If the fma operates on a legal vector type, the indexed variants can be
used, if the second operand is a splat of a valid index.
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D126234
Re-commit of 32e8b550e5
This patch rearranges emission of CFI instructions, so the resulting
DWARF and `.eh_frame` information is precise at every instruction.
The current state is that the unwind info is emitted only after the
function prologue. This is fine for synchronous (e.g. C++) exceptions,
but the information is generally incorrect when the program counter is
at an instruction in the prologue or the epilogue, for example:
```
stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
mov x29, sp
.cfi_def_cfa w29, 16
...
```
after the `stp` is executed the (initial) rule for the CFA still says
the CFA is in the `sp`, even though it's already offset by 16 bytes
A correct unwind info could look like:
```
stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
.cfi_def_cfa_offset 16
mov x29, sp
.cfi_def_cfa w29, 16
...
```
Having this information precise up to an instruction is useful for
sampling profilers that would like to get a stack backtrace. The end
goal (towards this patch is just a step) is to have fully working
`-fasynchronous-unwind-tables`.
Reviewed By: danielkiss, MaskRay
Differential Revision: https://reviews.llvm.org/D111411
It caused builds to assert with:
(StackSize == 0 && "We already have the CFA offset!"),
function generateCompactUnwindEncoding, file AArch64AsmBackend.cpp, line 624.
when targeting iOS. See comment on the code review for reproducer.
> This patch rearranges emission of CFI instructions, so the resulting
> DWARF and `.eh_frame` information is precise at every instruction.
>
> The current state is that the unwind info is emitted only after the
> function prologue. This is fine for synchronous (e.g. C++) exceptions,
> but the information is generally incorrect when the program counter is
> at an instruction in the prologue or the epilogue, for example:
>
> ```
> stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
> mov x29, sp
> .cfi_def_cfa w29, 16
> ...
> ```
>
> after the `stp` is executed the (initial) rule for the CFA still says
> the CFA is in the `sp`, even though it's already offset by 16 bytes
>
> A correct unwind info could look like:
> ```
> stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
> .cfi_def_cfa_offset 16
> mov x29, sp
> .cfi_def_cfa w29, 16
> ...
> ```
>
> Having this information precise up to an instruction is useful for
> sampling profilers that would like to get a stack backtrace. The end
> goal (towards this patch is just a step) is to have fully working
> `-fasynchronous-unwind-tables`.
>
> Reviewed By: danielkiss, MaskRay
>
> Differential Revision: https://reviews.llvm.org/D111411
This reverts commit 32e8b550e5.
This patch rearranges emission of CFI instructions, so the resulting
DWARF and `.eh_frame` information is precise at every instruction.
The current state is that the unwind info is emitted only after the
function prologue. This is fine for synchronous (e.g. C++) exceptions,
but the information is generally incorrect when the program counter is
at an instruction in the prologue or the epilogue, for example:
```
stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
mov x29, sp
.cfi_def_cfa w29, 16
...
```
after the `stp` is executed the (initial) rule for the CFA still says
the CFA is in the `sp`, even though it's already offset by 16 bytes
A correct unwind info could look like:
```
stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
.cfi_def_cfa_offset 16
mov x29, sp
.cfi_def_cfa w29, 16
...
```
Having this information precise up to an instruction is useful for
sampling profilers that would like to get a stack backtrace. The end
goal (towards this patch is just a step) is to have fully working
`-fasynchronous-unwind-tables`.
Reviewed By: danielkiss, MaskRay
Differential Revision: https://reviews.llvm.org/D111411
This teaches AArch64TargetLowering::shouldSinkOperands to sink the
operands of aarch64_neon_pmull intrinsic.
Differential Revision: https://reviews.llvm.org/D117944
Fixes the build issue with D111034, whose goal was to optimize
add/sub with long immediates.
Optimize ([add|sub] r, imm) -> ([ADD|SUB] ([ADD|SUB] r, #imm0, lsl #12), #imm1),
if imm == (imm0<<12)+imm1. and both imm0 and imm1 are non-zero 12-bit unsigned
integers.
Optimize ([add|sub] r, imm) -> ([SUB|ADD] ([SUB|ADD] r, #imm0, lsl #12), #imm1),
if imm == -(imm0<<12)-imm1, and both imm0 and imm1 are non-zero 12-bit unsigned
integers.
The change which fixed the build issue in D111034 was the use of new virtual
registers so that SSA form is maintained until deleting MI.
Differential Revision: https://reviews.llvm.org/D117429
Fixes the build issue with D111034, whose goal was to optimize
add/sub with long immediates.
Optimize ([add|sub] r, imm) -> ([ADD|SUB] ([ADD|SUB] r, #imm0, lsl #12), #imm1),
if imm == (imm0<<12)+imm1. and both imm0 and imm1 are non-zero 12-bit unsigned
integers.
Optimize ([add|sub] r, imm) -> ([SUB|ADD] ([SUB|ADD] r, #imm0, lsl #12), #imm1),
if imm == -(imm0<<12)-imm1, and both imm0 and imm1 are non-zero 12-bit unsigned
integers.
The change which fixed the build issue in D111034 was the use of new virtual
registers so that SSA form is maintained until deleting MI.
Differential Revision: https://reviews.llvm.org/D117429
This teaches AArch64TargetLowering::shouldSinkOperands to sink splat
shuffles to certain neon intrinsics, so that they can make use of the
lane variants of the instructions that are available.
Differential Revision: https://reviews.llvm.org/D112994
We would like to start pushing -mcpu=generic towards enabling the set of
features that improves performance for some CPUs, without hurting any
others. A blend of the performance options hopefully beneficial to all
CPUs. The largest part of that is enabling in-order scheduling using the
Cortex-A55 schedule model. This is similar to the Arm backend change
from eecb353d0e which made -mcpu=generic perform in-order scheduling
using the cortex-a8 schedule model.
The idea is that in-order cpu's require the most help in instruction
scheduling, whereas out-of-order cpus can for the most part out-of-order
schedule around different codegen. Our benchmarking suggests that
hypothesis holds. When running on an in-order core this improved
performance by 3.8% geomean on a set of DSP workloads, 2% geomean on
some other embedded benchmark and between 1% and 1.8% on a set of
singlecore and multicore workloads, all running on a Cortex-A55 cluster.
On an out-of-order cpu the results are a lot more noisy but show flat
performance or an improvement. On the set of DSP and embedded
benchmarks, run on a Cortex-A78 there was a very noisy 1% speed
improvement. Using the most detailed results I could find, SPEC2006 runs
on a Neoverse N1 show a small increase in instruction count (+0.127%),
but a decrease in cycle counts (-0.155%, on average). The instruction
count is very low noise, the cycle count is more noisy with a 0.15%
decrease not being significant. SPEC2k17 shows a small decrease (-0.2%)
in instruction count leading to a -0.296% decrease in cycle count. These
results are within noise margins but tend to show a small improvement in
general.
When specifying an Apple target, clang will set "-target-cpu apple-a7"
on the command line, so should not be affected by this change when
running from clang. This also doesn't enable more runtime unrolling like
-mcpu=cortex-a55 does, only changing the schedule used.
A lot of existing tests have updated. This is a summary of the important
differences:
- Most changes are the same instructions in a different order.
- Sometimes this leads to very minor inefficiencies, such as requiring
an extra mov to move variables into r0/v0 for the return value of a test
function.
- misched-fusion.ll was no longer fusing the pairs of instructions it
should, as per D110561. I've changed the schedule used in the test
for now.
- neon-mla-mls.ll now uses "mul; sub" as opposed to "neg; mla" due to
the different latencies. This seems fine to me.
- Some SVE tests do not always remove movprfx where they did before due
to different register allocation giving different destructive forms.
- The tests argument-blocks-array-of-struct.ll and arm64-windows-calls.ll
produce two LDR where they previously produced an LDP due to
store-pair-suppress kicking in.
- arm64-ldp.ll and arm64-neon-copy.ll are missing pre/postinc on LPD.
- Some tests such as arm64-neon-mul-div.ll and
ragreedy-local-interval-cost.ll have more, less or just different
spilling.
- In aarch64_generated_funcs.ll.generated.expected one part of the
function is no longer outlined. Interestingly if I switch this to use
any other scheduled even less is outlined.
Some of these are expected to happen, such as differences in outlining
or register spilling. There will be places where these result in worse
codegen, places where they are better, with the SPEC instruction counts
suggesting it is not a decrease overall, on average.
Differential Revision: https://reviews.llvm.org/D110830
This updates a few more check lines, in some mte tests that were close
to auto generated already and some CodeGenPrepare/consthoist tests where
being able to see the entire code sequence is useful for determining
whether code differences are improvements or not.
In the combination of addressing modes, when replacing the matched phi nodes,
sometimes the phi node to be replaced has been modified. For example,
there’s matcher set [A, B] and [C, A], which will have cyclic dependency:
A is replaced by B and C will be replaced by A. Because we tried to match new phi node
to another new phi node, we should ignore new phi nodes when mapping new phi node to old one.
Reviewed By: skatkov
Differential Revision: https://reviews.llvm.org/D108635
In current implementation, the instruction to be sunk will be inserted before the target instruction without considering the def-use tree,
which may case Instruction does not dominate all uses error. We need to choose a suitable location to insert according to the use chain
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D107262
This was checking extends as shuffles, where as we should be checking
the operands. This helps sink the shuffles, creating more addl/subl
instructions.
Differential Revision: https://reviews.llvm.org/D107623
This patch updates ConstantVector::getSplat to use poison instead
of undef when using insertelement/shufflevector to splat.
This follows on from D93793.
Differential Revision: https://reviews.llvm.org/D107751
This commit copies existing tests at llvm/Transforms containing
'shufflevector X, undef' and replaces them with 'shufflevector X, poison'.
The new copied tests have *-inseltpoison.ll suffix at its file name
(as db7a2f347f did)
See https://reviews.llvm.org/D93793
Test files listed using
grep -R -E "^[^;]*shufflevector <.*> .*, <.*> undef" | cut -d":" -f1 | uniq
Test files copied & updated using
file_org=llvm/test/Transforms/$1
if [[ "$file_org" = *-inseltpoison.ll ]]; then
file=$file_org
else
file=${file_org%.ll}-inseltpoison.ll
if [ ! -f $file ]; then
cp $file_org $file
fi
fi
sed -i -E 's/^([^;]*)shufflevector <(.*)> (.*), <(.*)> undef/\1shufflevector <\2> \3, <\4> poison/g' $file
head -1 $file | grep "Assertions have been autogenerated by utils/update_test_checks.py" -q
if [ "$?" == 1 ]; then
echo "$file : should be manually updated"
# The test is manually updated
exit 1
fi
python3 ./llvm/utils/update_test_checks.py --opt-binary=./build-releaseassert/bin/opt $file
This commit copies existing tests at llvm/Transforms and replaces
'insertelement undef' in those files with 'insertelement poison'.
(see https://reviews.llvm.org/D93586)
Tests listed using this script:
grep -R -E '^[^;]*insertelement <.*> undef,' . | cut -d":" -f1 | uniq |
wc -l
Tests updated:
file_org=llvm/test/Transforms/$1
file=${file_org%.ll}-inseltpoison.ll
cp $file_org $file
sed -i -E 's/^([^;]*)insertelement <(.*)> undef/\1insertelement <\2> poison/g' $file
head -1 $file | grep "Assertions have been autogenerated by utils/update_test_checks.py" -q
if [ "$?" == 1 ]; then
echo "$file : should be manually updated"
# I manually updated the script
exit 1
fi
python3 ./llvm/utils/update_test_checks.py --opt-binary=./build-releaseassert/bin/opt $file
optimizeGatherScatterInst does nothing specific to fixed length vectors
but uses FixedVectorType to extract the number of elements. This patch
simply updates the code to use VectorType and getElementCount instead.
For testing I just copied Transforms/CodeGenPrepare/X86/gather-scatter-opt.ll
replacing `<4 x ` with `<vscale x 4`.
Differential Revision: https://reviews.llvm.org/D92572
This version fixes a buildbot failure cause by picking the wrong insert
point for XORs. We cannot pick the XOR binary operator as insert point,
as it is not guaranteed that both input operands for the overflow
intrinsic are defined before it.
This reverts the revert commit
c7fc0e5da6.
Instcombine folds (a + b <u a) to (a ^ -1 <u b) and that does not match
the expected pattern in CodeGenPerpare via UAddWithOverflow.
This causes a regression over Clang 7 on both X86 and AArch64:
https://gcc.godbolt.org/z/juhXYV
This patch extends UAddWithOverflow to also catch the XOR case, if the
XOR is only used in the ICMP. This covers just a single case, but I'd
like to make sure I am not missing anything before tackling the other
cases.
Reviewers: nikic, RKSimon, lebedev.ri, spatel
Reviewed By: nikic, lebedev.ri
Differential Revision: https://reviews.llvm.org/D74228
As it's causing some bot failures (and per request from kbarton).
This reverts commit r358543/ab70da07286e618016e78247e4a24fcb84077fda.
llvm-svn: 358546
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
Creating the IR builder, then modifying the CFG, leads to an IRBuilder
where the BB and insertion point are inconsistent, so new instructions
have the wrong parent.
Modified an existing test because the test wasn't covering anything
useful (the "invoke" was not actually an invoke by the time we hit the
code in question).
Differential Revision: https://reviews.llvm.org/D55729
llvm-svn: 349693
Summary:
Large GEP splitting, introduced in rL332015, uses a `DenseMap<AssertingVH<Value>, ...>`. This causes an assertion to fail (in debug builds) or undefined behaviour to occur (in release builds) when a value is RAUWed.
This manifested itself in the 7zip benchmark from the llvm test suite built on ARM with `-fstrict-vtable-pointers` enabled while RAUWing invariant group launders and splits in CodeGenPrepare.
This patch merges the large offsets of the argument and the result of an invariant.group strip/launder intrinsic before RAUWing.
Reviewers: Prazek, javed.absar, haicheng, efriedma
Reviewed By: Prazek, efriedma
Subscribers: kristof.beyls, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D51936
llvm-svn: 344802
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
This is recommit of r287553 after fixing the invalid loop info after eliminating an empty block and unit test failures in AVR and WebAssembly :
Summary: Merging an empty case block into the header block of switch could cause ISel to add COPY instructions in the header of switch, instead of the case block, if the case block is used as an incoming block of a PHI. This could potentially increase dynamic instructions, especially when the switch is in a loop. I added a test case which was reduced from the benchmark I was targetting.
Reviewers: t.p.northover, mcrosier, manmanren, wmi, joerg, davidxl
Subscribers: joerg, qcolombet, danielcdh, hfinkel, mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D22696
llvm-svn: 289988
This is recommit of r287553 after fixing the invalid loop info after eliminating an empty block:
Summary: Merging an empty case block into the header block of switch could cause ISel to add COPY instructions in the header of switch, instead of the case block, if the case block is used as an incoming block of a PHI. This could potentially increase dynamic instructions, especially when the switch is in a loop. I added a test case which was reduced from the benchmark I was targetting.
Reviewers: t.p.northover, mcrosier, manmanren, wmi, joerg, davidxl
Subscribers: joerg, qcolombet, danielcdh, hfinkel, mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D22696
llvm-svn: 289951
Summary: Merging an empty case block into the header block of switch could cause
ISel to add COPY instructions in the header of switch, instead of the case
block, if the case block is used as an incoming block of a PHI. This could
potentially increase dynamic instructions, especially when the switch is in a
loop. I added a test case which was reduced from the benchmark I was targetting.
Reviewers: t.p.northover, mcrosier, manmanren, wmi, davidxl
Subscribers: qcolombet, danielcdh, hfinkel, mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D22696
llvm-svn: 287553
This is a redo of r251849 except the tests have been split into arch-specific folders
to hopefully make the bots happy.
This is a follow-up from the discussion in D12965. The block-at-a-time limitation of
SelectionDAG also came up in D13297.
Without the InstCombine change from D12965, I don't expect this patch to make any
difference in the real world because InstCombine does not shrink cases like this in
visitSwitchInst(). But we need to have this CGP safety harness in place before
proceeding with any shrinkage in D12965, so we won't generate extra extends for compares.
I've opted for IR regression tests in the patch because that seems like a clearer way to
test the transform, but PowerPC CodeGen for an i16 widening test is shown below. x86
will need more work to solve: https://llvm.org/bugs/show_bug.cgi?id=22473
Before:
BB#0:
mr 4, 3
extsh. 3, 4
ble 0, .LBB0_5
BB#1:
cmpwi 3, 99
bgt 0, .LBB0_9
BB#2:
rlwinm 4, 4, 0, 16, 31 <--- 32-bit mask/extend
li 3, 0
cmplwi 4, 1
beqlr 0
BB#3:
cmplwi 4, 10
bne 0, .LBB0_12
BB#4:
li 3, 1
blr
.LBB0_5:
rlwinm 3, 4, 0, 16, 31 <--- 32-bit mask/extend
cmplwi 3, 65436
beq 0, .LBB0_13
BB#6:
cmplwi 3, 65526
beq 0, .LBB0_15
BB#7:
cmplwi 3, 65535
bne 0, .LBB0_12
BB#8:
li 3, 4
blr
.LBB0_9:
rlwinm 3, 4, 0, 16, 31 <--- 32-bit mask/extend
cmplwi 3, 100
beq 0, .LBB0_14
...
After:
BB#0:
rlwinm 4, 3, 0, 16, 31 <--- mask/extend to 32-bit and then use that for comparisons
cmpwi 4, 999
ble 0, .LBB0_5
BB#1:
lis 3, 0
ori 3, 3, 65525
cmpw 4, 3
bgt 0, .LBB0_9
BB#2:
cmplwi 4, 1000
beq 0, .LBB0_14
BB#3:
cmplwi 4, 65436
bne 0, .LBB0_13
BB#4:
li 3, 6
blr
.LBB0_5:
li 3, 0
cmplwi 4, 1
beqlr 0
BB#6:
cmplwi 4, 10
beq 0, .LBB0_12
BB#7:
cmplwi 4, 100
bne 0, .LBB0_13
BB#8:
li 3, 2
blr
.LBB0_9:
cmplwi 4, 65526
beq 0, .LBB0_15
BB#10:
cmplwi 4, 65535
bne 0, .LBB0_13
...
Differential Revision: http://reviews.llvm.org/D13532
llvm-svn: 251857
Florian Hahn