Summary:
The phase attempts to transform operations that extract a portion of a value
into an SDWA src operand in cases where that value is used only once. It
was not prepared for this use to be the preserved portion of a value for
dst:UNUSED_PRESERVE, resulting in a crash or assert.
This change either rejects the illegal SDWA attempt, or in the case where
dst:WORD_1 and the src_sel would be WORD_0, removes the unneeded
extract instruction.
Reviewers: arsenm, #amdgpu
Reviewed By: arsenm, #amdgpu
Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D44364
llvm-svn: 328856
For Hexagon, peeling loops with small runtime trip count is beneficial for our
benchmarks. We set PeelCount in HexagonTargetInfo.cpp and we use PeelCount set
by the target for computing the desired peel count.
Differential Revision: https://reviews.llvm.org/D44880
llvm-svn: 328854
Sometimes the operand comes after the memory operand so we need 5 ReadDefaults first.
I suspect we also need to do something for the mask operand for masked avx512 instructions? I'm not sure if the mask should be ReadAfterLd or not since it can mask faults. If it shouldn't be ReadAfterLd then we're probably wrong for zero masking instructions already.
Differential Revision: https://reviews.llvm.org/D44726
llvm-svn: 328834
While the stack access instructions don't care about
alignment > 4, some transformations on the pointer calculation
do make assumptions based on knowing the low bits of a pointer
are 0. If a stack object ends up being accessed through its
absolute address (relative to the kernel scratch wave offset),
the addressing expression may depend on the stack frame being
properly aligned. This was breaking in a testcase due to the
add->or combine.
I think some of the SP/FP handling logic is still backwards,
and overly simplistic to support all of the stack features.
Code which tries to modify the SP with inline asm for example
or variable sized objects will probably require redoing this.
llvm-svn: 328831
The memory form of these instructions only read an input from memory. They don't have any register operands.
Differential Revision: https://reviews.llvm.org/D44836
llvm-svn: 328828
These instructions have the memory operand before the register operand. So we need to put ReadDefault for all the load ops first. Then the ReadAfterLd
Differential Revision: https://reviews.llvm.org/D44838
llvm-svn: 328823
Summary:
r327219 added wrappers to std::sort which randomly shuffle the container before sorting.
This will help in uncovering non-determinism caused due to undefined sorting
order of objects having the same key.
To make use of that infrastructure we need to invoke llvm::sort instead of std::sort.
Note: This patch is one of a series of patches to replace *all* std::sort to llvm::sort.
Refer the comments section in D44363 for a list of all the required patches.
Reviewers: sdardis, RKSimon, dsanders, atanasyan
Reviewed By: atanasyan
Subscribers: atanasyan, arichardson, llvm-commits
Differential Revision: https://reviews.llvm.org/D44869
llvm-svn: 328815
Currently EVT is in the IR layer only because of Function.cpp needing a very small piece of the functionality of EVT::getEVTString(). The rest of EVT is used in codegen making CodeGen a better place for it.
The previous code converted a Type* to EVT and then called getEVTString. This was only expected to handle the primitive types from Type*. Since there only a few primitive types, we can just print them as strings directly.
Differential Revision: https://reviews.llvm.org/D45017
llvm-svn: 328806
We are re-adding all the bitcasts, constant masks and target shuffles to the work list for no apparent gain.
Found while investigating adding SimplifyDemandedVectorElts to target shuffles.
Differential Revision: https://reviews.llvm.org/D44942
llvm-svn: 328771
I believe the role of ehDataReg has been replaced by MipsABIInfo::GetEhDataReg, thus removing the dead code.
Patch By: Wei-Ren Chen.
Reviewers: ehostunreach, sdardis
Differential Revision: https://reviews.llvm.org/D44867
llvm-svn: 328767
The IntelPrinter and the ATTPrinter produce the same strings for the same input. We already use the ATTPrinter explicitly in several other places.
llvm-svn: 328762
Most of these were optional matches at the end of the strings, but since the strings themselves are prefix matches by default you don't need to check for something optional at the end.
I've left the 'b' on memory instructions where it means 'broadcast' because I'm not sure those really have the same load latency and we may need to split them explicitly in the future.
llvm-svn: 328730
These instructions have been around for a long time, but we
haven't supported intrinsics for them. The "new" versions use
the CSx register for the start of the buffer instead of the K
field in the Mx register.
We need to use pseudo instructions for these instructions until
after register allocation. The problem is that these instructions
allocate a M0/CS0 or M1/CS1 pair. But, we can't generate code for
the CSx set-up until after register allocation when the Mx
register has been fixed for the instruction.
There is a related clang patch.
Patch by Brendon Cahoon.
llvm-svn: 328724
This commit simplifies the call outlining logic by removing references to the
Function associated with the callee. To do this, it requires that valid
callee save info is available to the outliner.
llvm-svn: 328719
Similar to r328694. The number of micro opcodes should be 2 for those
instructions.
This was found when testing AVX code for BtVer2 using llvm-mca.
llvm-svn: 328698
This reverts commit 0daf86291d3aa04d3cc280cd0ef24abdb0174981.
It was causing an assert in test/CodeGen/AMDGPU/amdpal.ll only on a
release-with-asserts build. I will resubmit the change when I have fixed
that.
Change-Id: If270594eba27a7dc4076bdeab3fa8e6bfda3288a
llvm-svn: 328695
The Jaguar backend natively supports 128-bit data types. Operations on YMM
registers are split into two COPs (complex operations). Each COP consumes a slot
in the dispatch group, and in the reorder buffer.
The scheduling model for Jaguar should mark those instructions as `let
NumMicroOps = 2`.
This was found when testing AVX code for BtVer2 using llvm-mca.
llvm-svn: 328694
Follow up patch of r328313 to support the UseVMOVSR constraint. Removed
some unneeded instructions from the test and removed some stray
comments.
Differential Revision: https://reviews.llvm.org/D44941
llvm-svn: 328691
If an ADRP appears with, say, a CPI operand, we shouldn't outline it.
This moves the check for unsafe operands so that it occurs before the special-case
for ADRPs. Also add a test for outlining ADRPs.
llvm-svn: 328674
Summary:
For OS type AMDPAL, the scratch descriptor is loaded from offset 0 of
the GIT, whose 32 bit pointer is in s0 (s8 for gfx9 merged shaders).
This commit fixes that to use offset 0x10 instead of offset 0 for a
compute shader, per the PAL ABI spec.
Reviewers: kzhuravl, nhaehnle, timcorringham
Subscribers: kzhuravl, wdng, yaxunl, t-tye, llvm-commits, dstuttard, nhaehnle, arsenm
Differential Revision: https://reviews.llvm.org/D44468
Change-Id: I93dffa647758e37f613bb5e0dfca840d82e6d26f
llvm-svn: 328673
Currently MOVMSK instructions use the WriteVecLogic class, which is a very poor choice given that MOVMSK involves a SSE->GPR transfer.
Differential Revision: https://reviews.llvm.org/D44924
llvm-svn: 328664
Before this was not done if the function had no calls in it. This
is still a possible issue with any callable function, regardless
of calls present.
llvm-svn: 328659
The combine on a select of a load only triggers for
addrspace 0, and discards the MachinePointerInfo. The
conservative default needs to be used for this.
llvm-svn: 328652
In a function, s5 is used as the frame base SGPR. If a function
is calling another function, during the call sequence
it is copied to a preserved SGPR and restored.
Before it was possible for the scheduler to move stack operations
before the restore of s5, since there's nothing to associate
a frame index access with the restore.
Add an implicit use of s5 to the adjcallstack pseudo which ends
the call sequence to preven this from happening. I'm not 100%
satisfied with this solution, but I'm not sure what else would be
better.
llvm-svn: 328650
This implements a set of TTI functions that the loop vectorizer uses.
The only purpose of this is to enable testing. Auto-vectorization is
disabled by default, enabled by -hexagon-autohvx.
llvm-svn: 328639
Summary:
This is a canonical way to teach objdump to print the target
symbols for branches when disassembling AArch64 code.
Reviewers: evandro, t.p.northover, espindola
Reviewed By: t.p.northover
Differential Revision: https://reviews.llvm.org/D44851
llvm-svn: 328638
Summary:
I recently added a new Fixup kind to our fork of LLVM but forgot to add
it to the table in MipsAsmBackend.cpp. With this static_assert the error
would have been caught instead of zero-initializing the array entries for
the new fixups.
Reviewers: sdardis, atanasyan
Reviewed By: atanasyan
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D44895
llvm-svn: 328616
Currently CRC32 instructions use the WriteFAdd class, this patch splits them off into their own, at the moment it is still mostly just a duplicate of WriteFAdd but it can now be tweaked on a target by target basis.
Differential Revision: https://reviews.llvm.org/D44647
llvm-svn: 328582
Summary:
Re-lands r328386 and r328443, reverting r328482.
Incorporates fixes from @mstorsjo in D44876 (thanks!) so that small
parameters in i8 and i16 do not end up in the SysV register parameters
(EDI, ESI, etc).
I added tests for how we receive small parameters, since that is the
important part. It's always safe to store more bytes than will be read,
but the assumptions you make when loading them are what really matter.
I also tested this by self-hosting clang and it passed tests on win64.
Reviewers: mstorsjo, hans
Subscribers: hiraditya, mstorsjo, llvm-commits
Differential Revision: https://reviews.llvm.org/D44900
llvm-svn: 328570
Give the bit count instructions their own scheduler classes instead of forcing them into existing classes.
These were mostly overridden anyway, but I had to add in costs from Agner for silvermont and znver1 and the Fam16h SoG for btver2 (Jaguar).
Differential Revision: https://reviews.llvm.org/D44879
llvm-svn: 328566
Summary:
r327219 added wrappers to std::sort which randomly shuffle the container before sorting.
This will help in uncovering non-determinism caused due to undefined sorting
order of objects having the same key.
To make use of that infrastructure we need to invoke llvm::sort instead of std::sort.
Note: This patch is one of a series of patches to replace *all* std::sort to llvm::sort.
Refer the comments section in D44363 for a list of all the required patches.
Reviewers: dblaikie, RKSimon, robertlytton
Reviewed By: robertlytton
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D44875
llvm-svn: 328564
Legalize and emit code for quad-precision floating point operation xscvdpqp
and add option to guard the quad precision operation support.
Differential Revision: https://reviews.llvm.org/D44746
llvm-svn: 328558
A new function getOpcodeForSpill should now be the only place to get
the opcode for a given spilled register.
Differential Revision: https://reviews.llvm.org/D43086
llvm-svn: 328556
Summary:
llvm-objdump now disassembles unrecognised opcodes as data, using
the .long directive. We treat unrecognised opcodes as being 32 bit
values, so move along 4 bytes rather than the single byte which
previously resulted in a cascade of bogus disassembly following an
unrecognised opcode.
While no solution can always disassemble code that contains
embedded data correctly this provides a significant improvement.
The disassembler will now cope with an arbitrary length section
as it no longer truncates it to a multiple of 4 bytes, and will
use the .byte directive for trailing bytes.
Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D44685
llvm-svn: 328553
The patch contains severals changes needed to pipeline an example
that was transformed so that a Phi with a subreg is converted to
copies.
The pipeliner wasn't working for a couple of reasons.
- The RecMII was 3 instead of 2 due to the extra copies.
- Copy instructions contained a latency of 1.
- The node order algorithm was not choosing the best "bottom"
node, which caused an instruction to be scheduled that had a
predecessor and successor already scheduled.
- Updated the Hexagon Machine Scheduler to check if the node is
latency bound when adding the cost for a 0-latency dependence.
The RecMII was 3 because the computation looks at the number of
nodes in the recurrence. The extra copy is an extra node but
it shouldn't increase the latency. The new RecMII computation
looks at the latency of the instructions in the recurrence. We
changed the latency of the dependence of a copy to 0. The latency
computation for the copy also checks the use of the copy (similar
to a reg_sequence).
The node order algorithm was not choosing the last instruction
in the recurrence for a bottom up traversal. This was when the
last instruction is a copy. A check was added when choosing the
instruction to check for NodeNum if the maxASAP is the same. This
means that the scheduler will not end up with another node in
the recurrence that has both a predecessor and successor already
scheduled.
The cost computation in Hexagon Machine Scheduler adds cost when
an instruction can be packetized with a zero-latency instruction.
We should only do this if the schedule is latency bound.
Patch by Brendon Cahoon.
llvm-svn: 328542
This broke Chromium (see crbug.com/825748). It looks like mstorsjo's follow-up
patch at D44876 fixes this, but let's revert back to green for now until that's
ready to land.
(Also reverts r328443.)
> Both GCC and MSVC only look at the low byte of a boolean when it is
> passed.
llvm-svn: 328482
Add fdiv costs for Goldmont using table 16-17 of the Intel Optimization Manual. Also add overrides for FSQRT for Goldmont and Silvermont.
Reviewers: RKSimon
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D44644
llvm-svn: 328451
The Intel models need an extra 1uop for memory folded instructions, plus a lot of instructions take a non-default memory latency which should allow us to use the multiclass a lot more to tidy things up.
Differential Revision: https://reviews.llvm.org/D44840
llvm-svn: 328446
Summary:
LLVM defaults to the newer .init_array/.fini_array scheme for static
constructors rather than the less desirable .ctors/.dtors (the UseCtors
flag defaults to false). This wasn't being respected in the RISC-V
backend because it fails to call TargetLoweringObjectFileELF::InitializeELF with the the appropriate
flag for UseInitArray.
This patch fixes this by implementing RISCVELFTargetObjectFile and overriding its Initialize method to call
InitializeELF(TM.Options.UseInitArray).
Reviewers: asb, apazos
Reviewed By: asb
Subscribers: mgorny, rbar, johnrusso, simoncook, jordy.potman.lists, sabuasal, niosHD, kito-cheng, shiva0217, llvm-commits
Differential Revision: https://reviews.llvm.org/D44750
llvm-svn: 328433
Summary:
r327219 added wrappers to std::sort which randomly shuffle the container before sorting.
This will help in uncovering non-determinism caused due to undefined sorting
order of objects having the same key.
To make use of that infrastructure we need to invoke llvm::sort instead of std::sort.
Note: This patch is one of a series of patches to replace *all* std::sort to llvm::sort. Refer the comments section in D44363 for a list of all the required patches.
Reviewers: kparzysz
Reviewed By: kparzysz
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D44857
llvm-svn: 328430
Summary:
r327219 added wrappers to std::sort which randomly shuffle the container before sorting.
This will help in uncovering non-determinism caused due to undefined sorting
order of objects having the same key.
To make use of that infrastructure we need to invoke llvm::sort instead of std::sort.
Reviewers: tstellar, RKSimon, arsenm
Reviewed By: arsenm
Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, llvm-commits, t-tye
Differential Revision: https://reviews.llvm.org/D44856
llvm-svn: 328429
These nodes only use the lower 32 bits of their inputs so we can use SimplifyDemandedBits to simplify them.
Differential Revision: https://reviews.llvm.org/D44375
llvm-svn: 328405
Should be NFC since nothing used the enum value. The instruction descriptions are generated from tablegen which had the correct value.
llvm-svn: 328398
This is used by llvm tblgen as well as by LLVM Targets, so the only
common place is Support for now. (maybe we need another target for these
sorts of things - but for now I'm at least making them correct & we can
make them better if/when people have strong feelings)
llvm-svn: 328395
This includes llvm-c/TargetMachine.h which is logically part of
libTarget (since libTarget implements llvm-c/TargetMachine.h's
functions).
llvm-svn: 328394
This is used from llvm tblgen and the X86Disassembler - the only common
library (apart from TableGen, which probably doesn't make sense to have
as a dependency from a release tool (rather than a use-while-building-llvm
tool) of LLVM)
llvm-svn: 328393
The branch relaxation pass collects sizes of all instructions at the
beginning, before any changes have been made. It then performs one pass
over all branches to see which ones need to be extended. It does not
account for the case when a previously valid branch becomes out-of-range
due to relaxing other branches.
This approach fixes this problem by assuming from the beginning that
all extendable branches have been extended. This may cause unneeded
relaxation in some cases, but avoids iteration and recomputing instruction
sizes.
llvm-svn: 328360
The HexagonExpandCondsets pass is incorrectly removing the dead
flag on a definition that is really dead, and adding a kill flag
to a use that is tied to a definition. This causes an assert later
during the machine scheduler when querying the live interval
information.
Patch by Brendon Cahoon.
llvm-svn: 328357
- Remove use of the opencl and amdopencl environment member of the target triple for the AMDGPU target.
- Use function attribute to communicate to the AMDGPU backend to add implicit arguments for OpenCL kernels for the AMDHSA OS.
Differential Revision: https://reviews.llvm.org/D43736
llvm-svn: 328349
HexagonGenMux would collapse pairs of predicated transfers if it assumed
that the predicated .new forms cannot be created. Turns out that generating
mux is preferable in almost all cases.
Introduce an option -hexagon-gen-mux-threshold that controls the minimum
distance between the instruction defining the predicate and the later of
the two transfers. If the distance is closer than the threshold, mux will
not be generated. Set the threshold to 0 by default.
llvm-svn: 328346
This patch fixes PR36658, "Constant pool entry out of range!" in Thumb1 mode.
In ARMConstantIslands::optimizeThumb2JumpTables() in Thumb1 mode,
adjustBBOffsetsAfter() is not calculating postOffset correctly by
properly accounting for the padding that is required for the constant pool
that immediately follows the jump table branch instruction.
Reviewers: t.p.northover, eli.friedman
Reviewed By: t.p.northover
Subscribers: chrib, tstellar, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D44709
llvm-svn: 328341
When converting an instruction to the wider version, copy any
subregisters if the original operand has a subregister.
Patch by Brendon Cahoon.
llvm-svn: 328333
This patch adds functions to allow MachineLICM to hoist invariant stores.
Currently, MachineLICM does not hoist any store instructions, however
when storing the same value to a constant spot on the stack, the store
instruction should be considered invariant and be hoisted. The function
isInvariantStore iterates each operand of the store instruction and checks
that each register operand satisfies isCallerPreservedPhysReg. The store
may be fed by a copy, which is hoisted by isCopyFeedingInvariantStore.
This patch also adds the PowerPC changes needed to consider the stack
register as caller preserved.
Differential Revision: https://reviews.llvm.org/D40196
llvm-svn: 328326
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
This was due to a misunderstanding over what llvm calls a micro-op (retirement unit) is actually called a macro-op on the AMD/Jaguar target. Folded loads don't affect num macro ops.
llvm-svn: 328320
When targeting execute-only and fp-armv8, float constants in a compare
resulted in instruction selection failures. This is now fixed by using
vmov.f32 where possible, otherwise the floating point constant is
lowered into a integer constant that is moved into a floating point
register.
This patch also restores using fpcmp with immediate 0 under fp-armv8.
Change-Id: Ie87229706f4ed879a0c0cf66631b6047ed6c6443
llvm-svn: 328313
The VMOVMSKBrr was in a separate InstRW with a lower latency, but I assume they should be the same and the higher latency matches Agners table so I'm going with that.
llvm-svn: 328291
This makes the Y position consistent with other instructions.
This should have been NFC, but while refactoring the multiclass I noticed that VROUNDPD memory forms were using the register itinerary.
llvm-svn: 328254
Summary:
This pass sinks COPY instructions into a successor block, if the COPY is not
used in the current block and the COPY is live-in to a single successor
(i.e., doesn't require the COPY to be duplicated). This avoids executing the
the copy on paths where their results aren't needed. This also exposes
additional opportunites for dead copy elimination and shrink wrapping.
These copies were either not handled by or are inserted after the MachineSink
pass. As an example of the former case, the MachineSink pass cannot sink
COPY instructions with allocatable source registers; for AArch64 these type
of copy instructions are frequently used to move function parameters (PhyReg)
into virtual registers in the entry block..
For the machine IR below, this pass will sink %w19 in the entry into its
successor (%bb.1) because %w19 is only live-in in %bb.1.
```
%bb.0:
%wzr = SUBSWri %w1, 1
%w19 = COPY %w0
Bcc 11, %bb.2
%bb.1:
Live Ins: %w19
BL @fun
%w0 = ADDWrr %w0, %w19
RET %w0
%bb.2:
%w0 = COPY %wzr
RET %w0
```
As we sink %w19 (CSR in AArch64) into %bb.1, the shrink-wrapping pass will be
able to see %bb.0 as a candidate.
With this change I observed 12% more shrink-wrapping candidate and 13% more dead copies deleted in spec2000/2006/2017 on AArch64.
Reviewers: qcolombet, MatzeB, thegameg, mcrosier, gberry, hfinkel, john.brawn, twoh, RKSimon, sebpop, kparzysz
Reviewed By: sebpop
Subscribers: evandro, sebpop, sfertile, aemerson, mgorny, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D41463
llvm-svn: 328237
As in SystemZ backend, correctly propagate node ids when inserting new
unselected nodes into the DAG during instruction Seleciton for X86
target.
Fixes PR36865.
Reviewers: jyknight, craig.topper
Subscribers: hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D44797
llvm-svn: 328233
This fixes a few issues with the R52 instregexs to enable the full overlap checking
Differential Revision: https://reviews.llvm.org/D44767
llvm-svn: 328216
Models were completely overriding all CLMUL instructions when the WriteCLMUL default classes could be used for exactly the same coverage.
llvm-svn: 328194
PCLMULQDQrm was using the rr itinerary.
Difference in itineraries between PCLMULQDQ/VPCLMULQDQ variants was causing an unnecessary duplication of scheduler class entries.
llvm-svn: 328193
Models were completely overriding all AES instructions when the WriteAES default classes could be used for exactly the same coverage.
Removes 6 unnecessary scheduler classes from every model.
Note: Still looking for a way for tblgen to warn when this is happening - often the override is more complete than the default.
llvm-svn: 328192
I've also merged some VEX/non-VEX instregex strings with a (V?) prefix or (Y?) ymm variant - there are still a lot more of these to do.
This reduces the size of the optimized llc binary on my computer by 400K. Presumably because we went from 5000+ scheduler classes per CPU to ~2000.
llvm-svn: 328179
Remove #include of Transforms/Scalar.h from Transform/Utils to fix layering.
Transforms depends on Transforms/Utils, not the other way around. So
remove the header and the "createStripGCRelocatesPass" function
declaration (& definition) that is unused and motivated this dependency.
Move Transforms/Utils/Local.h into Analysis because it's used by
Analysis/MemoryBuiltins.cpp.
llvm-svn: 328165
This is needed for the upcoming implementation of the
new 8x32x16 and 32x8x16 variants of WMMA instructions
introduced in CUDA 9.1.
Differential Revision: https://reviews.llvm.org/D44719
llvm-svn: 328158
The "ShouldEmitMatchRegisterName" bit wasn't taking effect because the
WebAssembly target didn't point to the custom WebAssemblyAsmParser
record.
llvm-svn: 328155
Add barrier edges to check for any physical register. The previous code
worked for the function return registers: r0/d0, v0/w0.
Patch by Brendon Cahoon.
llvm-svn: 328120
I've also merged some VEX/non-VEX instregex strings with a (V?) prefix or (Y?) ymm variant - there are still a lot more of these to do.
llvm-svn: 328111
This patch also includes extensive tests targeted at select and br+fcmp IR
inputs. A sequence of br+fcmp required support for FPR32 registers to be added
to RISCVInstrInfo::storeRegToStackSlot and
RISCVInstrInfo::loadRegFromStackSlot.
llvm-svn: 328104
Also restrict to port 0 and 1 for SkylakeClient. It looks like the scheduler models don't account for client not having a full vector ALU on port 5 like server.
Fixes PR36808.
llvm-svn: 328061
The default thread model for wasm is single, and in this mode thread-local
global variables can be lowered identically to non-thread-local variables.
Differential Revision: https://reviews.llvm.org/D44703
llvm-svn: 328049
Mingw uses the same stack protector functions as GCC provides
on other platforms as well.
Patch by Valentin Churavy!
Differential Revision: https://reviews.llvm.org/D27296
llvm-svn: 328039
It uses the MC framework and the tablegen matcher to do the
heavy lifting. Can handle both explicit and implicit locals
(-disable-wasm-explicit-locals). Comes with a small regression
test.
This is a first basic implementation that can parse most llvm .s
output and round-trips most instructions succesfully, but in order
to keep the commit small, does not address all issues.
There are a fair number of mismatches between what MC / assembly
matcher think a "CPU" should look like and what WASM provides,
some already have workarounds in this commit (e.g. the way it
deals with register operands) and some that require further work.
Some of that further work may involve changing what the
Disassembler outputs (and what s2wasm parses), so are probably
best left to followups.
Some known things missing:
- Many directives are ignored and not emitted.
- Vararg calls are parsed but extra args not emitted.
- Loop signatures are likely incorrect.
- $drop= is not emitted.
- Disassembler does not output SIMD types correctly, so assembler
can't test them.
Patch by Wouter van Oortmerssen
Differential Revision: https://reviews.llvm.org/D44329
llvm-svn: 328028
I'm not entirely sure these hacks are still needed. If you remove the hacks completely, the name of the library call that gets generated doesn't match the grep the test previously had. So the test wasn't really checking anything.
If the hack is still needed it belongs in PPC specific code. I believe the FP_TO_SINT code here is the only place in the tree where a FP_ROUND_INREG node is created today. And I don't think its even being used correctly because the legalization returned a BUILD_PAIR with the same value twice. That doesn't seem right to me. By moving the code entirely to PPC we can avoid creating the FP_ROUND_INREG at all.
I replaced the grep in the existing test with full checks generated by hacking update_llc_test_check.py to support ppc32 just long enough to generate it.
Differential Revision: https://reviews.llvm.org/D44061
llvm-svn: 328017
Registers E[A-D]X, E[SD]I, E[BS]P, and EIP have 16-bit subregisters
that cover the low halves of these registers. This change adds artificial
subregisters for the high halves in order to differentiate (in terms of
register units) between the 32- and the low 16-bit registers.
This patch contains parts that aim to preserve the calculated register
pressure. This is in order to preserve the current codegen (minimize the
impact of this patch). The approach of having artificial subregisters
could be used to fix PR23423, but the pressure calculation would need
to be changed.
Differential Revision: https://reviews.llvm.org/D43353
llvm-svn: 328016
This way we can support address-space specific variants without explicitly
encoding the space in the name of the intrinsic. Less intrinsics to deal with ->
less boilerplate.
Added a bit of tablegen magic to match/replace an intrinsics with a pointer
argument in particular address space with the space-specific instruction
variant.
Updated tests to use non-default address spaces.
Differential Revision: https://reviews.llvm.org/D43268
llvm-svn: 328006
TopReadyCycle and BotReadyCycle were off by one cycle when an SU is either
the first instruction or the last instruction in a packet.
Patch by Ikhlas Ajbar.
llvm-svn: 328000
This patch changes the isLatencyBound heuristic to look at the
path length based upon the number of packets needed to schedule
a basic block. For small basic blocks, the heuristic uses a small
threshold for isLatencyBound. For large basic blocks, the
heuristic uses a large threshold.
The goal is to increase the priority of an instruction in a small
basic block that has a large height or depth relative to the code
size. For large functions, the height and depth are ignored
because it increases the live range of a register and causes more
spills. That is, for large functions, it is more important to
schedule instructions when available, and attempt to keep the defs
and uses closer together.
Patch by Brendon Cahoon.
llvm-svn: 327987
In these cases, both parameters and return values are passed
as a pointer to a stack allocation.
MSVC doesn't use the f80 data type at all, while it is used
for long doubles on mingw.
Normally, this part of the calling convention is handled
within clang, but for intrinsics that are lowered to libcalls,
it may need to be handled within llvm as well.
Differential Revision: https://reviews.llvm.org/D44592
llvm-svn: 327957
They were incorrectly marked as RMW operations. Some of the CMP instrucions worked, but the ones that use a similar encoding as RMW form of ADD ended up marked as RMW.
TEST used the same tablegen class as some of the CMPs.
llvm-svn: 327947
E.g.
bar (int x)
{
char p[x];
push outgoing variables for foo.
call foo
}
We need to generate stack adjustment instructions for outgoing arguments by
eliminateCallFramePseudoInstr when the function contains variable size
objects to avoid outgoing variables corrupt the variable size object.
Default hasReservedCallFrame will return !hasFP().
We don't want to generate extra sp adjustment instructions when hasFP()
return true, So We override hasReservedCallFrame as !hasVarSizedObjects().
Differential Revision: https://reviews.llvm.org/D43752
llvm-svn: 327938
When outlining calls, the outliner needs to update CFI to ensure that, say,
exception handling works. This commit adds that functionality and adds a test
just for call outlining.
Call outlining stuff in machine-outliner.mir should be moved into
machine-outliner-calls.mir in a later commit.
llvm-svn: 327917
We don't need to create an ISD::TRUNCATE node to return, we started with one and can return it. Also remove the call to getExtendInVec, the result is just going to be a getNode of that value passed in.
llvm-svn: 327914
This extends the use of this attribute on ARM and AArch64 from
SVN r325900 (where it was only checked for fixed stack
allocations on ARM/AArch64, but for all stack allocations on X86).
This also adds a testcase for the existing use of disabling the
fixed stack probe with the attribute on ARM and AArch64.
Differential Revision: https://reviews.llvm.org/D44291
llvm-svn: 327897
PR35590 was already filed for this information being wrong. It's probably better to default to WriteSystem behavior instead of using something completely wrong.
llvm-svn: 327882
JRCXZ was already present, but not the others.
We never codegen this instruction so this doesn't affect much just trying to get them all into a single generated scheduler class in the output.
llvm-svn: 327881
The regex was looking for JECXZ_32 or JECXZ_64, but their is just one instruction called JECXZ. They used to exist as separate instructions, but were merged over 3 years ago.
llvm-svn: 327880
PowerPC targets do not use address spaces. As a result, we can get selection
failures with address space casts. This patch makes those casts noops.
Patch by Valentin Churavy.
Differential revision: https://reviews.llvm.org/D43781
llvm-svn: 327877
With the SRAs removed from the SSE2 code in D44267, then there doesn't appear to be any advantage to the sse41 code. The punpcklbw instruction and pmovsx seem to have the same latency and throughput on most CPUs. And the SSE41 code requires moving the upper 64-bits into the lower 64-bit before the sign extend can be done. The unpckhbw in sse2 code can do better than that.
llvm-svn: 327869
Sometimes we used the same itinerary for MEM and REG forms, but that seems inconsistent with our usual usage.
We also used the MUL8 itinerary for MULX32/64 which was also weird.
The test changes are because we were using IIC_IMUL32_RR and IIC_IMUL64_RR instead of IIC_IMUL32_REG/IIC_IMUL64_REG for the 32 and 64 bit multiplies that produce double width result.
llvm-svn: 327866
This patch adds functions to allow MachineLICM to hoist invariant stores.
Currently, MachineLICM does not hoist any store instructions, however
when storing the same value to a constant spot on the stack, the store
instruction should be considered invariant and be hoisted. The function
isInvariantStore iterates each operand of the store instruction and checks
that each register operand satisfies isCallerPreservedPhysReg. The store
may be fed by a copy, which is hoisted by isCopyFeedingInvariantStore.
This patch also adds the PowerPC changes needed to consider the stack
register as caller preserved.
Differential Revision: https://reviews.llvm.org/D40196
llvm-svn: 327856
Currently the WriteResPair style multi-classes take a single pipeline stage and latency, this patch generalizes this to make it easier to create complex schedules with ResourceCycles and NumMicroOps be overriden from their defaults.
This has already been done for the Jaguar scheduler to remove a number of custom schedule classes and adding it to the other x86 targets will make it much tidier as we add additional classes in the future to try and replace so many custom cases.
I've converted some instructions but a lot of the models need a bit of cleanup after the patch has been committed - memory latencies not being consistent, the class not actually being used when we could remove some/all customs, etc. I'd prefer to keep this as NFC as possible so later patches can be smaller and target specific.
Differential Revision: https://reviews.llvm.org/D44612
llvm-svn: 327855
1. Given that we already have a classification bucket with 'nop' in the name,
that's where 'nop' belongs. Right now, it's only used for prefix bytes and 'pause'.
2. Make the latency of this class '1' for Jaguar to tell the scheduler (and presumably
llvm-mca) how to model the resource requirements better even though a nop has no
dependencies.
Differential Revision: https://reviews.llvm.org/D44608
llvm-svn: 327853
Summary:
The docs already claim that this happens, but so far it hasn't. As a
consequence, existing TableGen files get this wrong a lot, but luckily
the fixes are all reasonably straightforward.
To make this work with all the existing forms of self-references (since
the true type of a record is only built up over time), the lookup of
self-references in !cast is delayed until the final resolving step.
Change-Id: If5923a72a252ba2fbc81a889d59775df0ef31164
Reviewers: arsenm, craig.topper, tra, MartinO
Subscribers: wdng, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D44475
llvm-svn: 327849
Summary:
These are cases of self-references that exist today in practice. Let's
add tests for them to avoid regressions.
The self-references in PPCInstrInfo.td can be expressed in a simpler
way. Allowing this type of self-reference while at the same time
consistently doing late-resolve even for self-references is problematic
because there are references to fields that aren't in any class. Since
there's no need for this type of self-reference anyway, let's just
remove it.
Change-Id: I914e0b3e1ae7adae33855fac409b536879bc3f62
Reviewers: arsenm, craig.topper, tra, MartinO
Subscribers: nemanjai, wdng, kbarton, llvm-commits
Differential Revision: https://reviews.llvm.org/D44474
llvm-svn: 327848
Normally DCE kills these, but at -O0 these get left behind
leaving suspicious looking illegal copies.
Replace with IMPLICIT_DEF to avoid iterator issues.
llvm-svn: 327842
This is the groundwork for adding the Armv8.2-A FP16 vector intrinsics, which
uses v4f16 and v8f16 vector operands and return values. All the moving parts
are tested with two intrinsics, a 1-operand v8f16 and a 2-operand v4f16
intrinsic. In a follow-up patch the rest of the intrinsics and tests will be
added.
Differential Revision: https://reviews.llvm.org/D44538
llvm-svn: 327839
If DoneMBB becomes empty it must have CC added to its live-in list, since it
will fall-through into EndMBB. This happens when the CLC loop does the
complete range.
Review: Ulrich Weigand
llvm-svn: 327834
Also move ADC8i8 and SBB8i8 in the Sandy Bridge model to the same class as ADC8ri and SBB8ri. That seems more accurate since its the 8i8 is just the register forced to AL instead of coming from modrm.
llvm-svn: 327820
This patch adds i128 division support by instruction LLVM to lower
128-bit divisions to the __udivmodti4 and __divmodti4 rtlib functions.
This also adds test for 64-bit division and 128-bit division.
Patch by Peter Nimmervoll.
llvm-svn: 327814
This is similar to the check later when we remap some of the instructions from one class to a new one. But if we reuse the class we don't get to do that check.
So many CPUs have violations of this check that I had to add a flag to the SchedMachineModel to allow it to be disabled. Hopefully we can get those cleaned up quickly and remove this flag.
A lot of the violations are due to overlapping regular expressions, but that's not the only kind of issue it found.
llvm-svn: 327808
Jaguar's FPU has 2 scheduler pipes (JFPU0/JFPU1) which forward to multiple functional sub-units each. We need to model that an micro-op will both consume the scheduler pipe and a functional unit.
This patch just handles the ops defined through JWriteResFpuPair, I'll go through the custom cases later.
llvm-svn: 327791
The information was so wildly inaccurate and incomplete its better to just remove it.
MMX_MASKMOVQ64 showed up twice in several scheduler models. In Haswell and Broadwell they were on adjacent lines. On Skylake the copies had different information.
MMX_MASKMOVQ and MASKMOVDQU were completely missing.
MMX_MASKMOVQ64 was listed on Haswell/Broadwell as 1 cycle on port 1 despite it being a store instruction.
Filed PR36780 to track fixing this right.
llvm-svn: 327783
X86 Supports Indirect Branch Tracking (IBT) as part of Control-Flow Enforcement Technology (CET).
IBT instruments ENDBR instructions used to specify valid targets of indirect call / jmp.
The `nocf_check` attribute has two roles in the context of X86 IBT technology:
1. Appertains to a function - do not add ENDBR instruction at the beginning of the function.
2. Appertains to a function pointer - do not track the target function of this pointer by adding nocf_check prefix to the indirect-call instruction.
This patch implements `nocf_check` context for Indirect Branch Tracking.
It also auto generates `nocf_check` prefixes before indirect branchs to jump tables that are guarded by range checks.
Differential Revision: https://reviews.llvm.org/D41879
llvm-svn: 327767
Improve/implement these methods to improve DAG combining. This mainly
concerns intrinsics.
Some constant operands to SystemZISD nodes have been marked Opaque to avoid
transforming back and forth between generic and target nodes infinitely.
Review: Ulrich Weigand
llvm-svn: 327765
At the point the outliner runs, KILLs don't impact anything, but they're still
considered unique instructions. This commit makes them invisible like
DebugValues so that they can still be outlined without impacting outlining
decisions.
llvm-svn: 327760
This prevents a crash in SelectionDAGDumper with -debug when trying to print mem operands if one of the registers in the addressing mode comes from a load.
llvm-svn: 327744
Avoid scheduling two loads in such a way that they would end up in the
same packet. If there is a load in a packet, try to schedule a non-load
next.
Patch by Brendon Cahoon.
llvm-svn: 327742
Previously, we called the same functions twice with a bool flag determining whether we should look for ADDSUB or SUBADD. It would be more efficient to run the code once and detect either pattern with a flag to tell which type it found.
Differential Revision: https://reviews.llvm.org/D44540
llvm-svn: 327730
We previously avoided inserting these moves during isel in a few cases which is implemented using a whitelist of opcodes. But it's too difficult to generate a perfect list of opcodes to whitelist. Especially with AVX512F without AVX512VL using 512 bit vectors to implement some 128/256 bit operations. Since isel is done bottoms up, we'd have to check the VT and opcode and subtarget in order to determine whether an EXTRACT_SUBREG would be generated for some operations.
So instead of doing that, this patch adds a post processing step that detects when the moves are unnecesssary after isel. At that point any EXTRACT_SUBREGs would have already been created and appear in the DAG. So then we just need to ensure the input to the move isn't one.
Differential Revision: https://reviews.llvm.org/D44289
llvm-svn: 327724
AnyReg is just for the assembler and it is better to have it as not
allocatable in order to simplify (make more intuitive) the RegPressureSets.
Review: Ulrich Weigand
llvm-svn: 327715
Summary:
Currently the LLVM MC assembler is able to convert e.g.
vmov.i32 d0, #0xabababab
(which is technically invalid) into a valid instruction
vmov.i8 d0, #0xab
this patch adds support for vmov.i64 and for cases with the resulting
load types other than i8, e.g.:
vmov.i32 d0, #0xab00ab00 ->
vmov.i16 d0, #0xab00
Reviewers: olista01, rengolin
Reviewed By: rengolin
Subscribers: rengolin, javed.absar, kristof.beyls, rogfer01, llvm-commits
Differential Revision: https://reviews.llvm.org/D44467
llvm-svn: 327709
Summary:
Currently the check is incorrect and the following invalid
instruction is accepted and incorrectly assembled:
vmov.i32 d2, #0x00a500a6
This patch fixes the issue.
Reviewers: olista01, rengolin
Reviewed By: rengolin
Subscribers: SjoerdMeijer, javed.absar, rogfer01, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D44460
llvm-svn: 327704
This patch provides an implementation of getArithmeticReductionCost for
AArch64. We can specialize the cost of add reductions since they are computed
using the 'addv' instruction.
Differential Revision: https://reviews.llvm.org/D44490
llvm-svn: 327702
This implements lowering of SELECT_CC for f16s, which enables
codegen of VSEL with f16 types.
Differential Revision: https://reviews.llvm.org/D44518
llvm-svn: 327695
Previously if getSetccResultType returned an illegal type we just fell back to using the default promoted type. This appears to have been to handle the case where for vectors getSetccResultType returns the input type, but the input type itself isn't legal and will need to be promoted. Without the legality check we would never reach a legal type.
But just picking the promoted type to be the setcc type can create strange setccs where the result type is 128 bits and the operand type is 256 bits. If for example the result type was promoted to v8i16 from v8i1, but the input type was promoted from v8i23 to v8i32. We currently handle this with custom lowering code in X86.
This legality check also caused us reject the getSetccResultType when the input type needed to be widened or split. Even though that result wouldn't have caused legalization to get stuck.
This patch tries to fix this by detecting the getSetccResultType needs to be promoted. If its input type also needs to be promoted we'll try a ask for a new setcc result type based on its eventual promoted value. Otherwise we fall back to default type to promote to.
For any other illegal values we might get back from the initial call to getSetccResultType we just keep and allow it to be re-legalized later via splitting or widening or scalarizing.
llvm-svn: 327683
YMM FDiv/FSqrt are dispatched on pipe JFPU1 but should be performed on the JFPM unit - that is where most of the cycles are spent.
This matches the pipes for WriteFSqrt/WriteFDiv definitions.
llvm-svn: 327682
The FADD part of the addsub/subadd pattern can have its operands commuted, but when checking for fsubadd we were using the fadd as reference and commuting the fsub node.
llvm-svn: 327660
PR35402 triggered this case. It bswap and stores a 48bit value, current STBRX optimization transforms it into STBRX. Unfortunately 48bit is not a simple MVT, there is no PPC instruction to support it, and it can't be automatically expanded by llvm, so caused a crash.
This patch detects the non-simple MVT and returns early.
Differential Revision: https://reviews.llvm.org/D44500
llvm-svn: 327651
Rather than enumerating all specific types, for the DAG combine we can just use TLI::isTypeLegal and an SSE3 check. For the BUILD_VECTOR version we already know the type is legal so we just need to check SSE3.
llvm-svn: 327649
This patch adds new load/store instructions for integer scalar types
which can be used for X-Form when fed by add with an @tls relocation.
Differential Revision: https://reviews.llvm.org/D43315
llvm-svn: 327635
As discussed on D44428 and PR36726, this patch splits off WriteFMove/WriteVecMove, WriteFLoad/WriteVecLoad and WriteFStore/WriteVecStore scheduler classes to permit vectors to be handled separately from gpr/scalar types.
I've minimised the diff here by only moving various basic SSE/AVX vector instructions across - we can fix the rest when called for. This does fix the MOVDQA vs MOVAPS/MOVAPD discrepancies mentioned on D44428.
Differential Revision: https://reviews.llvm.org/D44471
llvm-svn: 327630
Optionally allow the order of restoring the callee-saved registers in the
epilogue to be reversed.
The flag -reverse-csr-restore-seq generates the following code:
```
stp x26, x25, [sp, #-64]!
stp x24, x23, [sp, #16]
stp x22, x21, [sp, #32]
stp x20, x19, [sp, #48]
; [..]
ldp x24, x23, [sp, #16]
ldp x22, x21, [sp, #32]
ldp x20, x19, [sp, #48]
ldp x26, x25, [sp], #64
ret
```
Note how the CSRs are restored in the same order as they are saved.
One exception to this rule is the last `ldp`, which allows us to merge
the stack adjustment and the ldp into a post-index ldp. This is done by
first generating:
ldp x26, x27, [sp]
add sp, sp, #64
which gets merged by the arm64 load store optimizer into
ldp x26, x25, [sp], #64
The flag is disabled by default.
llvm-svn: 327569
I removed this in r316797 because the coverage report showed no coverage and I thought it should have been handled by the auto generated table. I now see that there is code that bypasses the table if the shift amount is out of bounds.
This adds back the code. We'll codegen out of bounds i8 shifts to effectively (amount & 0x1f). The 0x1f is a strange quirk of x86 that shift amounts are always masked to 5-bits(except 64-bits). So if the masked value is still out bounds the result will be 0.
Fixes PR36731.
llvm-svn: 327540
I had to modify the bswap recognition to allow unshrunk masks to make this work.
Fixes PR36689.
Differential Revision: https://reviews.llvm.org/D44442
llvm-svn: 327530
Support G_LSHR/G_ASHR/G_SHL. We have 3 variance for
shift instructions : shift gpr, shift imm, shift 1.
Currently GlobalIsel TableGen generate patterns for
shift imm and shift 1, but with shiftCount i8.
In G_LSHR/G_ASHR/G_SHL like LLVM-IR both arguments
has the same type, so for now only shift i8 can use
auto generated TableGen patterns.
The support of G_SHL/G_ASHR enables tryCombineSExt
from LegalizationArtifactCombiner.h to hit, which
results in different legalization for the following tests:
LLVM :: CodeGen/X86/GlobalISel/ext-x86-64.ll
LLVM :: CodeGen/X86/GlobalISel/gep.ll
LLVM :: CodeGen/X86/GlobalISel/legalize-ext-x86-64.mir
-; X64-NEXT: movsbl %dil, %eax
+; X64-NEXT: movl $24, %ecx
+; X64-NEXT: # kill: def $cl killed $ecx
+; X64-NEXT: shll %cl, %edi
+; X64-NEXT: movl $24, %ecx
+; X64-NEXT: # kill: def $cl killed $ecx
+; X64-NEXT: sarl %cl, %edi
+; X64-NEXT: movl %edi, %eax
..which is not optimal and should be addressed later.
Rework of the patch by igorb
Reviewed By: igorb
Differential Revision: https://reviews.llvm.org/D44395
llvm-svn: 327499
We now only create recursive concats if we have more than two non-zero values. This keeps our subvector broadcast DAG combine functioning.
llvm-svn: 327457
This better able to detect undef and zeros pieces in the concat. Or cases when only one subvector is non-zero. This allows us to avoid silly things like double inserts into progressively larger undefs.
This still builds 512 bit concats of 128 bits by building up through 256 bits first. But I don't know if that's best.
We probably want to merge this with the vXi1 concat code since they are very similar.
llvm-svn: 327454
Summary: Unless you were intentionally avoiding this syntax? I saw you mentioned makeArrayRef in your commit that added SplitOpsAndApply.
Reviewers: RKSimon
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D44403
llvm-svn: 327418
This is part of fixing the instruction predicates for MIPS.
Reviewers: atanasyan, abeserminji
Differential Revision: https://reviews.llvm.org/D44212
llvm-svn: 327409
For the MIPS O32 ABI, the current call lowering logic naively lowers each
call, creating the reserved argument area to hold the argument spill areas for
$a0..$a3 and the outgoing parameter area if one is required at each call site.
In the case of a sufficently large byval argument, a call to memcpy is used
to write the start+16..end of the argument into the outgoing parameter area.
This is done within the CALLSEQ_START..CALLSEQ_END of the callee. The CALLSEQ
nodes are responsible for performing the necessary stack adjustments.
Since the O32/N32/N64 MIPS ABIs do not have a red-zone and writing below the
stack pointer and reading the values back is unpredictable, the call to memcpy
cannot be hoisted out of the callee's CALLSEQ nodes.
However, for the O32 ABI requires the reserved argument area for functions
which have parameters. The naive lowering of calls will then create nested
CALLSEQ sequences. For N32 and N64 these nodes are also created, but with
zero stack adjustments as those ABIs do not have a reserved argument area.
This patch addresses the correctness issue by recognizing the special case
of lowering a byval argument that uses memcpy. By recognizing that the
incoming chain already has a CALLSEQ_START node on it when calling memcpy,
the CALLSEQ nodes are not created. For the N32 and N64 ABIs, this is not an
issue, as no stack adjustment has to be performed.
For the O32 ABI, the correctness reasoning is different. In the case of a
sufficently large byval argument, registers a0..a3 are going to be used for
the callee's arguments, mandating the creation of the reserved argument area.
The call to memcpy in the naive case will also create its own reserved
argument area. However, since the reserved argument area consists of undefined
values, both calls can use the same reserved argument area.
Reviewers: abeserminji, atanasyan
Differential Revision: https://reviews.llvm.org/D44296
llvm-svn: 327388
Add more debug information for peephole optimization passes.
These would only be enabled for debug version binary and could help
analyzing why some optimization opportunities were missed.
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
llvm-svn: 327371
This new pass eliminate identical move:
MOV rA, rA
This is particularly possible to happen when sub-register support
enabled. The special type cast insn MOV_32_64 involves different
register class on src (i32) and dst (i64), RA could generate useless
instruction due to this.
This pass also could serve as the bast for further post-RA optimization.
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
llvm-svn: 327370
Currently, there is no ALU32 bswap support in eBPF ISA.
BSWAP on i32 was set to EXPAND which would need about eight instructions
for single BSWAP.
It would be more efficient to promote it to i64, then doing BSWAP on i64.
For eBPF programs, most of the promotion are zero extensions which are
likely be elimiated later by peephole optimizations.
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
llvm-svn: 327369
This patch relax the subregister definition check on Phi node.
Previously, we just cancel the optimizatoin when the definition is Phi
node while actually we could further check the definitions of incoming
parameters of PHI node.
This helps catch more elimination opportunities.
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
llvm-svn: 327368
The current zero extension elimination was restricted to operands of
comparison. It actually could be extended to more cases.
For example:
int *inc_p (int *p, unsigned a)
{
return p + a;
}
'a' will be promoted to i64 during addition, and the zero extension could
be eliminated as well.
For the elimination optimization, it should be much better to start
recognizing the candidate sequence from the SRL instruction instead of J*
instructions.
This patch makes it an generic zero extension elimination pass instead of
one restricted with comparison.
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
llvm-svn: 327367
There is a mistake in current code that we "break" out the optimization
when the first operand of J*_RR doesn't qualify the elimination. This
caused some elimination opportunities missed, for example the one in the
testcase.
The code should just fall through to handle the second operand.
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
llvm-svn: 327366
The current subregister definition check stops after the MOV_32_64
instruction.
This means we are thinking all the following instruction sequences
are safe to be eliminated:
MOV_32_64 rB, wA
SLL_ri rB, rB, 32
SRL_ri rB, rB, 32
However, this is *not* true. The source subregister wA of MOV_32_64 could
come from a implicit truncation of 64-bit register in which case the high
bits of the 64-bit register is not zeroed, therefore we can't eliminate
above sequence.
For example, for i32_val, we shouldn't do the elimination:
long long bar ();
int foo (int b, int c)
{
unsigned int i32_val = (unsigned int) bar();
if (i32_val < 10)
return b;
else
return c;
}
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
llvm-svn: 327365
This adds two features: "packets", and "nvj".
Enabling "packets" allows the compiler to generate instruction packets,
while disabling it will prevent it and disable all optimizations that
generate them. This feature is enabled by default on all subtargets.
The feature "nvj" allows the compiler to generate new-value jumps and it
implies "packets". It is enabled on all subtargets.
The exception is made for packets with endloop instructions, since they
require a certain minimum number of instructions in the packets to which
they apply. Disabling "packets" will not prevent hardware loops from
being generated.
llvm-svn: 327302
MVT belongs to the CodeGen layer, but ShuffleDecode is used by the X86 InstPrinter which is part of the MC layer. This only worked because MVT is completely implemented in a header file with no other library dependencies.
Differential Revision: https://reviews.llvm.org/D44353
llvm-svn: 327292
Since the enqueued kernels have internal linkage, their names may be dropped.
In this case, give them unique names __amdgpu_enqueued_kernel or
__amdgpu_enqueued_kernel.n where n is a sequential number starting from 1.
Differential Revision: https://reviews.llvm.org/D44322
llvm-svn: 327291
This simplifies tagging instructions with the correct ISA and ASE, albeit making
instruction definitions a bit more verbose.
Reviewers: atanasyan, abeserminji
Differential Revision: https://reviews.llvm.org/D44299
llvm-svn: 327265
We called MaskedValueIsZero with two different masks, but underneath that calls computeKnownBits before applying the mask. This means we compute the same known bits twice due to the two calls. Instead just call computeKnownBits directly and apply the two masks ourselves.
llvm-svn: 327251
64-bit MMX vector generation usually ends up lowering into SSE instructions before being spilled/reloaded as a MMX type.
This patch creates a MMX vector from MMX source values, taking the lowest element from each source and constructing broadcasts/build_vectors with direct calls to the MMX PUNPCKL/PSHUFW intrinsics.
We're missing a few consecutive load combines that could be handled in a future patch if that would be useful - my main interest here is just avoiding a lot of the MMX/SSE crossover.
Differential Revision: https://reviews.llvm.org/D43618
llvm-svn: 327247
Same as the VPERMILPS/VPERMILPD approach for v8f32/v4f64 cases, rely on PSHUFB using bits[3:0] for indexing - we can ignore the sign bit (zero element) as those index vector values are considered undefined. The select between the lo/hi permute results based on the index size.
llvm-svn: 327242
As VPERMILPS/VPERMILPD only selects elements based on the bits[1:0]/bit[1] then we can permute both the (repeated) lo/hi 128-bit vectors in each case and then select between these results based on whether the index was for for lo/hi.
For v4i64/v4f64 this avoids some rather nasty v4i64 multiples on the AVX2 implementation, which seems to be worse than the extra port5 pressure from the additional shuffles/blends.
llvm-svn: 327239
Helper function to insert a subvector into the bottom elements of a larger zero/undef vector with the same scalar type.
I've converted a couple of INSERT_SUBVECTOR calls to use it, there are plenty more although in some cases I was worried it might make the code more ambiguous.
llvm-svn: 327236
Summary:
There are 3 different operand orders for FMA instructions so figuring out the exact operation being performed requires a lot of thought.
This patch adds a comment to the end of the assembly line to print the exact operation.
I think I've got all the instructions in here except the ones with builtin rounding.
I didn't update all tests, but I assume we can get them as we regenerate tests in the future.
Reviewers: spatel, v_klochkov, RKSimon
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D44345
llvm-svn: 327225
X86InstComments.h is used by tools that only have the MC layer. We shouldn't be importing a file from CodeGen into this.
X86InstrInfo.h isn't a great place, but I couldn't find a better one.
llvm-svn: 327202
This fixes pr36674.
While it is valid for shouldAssumeDSOLocal to return false anytime,
always returning false for intrinsics is not optimal on i386 and also
hits a bug in the backend.
To use a plt, the caller must first setup ebx to handle the case of
that file being linked into a PIE executable or shared library. In
those cases the generated PLT uses ebx.
Currently we can produce "calll expf@plt" without setting ebx. We
could fix that by correctly setting ebx, but this would produce worse
code for the case where the runtime library is statically linked. It
would also required other tools to handle R_386_PLT32.
llvm-svn: 327198
r327171 "Improve Dependency analysis when doing multi-node Instruction Selection"
r328170 "[DAG] Enforce stricter NodeId invariant during Instruction selection"
Reverting patch as NodeId invariant change is causing pathological
increases in compile time on PPC
llvm-svn: 327197
Did some code cleanup up removing ItinRW that are not needed and resource types
that are no longer used.
Also added more comments to the td files related to the Power 9 sheduler model.
llvm-svn: 327174
Relanding after fixing NodeId Invariant.
Cleanup cycle/validity checks in ISel (IsLegalToFold,
HandleMergeInputChains) and X86 (isFusableLoadOpStore). Now do a full
search for cycles / dependencies pruning the search when topological
property of NodeId allows.
As part of this propogate the NodeId-based cutoffs to narrow
hasPreprocessorHelper searches.
Reviewers: craig.topper, bogner
Subscribers: llvm-commits, hiraditya
Differential Revision: https://reviews.llvm.org/D41293
llvm-svn: 327171
Instruction Selection makes use of the topological ordering of nodes
by node id (a node's operands have smaller node id than it) when doing
cycle detection. During selection we may violate this property as a
selection of multiple nodes may induce a use dependence (and thus a
node id restriction) between two unrelated nodes. If a selected node
has an unselected successor this may allow us to miss a cycle in
detection an invalid selection.
This patch fixes this by marking all unselected successors of a
selected node have negated node id. We avoid pruning on such negative
ids but still can reconstruct the original id for pruning.
In-tree targets have been updated to replace DAG-level replacements
with ISel-level ones which enforce this property.
This preemptively fixes PR36312 before triggering commit r324359 relands
Reviewers: craig.topper, bogner, jyknight
Subscribers: arsenm, nhaehnle, javed.absar, llvm-commits, hiraditya
Differential Revision: https://reviews.llvm.org/D43198
llvm-svn: 327170
The retpoline mitigation for variant 2 of CVE-2017-5715 inhibits the
branch predictor, and as a result it can lead to a measurable loss of
performance. We can reduce the performance impact of retpolined virtual
calls by replacing them with a special construct known as a branch
funnel, which is an instruction sequence that implements virtual calls
to a set of known targets using a binary tree of direct branches. This
allows the processor to speculately execute valid implementations of the
virtual function without allowing for speculative execution of of calls
to arbitrary addresses.
This patch extends the whole-program devirtualization pass to replace
certain virtual calls with calls to branch funnels, which are
represented using a new llvm.icall.jumptable intrinsic. It also extends
the LowerTypeTests pass to recognize the new intrinsic, generate code
for the branch funnels (x86_64 only for now) and lay out virtual tables
as required for each branch funnel.
The implementation supports full LTO as well as ThinLTO, and extends the
ThinLTO summary format used for whole-program devirtualization to
support branch funnels.
For more details see RFC:
http://lists.llvm.org/pipermail/llvm-dev/2018-January/120672.html
Differential Revision: https://reviews.llvm.org/D42453
llvm-svn: 327163
Summary: Starting from GCN 2nd generation, ISA supports ds_read_b128 on top of ds_read_b64.
This patch supports ds_read_b128 instruction pattern and generation of this instruction.
In the vectorizer, this patch also widen the vector length so that vectorizer generates
128 bit loads for local address-space which gets translated to ds_read_b128.
Since the performance benefit is not clear; compiler generates ds_read_b128 under -amdgpu-ds128.
Author: FarhanaAleen
Reviewed By: rampitec, arsenm
Subscribers: llvm-commits, AMDGPU
Differential Revision: https://reviews.llvm.org/D44210
llvm-svn: 327153
The code to match and produce more x86 vector blends was enabled for all
architectures even though the transform may pessimize the code for other
architectures that do not provide a vector blend instruction.
Added an aarch64 testcase to check that a VZIP instruction is generated instead
of byte movs.
Differential Revision: https://reviews.llvm.org/D44118
llvm-svn: 327132
Previously we unpacked the even bytes of each input into the high byte of 16-bit elements then did an v8i16 arithmetic shift right by 8 bits to fill the upper bits of each word with sign bits. Then we did the v8i16 multiply and then masked to zero the upper 8-bits of each result. The similar was done for all the odd bytes. The results are then packed together with packuswb
Since we are masking each multiply result element to 8-bits, and those 8-bits are determined only by the lower 8-bits of each of the inputs, we don't need to fill the upper bits with sign bits. So we can just unpack into the low byte of each element and treat the upper bits as garbage. This is what gcc also does.
Differential Revision: https://reviews.llvm.org/D44267
llvm-svn: 327093
This instruction can be thought of as reading either the even elements of a vXi32 input or the lower half of each element of a vXi64 input. We currently use the vXi32 interpretation, but vXi64 matches better with its broadcast behavior in EVEX.
I'm looking at moving MULDQ/MULUDQ creation to a DAG combine so we can do it when AVX512DQ is enabled without having to go through Custom lowering. But in some of the test cases we failed to use a broadcast load due to the size difference. This should help with that.
I'm also wondering if we can model these instructions in native IR and remove the intrinsics and I think using a vXi64 type will work better with that.
llvm-svn: 326991
Summary:
Fixes an UB caught by sanitizer. The shift amount might be larger than 32 so the operand should be 1ULL.
In this patch, we replace the original expression with existing API with uint64_t type.
Reviewers: eli.friedman, rengolin
Reviewed By: rengolin
Subscribers: rengolin, javed.absar, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D44234
llvm-svn: 326969
These patterns weren't checking the alignment of the load, but were using the aligned instructions. This will cause a GP fault if the data isn't aligned.
I believe these were introduced in r312450.
llvm-svn: 326967
Since there is no instruction for integer vector division, factor in the
cost of singling out each element to be used with the scalar division
instruction.
Differential revision: https://reviews.llvm.org/D43974
llvm-svn: 326955
The attached testcase started failing after the patch to define
isExtractSubvectorCheap with the following pattern mismatch:
ISEL: Starting pattern match
Initial Opcode index to 85068
Match failed at index 85076
LLVM ERROR: Cannot select: t47: v8i16 = insert_subvector undef:v8i16, t43, Constant:i64<0>
The code generated from llvm/lib/Target/AArch64/AArch64InstrInfo.td
def : Pat<(insert_subvector undef, (v4i16 FPR64:$src), (i32 0)),
(INSERT_SUBREG (v8i16 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
is in ninja/lib/Target/AArch64/AArch64GenDAGISel.inc
At the location of the error it is:
/* 85076*/ OPC_CheckChild2Type, MVT::i32,
And it failed to match the type of operand 2.
Adding another def-pat for i64 fixes the failed def-pat error:
def : Pat<(insert_subvector undef, (v4i16 FPR64:$src), (i64 0)),
(INSERT_SUBREG (v8i16 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
llvm-svn: 326949
The v8i32 conversion on AVX1 targets was only working after LowerMUL splits 256-bit vectors.
While I was there I've also made it so we don't have to check for AVX2 and BWI directly and instead just ask if the type is legal.
Differential Revision: https://reviews.llvm.org/D44190
llvm-svn: 326917
This is a follow-up to r325169, this time for all types, not just HVX
vector types.
Disable this by default, since it's not always safe.
llvm-svn: 326915
Summary: GCN ISA supports instructions that can read 16 consecutive dwords from memory through the scalar data cache;
loadstoreVectorizer should take advantage of the wider vector length and pack 16/8 elements of dwords/quadwords.
Author: FarhanaAleen
Reviewed By: rampitec
Subscribers: llvm-commits, AMDGPU
Differential Revision: https://reviews.llvm.org/D44179
llvm-svn: 326910
The purpose of this patch is to have LSR generate better code on Power.
This is done by overriding isLSRCostLess.
Differential Revision: https://reviews.llvm.org/D40855
llvm-svn: 326906
These instructions are defined as taking a GPR register and a
coprocessor register for ISAs up to MIPS32. MIPS32 extended the
definition to allow a selector--a value from 0 to 32--to access
another register.
These instructions are now internally defined as being MIPS-I
instructions, but are rejected for pre-MIPS32 ISA's if they have
an explicit selector which is non-zero. This deviates slightly from
GAS's behaviour which rejects assembly instructions with an
explicit selector for pre-MIPS32 ISAs.
E.g:
mfc0 $4, $5, 0
is rejected by GAS for MIPS-I to MIPS-V but will be accepted
with this patch for MIPS-I to MIPS-V.
Reviewers: atanasyan
Differential Revision: https://reviews.llvm.org/D41662
llvm-svn: 326890
getCurrCycleIdx() returns the decoder cycle index which the next candidate SU
will be placed on.
This patch improves this method by passing the candidate SU to it so that if
SU will begin a new group, the index of that group is returned instead.
Review: Ulrich Weigand
llvm-svn: 326880
Handle the not-taken branch in emitInstruction() where the TakenBranch
argument is available. This is cleaner than relying on EmitInstruction().
Review: Ulrich Weigand
llvm-svn: 326879
Summary:
Only IMUL16rri uses an extra P0156. IMUL32* and IMUL16rr only use
P1.
This was computed using https://github.com/google/EXEgesis/blob/master/exegesis/tools/compute_itineraries.cc
This can easily be validated by running perf on the following code:
```
int main(int argc, char**argv) {
int a = argc;
int b = argc;
int c = argc;
int d = argc;
for (int i = 0; i < LOOP_ITERATIONS; ++i) {
asm volatile(
R"(
.rept 10000
imull $0x2, %%edx, %%eax
imull $0x2, %%ecx, %%ebx
imull $0x2, %%eax, %%edx
imull $0x2, %%ebx, %%ecx
.endr
)"
: "+a"(a), "+b"(b), "+c"(c), "+d"(d)
:
:);
}
return a+b+c+d;
}
```
-> test.cc
perf stat -x, -e cycles --pfm-events=uops_executed_port:port_0:u,uops_executed_port:port_1:u,uops_executed_port:port_2:u,uops_executed_port:port_3:u,uops_executed_port:port_4:u,uops_executed_port:port_5:u,uops_executed_port:port_6:u,uops_executed_port:port_7:u test
Reviewers: craig.topper, RKSimon, gadi.haber
Subscribers: llvm-commits, gchatelet, chandlerc
Differential Revision: https://reviews.llvm.org/D43460
llvm-svn: 326877
The code checks Level == AfterLegalizeDAG which is the fourth and last of the possible DAG combine stages that we have.
There is a Level called AfterLegalVectorOps, but that's the third DAG combine and it doesn't always run.
A function called isAfterLegalVectorOps should imply it returns true in either of the DAG combines that runs after the legalize vector ops stage, but that's not what this function does.
llvm-svn: 326832
In case if -mattr used to modify feature set bits in llvm-mc call
getIsaVersion can fail to identify specific ISA due to test mismatch.
Adding default fallback tests which will always correctly report at
least major version.
Differential Revision: https://reviews.llvm.org/D44163
llvm-svn: 326825
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
One addrspacecast disappeared in clang emitted IR for
block invoke function due to adoption of the new
addr space mapping.
Differential Revision: https://reviews.llvm.org/D43785
llvm-svn: 326806
This patch handling:
Enable parsing of raw encodings of system registers .
Allows UNPREDICTABLE sysregs to be decoded to a raw number in the same way that disasslib does, rather than llvm crashing.
Disassemble msr/mrs with unpredictable sysregs as SoftFail.
Fix regression due to SoftFailing some encodings.
Patch by Chris Ryder
Differential revision:https://reviews.llvm.org/D43374
llvm-svn: 326803
Before I started maintaining the AVR backend, this instruction
never originally used to have an earlyclobber flag.
Some time afterwards (years ago), I must've added it back in, not realising that it
was left out for a reason.
This pseudo instrction exists solely to work around a long standing bug
in the register allocator.
Before this commit, the LDDWRdYQ pseudo was not actually working around
any bug. With the earlyclobber flag removed again, the LDDWRdYQ pseudo
now correctly works around PR13375 again.
llvm-svn: 326774
EAX can turn out to be alive here, when shrink wrapping is done
(which is allowed when using dwarf exceptions, contrary to the
normal case with WinCFI).
This fixes PR36487.
Differential Revision: https://reviews.llvm.org/D43968
llvm-svn: 326764
Up until Power9, the performance profile for rlwinm., rldicl. and andi. looked
more or less equivalent. However with Power9, the rotates are still 2-way
cracked whereas the and-immediate is not.
This patch just ensures that we don't emit record-form rotates when an andi.
is adequate.
As first pointed out by Carrot in https://bugs.llvm.org/show_bug.cgi?id=30833
(this patch is a fix for that PR).
Differential Revision: https://reviews.llvm.org/D43977
llvm-svn: 326736
The error occurs when reading i16 elements (as in the testcase) from a v8i8
with a pattern of <0,2,4,6>. As all the data in the vector is accessed, the
operation is not a VUZP. The patch stops the pattern recognition of VUZP when
EXTRACT_VECTOR_ELT has a different element type than BUILD_VECTOR.
llvm-svn: 326722
Use the whole gammut of constant immediates available to set up a vector.
Instead of using, for example, `mov w0, #0xffff; dup v0.4s, w0`, which
transfers between register files, use the more efficient `movi v0.4s, #-1`
instead. Not limited to just a few values, but any immediate value that can
be encoded by all the variants of `FMOV`, `MOVI`, `MVNI`, thus eliminating
the need to there be patterns to optimize special cases.
Differential revision: https://reviews.llvm.org/D42133
llvm-svn: 326718
These instructions require that the two S registers are adjacent (but not the R
registers), because only the first register is included in the encoding, but we
were not checking this in the assembler.
Differential revision: https://reviews.llvm.org/D44084
llvm-svn: 326696
Almost none of these usages were FP specific. And we had no clear guideliness on when to use hasAVX vs hasFP256.
I might also remove hasInt256 too since its an alias for hasAVX2.
llvm-svn: 326682
rL322525 - mmx zero constant support
rL322553 - mmx i32 zero extended value
rL326497 - mmx i64 general constant handling
Not all constants are folded, we generate some on the GPRs (similar to SSE build vector) where appropriate
llvm-svn: 326673
Krzysztof Parzyszek