bb2
i32 5, label %bb2
i32 6, label %bb2
]
default: unreachable
llvm-svn: 357252
Summary:
PowerPC64/PowerPC64le supports the builtin function __builtin_setrnd to set the floating point rounding mode. This function will use the least significant two bits of integer argument to set the floating point rounding mode.
double __builtin_setrnd(int mode);
The effective values for mode are:
0 - round to nearest
1 - round to zero
2 - round to +infinity
3 - round to -infinity
Note that the mode argument will modulo 4, so if the int argument is greater than 3, it will only use the least significant two bits of the mode. Namely, builtin_setrnd(102)) is equal to builtin_setrnd(2).
Reviewed By: jsji
Differential Revision: https://reviews.llvm.org/D59405
llvm-svn: 357241
The register index can only really be an SGPR. Lie that a VGPR index
is legal, and then rewrite the instruction in a waterfall loop to
handle the index.
llvm-svn: 357235
A shift and add/sub sequence combination is faster in place of a multiply by constant.
Because the cycle or latency of multiply is not huge, we only consider such following
worthy patterns.
```
(mul x, 2^N + 1) => (add (shl x, N), x)
(mul x, -(2^N + 1)) => -(add (shl x, N), x)
(mul x, 2^N - 1) => (sub (shl x, N), x)
(mul x, -(2^N - 1)) => (sub x, (shl x, N))
```
And the cycles or latency is subtarget-dependent so that we need consider the
subtarget to determine to do or not do such transformation.
Also data type is considered for different cycles or latency to do multiply.
Differential Revision: https://reviews.llvm.org/D58950
llvm-svn: 357233
Summary:
It does not currently make sense to use WebAssembly features in some functions
but not others, so this CL adds an IR pass that takes the union of all used
feature sets and applies it to each function in the module. This allows us to
prevent atomics from being lowered away if some function has opted in to using
them. When atomics is not enabled anywhere, we detect whether there exists any
atomic operations or thread local storage that would be stripped and disallow
linking with objects that contain atomics if and only if atomics or tls are
stripped. When atomics is enabled, mark it as used but do not require it of
other objects in the link. These changes allow libraries that do not use atomics
to be built once and linked into both single-threaded and multithreaded
binaries.
Reviewers: aheejin, sbc100, dschuff
Subscribers: jgravelle-google, hiraditya, sunfish, jfb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59625
llvm-svn: 357226
For multi-dimensional array like below
int a[2][3];
the previous implementation generates BTF_KIND_ARRAY type
like below:
. element_type: int
. index_type: unsigned int
. number of elements: 6
This is not the best way to represent arrays, esp.,
when converting BTF back to headers and users will see
int a[6];
instead.
This patch generates proper support for multi-dimensional arrays.
For "int a[2][3]", the two BTF_KIND_ARRAY types will be
generated:
Type #n:
. element_type: int
. index_type: unsigned int
. number of elements: 3
Type #(n+1):
. element_type: #n
. index_type: unsigned int
. number of elements: 2
The linux kernel already supports such a multi-dimensional
array representation properly.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59943
llvm-svn: 357215
For 64-bit operations we should consider if the immediate can be made to fit
in an unsigned 32-bits immedate. For OR/XOR this allows us to load the immediate
with MOV32ri instead of movabsq. For AND this allows us to fold the immediate.
Differential Revision: https://reviews.llvm.org/D59867
llvm-svn: 357196
This is probably the least important of our movmsk problems, but I'm starting
at the bottom to reduce distractions.
We were creating a select_cc which bypasses the select and bitmask codegen
optimizations that we have now. If we produce a compare+negate instead, we
allow things like neg/sbb carry bit hacks, and in all cases we avoid a cmov.
There's no partial register update danger in these sequences because we always
produce the zero-register xor ahead of the 'set' if needed.
There seems to be a missing fold for sext of a bool bit here:
negl %ecx
movslq %ecx, %rax
...but that's an independent transform.
Differential Revision: https://reviews.llvm.org/D59818
llvm-svn: 357172
Summary:
This adds a BranchFusion feature to replace the usage of the MacroFusion
for AMD CPUs.
See D59688 for context.
Reviewers: andreadb, lebedev.ri
Subscribers: hiraditya, jdoerfert, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59872
llvm-svn: 357171
If scalar truncates are free, attempt to pre-truncate build_vectors source operands.
Only attempt to do this before legalization as we often end up with truncations/extensions during build_vector lowering.
Differential Revision: https://reviews.llvm.org/D59654
llvm-svn: 357161
G_SELECT uses a 1-bit scalar for the condition, and is currently
implemented with a plain CMPri against 0. This means that values such as
0x1110 are interpreted as true, when instead the higher bits should be
treated as undefined and therefore ignored. Replace the CMPri with a
TSTri against 0x1, which performs an implicit AND, yielding the expected
result.
llvm-svn: 357153
Summary:
Add tests for selection across basic block boundary:
* one test containing a buffer load, where part of the offset
computation is placed in the predecessor of the load
* similar test, but containing two buffer loads and shared
computations
Please note that the behaviour being tested will be updated in
a subsequent commit.
This commit was extracted from https://reviews.llvm.org/D59535.
Reviewers: RKSimon
Reviewed By: RKSimon
Subscribers: jvesely, nhaehnle, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59690
llvm-svn: 357149
If we know the 2 halves of an oversized zext-in-reg are the same,
don't create those halves independently.
I tried several different approaches to fold this, but it's difficult
to get right during legalization. In the default path, we are creating
a generic shuffle that looks like an unpack high, but it can get
transformed into a different mask (a blend), so it's not
straightforward to match that. If we try to fold after it actually
becomes an X86ISD::UNPCKH node, we can't be sure what the operand node
is - it might be a generic shuffle, or it could be some x86-specific op.
From the test output, we should be doing something like this for SSE4.1
as well, but I'd rather leave that as a follow-up since it involves
changing lowering actions.
Differential Revision: https://reviews.llvm.org/D59777
llvm-svn: 357129
When lowering a load or store for TypeWidenVector, the type legalizer
would use a single load or store if the associated integer type was legal
or promoted. E.g. it loads a v4i8 as an i32 if i32 is legal/promotable.
(See https://reviews.llvm.org/rL236528 for reference.)
This applies that behaviour to vector types. If the vector type is
TypePromoteInteger, the element type is going to be TypePromoteInteger
as well, which will lead to have a single promoting load rather than N
individual promoting loads. For instance, if we have a v3i1, we would
now have a load of v4i1 instead of 3 loads of i1.
Patch by Guillaume Marques. Thanks!
Differential Revision: https://reviews.llvm.org/D56201
llvm-svn: 357120
ARMBaseInstrInfo::getNumLDMAddresses is making bad assumptions about the
memory operands of load and store-multiple operations. This doesn't
really fix the problem properly, but it's enough to prevent crashing,
at least.
Fixes https://bugs.llvm.org/show_bug.cgi?id=41231 .
Differential Revision: https://reviews.llvm.org/D59834
llvm-svn: 357109
If there were only dbg_values in the block, recede would hit the
beginning of the block and try to use thet dbg_value as a real
instruction.
llvm-svn: 357105
The artifact combiners push instructions which have been marked for deletion
onto an list for the legalizer to deal with on return. However, for trunc(ext)
combines the combiner routine recursively calls itself. When it does this the
dead instructions list may not be empty, and the other combiners don't expect
to be dealing with essentially invalid MIR (multiple vreg defs etc).
This change fixes it by ensuring that the dead instructions are processed on
entry into tryCombineInstruction.
As a result, this fix exposed a few places in tests where G_TRUNC instructions
were not being deleted even though they were dead.
Differential Revision: https://reviews.llvm.org/D59892
llvm-svn: 357101
This reapplies r356149, using the correct overload of findUnusedReg
which passes the current iterator.
This worked most of the time, because the scavenger iterator was moved
at the end of the frame index loop in PEI. This would fail if the
spill was the first instruction. This was further hidden by the fact
that the scavenger wasn't passed in for normal frame index
elimination.
llvm-svn: 357098
Haswell CPUs have special support for SHLD/SHRD with the same register for both sources. Such an instruction will go to the rotate/shift unit on port 0 or 6. This gives it 1 cycle latency and 0.5 cycle reciprocal throughput. When the register is not the same, it becomes a 3 cycle operation on port 1. Sandybridge and Ivybridge always have 1 cyc latency and 0.5 cycle reciprocal throughput for any SHLD.
When FastSHLDRotate feature flag is set, we try to use SHLD for rotate by immediate unless BMI2 is enabled. But MachineCopyPropagation can look through a copy and change one of the sources to be different. This will break the hardware optimization.
This patch adds psuedo instruction to hide the second source input until after register allocation and MachineCopyPropagation. I'm not sure if this is the best way to do this or if there's some other way we can make this work.
Fixes PR41055
Differential Revision: https://reviews.llvm.org/D59391
llvm-svn: 357096
This patch removes an overly conservative check that would prevent
simplifying copies when the value we were tracking would go through
several subregister indices.
Indeed, the intend of this check was to not track values whenever
we have to compose subregister, but actually what the check was
doing was bailing anytime we see a second subreg, even if that
second subreg would actually be the new source of truth (as opposed
to a part of that subreg).
Differential Revision: https://reviews.llvm.org/D59891
llvm-svn: 357095
Also includes one example of how this transform is unsound. This isn't
verifying the copies are used in the control flow intrinisic patterns.
Also add option to disable exec mask opt pass. Since this pass is
unsound, it may be useful to turn it off until it is fixed.
llvm-svn: 357091
The AMDGPU implementation of getReservedRegs depends on
MachineFunctionInfo fields that are parsed from the YAML section. This
was reserving the wrong register since it was setting the reserved
regs before parsing the correct one.
Some tests were relying on the default reserved set for the assumed
default calling convention.
llvm-svn: 357083
The .BTF.ext FuncInfoTable and LineInfoTable contain
information organized per ELF section. Current definition
of FuncInfoTable/LineInfoTable is:
std::unordered_map<uint32_t, std::vector<BTFFuncInfo>> FuncInfoTable
std::unordered_map<uint32_t, std::vector<BTFLineInfo>> LineInfoTable
where the key is the section name off in the string table.
The unordered_map may cause the order of section output
different for different platforms.
The same for unordered map definition of
std::unordered_map<std::string, std::unique_ptr<BTFKindDataSec>>
DataSecEntries
where BTF_KIND_DATASEC entries may have different ordering
for different platforms.
This patch fixed the issue by using std::map.
Test static-var-derived-type.ll is modified to generate two
DataSec's which will ensure the ordering is the same for all
supported platforms.
Signed-off-by: Yonghong Song <yhs@fb.com>
llvm-svn: 357077
Original commit by Ayonam Ray.
This commit adds a regression test for the issue discovered in the
previous commit: that the range check for the jump table can only be
omitted if the fall-through destination of the jump table is
unreachable, which isn't necessarily true just because the default of
the switch is unreachable.
This addresses the missing optimization in PR41242.
> During the lowering of a switch that would result in the generation of a
> jump table, a range check is performed before indexing into the jump
> table, for the switch value being outside the jump table range and a
> conditional branch is inserted to jump to the default block. In case the
> default block is unreachable, this conditional jump can be omitted. This
> patch implements omitting this conditional branch for unreachable
> defaults.
>
> Differential Revision: https://reviews.llvm.org/D52002
> Reviewers: Hans Wennborg, Eli Freidman, Roman Lebedev
llvm-svn: 357067
Enable SSE41 ZERO_EXTEND_VECTOR_INREG shuffle combines - for the PMOVZX(PSHUFD(V)) -> UNPCKH(V,0) pattern we reduce the shuffles (port5-bottleneck on Intel) at the expense of creating a zero (pxor v,v) and an extra register move - which is a good trade off as these are pretty cheap and in most cases it doesn't increase register pressure.
This also exposed a missed opportunity to use combine to ZERO_EXTEND_VECTOR_INREG with folded loads - even if we're in the float domain.
........
Causes PR41249
llvm-svn: 357057
getAsCarry() checks that the input argument is a carry-producing node before
allowing a transformation to addcarry. This patch adds a check to make sure
that the carry-producing node is legal. If it is not, it may not remain in a
form that is manageable by the target backend. The test case caused a
compilation failure during instruction selection for this reason on SystemZ.
Patch by Ulrich Weigand.
Review: Sanjay Patel
https://reviews.llvm.org/D59822
llvm-svn: 357052
We handle the case where the C2 does not fit in a signed 32-bit immediate, but
(C2>>C1) does. But there's also some 64-bit opportunities when C2 is not an unsigned
32-bit immediate, but (C2>>C1) is. For OR/XOR this allows us to load the
immediate with with MOV32ri instead of a movabsq. For AND it allows us to use a
32-bit AND and fold the immediate.
llvm-svn: 357050
Previously we manually selected the AND/OR/XOR with immediate and the SHL(or ADD if the shift is 1). But this was missing out on the opportunity to use a 64 bit AND with a 32-bit immediate and possibly other isel tricks we have built into the tables.
Instead, insert the new nodes into the DAG using insertDAGNode and allow them each to be selected through the normal table.
llvm-svn: 357049
A section containing metadata on remark diagnostics will be emitted if
the flag (-mllvm) -remarks-section is present.
For now, the metadata is:
* a magic number for remarks: "REMARKS\0"
* the version number: a little-endian uint64_t
* the absolute file path to the serialized remark diagnostics: a
null-terminated string.
Differential Revision: https://reviews.llvm.org/D59571
llvm-svn: 357043
When splitting a subrange we end up with two different subranges covering
two different, non overlapping, lanes.
As part of this splitting the VNIs of the original live-range need
to be dispatched to the subranges according to which lanes they are
actually defining.
Prior to this patch we were assuming that all values were defining
all lanes. This was wrong as demonstrated by llvm.org/PR40835.
Differential Revision: https://reviews.llvm.org/D59731
llvm-svn: 357032
We have the folds for fadd/fsub/fmul already in DAGCombiner,
so it may be possible to remove that code if we can guarantee that
these ops are zapped before they can exist.
llvm-svn: 357029
The UseVSXReg flag can be safely removed and the code cleaned up.
Patch By: Yi-Hong Liu
Differential Revision: https://reviews.llvm.org/D58685
llvm-svn: 357028
This change implements lowering of references global symbols in PIC
mode.
This change implements lowering of global references in PIC mode using a
new @GOT reference type. @GOT references can be used with function or
data symbol names combined with the get_global instruction. In this case
the linker will insert the wasm global that stores the address of the
symbol (either in memory for data symbols or in the wasm table for
function symbols).
For now I'm continuing to use the R_WASM_GLOBAL_INDEX_LEB relocation
type for this type of reference which means that this relocation type
can refer to either a global or a function or data symbol. We could
choose to introduce specific relocation types for GOT entries in the
future. See the current dynamic linking proposal:
https://github.com/WebAssembly/tool-conventions/blob/master/DynamicLinking.md
Differential Revision: https://reviews.llvm.org/D54647
llvm-svn: 357022
Summary:
`WebAssembly::analyzeBranch` now does not analyze anything if the
function is CFG stackified. We were previously doing similar things by
checking if a branch's operand is whether an integer or an MBB, but this
failed to bail out when a BB did not have any terminators.
Consider this case:
```
bb0:
try $label0
call @foo // unwinds to %ehpad
bb1:
...
br $label0 // jumps to %cont. can be deleted
ehpad:
catch
...
cont:
end_try
```
Here `br $label0` will be deleted in CFGStackify's
`removeUnnecessaryInstrs` function, because we jump to the %cont block
even without the branch. But in this case, MachineVerifier fails to
verify this, because `ehpad` is not a successor of `bb1` even if `bb1`
does not have any terminators. MachineVerifier incorrectly thinks `bb1`
falls through to the next block.
This pass now consistently rejects all analysis after CFGStackify
whether a BB has terminators or not, also making the MachineVerifier
work. (MachineVerifier does not try to verify relationships between BBs
if `analyzeBranch` fails, the behavior we want after CFGStackify.)
This also adds a new option `-wasm-disable-ehpad-sort` for testing. This
option helps create the sorted order we want to test, and without the
fix in this patch, the tests in cfg-stackify-eh.ll fail at
MachineVerifier with `-wasm-disable-ehpad-sort`.
Reviewers: dschuff
Subscribers: sunfish, sbc100, jgravelle-google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59740
llvm-svn: 357015
Summary:
This adds `CFGStackified` field and its serialization to
WebAssemblyFunctionInfo.
Reviewers: dschuff
Subscribers: sunfish, sbc100, jgravelle-google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59747
llvm-svn: 357011
Summary:
The framework for supporting target-specific MachineFunctionInfo was
added in r356215. This adds serialization support for
WebAssemblyFunctionInfo on top of that. This patch only adds the
framework and does not actually serialize anything at this point; we
have to add YAML mapping later for the fields in WebAssemblyFunctionInfo
we want to serialize if necessary.
Reviewers: dschuff, arsenm
Subscribers: sunfish, wdng, sbc100, jgravelle-google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59737
llvm-svn: 357009
Summary:
When TRY and LOOP markers are in the same BB and END_TRY and END_LOOP
markers are in the same BB, END_TRY should be _before_ END_LOOP, because
LOOP is always before TRY if they are in the same BB. (TRY is placed in
the latest possible position, whereas LOOP is in the earliest possible
position.)
Reviewers: dschuff
Subscribers: sunfish, sbc100, jgravelle-google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59751
llvm-svn: 357008
Summary:
Before we placed all TRY/END_TRY markers before placing BLOCK/END_BLOCK
markers. This couldn't handle this case:
```
bb0:
br bb2
bb1: // nearest common dominator of bb3 and bb4
br_if ... bb3
br bb4
bb2:
...
bb3:
call @foo // unwinds to ehpad
bb4:
call @bar // unwinds to ehpad
ehpad:
catch
...
```
When we placed TRY markers, we placed it in bb1 because it is the
nearest common dominator of bb3 and bb4. But because bb0 jumps to bb2,
when we placed block markers, we ended up with interleaved scopes like
```
block
try
end_block
catch
end_try
```
which was not correct.
This patch fixes the bug by placing BLOCK and TRY markers in one pass
while iterating BBs in a function. This also adds some more routines to
`placeTryMarkers`, because we now have to assume that there can be
previously placed BLOCK and END_BLOCK.
Reviewers: dschuff
Subscribers: sunfish, sbc100, jgravelle-google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59739
llvm-svn: 357007
Various SelectionDAG non-combine operations (e.g. the getNode smart
constructor and legalization) may leave dangling nodes by applying
optimizations or not fully pruning unused result values. This can
result in nodes that are never added to the worklist and therefore can
not be pruned.
Add a node inserter as the current node deleter to make sure such
nodes have the chance of being pruned.
Many minor changes, mostly positive.
llvm-svn: 356996
Adds two patterns to improve the codegen of GPR value comparisons with small
constants. Instead of first loading the constant into another register and then
doing an XOR of those registers, these patterns directly use the constant as an
XORI immediate.
llvm-svn: 356990
This helps us relax the extension of a lot of scalar elements before they are inserted into a vector.
Its exposes an issue in DAGCombiner::convertBuildVecZextToZext as some/all the zero-extensions may be relaxed to ANY_EXTEND, so we need to handle that case to avoid a couple of AVX2 VPMOVZX test regressions.
Once this is in it should be easier to fix a number of remaining failures to fold loads into VBROADCAST nodes.
Differential Revision: https://reviews.llvm.org/D59484
llvm-svn: 356989
DenseMap iteration order is not guaranteed, use MapVector instead.
Fix provided by srhines.
Differential Revision: https://reviews.llvm.org/D59807
llvm-svn: 356988
This should hopefully lead to minor improvements in code generation, and
more accurate spill/reload comments in assembly.
Also fix isLoadFromStackSlotPostFE/isStoreToStackSlotPostFE so they
don't lead to misleading assembly comments for merged memory operands;
this is technically orthogonal, but in practice the relevant memory
operand lists don't show up without this change.
Differential Revision: https://reviews.llvm.org/D59713
llvm-svn: 356963
Without a VALU instruction in the return block, these were mostly
testing the path to delete exec mask code before s_endpgm rather than
the end cf handling.
llvm-svn: 356955
This is generally more readable due to the way the assembler aliases
work.
(This causes a lot of test changes, but it's not really as scary as it
looks at first glance; it's just mechanically changing a bunch of checks
for orr to check for mov instead.)
Differential Revision: https://reviews.llvm.org/D59720
llvm-svn: 356954
First half of PR40800, this patch adds DAG undef handling to icmp instructions to match the behaviour in llvm::ConstantFoldCompareInstruction and SimplifyICmpInst, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.).
This involved a lot of tweaking to reduced tests as bugpoint loves to reduce icmp arguments to undef........
Differential Revision: https://reviews.llvm.org/D59363
llvm-svn: 356938
I think this is correct, but may not necessarily be the correct fix
for the assertion I'm really trying to solve. If a scheduling region
was found that only has dbg_value instructions, the RegPressure
tracker would end up in an inconsistent state because it would skip
over any debug instructions and point to an instruction outside of the
scheduling region. It may still be possible for this to happen if
there are some real schedulable instructions between dbg_values, but I
haven't managed to break this.
The testcase is extremely sensitive and I'm not sure how to make it
more resistent to future scheduler changes that would avoid stressing
this situation.
llvm-svn: 356926
Remove the IR part from test/CodeGen/X86/regalloc-copy-hints.mir (added by
r355854).
To make the test remain functional, the parts of the MBB names referring to
BB names have been removed, as well as all machine memory operands.
llvm-svn: 356899
Move selectCopy into MipsInstructionSelector class.
Select copy for arguments from FPRBRegBank for MIPS32.
Differential Revision: https://reviews.llvm.org/D59644
llvm-svn: 356886
Add floating point register bank for MIPS32.
Implement getRegBankFromRegClass for float register classes.
Differential Revision: https://reviews.llvm.org/D59643
llvm-svn: 356883
Lower float and double arguments in registers for MIPS32.
When float/double argument is passed through gpr registers
select appropriate move instruction.
Differential Revision: https://reviews.llvm.org/D59642
llvm-svn: 356882
We currently use only VLDR/VSTR for all 64-bit loads/stores, so the
memory operands must be word-aligned. Mark aligned operations as legal
and narrow non-aligned ones to 32 bits.
While we're here, also mark non-power-of-2 loads/stores as unsupported.
llvm-svn: 356872
Enable SSE41 ZERO_EXTEND_VECTOR_INREG shuffle combines - for the PMOVZX(PSHUFD(V)) -> UNPCKH(V,0) pattern we reduce the shuffles (port5-bottleneck on Intel) at the expense of creating a zero (pxor v,v) and an extra register move - which is a good trade off as these are pretty cheap and in most cases it doesn't increase register pressure.
This also exposed a missed opportunity to use combine to ZERO_EXTEND_VECTOR_INREG with folded loads - even if we're in the float domain.
llvm-svn: 356864
Just enable this for AVX for now as SSE41 introduces extra register moves for the PMOVZX(PSHUFD(V)) -> UNPCKH(V,0) pattern (but otherwise helps reduce port5 usage on Intel targets).
Only AVX support is required for PR40685 as the issue is due to 8i8->8i32 zext shuffle leftovers.
llvm-svn: 356858
This is yet another step towards solving PR14613:
https://bugs.llvm.org/show_bug.cgi?id=14613
uaddsat X, Y --> (X >u (X + Y)) ? -1 : X + Y
usubsat X, Y --> (X >u Y) ? X - Y : 0
We can't count on a sane vector ISA, so override the default (umin/umax)
expansion of unsigned add/sub saturate in cases where we do not have umin/umax.
Differential Revision: https://reviews.llvm.org/D59006
llvm-svn: 356855
In r322972/r323136, the iteration here was changed to catch cases at the
beginning of a basic block... but we accidentally deleted an important
safety check. Restore that check to the way it was.
Fixes https://bugs.llvm.org/show_bug.cgi?id=41116
Differential Revision: https://reviews.llvm.org/D59680
llvm-svn: 356809
On 32-bit targets without popcnt, we currently expand 64-bit popcnt to sequences of arithmetic and logic ops for each 32-bit half and then add the 32 bit halves together. If we have xmm registers we can use use those to implement the operation instead. This results in less instructions then doing two separate 32-bit popcnt sequences.
This mitigates some of PR41151 for the i64 on i686 case when we have SSE2.
Differential Revision: https://reviews.llvm.org/D59662
llvm-svn: 356808
We used a lock cmpxchg8b to do i64 atomic loads. But if we have SSE2 we can do better and use a plain movq to do the load instead.
I tried to just use an f64 atomic load and add isel patterns to MOVSD(which the domain fixing pass can turn to MOVQ), but the atomic_load SDNode in TargetSelectionDAG.td requires the type to be integer.
So I've emitted VZEXT_LOAD instead which should be selected by isel to a MOVQ. Hopefully we don't need a specific atomic flavor of this. I kept the memory operand from the original AtomicSDNode. I wasn't sure if I might need to set the MOVolatile flag?
I've left some FIXMEs for improvements we can do without SSE2.
Differential Revision: https://reviews.llvm.org/D59679
llvm-svn: 356807
Just as as llvm IR supports explicitly specifying numeric value ids
for instructions, and emits them by default in textual output, now do
the same for blocks.
This is a slightly incompatible change in the textual IR format.
Previously, llvm would parse numeric labels as string names. E.g.
define void @f() {
br label %"55"
55:
ret void
}
defined a label *named* "55", even without needing to be quoted, while
the reference required quoting. Now, if you intend a block label which
looks like a value number to be a name, you must quote it in the
definition too (e.g. `"55":`).
Previously, llvm would print nameless blocks only as a comment, and
would omit it if there was no predecessor. This could cause confusion
for readers of the IR, just as unnamed instructions did prior to the
addition of "%5 = " syntax, back in 2008 (PR2480).
Now, it will always print a label for an unnamed block, with the
exception of the entry block. (IMO it may be better to print it for
the entry-block as well. However, that requires updating many more
tests.)
Thus, the following is supported, and is the canonical printing:
define i32 @f(i32, i32) {
%3 = add i32 %0, %1
br label %4
4:
ret i32 %3
}
New test cases covering this behavior are added, and other tests
updated as required.
Differential Revision: https://reviews.llvm.org/D58548
llvm-svn: 356789
Some image ops return three or five dwords. Previously, we modeled that
with a 4 or 8 dword register class. The register allocator could
cleverly spot that some subregs were dead and allocate something else
there, but that caused the de-optimization that waitcnt insertion would
think that the result was used immediately.
This commit allows such an image op to have a result with a three or
five dword result, avoiding the above de-optimization.
Differential Revision: https://reviews.llvm.org/D58905
Change-Id: I3651211bbd7ed22721ee7b9fefd7bcc60a809d8b
llvm-svn: 356757
Now we have vec3 MVTs, this commit implements dwordx3 variants of the
buffer intrinsics.
On gfx6, a dwordx3 buffer load intrinsic is implemented as a dwordx4
instruction, and a dwordx3 buffer store intrinsic is not supported.
We need to support the dwordx3 load intrinsic because it is generated by
subtarget-unaware code in InstCombine.
Differential Revision: https://reviews.llvm.org/D58904
Change-Id: I016729d8557b98a52f529638ae97c340a5922a4e
llvm-svn: 356755
The RISC-V ISA defines RV32E as an alternative "base" instruction set
encoding, that differs from RV32I by having only 16 rather than 32 registers.
This patch adds basic definitions for RV32E as well as MC layer support
(assembling, disassembling) and tests. The only supported ABI on RV32E is
ILP32E.
Add a new RISCVFeatures::validate() helper to RISCVUtils which can be called
from codegen or MC layer libraries to validate the combination of TargetTriple
and FeatureBitSet. Other targets have similar checks (e.g. erroring if SPE is
enabled on PPC64 or oddspreg + o32 ABI on Mips), but they either duplicate the
checks (Mips), or fail to check for both codegen and MC codepaths (PPC).
Codegen for the ILP32E ABI support and RV32E codegen are left for a future
patch/patches.
Differential Revision: https://reviews.llvm.org/D59470
llvm-svn: 356744
This patch optimizes the emission of a sequence of SELECTs with the same
condition, avoiding the insertion of unnecessary control flow. Such a sequence
often occurs when a SELECT of values wider than XLEN is legalized into two
SELECTs with legal types. We have identified several use cases where the
SELECTs could be interleaved with other instructions. Therefore, we extend the
sequence to include non-SELECT instructions if we are able to detect that the
non-SELECT instructions do not impact the optimization.
This patch supersedes https://reviews.llvm.org/D59096, which attempted to
address this issue by introducing a new SelectionDAG node. Hat tip to Eli
Friedman for his feedback on how to best handle this issue.
Differential Revision: https://reviews.llvm.org/D59355
Patch by Luís Marques.
llvm-svn: 356741
Indicates in the TargetLowering interface that conversions from CC logic to
bitwise logic are allowed. Adds tests that show the benefit when optimization
opportunities are detected. Also adds tests that show that when the optimization
is not applied correct code is generated (but opportunities for other
optimizations remain).
Differential Revision: https://reviews.llvm.org/D59596
Patch by Luís Marques.
llvm-svn: 356740
They are not used by anything yet, but a subsequent commit will start
using them for image ops that return 5 dwords.
Differential Revision: https://reviews.llvm.org/D58903
Change-Id: I63e1904081e39a6d66e4eb96d51df25ad399d271
llvm-svn: 356735
The DataSecEentries is defined as an unordered_map since
order does not really matter.
std::unordered_map<std::string, std::unique_ptr<BTFKindDataSec>>
DataSecEntries;
This seems causing the test static-var-derived-type.ll flaky
as two sections ".bss" and ".readonly" have undeterministic
ordering when performing map iterating, which decides the
output assembly code sequence of BTF_KIND_DATASEC entries.
Fix the test to have only one data section to remove
flakiness.
Signed-off-by: Yonghong Song <yhs@fb.com>
llvm-svn: 356731
Currently, the type id for a derived type is computed incorrectly.
For example,
type #1: int
type #2: ptr to #1
For a global variable "int *a", type #1 will be attributed to variable "a".
This is due to a bug which assigns the type id of the basetype of
that derived type as the derived type's type id. This happens
to "const", "volatile", "restrict", "typedef" and "pointer" types.
This patch fixed this bug, fixed existing test cases and added
a new one focusing on pointers plus other derived types.
Signed-off-by: Yonghong Song <yhs@fb.com>
llvm-svn: 356727
This is the result of discussions on the list about how to deal with intrinsics
which require codegen to disambiguate them via only the integer/fp overloads.
It causes problems for GlobalISel as some of that information is lost during
translation, while with other operations like IR instructions the information is
encoded into the instruction opcode.
This patch changes clang to emit the new faddp intrinsic if the vector operands
to the builtin have FP element types. LLVM IR AutoUpgrade has been taught to
upgrade existing calls to aarch64.neon.addp with fp vector arguments, and
we remove the workarounds introduced for GlobalISel in r355865.
This is a more permanent solution to PR40968.
Differential Revision: https://reviews.llvm.org/D59655
llvm-svn: 356722
This was creating a copy of the register the pseudo itself was
def'ing, leaving a copy of an undefined register. I'm not sure how
the verifier is not catching this, but this avoids asserting in a
future change to RegAllocFast
llvm-svn: 356716
The AArch64 test was broken since the result register already had a
set register class, so this test was a no-op. The mapping verify call
would fail because the result size is not the same as the inputs like
in a copy or phi.
The AMDGPU testcases are half broken and introduce illegal VGPR->SGPR
copies which need much more work to handle correctly (same for phis),
but add them as a baseline.
llvm-svn: 356713
Under optsize we try to avoid folding immediates into instructions under optsize. But if the immediate is 16-bits or 32 bits, but can be encoded as an 8-bit immediate we don't save enough from disabling the folding unless the immediate has enough uses to make up for the size of the move which is either 3 bytes or 5 bytes since there are no sign extended 8-bit moves. We would also save something if the immediate was a live out of the basic block and thus a move was unavoidable, but that would require a more advanced heuristic than just counting uses.
Note we only avoid folding multiple use immediates into the patterns that use X86ISD::ADD/SUB/XOR/OR/AND/CMP/ADC/SBB nodes and not the more common ISD::ADD/SUB/XOR/OR/AND nodes.
Differential Revision: https://reviews.llvm.org/D59522
llvm-svn: 356688
This adds support for scalarizing these intrinsics as well the X86TargetTransformInfo support to avoid scalarizing them in the cases X86 can handle.
I've omitted handling special cases for constant masks for this first pass. Though CodeGenPrepare can constant fold the branch conditions and remove some of the control flow anyway.
Fixes PR40994 and is covers most of PR3666. Might want to implement constant masks to close that.
Differential Revision: https://reviews.llvm.org/D59180
llvm-svn: 356687
This is probably a bigger limitation than necessary, but since we don't have any evidence yet
that this transform led to real-world perf improvements rather than regressions, I'm making a
quick, blunt fix.
In the motivating x86 example from:
https://bugs.llvm.org/show_bug.cgi?id=41129
...and shown in the regression test, we want to avoid an extra instruction in the dominating
block because that could be costly.
The x86 LSR test diff is reversing the changes from D57789. There's no evidence that 1 version
is any better than the other yet.
Differential Revision: https://reviews.llvm.org/D59602
llvm-svn: 356665
Added support for dwordx3 for most load/store types, but not DS, and not
intrinsics yet.
SI (gfx6) does not have dwordx3 instructions, so they are not enabled
there.
Some of this patch is from Matt Arsenault, also of AMD.
Differential Revision: https://reviews.llvm.org/D58902
Change-Id: I913ef54f1433a7149da8d72f4af54dbb13436bd9
llvm-svn: 356659
Added subtarget features for AArch64 to use TPIDR_EL[1|2|3] as the TLS base
register, rather than the default TPIDR_EL0.
Patch by Philip Derrin!
Differential revision: https://reviews.llvm.org/D54685
llvm-svn: 356657
CMPXCHG8B was introduced on i586/pentium generation.
If its not enabled, limit the atomic width to 32 bits so the AtomicExpandPass will expand to lib calls. Unclear if we should be using a different limit for other configs. The default is 1024 and experimentation shows that using an i256 atomic will cause a crash in SelectionDAG.
Differential Revision: https://reviews.llvm.org/D59576
llvm-svn: 356631
Machine DCE cannot remove a dead definition if there are non-dbg uses.
A use however can be in the same instruction:
dead %0 = INST %0
Such instructions sometimes created by Detect dead lanes pass.
Allow this instruction to be deleted despite the use if the only use
belongs to the same instruction.
Differential Revision: https://reviews.llvm.org/D59565
llvm-svn: 356619
This patch enables the use of lowerShuffleAsBitMask for 512-bit blends before
falling back to move immedate, GPR to k-register, and masked op.
I had to make some changes to support v8i64 when i64 is not a legal type. And to
support floating point types.
This trades a load for the move immediate and GPR move which is higher latency.
But its probably better for register pressure not having to hop through other
register classes. The load+and should play better with LICM and
rematerialization I think.
Differential Revision: https://reviews.llvm.org/D59479
llvm-svn: 356618
Krzysztof Parzyszek