This patch improves code generation for some AArch64 ACLE intrinsics. It adds
support to CGP to duplicate and sink operands to their user, if they can be
folded into a target instruction, like zexts and sub into usubl. It adds a
TargetLowering hook shouldSinkOperands, which looks at the operands of
instructions to see if sinking is profitable.
I decided to add a new target hook, as for the sinking to be profitable,
at least on AArch64, we have to look at multiple operands of an
instruction, instead of looking at the users of a zext for example.
The sinking is done in CGP, because it works around an instruction
selection limitation. If instruction selection is not limited to a
single basic block, this patch should not be needed any longer.
Alternatively this could be done in the LoopSink pass, which tries to
undo LICM for instructions in blocks that are not executed frequently.
Note that we do not force the operands to sink to have a single user,
because we duplicate them before sinking. Therefore this is only
desirable if they really can be done for free. Additionally we could
consider the impact on live ranges later on.
This should fix https://bugs.llvm.org/show_bug.cgi?id=40025.
As for performance, we have internal code that uses intrinsics and can
be speed up by 10% by this change.
Reviewers: SjoerdMeijer, t.p.northover, samparker, efriedma, RKSimon, spatel
Reviewed By: samparker
Differential Revision: https://reviews.llvm.org/D57377
llvm-svn: 353152
This cleans up all CallInst creation in LLVM to explicitly pass a
function type rather than deriving it from the pointer's element-type.
Differential Revision: https://reviews.llvm.org/D57170
llvm-svn: 352909
And instead just generate a libcall. My motivating example on ARM was a simple:
shl i64 %A, %B
for which the code bloat is quite significant. For other targets that also
accept __int128/i128 such as AArch64 and X86, it is also beneficial for these
cases to generate a libcall when optimising for minsize. On these 64-bit targets,
the 64-bits shifts are of course unaffected because the SHIFT/SHIFT_PARTS
lowering operation action is not set to custom/expand.
Differential Revision: https://reviews.llvm.org/D57386
llvm-svn: 352736
to reflect the new license.
We understand that people may be surprised that we're moving the header
entirely to discuss the new license. We checked this carefully with the
Foundation's lawyer and we believe this is the correct approach.
Essentially, all code in the project is now made available by the LLVM
project under our new license, so you will see that the license headers
include that license only. Some of our contributors have contributed
code under our old license, and accordingly, we have retained a copy of
our old license notice in the top-level files in each project and
repository.
llvm-svn: 351636
This patch adds support for funclets in frame lowering and ISel
lowering. Together with D50288 and D50166, it enables C++ exception
handling.
Patch by Sanjin Sijaric, with some fixes by me.
Differential Revision: https://reviews.llvm.org/D51524
llvm-svn: 346568
The main caller of this already has an MVT and several targets called getSimpleVT inside without checking isSimple. This makes the simpleness explicit.
llvm-svn: 346180
This involves changing the shouldExpandAtomicCmpXchgInIR interface, but I have
updated the in-tree backends using this hook (ARM, AArch64, Hexagon) so they
will see no functional change. Previously this hook returned bool, but it now
returns AtomicExpansionKind.
This hook allows targets to select how a given cmpxchg is to be expanded.
D48131 uses this to expand part-word cmpxchg to a target-specific intrinsic.
See my associated RFC for more info on the motivation for this change
<http://lists.llvm.org/pipermail/llvm-dev/2018-June/123993.html>.
Differential Revision: https://reviews.llvm.org/D48130
llvm-svn: 342550
This adds the plumbing for the Tiny code model for the AArch64 backend. This,
instead of loading addresses through the normal ADRP;ADD pair used in the Small
model, uses a single ADR. The 21 bit range of an ADR means that the code and
its statically defined symbols need to be within 1MB of each other.
This makes it mostly interesting for embedded applications where we want to fit
as much as we can in as small a space as possible.
Differential Revision: https://reviews.llvm.org/D49673
llvm-svn: 340397
Intentionally excluding nodes from the DAGCombine worklist is likely to
lead to weird optimizations and infinite loops, so it's generally a bad
idea.
To avoid the infinite loops, fix DAGCombine to use the
isDesirableToCommuteWithShift target hook before performing the
transforms in question, and implement the target hook in the ARM backend
disable the transforms in question.
Fixes https://bugs.llvm.org/show_bug.cgi?id=38530 . (I don't have a
reduced testcase for that bug. But we should have sufficient test
coverage for PerformSHLSimplify given that we're not playing weird
tricks with the worklist. I can try to bugpoint it if necessary,
though.)
Differential Revision: https://reviews.llvm.org/D50667
llvm-svn: 339734
The vector contains the SDNodes that these functions create. The number of nodes is always a small number so we should use SmallVector to avoid a heap allocation.
llvm-svn: 338329
Summary:
[[ https://bugs.llvm.org/show_bug.cgi?id=38149 | PR38149 ]]
As discussed in https://reviews.llvm.org/D49179#1158957 and later,
the IR for 'check for [no] signed truncation' pattern can be improved:
https://rise4fun.com/Alive/gBf
^ that pattern will be produced by Implicit Integer Truncation sanitizer,
https://reviews.llvm.org/D48958https://bugs.llvm.org/show_bug.cgi?id=21530
in signed case, therefore it is probably a good idea to improve it.
But the IR-optimal patter does not lower efficiently, so we want to undo it..
This handles the simple pattern.
There is a second pattern with predicate and constants inverted.
NOTE: we do not check uses here. we always do the transform.
Reviewers: spatel, craig.topper, RKSimon, javed.absar
Reviewed By: spatel
Subscribers: kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D49266
llvm-svn: 337166
This patch adds a custom trunc store lowering for v4i8 vector types.
Since there is not v.4b register, the v4i8 is promoted to v4i16 (v.4h)
and default action for v4i8 is to extract each element and issue 4
byte stores.
A better strategy would be to extended the promoted v4i16 to v8i16
(with undef elements) and extract and store the word lane which
represents the v4i8 subvectores. The construction:
define void @foo(<4 x i16> %x, i8* nocapture %p) {
%0 = trunc <4 x i16> %x to <4 x i8>
%1 = bitcast i8* %p to <4 x i8>*
store <4 x i8> %0, <4 x i8>* %1, align 4, !tbaa !2
ret void
}
Can be optimized from:
umov w8, v0.h[3]
umov w9, v0.h[2]
umov w10, v0.h[1]
umov w11, v0.h[0]
strb w8, [x0, #3]
strb w9, [x0, #2]
strb w10, [x0, #1]
strb w11, [x0]
ret
To:
xtn v0.8b, v0.8h
str s0, [x0]
ret
The patch also adjust the memory cost for autovectorization, so the C
code:
void foo (const int *src, int width, unsigned char *dst)
{
for (int i = 0; i < width; i++)
*dst++ = *src++;
}
can be vectorized to:
.LBB0_4: // %vector.body
// =>This Inner Loop Header: Depth=1
ldr q0, [x0], #16
subs x12, x12, #4 // =4
xtn v0.4h, v0.4s
xtn v0.8b, v0.8h
st1 { v0.s }[0], [x2], #4
b.ne .LBB0_4
Instead of byte operations.
llvm-svn: 335735
As suggested in https://bugs.llvm.org/show_bug.cgi?id=32384#c1, this change
makes the inlining of `memset()` and `memcpy()` more aggressive when
compiling for speed. The tuning remains the same when optimizing for size.
Patch by: Sebastian Pop <s.pop@samsung.com>
Evandro Menezes <e.menezes@samsung.com>
Differential revision: https://reviews.llvm.org/D45098
llvm-svn: 333429
Summary:
This **appears** to be the last missing piece for the masked merge pattern handling in the backend.
This is [[ https://bugs.llvm.org/show_bug.cgi?id=37104 | PR37104 ]].
[[ https://bugs.llvm.org/show_bug.cgi?id=6773 | PR6773 ]] will introduce an IR canonicalization that is likely bad for the end assembly.
Previously, `andps`+`andnps` / `bsl` would be generated. (see `@out`)
Now, they would no longer be generated (see `@in`), and we need to make sure that they are generated.
Differential Revision: https://reviews.llvm.org/D46528
llvm-svn: 332904
Accessing the members of a large data structures needs a lot of GEPs which
usually have large offsets due to the size of the underlying data structure. If
the offsets are too large to fit into the r+i addressing mode, these GEPs cannot
be sunk to their users' blocks and many extra registers are needed then to carry
the values of these GEPs.
This patch tries to split a large data struct starting from %base like the
following.
Before:
BB0:
%base =
BB1:
%gep0 = gep %base, off0
%gep1 = gep %base, off1
%gep2 = gep %base, off2
BB2:
%load1 = load %gep0
%load2 = load %gep1
%load3 = load %gep2
After:
BB0:
%base =
%new_base = gep %base, off0
BB1:
%new_gep0 = %new_base
%new_gep1 = gep %new_base, off1 - off0
%new_gep2 = gep %new_base, off2 - off0
BB2:
%load1 = load i32, i32* %new_gep0
%load2 = load i32, i32* %new_gep1
%load3 = load i32, i32* %new_gep2
In the above example, the struct is split into two parts. The first part still
starts from %base and the second part starts from %new_base. After the
splitting, %new_gep1 and %new_gep2 have smaller offsets and then can be sunk to
BB2 and folded into their users.
The algorithm to split data structure is simple and very similar to the work of
merging SExts. First, it collects GEPs that have large offsets when iterating
the blocks. Second, it splits the underlying data structures and updates the
collected GEPs to use smaller offsets.
Differential Revision: https://reviews.llvm.org/D42759
llvm-svn: 332015
We've been running doxygen with the autobrief option for a couple of
years now. This makes the \brief markers into our comments
redundant. Since they are a visual distraction and we don't want to
encourage more \brief markers in new code either, this patch removes
them all.
Patch produced by
for i in $(git grep -l '\\brief'); do perl -pi -e 's/\\brief //g' $i & done
Differential Revision: https://reviews.llvm.org/D46290
llvm-svn: 331272
Loads and stores can only shift the offset register by the size of the value
being loaded, but currently the DAGCombiner will reduce the width of the load
if it's followed by a trunc making it impossible to later combine the shift.
Solve this by implementing shouldReduceLoadWidth for the AArch64 backend and
make it prevent the width reduction if this is what would happen, though do
allow it if reducing the load width will let us eliminate a later sign or zero
extend.
Differential Revision: https://reviews.llvm.org/D44794
llvm-svn: 328321
Following the ARM-neon backend, define isExtractSubvectorCheap to return true
when extracting low and high part of a neon register.
The patch disables a test in llvm/test/CodeGen/AArch64/arm64-ext.ll This
testcase is fragile in the sense that it requires a BUILD_VECTOR to "survive"
all DAG transforms until ISelLowering. The testcase is supposed to check that
AArch64TargetLowering::ReconstructShuffle() works, and for that we need a
BUILD_VECTOR in ISelLowering. As we now transform the BUILD_VECTOR earlier into
an VEXT + vector_shuffle, we don't have the BUILD_VECTOR pattern when we get to
ISelLowering. As there is no way to disable the combiner to only exercise the
code in ISelLowering, the patch disables the testcase.
Differential revision: https://reviews.llvm.org/D43973
llvm-svn: 326811
This makes sure that alloca() function calls properly probe the
stack as needed.
Differential Revision: https://reviews.llvm.org/D42356
llvm-svn: 325433
Armv8.1-A added an atomic load-clear instruction (which performs bitwise
and with the complement of it's operand), but not a load-and
instruction. Our current code-generation for atomic load-and always
inserts an MVN instruction to invert its argument, even if it could be
folded into a constant or another instruction.
This adds lowering early in selection DAG to convert a load-and
operation into an xor with -1 and a load-clear, allowing the normal DAG
optimisations to work on it.
To do this, I've had to add a new ISD opcode, ATOMIC_LOAD_CLR. I don't
see any easy way to do this with an AArch64-specific ISD node, because
the code-generation for atomic operations assumes the SDNodes are of
type AtomicSDNode.
I've left the old tablegen patterns in because they are still needed for
global isel.
Differential revision: https://reviews.llvm.org/D42478
llvm-svn: 324908
Armv8.1-A added an atomic load-add instruction, but not a load-subtract
instruction. Our current code-generation for atomic load-subtract always
inserts a NEG instruction to negate it's argument, even if it could be
folded into a constant or another instruction.
This adds lowering early in selection DAG to convert a load-subtract
operation into a subtract and a load-add, allowing the normal DAG
optimisations to work on it.
I've left the old tablegen patterns in because they are still needed for
global isel.
Some of the tests in this patch are copied from D35375 by Chad Rosier (which
was abandoned).
Differential revision: https://reviews.llvm.org/D42477
llvm-svn: 324892
This patch enables aggressive FMA by default on T99, and provides a -mllvm
option to enable the same on other AArch64 micro-arch's (-mllvm
-aarch64-enable-aggressive-fma).
Test case demonstrating the effects on T99 is included.
Patch by: steleman (Stefan Teleman)
Differential Revision: https://reviews.llvm.org/D40696
llvm-svn: 323474
Re-commit of r322200: The testcase shouldn't hit machineverifiers
anymore with r322917 in place.
Large callframes (calls with several hundreds or thousands or
parameters) could lead to situations in which the emergency spillslot is
out of range to be addressed relative to the stack pointer.
This commit forces the use of a frame pointer in the presence of large
callframes.
This commit does several things:
- Compute max callframe size at the end of instruction selection.
- Add mirFileLoaded target callback. Use it to compute the max callframe size
after loading a .mir file when the size wasn't specified in the file.
- Let TargetFrameLowering::hasFP() return true if there exists a
callframe > 255 bytes.
- Always place the emergency spillslot close to FP if we have a frame
pointer.
- Note that `useFPForScavengingIndex()` would previously return false
when a base pointer was available leading to the emergency spillslot
getting allocated late (that's the whole effect of this callback).
Which made no sense to me so I took this case out: Even though the
emergency spillslot is technically not referenced by FP in this case
we still want it allocated early.
Differential Revision: https://reviews.llvm.org/D40876
llvm-svn: 322919
Summary:
Very basic stack instrumentation using tagged pointers.
Tag for N'th alloca in a function is built as XOR of:
* base tag for the function, which is just some bits of SP (poor
man's random)
* small constant which is a function of N.
Allocas are aligned to 16 bytes. On every ReturnInst allocas are
re-tagged to catch use-after-return.
This implementation has a bunch of issues that will be taken care of
later:
1. lifetime intrinsics referring to tagged pointers are not
recognized in SDAG. This effectively disables stack coloring.
2. Generated code is quite inefficient. There is one extra
instruction at each memory access that adds the base tag to the
untagged alloca address. It would be better to keep tagged SP in a
callee-saved register and address allocas as an offset of that XOR
retag, but that needs better coordination between hwasan
instrumentation pass and prologue/epilogue insertion.
3. Lifetime instrinsics are ignored and use-after-scope is not
implemented. This would be harder to do than in ASan, because we
need to use a differently tagged pointer depending on which
lifetime.start / lifetime.end the current instruction is dominated
/ post-dominated.
Reviewers: kcc, alekseyshl
Subscribers: srhines, kubamracek, javed.absar, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D41602
llvm-svn: 322324
Revert for now as the testcase is hitting a pre-existing verifier error
that manifest as a failure when expensive checks are enabled (or
-verify-machineinstrs) is used.
This reverts commit r322200.
llvm-svn: 322231
Large callframes (calls with several hundreds or thousands or
parameters) could lead to situations in which the emergency spillslot is
out of range to be addressed relative to the stack pointer.
This commit forces the use of a frame pointer in the presence of large
callframes.
This commit does several things:
- Compute max callframe size at the end of instruction selection.
- Add mirFileLoaded target callback. Use it to compute the max callframe size
after loading a .mir file when the size wasn't specified in the file.
- Let TargetFrameLowering::hasFP() return true if there exists a
callframe > 255 bytes.
- Always place the emergency spillslot close to FP if we have a frame
pointer.
- Note that `useFPForScavengingIndex()` would previously return false
when a base pointer was available leading to the emergency spillslot
getting allocated late (that's the whole effect of this callback).
Which made no sense to me so I took this case out: Even though the
emergency spillslot is technically not referenced by FP in this case
we still want it allocated early.
Differential Revision: https://reviews.llvm.org/D40876
llvm-svn: 322200
All these headers already depend on CodeGen headers so moving them into
CodeGen fixes the layering (since CodeGen depends on Target, not the
other way around).
llvm-svn: 318490
Previously, the dllimport attribute did the right thing in terms
of treating it as a pointer to a value, but this makes sure the
names get mangled properly, and calls to such functions load the
function from the __imp_ pointer.
This is based on SVN r212431 and r212430 where the same was
implemented for ARM.
Differential Revision: https://reviews.llvm.org/D38530
llvm-svn: 316555
If a struct would end up half in GPRs and half on SP the ABI says it should
actually go entirely on the stack. We were getting this wrong in GlobalISel
before, causing compatibility issues.
llvm-svn: 311388
Changing mask argument type from const SmallVectorImpl<int>& to
ArrayRef<int>.
This came up in D35700 where a mask is received as an ArrayRef<int> and
we want to pass it to TargetLowering::isShuffleMaskLegal().
Also saves a few lines of code.
llvm-svn: 309085
This patch makes LSR generate better code for SystemZ in the cases of memory
intrinsics, Load->Store pairs or comparison of immediate with memory.
In order to achieve this, the following common code changes were made:
* New TTI hook: LSRWithInstrQueries(), which defaults to false. Controls if
LSR should do instruction-based addressing evaluations by calling
isLegalAddressingMode() with the Instruction pointers.
* In LoopStrengthReduce: handle address operands of memset, memmove and memcpy
as address uses, and call isFoldableMemAccessOffset() for any LSRUse::Address,
not just loads or stores.
SystemZ changes:
* isLSRCostLess() implemented with Insns first, and without ImmCost.
* New function supportedAddressingMode() that is a helper for TTI methods
looking at Instructions passed via pointers.
Review: Ulrich Weigand, Quentin Colombet
https://reviews.llvm.org/D35262https://reviews.llvm.org/D35049
llvm-svn: 308729
Prevent store merge from merging stores into an invalid 128-bit store
(realized as a f128 value in the context of the noimplicitfloat
attribute). Previously, such stores are immediately split back into
valid stores.
llvm-svn: 308184
Summary:
This patch is the first step in reducing HW prefetcher instruction tag
collisions in inner loops for Falkor. It adds a pass that annotates IR
loads with metadata to indicate that they are known to be strided loads,
and adds a target lowering hook that translates this metadata to a
target-specific MachineMemOperand flag.
A follow on change will use this MachineMemOperand flag to re-write
instructions to reduce tag collisions.
Reviewers: mcrosier, t.p.northover
Subscribers: aemerson, rengolin, mgorny, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D34963
llvm-svn: 308059
Pass parameters properly in calls to such functions (pass all
floats in integer registers), and handle va_start properly (allocate
stack immediately below the arguments on the stack, to save the
register arguments into a single continuous array).
Differential Revision: https://reviews.llvm.org/D35006
llvm-svn: 307928
This caused PR33053.
Original commit message:
> The new experimental reduction intrinsics can now be used, so I'm enabling this
> for AArch64. We will need this for SVE anyway, so it makes sense to do this for
> NEON reductions as well.
>
> The existing code to match shufflevector patterns are replaced with a direct
> lowering of the reductions to AArch64-specific nodes. Tests updated with the
> new, simpler, representation.
>
> Differential Revision: https://reviews.llvm.org/D32247
llvm-svn: 303115
The new experimental reduction intrinsics can now be used, so I'm enabling this
for AArch64. We will need this for SVE anyway, so it makes sense to do this for
NEON reductions as well.
The existing code to match shufflevector patterns are replaced with a direct
lowering of the reductions to AArch64-specific nodes. Tests updated with the
new, simpler, representation.
Differential Revision: https://reviews.llvm.org/D32247
llvm-svn: 302678
This patch replaces the separate APInts for KnownZero/KnownOne with a single KnownBits struct. This is similar to what was done to ValueTracking's version recently.
This is largely a mechanical transformation from KnownZero to Known.Zero.
Differential Revision: https://reviews.llvm.org/D32569
llvm-svn: 301620
Florian Hahn