Implement shouldCoalesce() to help regalloc avoid running out of GR128
registers.
If a COPY involving a subreg of a GR128 is coalesced, the live range of the
GR128 virtual register will be extended. If this happens where there are
enough phys-reg clobbers present, regalloc will run out of registers (if
there is not a single GR128 allocatable register available).
This patch tries to allow coalescing only when it can prove that this will be
safe by checking the (local) interval in question.
Review: Ulrich Weigand, Quentin Colombet
https://reviews.llvm.org/D37899https://bugs.llvm.org/show_bug.cgi?id=34610
llvm-svn: 314516
Summary:
This commit adds comments on how the AMDPAL OS type overloads the
existing AMDGPU_ calling conventions used by Mesa, and adds a couple of
new ones.
Reviewers: arsenm, nhaehnle, dstuttard
Subscribers: mehdi_amini, kzhuravl, wdng, yaxunl, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D37752
llvm-svn: 314502
Summary:
Added support for scratch (including spilling) for OS type amdpal:
generates code to set up the scratch descriptor if it is needed.
With amdpal, the scratch resource descriptor is loaded from offset 0 of
the global information table. The low 32 bits of the address of the
global information table is passed in s0.
Added amdgpu-git-ptr-high function attribute to hard-wire the high 32
bits of the address of the global information table. If the function
attribute is not specified, or is 0xffffffff, then the backend generates
code to use the high 32 bits of pc.
The documentation for the AMDPAL ABI will be added in a later commit.
Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye
Differential Revision: https://reviews.llvm.org/D37483
llvm-svn: 314501
Summary:
This operating system type represents the AMDGPU PAL runtime, and will
be required by the AMDGPU backend in order to generate correct code for
this runtime.
Currently it generates the same code as not specifying an OS at all.
That will change in future commits.
Patch from Tim Corringham.
Subscribers: arsenm, nhaehnle
Differential Revision: https://reviews.llvm.org/D37380
llvm-svn: 314500
This was intended to be no-functional-change, but it's not - there's a test diff.
So I thought I should stop here and post it as-is to see if this looks like what was expected
based on the discussion in PR34603:
https://bugs.llvm.org/show_bug.cgi?id=34603
Notes:
1. The test improvement occurs because the existing 'LateSimplifyCFG' marker is not carried
through the recursive calls to 'SimplifyCFG()->SimplifyCFGOpt().run()->SimplifyCFG()'.
The parameter isn't passed down, so we pick up the default value from the function signature
after the first level. I assumed that was a bug, so I've passed 'Options' down in all of the
'SimplifyCFG' calls.
2. I split 'LateSimplifyCFG' into 2 bits: ConvertSwitchToLookupTable and KeepCanonicalLoops.
This would theoretically allow us to differentiate the transforms controlled by those params
independently.
3. We could stash the optional AssumptionCache pointer and 'LoopHeaders' pointer in the struct too.
I just stopped here to minimize the diffs.
4. Similarly, I stopped short of messing with the pass manager layer. I have another question that
could wait for the follow-up: why is the new pass manager creating the pass with LateSimplifyCFG
set to true no matter where in the pipeline it's creating SimplifyCFG passes?
// Create an early function pass manager to cleanup the output of the
// frontend.
EarlyFPM.addPass(SimplifyCFGPass());
-->
/// \brief Construct a pass with the default thresholds
/// and switch optimizations.
SimplifyCFGPass::SimplifyCFGPass()
: BonusInstThreshold(UserBonusInstThreshold),
LateSimplifyCFG(true) {} <-- switches get converted to lookup tables and loops may not be in canonical form
If this is unintended, then it's possible that the current behavior of dropping the 'LateSimplifyCFG'
setting via recursion was masking this bug.
Differential Revision: https://reviews.llvm.org/D38138
llvm-svn: 314308
We can have a v_mac with an immediate src0.
We can still fold if it's an inline immediate,
otherwise it already uses the constant bus.
llvm-svn: 313852
These write to the low and high half of the destination
register and leave the other 16-bits unchanged. This is true
for most 16-bit instructions on gfx9, but we don't use that
now.
llvm-svn: 313812
Also add some tests that should be able to use v_mad_mixhi_f16,
but do not yet. This is trickier because we don't really model
the partial update of the register done by 16-bit instructions.
llvm-svn: 313806
Also starts selecting global loads for constant address
in some cases. Some end up selecting to mubuf still, which
requires investigation.
We still get sub-optimal regalloc and extra waitcnts inserted
due to not really tracking the liveness of the separate register
halves.
llvm-svn: 313716
The pre-RA scheduler does load/store clustering, but post-RA
scheduler undoes it. Add mutation to prevent it.
Differential Revision: https://reviews.llvm.org/D38014
llvm-svn: 313670
Because the stack growth direction and addressing is done
in the same direction, modifying SP at the beginning of the
call sequence was incorrect. If we had a stack passed argument,
we would end up skipping that number of bytes before pushing
arguments, leaving unused/inconsistent space.
The callee creates fixed stack objects in its frame, so
the space necessary for these is already logically allocated
in the callee, so we just let the callee increment SP if
it really requires it.
llvm-svn: 313279
Using SplitCSR for the frame register was very broken. Often
the copies in the prolog and epilog were optimized out, in addition
to them being inserted after the true prolog where the FP
was clobbered.
I have a hacky solution which works that continues to use
split CSR, but for now this is simpler and will get to working
programs.
llvm-svn: 313274
MachineScheduler when clustering loads or stores checks if base
pointers point to the same memory. This check is done through
comparison of base registers of two memory instructions. This
works fine when instructions have separate offset operand. If
they require a full calculated pointer such instructions can
never be clustered according to such logic.
Changed shouldClusterMemOps to accept base registers as well and
let it decide what to do about it.
Differential Revision: https://reviews.llvm.org/D37698
llvm-svn: 313208
These two instructions are normally selected, but when the
two address pass converts mac into mad we end up with the
mad where we could have one of these.
Differential Revision: https://reviews.llvm.org/D37389
llvm-svn: 312928
A mrt exp with vm=1 must be in exact (non-WQM) mode, as it also exports
the exec mask as the valid mask to determine which pixels to render.
This commit marks any exp as needing to be in exact mode.
Actually, if there are multiple mrt exps, only one needs to have vm=1,
and only that one needs to be in exact mode. But that is an optimization
for another day.
Differential Revision: https://reviews.llvm.org/D36305
llvm-svn: 312915
We have a lot of operand definition work essentially producing
every valid permutation of operands to workaround builiding
operand lists based on the instruction features. Apparently tablegen
already has a mostly undocumented operator to concat dags which
simplies this.
Convert one simple place to use this. The BUF instruction definitions
have much more complicated logic that can be totally rewritten now.
llvm-svn: 312822
The various scalar bit operations set SCC,
so one is erased or moved it needs to be recomputed.
Not sure why the existing tests don't fail on this.
llvm-svn: 312819
Summary:
Mesa still uses a hack where empty inline assembly is used as a kind of
optimization barrier. This exposed a problem where not enough wait states
were inserted, because the hazard recognizer implicitly assumed that each
inline assembly "instruction" has at least one wait state.
Reviewers: arsenm
Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye
Differential Revision: https://reviews.llvm.org/D37205
llvm-svn: 312635
When packet size equals packet align and is power of 2, transform
__read_pipe* and __write_pipe* to specialized library function.
Differential Revision: https://reviews.llvm.org/D36831
llvm-svn: 312598
- Make SIMemOpInfo a class
- Add accessor methods to SIMemOpInfo
- Move get*Info methods to SIMemOpInfo
Differential Revision: https://reviews.llvm.org/D37395
llvm-svn: 312541
- Rename MemOpInfo -> SIMemOpInfo
- Move SIMemOpInfo class out of SIMemoryLegalizer class
Differential Revision: https://reviews.llvm.org/D37394
llvm-svn: 312540
Summary:
This fixes a bug that was exposed on gfx9 in various
GL45-CTS.shaders.loops.*_iterations.select_iteration_count_fragment tests,
e.g. GL45-CTS.shaders.loops.do_while_uniform_iterations.select_iteration_count_fragment
Reviewers: arsenm
Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D36193
llvm-svn: 312337
build_vector is a more useful canonical form when
pattern matching packed operations, so turn shift
into high element into a build_vector.
Should show no change for now.
llvm-svn: 312282
The majority of the time spent in the pass checking
for the register reads. Rather than searching all of
the defined registers for uses in each instruction,
use a set of defined registers and check the operands
of the instruction.
This process still is algorithmically not great,
but with the additional trick of skipping the analysis
for addresses with one use, this brings one slow
testcase into a reasonable range.
llvm-svn: 312206
These aren't really packed instructions, so the default
op_sel_hi should be 0 since this indicates a conversion.
The operand types are scalar values that behave similar
to an f16 scalar that may be converted to f32.
Doesn't change the default printing for op_sel_hi, just
the parsing.
llvm-svn: 312179
The merge is only possible if the base address register is the
same for the two instructions. If there is only the one use,
there's no point in doing an expensive forward scan checking
for memory interference looking for a merge candidate.
This gives a signficant improvement in one extreme testcase.
The code to do the scan is still algorithmically terrible,
so this is still the slowest pass in that example.
llvm-svn: 312096
If denorms are not flushed we can use max instead of multiplication
by 1. For double that is simply faster, while for float and half
it is shorter, because mul uses constant bus and VOP3.
Differential Revision: https://reviews.llvm.org/D36856
llvm-svn: 312095
Under -cl-fast-relaxed-math we could use native_sqrt, but f64 was
allowed to produce HSAIL's nsqrt instruction. HSAIL is not here
and we stick with non-existing native_sqrt(double) as a result.
Add check for f64 to not return native functions and also remove
handling of f64 case for fold_sqrt.
Differential Revision: https://reviews.llvm.org/D37223
llvm-svn: 311900
Summary:
This is step towards separating the GCN and R600 tablegen'd code.
This is a little awkward for now, because the R600 functions won't have the
MCSubtargetInfo parameter, so we need to have AMDMGPUInstPrinter
delegate to R600InstPrinter, but once the tablegen'd code is split,
we will be able to drop the delegation and use R600InstPrinter directly.
Reviewers: arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D36444
llvm-svn: 311128
This reverts commit r310425, thus reapplying r310335 with a fix for link
issue of the AArch64 unittests on Linux bots when BUILD_SHARED_LIBS is ON.
Original commit message:
[GlobalISel] Remove the GISelAccessor API.
Its sole purpose was to avoid spreading around ifdefs related to
building global-isel. Since r309990, GlobalISel is not optional anymore,
thus, we can get rid of this mechanism all together.
NFC.
----
The fix for the link issue consists in adding the GlobalISel library in
the list of dependencies for the AArch64 unittests. This dependency
comes from the use of AArch64Subtarget that needs to know how
to destruct the GISel related APIs when being detroyed.
Thanks to Bill Seurer and Ahmed Bougacha for helping me reproducing and
understand the problem.
llvm-svn: 310969
The pass does simplifications of well known AMD library calls.
If given -amdgpu-prelink option it works in a pre-link mode which
allows to reference new library functions which will be linked in
later.
In addition it also used to process traditional AMD option
-fuse-native which allows to replace some of the functions with
their fast native implementations from the library.
The necessary glue to pass the prelink option and translate
-fuse-native is to be added to the driver.
Differential Revision: https://reviews.llvm.org/D36436
llvm-svn: 310731
This reverts commit r310115.
It causes a linker failure for the one of the unittests of AArch64 on one
of the linux bot:
http://lab.llvm.org:8011/builders/clang-ppc64le-linux-multistage/builds/3429
: && /home/fedora/gcc/install/gcc-7.1.0/bin/g++ -fPIC
-fvisibility-inlines-hidden -Werror=date-time -std=c++11 -Wall -W
-Wno-unused-parameter -Wwrite-strings -Wcast-qual
-Wno-missing-field-initializers -pedantic -Wno-long-long
-Wno-maybe-uninitialized -Wdelete-non-virtual-dtor -Wno-comment
-ffunction-sections -fdata-sections -O2
-L/home/fedora/gcc/install/gcc-7.1.0/lib64 -Wl,-allow-shlib-undefined
-Wl,-O3 -Wl,--gc-sections
unittests/Target/AArch64/CMakeFiles/AArch64Tests.dir/InstSizes.cpp.o -o
unittests/Target/AArch64/AArch64Tests
lib/libLLVMAArch64CodeGen.so.6.0.0svn lib/libLLVMAArch64Desc.so.6.0.0svn
lib/libLLVMAArch64Info.so.6.0.0svn lib/libLLVMCodeGen.so.6.0.0svn
lib/libLLVMCore.so.6.0.0svn lib/libLLVMMC.so.6.0.0svn
lib/libLLVMMIRParser.so.6.0.0svn lib/libLLVMSelectionDAG.so.6.0.0svn
lib/libLLVMTarget.so.6.0.0svn lib/libLLVMSupport.so.6.0.0svn -lpthread
lib/libgtest_main.so.6.0.0svn lib/libgtest.so.6.0.0svn -lpthread
-Wl,-rpath,/home/buildbots/ppc64le-clang-multistage-test/clang-ppc64le-multistage/stage1/lib
&& :
unittests/Target/AArch64/CMakeFiles/AArch64Tests.dir/InstSizes.cpp.o:(.toc+0x0):
undefined reference to `vtable for llvm::LegalizerInfo'
unittests/Target/AArch64/CMakeFiles/AArch64Tests.dir/InstSizes.cpp.o:(.toc+0x8):
undefined reference to `vtable for llvm::RegisterBankInfo'
The particularity of this bot is that it is built with
BUILD_SHARED_LIBS=ON
However, I was not able to reproduce the problem so far.
Reverting to unblock the bot.
llvm-svn: 310425
Summary:
Now that we've made all the necessary backend changes, we can add a new
intrinsic which exposes the new capabilities to IR producers. Since
llvm.amdgpu.update.dpp is a strict superset of llvm.amdgpu.mov.dpp, we
should deprecate the former. We also add tests for all the functionality
that was added in previous changes, now that we can access it via an IR
construct.
Reviewers: tstellar, arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34718
llvm-svn: 310399
Summary: This refactoring is required in order to split the R600 and GCN tablegen files.
Reviewers: arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, llvm-commits, t-tye
Differential Revision: https://reviews.llvm.org/D36286
llvm-svn: 310336
Summary:
All instructions with the DPP modifier may not write to certain lanes of
the output if bound_ctrl=1 is set or any bits in bank_mask or row_mask
aren't set, so the destination register may be both defined and modified.
The right way to handle this is to add a constraint that the destination
register is the same as one of the inputs. We could tie the destination
to the first source, but that would be too restrictive for some use-cases
where we want the destination to be some other value before the
instruction executes. Instead, add a fake "old" source and tie it to the
destination. Effectively, the "old" source defines what value unwritten
lanes will get. We'll expose this functionality to users with a new
intrinsic later.
Also, we want to use DPP instructions for computing derivatives, which
means we need to set WQM for them. We also need to enable the entire
wavefront when using DPP intrinsics to implement nonuniform subgroup
reductions, since otherwise we'll get incorrect results in some cases.
To accomodate this, add a new operand to all DPP instructions which will
be interpreted by the SI WQM pass. This will be exposed with a new
intrinsic later. We'll also add support for Whole Wavefront Mode later.
I also fixed llvm.amdgcn.mov.dpp to overwrite the source and fixed up
the test. However, I could also keep the old behavior (where lanes that
aren't written are undefined) if people want it.
Reviewers: tstellar, arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34716
llvm-svn: 310283
This hasn't done anything in a long time. This was
running after the the control flow pseudos were expanded,
so this would never find them. The control flow pseudo
expansion was moved to solve the problem this pass was
supposed to solve in the first place, except handling
it earlier also fixes it for fast regalloc which doesn't
use LiveIntervals.
Noticed by checking LCOV reports.
llvm-svn: 310274
Try to avoid mutually exclusive features. Don't use
a real default GPU, and use a fake "generic". The goal
is to make it easier to see which set of features are
incompatible between feature strings.
Most of the test changes are due to random scheduling changes
from not having a default fullspeed model.
llvm-svn: 310258
Its sole purpose was to avoid spreading around ifdefs related to
building global-isel. Since r309990, GlobalISel is not optional anymore,
thus, we can get rid of this mechanism all together.
NFC.
llvm-svn: 310115
Summary:
This intrinsic lets us set inactive lanes to an identity value when
implementing wavefront reductions. In combination with Whole Wavefront
Mode, it lets inactive lanes be skipped over as required by GLSL/Vulkan.
Lowering the intrinsic needs to happen post-RA so that RA knows that the
destination isn't completely overwritten due to the EXEC shenanigans, so
we need another pseudo-instruction to represent the un-lowered
intrinsic.
Reviewers: tstellar, arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34719
llvm-svn: 310088
Summary:
Whole Wavefront Wode (WWM) is similar to WQM, except that all of the
lanes are always enabled, regardless of control flow. This is required
for implementing wavefront reductions in non-uniform control flow, where
we need to use the inactive lanes to propagate intermediate results, so
they need to be enabled. We need to propagate WWM to uses (unless
they're explicitly marked as exact) so that they also propagate
intermediate results correctly. We do the analysis and exec mask munging
during the WQM pass, since there are interactions with WQM for things
that require both WQM and WWM. For simplicity, WWM is entirely
block-local -- blocks are never WWM on entry or exit of a block, and WWM
is not propagated to the block level. This means that computations
involving WWM cannot involve control flow, but we only ever plan to use
WWM for a few limited purposes (none of which involve control flow)
anyways.
Shaders can ask for WWM using the @llvm.amdgcn.wwm intrinsic. There
isn't yet a way to turn WWM off -- that will be added in a future
change.
Finally, it turns out that turning on inactive lanes causes a number of
problems with register allocation. While the best long-term solution
seems like teaching LLVM's register allocator about predication, for now
we need to add some hacks to prevent ourselves from getting into trouble
due to constraints that aren't currently expressed in LLVM. For the gory
details, see the comments at the top of SIFixWWMLiveness.cpp.
Reviewers: arsenm, nhaehnle, tpr
Subscribers: kzhuravl, wdng, mgorny, yaxunl, dstuttard, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D35524
llvm-svn: 310087
Summary:
Right now, the WQM pass conflates two different things when tracking the
Needs of an instruction:
1. Needs can be StateWQM, which is propagated to other instructions, and
means that this instruction (and everything it depends on) must be
calculated in WQM.
2. Needs can be StateExact, which is not propagated to other
instructions, and means that this instruction must not be calculated in
WQM and WQM-ness must not be propagated past this instruction.
This works now because there are only two different states, but in the
future we want to be able to express things like "calculate this in WQM,
but please disable WWM and don't propagate it" (to implement
@llvm.amdgcn.set.inactive). In order to do this, we need to split the
per-instruction Needs field in two: a new Needs field, which can only
contain StateWQM (and in the future, StateWWM) and is propagated to
sources, and a Disables field, which can also contain just StateWQM or
nothing for now.
We keep the per-block tracking the same for now, by translating
Needs/Disables to the old representation with only StateWQM or
StateExact. The other place that needs special handling is when we
emit the state transitions. We could just translate back to the old
representation there as well, which we almost do, but instead of 0 as a
placeholder value for "any state," we explicitly or together all the
states an instruction is allowed to be in. This lets us refactor the
code in preparation for WWM, where we'll need to be able to handle
things like "this instruction must be in Exact or WQM, but not WWM."
Reviewers: arsenm, nhaehnle, tpr
Subscribers: kzhuravl, wdng, yaxunl, dstuttard, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D35523
llvm-svn: 310086
Summary:
Previously, we assumed that certain types of instructions needed WQM in
pixel shaders, particularly DS instructions and image sampling
instructions. This was ok because with OpenGL, the assumption was
correct. But we want to start using DPP instructions for derivatives as
well as other things, so the assumption that we can infer whether to use
WQM based on the instruction won't continue to hold. This intrinsic lets
frontends like Mesa indicate what things need WQM based on their
knowledge of the API, rather than second-guessing them in the backend.
We need to keep around the old method of enabling WQM, but eventually we
should remove it once Mesa catches up. For now, this will let us use DPP
instructions for computing derivatives correctly.
Reviewers: arsenm, tpr, nhaehnle
Subscribers: kzhuravl, wdng, yaxunl, dstuttard, llvm-commits, t-tye
Differential Revision: https://reviews.llvm.org/D35167
llvm-svn: 310085
Error was:
field of type 'llvm::ArgDescriptor' has private default constructor
const AMDGPUFunctionArgInfo AMDGPUArgumentUsageInfo::ExternFunctionInfo{};
^
llvm-svn: 310048
In case if SI_KILL is in between of the SI_IF and SI_END_CF we need
to preserve the bits actually flipped by if rather then restoring
the original mask.
Differential Revision: https://reviews.llvm.org/D36299
llvm-svn: 310031
Summary:
Following the docs, we need at least 5 wait states between an EXEC write
and an instruction that uses DPP.
Reviewers: tstellar, arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D34849
llvm-svn: 310013
With this change, the GlobalISel library gets always built. In
particular, this is not possible to opt GlobalISel out of the build
using the LLVM_BUILD_GLOBAL_ISEL variable any more.
llvm-svn: 309990
Summary:
If a PHI has at lease one VGPR operand, we have to fix the PHI
in SIFixSGPRCopies.
Reviewer:
Matt
Differential Revision:
http://reviews.llvm.org/D34727
llvm-svn: 309959
IMHO it is an antipattern to have a enum value that is Default.
At any given piece of code it is not clear if we have to handle
Default or if has already been mapped to a concrete value. In this
case in particular, only the target can do the mapping and it is nice
to make sure it is always done.
This deletes the two default enum values of CodeModel and uses an
explicit Optional<CodeModel> when it is possible that it is
unspecified.
llvm-svn: 309911
If there are no calls, this is a faster path than
searching the entire program for calls.
This was supposed to be left in r309781.
Fixes unused variable warning.
llvm-svn: 309832
This was failing on out of bounds access to the extra operands
on the s_swappc_b64 beyond those in the instruction definition.
This was working, but somehow regressed within the past few weeks,
although I don't see any obvious commit.
llvm-svn: 309782
Previous change "Turn s_and_saveexec_b64 into s_and_b64 if
result is unused" introduced asan use-after-poison error.
Instruction was analyzed after eraseFromParent() calls.
Move analysys higher than erase.
llvm-svn: 309779
With SI_END_CF elimination for some nested control flow we can now
eliminate saved exec register completely by turning a saveexec version
of instruction into just a logical instruction.
Differential Revision: https://reviews.llvm.org/D36007
llvm-svn: 309766
Add a pass to remove redundant S_OR_B64 instructions enabling lanes in
the exec. If two SI_END_CF (lowered as S_OR_B64) come together without any
vector instructions between them we can only keep outer SI_END_CF, given
that CFG is structured and exec bits of the outer end statement are always
not less than exec bit of the inner one.
This needs to be done before the RA to eliminate saved exec bits registers
but after register coalescer to have no vector registers copies in between
of different end cf statements.
Differential Revision: https://reviews.llvm.org/D35967
llvm-svn: 309762
The src0 register must match src1 or src2, but if these
were undefined they could end up using different implicit_defed
virtual registers. Force these to use one undef vreg or pick the
defined other register.
Also fixes producing invalid nodes without the right number of
inputs when src2 is undef.
llvm-svn: 309743
Includes a hack to fix the type selected for
the GlobalAddress of the function, which will be
fixed by changing the default datalayout to use
generic pointers for 0.
llvm-svn: 309732
Summary:
Since r293359, most dump() function are only defined when
`!defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)` holds. print() functions
only used by dump() functions are now unused in release builds,
generating lots of warnings. This patch only defines some print()
functions if they are used.
Reviewers: MatzeB
Reviewed By: MatzeB
Subscribers: arsenm, mzolotukhin, nhaehnle, llvm-commits
Differential Revision: https://reviews.llvm.org/D35949
llvm-svn: 309553
Also refine the flat check to respect flat-for-global feature,
and constant fallback should check global handling, not
specifically MUBUF.
llvm-svn: 309471
This allows handling of a lot more of the interesting
cases in Blender. Most of the large functions unlikely
to be inlined have this pattern.
This is a special case for what clang emits for OpenCL 3
element vectors. Annoyingly, these are emitted as
<3 x elt>* pointers, but accessed as <4 x elt>* operations.
This also needs to handle cases where a struct containing
a single vector is used.
llvm-svn: 309419
It is better to return arguments directly in registers
if we are making a call rather than introducing expensive
stack usage. In one of sample compile from one of
Blender's many kernel variants, this fires on about
~20 different functions. Future improvements may be to
recognize simple cases where the pointer is indexing a small
array. This also fails when the store to the out argument
is in a separate block from the return, which happens in
a few of the Blender functions. This should also probably
be using MemorySSA which might help with that.
I'm not sure this is correct as a FunctionPass, but
MemoryDependenceAnalysis seems to not work with
a ModulePass.
I'm also not sure where it should run.I think it should
run before DeadArgumentElimination, so maybe either
EP_CGSCCOptimizerLate or EP_ScalarOptimizerLate.
llvm-svn: 309416
We need to pass something to functions for this to work.
It isn't derivable just from the kernarg segment pointer
because the implicit arguments are placed after the
kernel arguments.
Also fixes missing test for the intrinsic.
llvm-svn: 309398
Currently SI_IF results in a s_and_saveexec_b64 followed by s_xor_b64.
The xor is used to extract only the changed bits. In case of a simple
if region where the only use of that value is in the SI_END_CF to
restore the old exec mask, we can omit the xor and perform an or of
the exec mask with the original exec value saved by the
s_and_saveexec_b64.
Differential Revision: https://reviews.llvm.org/D35861
llvm-svn: 309185
Changing mask argument type from const SmallVectorImpl<int>& to
ArrayRef<int>.
This came up in D35700 where a mask is received as an ArrayRef<int> and
we want to pass it to TargetLowering::isShuffleMaskLegal().
Also saves a few lines of code.
llvm-svn: 309085
Fixes verifier errors in some call tests.
Not sure why we haven't run into this before.
Test split into separate patch for once
call support is committed.
llvm-svn: 308774
This patch makes LSR generate better code for SystemZ in the cases of memory
intrinsics, Load->Store pairs or comparison of immediate with memory.
In order to achieve this, the following common code changes were made:
* New TTI hook: LSRWithInstrQueries(), which defaults to false. Controls if
LSR should do instruction-based addressing evaluations by calling
isLegalAddressingMode() with the Instruction pointers.
* In LoopStrengthReduce: handle address operands of memset, memmove and memcpy
as address uses, and call isFoldableMemAccessOffset() for any LSRUse::Address,
not just loads or stores.
SystemZ changes:
* isLSRCostLess() implemented with Insns first, and without ImmCost.
* New function supportedAddressingMode() that is a helper for TTI methods
looking at Instructions passed via pointers.
Review: Ulrich Weigand, Quentin Colombet
https://reviews.llvm.org/D35262https://reviews.llvm.org/D35049
llvm-svn: 308729
Move the _RTN to the end of the name. It reads
better if the other addressing mode components
line up with the non-RTN version. It is also
more convenient to define saddr variants of
FLAT atomics to have the RTN last, and it is
good to have a consistent naming scheme.
llvm-svn: 308674
On AMDGPU SGPR spills are really spilled to another register.
The spiller creates the spills to new frame index objects,
which is used as a placeholder.
This will eventually be replaced with a reference to a position
in a VGPR to write to and the frame index deleted. It is
most likely not a real stack location that can be shared
with another stack object.
This is a problem when StackSlotColoring decides it should
combine a frame index used for a normal VGPR spill with
a real stack location and a frame index used for an SGPR.
Add an ID field so that StackSlotColoring has a way
of knowing the different frame index types are
incompatible.
llvm-svn: 308673
The soffset field needs to be be set to 0x7f to disable it,
not 0. 0 is interpreted as an SGPR offset.
This should be enough to get basic usage of the global instructions
working. Technically it is possible to use an SGPR_32 offset,
but I'm not sure if it's correct with 64-bit pointers, but
that is not handled now. This should also be cleaned up
to be more similar to how different MUBUF modes are handled,
and to have InstrMappings between the different types.
llvm-svn: 308583
As an approximation of the existing handling to avoid
regressions. Fixes using too many registers with calls
on subtargets with the SGPR allocation bug.
llvm-svn: 308326
Introduce pseudo-registers for registers needed for stack
access, which are replaced during finalizeLowering.
Note these pseudo-registers are currently only used for the
used register location, and not for determining their
input argument register.
This is better because it avoids the need to try to predict
whether a call will be emitted from the IR, and also
detects stack objects introduced by legalization.
Test changes are from the HasStackObjects check being more
accurate since stack objects introduced during legalization
are now known.
llvm-svn: 308325
Summary:
When an immediate is folded by constant folding, we re-scan the entire
use list for two reasons:
1. The constant folding may have created a new use of the same reg.
2. The constant folding may have removed an additional use in the list
we're currently traversing (e.g., constant folding an S_ADD_I32 c, c).
However, this could previously lead to a crash when an unrelated use was
added twice into the FoldList. Since we re-scan the whole list anyway, we
might as well just clear the FoldList again before we do so.
Using a MIR test to show this because real code seems to trigger the issue
only in connection with some really subtle control flow structures.
Fixes GL45-CTS.shading_language_420pack.binding_images on gfx9.
Reviewers: arsenm
Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye
Differential Revision: https://reviews.llvm.org/D35416
llvm-svn: 308314
This wasn't necessary before since they are always enabled
for kernels, but this is necessary if they need to be
forwarded to a callable function.
llvm-svn: 308226
Summary:
Previously, CodeGen checked first src operand type to determine if omod is supported by instruction. This isn't correct for some instructions: e.g. V_CMP_EQ_F32 has floating-point src operands but desn't support omod.
Changed .td files to check if dst operand instead of src operand.
Reviewers: arsenm, vpykhtin
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D35350
llvm-svn: 308179
The type needs to be casted back to the original argument type.
Fixes an assert that for some reason is only run when
using -debug.
Includes an additional combine to avoid test regressions
from having conversions mixed with multiple Assert[SZ]ext
nodes. On subtargets where i16 is legal, this was producing an i32
register with an i16 AssertZExt, truncated to i16 with another i8
AssertZExt.
t2: i32,ch = CopyFromReg t0, Register:i32 %vreg0
t3: i16 = truncate t2
t5: i16 = AssertZext t3, ValueType:ch:i8
t6: i8 = truncate t5
t7: i32 = zero_extend t6
llvm-svn: 308082
In moveToVALU(), move to vector ALU is performed, all instrs in
the use chain will be visited. We do not want the same node to be
pushed to the visit worklist more than once.
Differential Revision: https://reviews.llvm.org/D34726
llvm-svn: 308039
Since GFX9 supports denorm modes for v_min_f32/v_max_f32 that
is possible to further optimize fcanonicalize and remove it
if applied to min/max given their operands are known not to be
an sNaN or that sNaNs are not supported.
Additionally we can remove fcanonicalize if denorms are supported
for the VT and we know that its argument is never a NaN.
Differential Revision: https://reviews.llvm.org/D35335
llvm-svn: 307976
We are using multiplication by 1.0 to flush denormals and quiet sNaNs.
That is possible to omit this multiplication if source of the
fcanonicalize instruction is known to be flushed/quieted, i.e.
if it comes from another instruction known to do the normalization
and we are using IEEE mode to quiet sNaNs.
Differential Revision: https://reviews.llvm.org/D35218
llvm-svn: 307848
The issue is not if the value is pcrel. It is whether we have a
relocation or not.
If we have a relocation, the static linker will select the upper
bits. If we don't have a relocation, we have to do it.
llvm-svn: 307730
An instruction that has an immediate operand can't reach
this point. This is only called for a freshly shrunk instruction,
which prevously couldn't have had a literal constant operand.
This was also not conservative enough since it woudl also have
had to filter other constant-like inputs like frame indexes.
llvm-svn: 307574
Adds loop expansions for known-size and unknown-sized memcpy calls, allowing the
target to provide the operand types through TTI callbacks. The default values
for the TTI callbacks use int8 operand types and matches the existing behaviour
if they aren't overridden by the target.
Differential revision: https://reviews.llvm.org/D32536
llvm-svn: 307346
Regardless of relaxation options such as -cl-fast-relaxed-math
we are producing rather long code for fdiv via amdgcn_fdiv_fast
intrinsic. This intrinsic is used to replace fdiv with 2.5ulp
metadata and does not handle denormals, thus believed to be fast.
An fdiv instruction can also have fast math flag either by itself
or together with fpmath metadata. Clang used with a relaxation flag
always produces both metadata and fast flag:
%div = fdiv fast float %v, %0, !fpmath !12!12 = !{float 2.500000e+00}
Current implementation ignores fast flag and favors metadata. An
instruction with just fast flag would be lowered to a fastest rcp +
mul, but that never happen on practice because of described mutual
clang and BE behavior.
This change allows an "fdiv fast" to be always lowered as rcp + mul.
Differential Revision: https://reviews.llvm.org/D34844
llvm-svn: 307308
Going through the Constant methods requires redetermining that the Constant is a ConstantInt and then calling isZero/isOne/isMinusOne.
llvm-svn: 307292
Depending on the compare code that can be either an argument of
sext or negate of it. This helps to avoid v_cndmask_b64 instruction
for sext. A reversed value can be further simplified and folded into
its parent comparison if possible.
Differential Revision: https://reviews.llvm.org/D34545
llvm-svn: 306446
Also factored out function to check if a boolean is an already
deserialized value which does not require v_cndmask_b32 to be
loaded. Added binary logical operators to its check.
Differential Revision: https://reviews.llvm.org/D34500
llvm-svn: 306439
Summary:
1. Instruction V_CVT_U32_F32 allow omod operand (see SIInstrInfo.td:1435). In fact this operand shouldn't be allowed here. This fix checks if SDWA pseudo instruction has OMod operand and then copy it.
2. There were several problems with support of VOPC instructions in SDWA peephole pass.
Reviewers: tstellar, arsenm, vpykhtin, airlied, kzhuravl
Subscribers: wdng, nhaehnle, yaxunl, dstuttard, tpr, sarnex, t-tye
Differential Revision: https://reviews.llvm.org/D34626
llvm-svn: 306413
Summary:
With scalar stores, M0 is clobbered and therefore marked as implicitly
defined. However, it is also dead.
This fixes an assertion when the Greedy Register Allocator decides to
optimize a spill/restore pair away again (via tryHintsRecoloring).
Reviewers: arsenm
Subscribers: qcolombet, kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D33319
llvm-svn: 306375
This should not be treated as a different version of
private_segment_buffer. These are distinct things with
different uses and register classes, and requires the
function argument info to have more context about the
function's type and environment.
Also add missing test coverage for the intrinsic, and
emit an error for HSA. This also encovers that the intrinsic
is broken unless there happen to be stack objects.
llvm-svn: 306264
The intention of processFixupValue is not to redefine the semantics of
MCExpr. It is odd enough that a expression lowers to a PCRel MCExpr or
not depending on what it looks like. At least it is a local hack now.
I left a fix for anyone trying to figure out what producers should be
producing a different expression.
llvm-svn: 306200
processFixupValue is called on every relaxation iteration. applyFixup
is only called once at the very end. applyFixup is then the correct
place to do last minute changes and value checks.
While here, do proper range checks again for fixup_arm_thumb_bl. We
used to do it, but dropped because of thumb2. We now do it again, but
use the thumb2 range.
llvm-svn: 306177
Intrinsic already existed for llvm.SI.tbuffer.store
Needed tbuffer.load and also re-implementing the intrinsic as llvm.amdgcn.tbuffer.*
Added CodeGen tests for the 2 new variants added.
Left the original llvm.SI.tbuffer.store implementation to avoid issues with existing code
Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, tony-tye, tpr
Differential Revision: https://reviews.llvm.org/D30687
llvm-svn: 306031
Summary:
Despite that this instructions are listed in VOP2, they are treated as VOP3 in specs. They should not support SDWA.
There are no real instructions for them, but there are pseudo instructions.
Reviewers: arsenm, vpykhtin, cfang
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34403
llvm-svn: 305999
Summary:
Added support based on merged SDWA pseudo instructions. Now peephole allow one scalar operand, omod and clamp modifiers.
Added several subtarget features for GFX9 SDWA.
This diff also contains changes from D34026.
Depends D34026
Reviewers: vpykhtin, rampitec, arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D34241
llvm-svn: 305986
If one of the arguments of adde/sube is zero we can fold another
add/sub into it.
Differential Revision: https://reviews.llvm.org/D34374
llvm-svn: 305964
This simplification allows to avoid generating v_cndmask_b32
to serialize condition code between compare and use.
Differential Revision: https://reviews.llvm.org/D34300
llvm-svn: 305962
Summary: Previously there were two separate pseudo instruction for SDWA on VI and on GFX9. Created one pseudo instruction that is union of both of them. Added verifier to check that operands conform either VI or GFX9.
Reviewers: dp, arsenm, vpykhtin
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, artem.tamazov
Differential Revision: https://reviews.llvm.org/D34026
llvm-svn: 305886
If there is an immediate operand we shall not shrink V_SUBB_U32
and V_ADDC_U32, it does not fit e32 encoding.
Differential Revison: https://reviews.llvm.org/D34291
llvm-svn: 305840
Before it was possible to partially fold use instructions
before the defs. After the xor is folded into a copy, the same
mov can end up in the fold list twice, so on the second attempt
it will fail expecting to see a register to fold.
llvm-svn: 305821
The offset may not be an inline immediate, so this needs
to be materialized into a register. The post-RA run of
SIShrinkInstructions is able to fold it later if it can.
llvm-svn: 305761
It adds it for the target after inlining but before SROA where
we can get most out of it.
Differential Revision: https://reviews.llvm.org/D34366
llvm-svn: 305759
Summary: The method TargetTransformInfo::getRegisterBitWidth() is declared const, but the type erasing implementation classes (TargetTransformInfo::Concept & TargetTransformInfo::Model) that were introduced by Chandler in https://reviews.llvm.org/D7293 do not have the method declared const. This is an NFC to tidy up the const consistency between TTI and its implementation.
Reviewers: chandlerc, rnk, reames
Reviewed By: reames
Subscribers: reames, jfb, arsenm, dschuff, nemanjai, nhaehnle, javed.absar, sbc100, jgravelle-google, llvm-commits
Differential Revision: https://reviews.llvm.org/D33903
llvm-svn: 305189
Summary:
Alloca promotion pass not dealing with non-canonical input
Added some additional checks so the pass simply backs-off forms it can't deal with (non-canonical)
Also added some test cases in non-canonical form to check that it no longer crashes
Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D31710
llvm-svn: 305079
The V_MQSAD_PK_U16_U8, V_QSAD_PK_U16_U8, and V_MQSAD_U32_U8 take more than 1 pass in hardware. For these three instructions, the destination registers must be different than all sources, so that the first pass does not overwrite sources for the following passes.
Differential Revision: https://reviews.llvm.org/D33783
llvm-svn: 304998
This creates a new library called BinaryFormat that has all of
the headers from llvm/Support containing structure and layout
definitions for various types of binary formats like dwarf, coff,
elf, etc as well as the code for identifying a file from its
magic.
Differential Revision: https://reviews.llvm.org/D33843
llvm-svn: 304864
I did this a long time ago with a janky python script, but now
clang-format has built-in support for this. I fed clang-format every
line with a #include and let it re-sort things according to the precise
LLVM rules for include ordering baked into clang-format these days.
I've reverted a number of files where the results of sorting includes
isn't healthy. Either places where we have legacy code relying on
particular include ordering (where possible, I'll fix these separately)
or where we have particular formatting around #include lines that
I didn't want to disturb in this patch.
This patch is *entirely* mechanical. If you get merge conflicts or
anything, just ignore the changes in this patch and run clang-format
over your #include lines in the files.
Sorry for any noise here, but it is important to keep these things
stable. I was seeing an increasing number of patches with irrelevant
re-ordering of #include lines because clang-format was used. This patch
at least isolates that churn, makes it easy to skip when resolving
conflicts, and gets us to a clean baseline (again).
llvm-svn: 304787
Fixes bug #33302. Pass did not account that Src1 of max instruction
can be an immediate.
Differential Revision: https://reviews.llvm.org/D33884
llvm-svn: 304696
Remove dependency of SDWA pass on SIShrinkInstructions.
The goal is to move SDWA even higher in the stack to avoid second run
of MachineLICM, MachineCSE and SIFoldOperands.
Also added handling to preserve original src modifiers.
Differential Revision: https://reviews.llvm.org/D33860
llvm-svn: 304665
Summary:
These are mostly legal, but will probably need special lowering for some
cases.
Reviewers: arsenm
Reviewed By: arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, rovka, kristof.beyls, igorb, dstuttard, tpr, llvm-commits, t-tye
Differential Revision: https://reviews.llvm.org/D33791
llvm-svn: 304628
SIFoldOperands can commute operands even if no folding was done.
This change is to preserve IR is no folding was done.
Differential Revision: https://reviews.llvm.org/D33802
llvm-svn: 304625
-enable-si-insert-waitcnts=1 becomes the default
-enable-si-insert-waitcnts=0 to use old pass
Differential Revision: https://reviews.llvm.org/D33730
llvm-svn: 304551
This adds a callback to the LLVMTargetMachine that lets target indicate
that they do not pass the machine verifier checks in all cases yet.
This is intended to be a temporary measure while the targets are fixed
allowing us to enable the machine verifier by default with
EXPENSIVE_CHECKS enabled!
Differential Revision: https://reviews.llvm.org/D33696
llvm-svn: 304320
- new waitcnt pass remains off by default; -enable-si-insert-waitcnts=1 to enable it
- fix handling of PERMUTE ops
- fix insertion of waitcnt instrs at function begin/end ( port of analogous code that was added to old waitcnt pass )
- add new test
Differential Revision: https://reviews.llvm.org/D33114
llvm-svn: 304311
TargetPassConfig is not useful for targets that do not use the CodeGen
library, so we may just as well store a pointer to an
LLVMTargetMachine instead of just to a TargetMachine.
While at it, also change the constructor to take a reference instead of a
pointer as the TM must not be nullptr.
llvm-svn: 304247
An encoding does not allow to use SDWA in an instruction with
scalar operands, either literals or SGPRs. That is however possible
to copy these operands into a VGPR first.
Several copies of the value are produced if multiple SDWA conversions
were done. To cleanup MachineLICM (to hoist copies out of loops),
MachineCSE (to remove duplicate copies) and SIFoldOperands (to replace
SGPR to VGPR copy with immediate copy right to the VGPR) runs are added
after the SDWA pass.
Differential Revision: https://reviews.llvm.org/D33583
llvm-svn: 304219
[AMDGPU] add intrinsic for s_getpc
Summary: The s_getpc instruction is exposed as intrinsic llvm.amdgcn.s.getpc.
Patch by Tim Corringham
llvm-svn: 304031
Various address spaces on the SI and R600 subtargets have stricter
limits on memory access size that other address spaces. Use
canMergeStoresTo predicate to prevent the DAGCombiner from creating
these stores as they will be split up during legalization.
llvm-svn: 303767
This reverts commit e065977c4b5f68ab845400b256f6a3822b1325fa.
It doesn't work. S_LOAD_DWORD_IMM_ci and friends aren't selected by any of
the patterns, so it was putting 32-bit literals into the 8-bit field.
llvm-svn: 303754
This fixes 17 of the 41 -verify-machineinstrs test failures identified in PR33045
Differential Revision: https://reviews.llvm.org/D33451
llvm-svn: 303691
Summary:
Promoting Alloca to Vector and Promoting Alloca to LDS are two independent handling of Alloca and should not affect each other.
As a result, we should not give up promoting to vector if there is not enough LDS. This patch factors out the local memory usage
related checking out and replace it after the calling convention checking.
Reviewer:
arsenm
Differential Revision:
http://reviews.llvm.org/D33139
llvm-svn: 303684
Perform DAG combine:
and (srl x, c), mask => shl (bfe x, nb + c, mask >> nb), nb
Where nb is a number of trailing zeroes in mask.
It replaces two instructions with two and BFE is generally a more
expensive one. However this is only done if we are selecting a byte
or word at an aligned boundary which results in a proper SDWA
operand pattern. It is only done if SDWA is supported.
TODO: improve SDWA pass to actually convert this pattern. It is not
done now because we have an immediate in the instruction, which has
be moved into a VGPR.
Differential Revision: https://reviews.llvm.org/D33455
llvm-svn: 303681
This is just a cleanup. Also, it adds checking that ByteCount is aligned to 4.
Reviewers: arsenm, nhaehnle, tstellarAMD
Subscribers: kzhuravl, wdng, yaxunl, tony-tye
Differential Revision: https://reviews.llvm.org/D28994
llvm-svn: 303658
shl (or|add x, c2), c1 => or|add (shl x, c1), (c2 << c1)
This allows to fold a constant into an address in some cases as
well as to eliminate second shift if the expression is used as
an address and second shift is a result of a GEP.
Differential Revision: https://reviews.llvm.org/D33432
llvm-svn: 303641
Summary:
Added separate pseudo and real instruction for GFX9 SDWA instructions.
Currently supports only in assembler.
Depends D32493
Reviewers: vpykhtin, artem.tamazov
Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D33132
llvm-svn: 303620
Turn expensive 64 bit shift into 32 bit if shift does not overflow int:
shl (ext x) => zext (shl x)
Differential Revision: https://reviews.llvm.org/D33367
llvm-svn: 303569
This provides a new way to access the TargetMachine through
TargetPassConfig, as a dependency.
The patterns replaced here are:
* Passes handling a null TargetMachine call
`getAnalysisIfAvailable<TargetPassConfig>`.
* Passes not handling a null TargetMachine
`addRequired<TargetPassConfig>` and call
`getAnalysis<TargetPassConfig>`.
* MachineFunctionPasses now use MF.getTarget().
* Remove all the TargetMachine constructors.
* Remove INITIALIZE_TM_PASS.
This fixes a crash when running `llc -start-before prologepilog`.
PEI needs StackProtector, which gets constructed without a TargetMachine
by the pass manager. The StackProtector pass doesn't handle the case
where there is no TargetMachine, so it segfaults.
Related to PR30324.
Differential Revision: https://reviews.llvm.org/D33222
llvm-svn: 303360
Summary:
There should be no intesection between SDWA operands and potential MIs. E.g.:
```
v_and_b32 v0, 0xff, v1 -> src:v1 sel:BYTE_0
v_and_b32 v2, 0xff, v0 -> src:v0 sel:BYTE_0
v_add_u32 v3, v4, v2
```
In that example it is possible that we would fold 2nd instruction into 3rd (v_add_u32_sdwa) and then try to fold 1st instruction into 2nd (that was already destroyed). So if SDWAOperand is also a potential MI then do not apply it.
Reviewers: vpykhtin, arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D32804
llvm-svn: 303347
Partially implement callee-side for arguments and return values.
byval doesn't work properly, and most likely sret or other on-stack
return values most as well.
llvm-svn: 303308
In order for an arbitrary callee to access an object
in a caller's stack frame, the 32-bit offset used as
the private pointer needs to be relative to the kernel's
scratch wave offset register.
Convert to this by finding the difference from the current
stack frame and scaling by the wavefront size.
llvm-svn: 303303
Check the MachinePointerInfo for whether the access is
supposed to be relative to the stack pointer.
No tests because this is used in later commits implementing
calls.
llvm-svn: 303301
Avoids instructions to pack a vector when the source is really
a scalar being broadcast.
Also be smarter and look for per-component fneg.
Doesn't yet handle scalar from upper half of register
or other swizzles.
llvm-svn: 303291
Using LIS can be quite expensive, so caching of calculated region
live-ins and pressure is implemented. It does two things:
1. Caches the info for the second stage when we schedule with
decreased target occupancy.
2. Tracks the basic block from top to bottom thus eliminating the
need to scan whole register file liveness at every region split
in the middle of the block.
The scheduling is now done in 3 stages instead of two, with the first
one being really a no-op and only used to collect scheduling regions
as sent by the scheduler driver.
There is no functional change to the current behavior, only compilation
speed is affected. In general computeBlockPressure() could be simplified
if we switch to backward RP tracker, because scheduler sends regions
within a block starting from the last upward. We could use a natural
order of upward tracker to seamlessly change between regions of the same
block, since live reg set of a previous tracked region would become a
live-out of the next region. That however requires fixing upward tracker
to properly account defs and uses of the same instruction as both are
contributing to the current pressure. When we converge on the produced
pressure we should be able to switch between them back and forth. In
addition, backward tracker is less expensive as it uses LIS in recede
less often than forward uses it in advance.
At the moment the worst known case compilation time has improved from 26
minutes to 8.5.
Differential Revision: https://reviews.llvm.org/D33117
llvm-svn: 303184
This factors register pressure estimation mechanism from the
GCNSchedStrategy into the forward tracker to unify interface
with other strategies and expose it to other interested phases.
Differential Revision: https://reviews.llvm.org/D33105
llvm-svn: 303179
Summary:
We should not change volatile loads/stores in promoting alloca to vector.
Reviewers:
arsenm
Differential Revision:
http://reviews.llvm.org/D33107
llvm-svn: 302943
This patch adds min/max population count, leading/trailing zero/one bit counting methods.
The min methods return answers based on bits that are known without considering unknown bits. The max methods give answers taking into account the largest count that unknown bits could give.
Differential Revision: https://reviews.llvm.org/D32931
llvm-svn: 302925
We don't use it and it was removed in gfx9, and the encoding
bit repurposed.
Additionally actually using it requires changing the output register
class, which wasn't done anyway.
llvm-svn: 302814
Earlier fix D32572 introduced a bug where live-ins were calculated
for basic block instead of scheduling region. This change fixes it.
Differential Revision: https://reviews.llvm.org/D33086
llvm-svn: 302812
This is a step toward having statically allocated instruciton mapping.
We are going to tablegen them eventually, so let us reflect that in
the API.
NFC.
llvm-svn: 302316
This adds routines for reseting KnownBits to unknown, making the value all zeros or all ones. It also adds methods for querying if the value is zero, all ones or unknown.
Differential Revision: https://reviews.llvm.org/D32637
llvm-svn: 302262
This patch replaces the separate APInts for KnownZero/KnownOne with a single KnownBits struct. This is similar to what was done to ValueTracking's version recently.
This is largely a mechanical transformation from KnownZero to Known.Zero.
Differential Revision: https://reviews.llvm.org/D32569
llvm-svn: 301620
Summary of changes:
- corrected vmcnt, expcnt, lgkmcnt helpers to checks their argument for truncation;
- added saturated versions of these helpers.
See bug 32711 for details: https://bugs.llvm.org//show_bug.cgi?id=32711
Reviewers: artem.tamazov, vpykhtin
Differential Revision: https://reviews.llvm.org/D32546
llvm-svn: 301439
Commits were:
"Use WeakVH instead of WeakTrackingVH in AliasSetTracker's UnkownInsts"
"Add a new WeakVH value handle; NFC"
"Rename WeakVH to WeakTrackingVH; NFC"
The changes assumed pointers are 8 byte aligned on all architectures.
llvm-svn: 301429
Summary:
I plan to use WeakVH to mean "nulls itself out on deletion, but does
not track RAUW" in a subsequent commit.
Reviewers: dblaikie, davide
Reviewed By: davide
Subscribers: arsenm, mehdi_amini, mcrosier, mzolotukhin, jfb, llvm-commits, nhaehnle
Differential Revision: https://reviews.llvm.org/D32266
llvm-svn: 301424
Rely on MachineRegisterInfo's knowledge of used physical
registers.
Move flat_scratch initialization earlier, so the uses are visible
when making these decisions.
This will make it easier to add another reserved register
at the end for the stack pointer rather than handling another
special case.
llvm-svn: 301254
In call sequence setups, there may not be a frame index base
and the pointer is a constant offset from the frame
pointer / scratch wave offset register.
llvm-svn: 301230
Merges equivalent initializations of M0 and hoists them into a common
dominator block. Technically the same code can be used with any
register, physical or virtual.
Differential Revision: https://reviews.llvm.org/D32279
llvm-svn: 301228
1. RegisterClass::getSize() is split into two functions:
- TargetRegisterInfo::getRegSizeInBits(const TargetRegisterClass &RC) const;
- TargetRegisterInfo::getSpillSize(const TargetRegisterClass &RC) const;
2. RegisterClass::getAlignment() is replaced by:
- TargetRegisterInfo::getSpillAlignment(const TargetRegisterClass &RC) const;
This will allow making those values depend on subtarget features in the
future.
Differential Revision: https://reviews.llvm.org/D31783
llvm-svn: 301221
Currently the operand type for ATOMIC_FENCE assumes value type of a pointer in address space 0.
This is fine for most targets. However for amdgcn target, the size of pointer in address space 0
depends on triple environment. For amdgiz environment, it is 64 bit but for other environment it is
32 bit. On the other hand, amdgcn target expects 32 bit fence operands independent of the target
triple environment. Therefore a hook is need in target lowering for getting the fence operand type.
This patch has no effect on targets other than amdgcn.
Differential Revision: https://reviews.llvm.org/D32186
llvm-svn: 301215
Fixes traps in any block besides the entry block,
and fixes depending on a live-in physical register
by using a virtual register copy.
Also happens to stop emitting a nop in the case
debug trap is not supported.
llvm-svn: 301206
Summary:
Fix a compiler bug when the lane select happens to end up in a VGPR.
Clarify the semantic of the corresponding intrinsic to be that of
the corresponding GLSL: the lane select must be uniform across a
wave front, otherwise results are undefined.
Reviewers: arsenm
Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D32343
llvm-svn: 301197
SI_MASKED_UNREACHABLE does not have machine instruction encoding.
It needs special handling in AMDGPUAsmPrinter::EmitInstruction like some
other pseudo instructions.
This patch fixes compilation failure of RadeonRays.
Differential Revision: https://reviews.llvm.org/D32364
llvm-svn: 301025
immediate operands.
This commit adds an AArch64 dag-combine that optimizes code generation
for logical instructions taking immediate operands. The optimization
uses demanded bits to change a logical instruction's immediate operand
so that the immediate can be folded into the immediate field of the
instruction.
This recommits r300932 and r300930, which was causing dag-combine to
loop forever. The problem was that optimizeLogicalImm was returning
true even when there was no change to the immediate node (which happened
when the immediate was all zeros or ones), which caused dag-combine to
push and pop the same node to the work list over and over again without
making any progress.
This commit fixes the bug by returning false early in optimizeLogicalImm
if the immediate is all zeros or ones. Also, it changes the code to
compare the immediate with 0 or Mask rather than calling
countPopulation.
rdar://problem/18231627
Differential Revision: https://reviews.llvm.org/D5591
llvm-svn: 301019
It seems that r300930 was creating an infinite loop in dag-combine when
compling the following file:
MultiSource/Benchmarks/MiBench/consumer-typeset/z21.c
llvm-svn: 300940
immediate operands.
This commit adds an AArch64 dag-combine that optimizes code generation
for logical instructions taking immediate operands. The optimization
uses demanded bits to change a logical instruction's immediate operand
so that the immediate can be folded into the immediate field of the
instruction.
This recommits r300913, which broke bots because I didn't fix a call to
ShrinkDemandedConstant in SIISelLowering.cpp after changing the APIs of
TargetLoweringOpt and TargetLowering.
rdar://problem/18231627
Differential Revision: https://reviews.llvm.org/D5591
llvm-svn: 300930
immediate operands.
This commit adds an AArch64 dag-combine that optimizes code generation
for logical instructions taking immediate operands. The optimization
uses demanded bits to change a logical instruction's immediate operand
so that the immediate can be folded into the immediate field of the
instruction.
rdar://problem/18231627
Differential Revision: https://reviews.llvm.org/D5591
llvm-svn: 300913
This is inserted directly in the text section. The relocation
for the function ends up resolving to the beginning of the
amd_kernel_code_t header rather than the actual function
entry point.
Also skip some of the comments for initialization
that only makes sense for kernels.
llvm-svn: 300736
Avoid looping through program to determine register counts.
This avoids needing to look at regmask operands.
Also fixes some counting errors with flat_scr when there
are no stack objects.
llvm-svn: 300482
While the incoming stack for a kernel is 256-byte aligned,
this refers to the base address of the entire wave. This isn't
useful information for most of codegen. Fixes unnecessarily
aligning stack objects in callees.
llvm-svn: 300481
If a kernel's pointer argument is known to be readonly
set access qualifier accordingly. This allows RT not to
flush caches before dispatches.
Differential Revision: https://reviews.llvm.org/D32091
llvm-svn: 300362
Add hasParamAttribute() and use it instead of hasAttribute(ArgNo+1,
Kind) everywhere.
The fact that the AttributeList index for an argument is ArgNo+1 should
be a hidden implementation detail.
NFC
llvm-svn: 300272
In many cases ds operations can be combined even if offsets do not
fit into 8 bit encoding. What it takes is to adjust base address.
Differential Revision: https://reviews.llvm.org/D31993
llvm-svn: 300227
If workgroup size is known inform llvm about range returned by local
id and local size queries.
Differential Revision: https://reviews.llvm.org/D31804
llvm-svn: 300102
The unused dummy src2_modifiers is missing, so it crashes
when trying to print it.
I tried to fully remove src2_modifiers, but there are some
irritations in the places where it is converted to mad since
it starts to require modifying use lists while iterating over
them.
llvm-svn: 299861
Increase threshold to unroll a loop which contains an "if" statement
whose condition defined by a PHI belonging to the loop. This may help
to eliminate if region and potentially even PHI itself, saving on
both divergence and registers used for the PHI.
Add a small bonus for each of such "if" statements.
Differential Revision: https://reviews.llvm.org/D31693
llvm-svn: 299779
- corrected DS_GWS_* opcodes (see VI_Shader_Programming#16.pdf for detailed description)
- address operand is not used
- several opcodes have data operand
- all opcodes have offset modifier
- DS_AND_SRC2_B32: corrected typo in mnemo
- DS_WRAP_RTN_F32 replaced with DS_WRAP_RTN_B32
- added CI/VI opcodes:
- DS_CONDXCHG32_RTN_B64
- DS_GWS_SEMA_RELEASE_ALL
- added VI opcodes:
- DS_CONSUME
- DS_APPEND
- DS_ORDERED_COUNT
Differential Revision: https://reviews.llvm.org/D31707
llvm-svn: 299767
Summary:
Difference beetween PreRegAlloc() and MachineSSAOptimization() are that the former is run despite of -O0 optimization level. In my undestanding SiShrinkInstructions and SDWAPeephole shouldn't run when optimizations are disabled.
With this change order of passes will not change.
Reviewers: arsenm, vpykhtin, rampitec
Subscribers: qcolombet, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
Differential Revision: https://reviews.llvm.org/D31705
llvm-svn: 299757
This is possible in ways that are not compiler bugs,
so stop asserting on them.
This emits an extra error when emitting objects when it
can't encode the new pseudo, but I'm not sure that matters.
llvm-svn: 299712
Our final address space mapping is to let constant address space to be 4 to match nvptx.
However for now we will make it 2 to avoid unnecessary work in FE/BE/devlib
about intrinsics returning constant pointers.
Differential Revision: https://reviews.llvm.org/D31770
llvm-svn: 299690
If a workgroup size is known to be not greater than wavefront size
the s_barrier instruction is not needed since all threads are guarantied
to come to the same point at the same time.
Differential Revision: https://reviews.llvm.org/D31731
llvm-svn: 299659
A number of backends (AArch64, MIPS, ARM) have been using
MCContext::reportError to report issues such as out-of-range fixup values in
their TgtAsmBackend. This is great, but because MCContext couldn't easily be
threaded through to the adjustFixupValue helper function from its usual
callsite (applyFixup), these backends ended up adding an MCContext* argument
and adding another call to applyFixup to processFixupValue. Adding an
MCContext parameter to applyFixup makes this unnecessary, and even better -
applyFixup can take a reference to MCContext rather than a potentially null
pointer.
Differential Revision: https://reviews.llvm.org/D30264
llvm-svn: 299529
Add a new node to act as a fancy bitcast from f16 operations to
i32 that implicitly zero the high 16-bits of the result.
Alternatively could try making v2f16 legal and canonicalizing
on build_vectors.
llvm-svn: 299246
Currently ComputeNumSignBits returns the minimum number of sign bits for all elements of vector data, when we may only be interested in one/some of the elements.
This patch adds a DemandedElts argument that allows us to specify the elements we actually care about. The original ComputeNumSignBits implementation calls with a DemandedElts demanding all elements to match current behaviour. Scalar types set this to 1.
I've only added support for BUILD_VECTOR and EXTRACT_VECTOR_ELT so far, all others will default to demanding all elements but can be updated in due course.
Followup to D25691.
Differential Revision: https://reviews.llvm.org/D31311
llvm-svn: 299219
Previously compiler often extracted common immediates into specific register, e.g.:
```
%vreg0 = S_MOV_B32 0xff;
%vreg2 = V_AND_B32_e32 %vreg0, %vreg1
%vreg4 = V_AND_B32_e32 %vreg0, %vreg3
```
Because of this SDWA peephole failed to find SDWA convertible pattern. E.g. in previous example this could be converted into 2 SDWA src operands:
```
SDWA src: %vreg2 src_sel:BYTE_0
SDWA src: %vreg4 src_sel:BYTE_0
```
With this change peephole check if operand is either immediate or register that is copy of immediate.
llvm-svn: 299202
Follow up to D25691, this sets up the plumbing necessary to support vector demanded elements support in known bits calculations in target nodes.
Differential Revision: https://reviews.llvm.org/D31249
llvm-svn: 299201
What we really want to do is distinguish functions that may
be called by other functions, and graphics shaders are not
called kernels.
llvm-svn: 299140
If set to false it does not remove global aliases. With this parameter
set to false it should be safe to run the pass before link.
Differential Revision: https://reviews.llvm.org/D31489
llvm-svn: 299108
This is less important than increase threshold for private memory,
but still brings performance improvements in a wide range of tests.
Unrolling more for local memory serves three purposes: it allows
to combine ds operations if offset becomes static, saves registers
used for offsets in case of static offsets, and allows better lds
latency hiding.
Differential Revision: https://reviews.llvm.org/D31412
llvm-svn: 298948
This is incorrect to record region boundaries before scheduling,
it may change after scheduling. As a result second pass may see less
instructions to schedule than it should.
Differential Revision: https://reviews.llvm.org/D31434
llvm-svn: 298945
Previously it was covered by the internalization. It turns out we cannot
run internalizer in FE, it break separate compilation tests. Thus early
inliner gets its own option.
Differential Revision: https://reviews.llvm.org/D31429
llvm-svn: 298935
Enabled clamp and omod for v_cvt_* opcodes which have src0 of an integer type
Reviewers: vpykhtin, arsenm
Differential Revision: https://reviews.llvm.org/D31327
llvm-svn: 298852
As we introduced target triple environment amdgiz and amdgizcl, the address
space values are no longer enums. We have to decide the value by target triple.
The basic idea is to use struct AMDGPUAS to represent address space values.
For address space values which are not depend on target triple, use static
const members, so that they don't occupy extra memory space and is equivalent
to a compile time constant.
Since the struct is lightweight and cheap, it can be created on the fly at
the point of usage. Or it can be added as member to a pass and created at
the beginning of the run* function.
Differential Revision: https://reviews.llvm.org/D31284
llvm-svn: 298846
Switch data layout by target triple environment amdgiz and amdgizcl indicating using of an address space mapping in which generic address space is 0.
amdgiz is for non-OpenCL environment where generic address space is 0.
amdgizcl is for OpenCL environment where generic address space is 0.
Differential Revision: https://reviews.llvm.org/D31211
llvm-svn: 298758
If the branch condition for a loop was a phi which itself
was fed from a phi from a loop, it isn't safe to try
to delete the phi until after the loop is handled.
llvm-svn: 298737
StructurizeCFG can't handle cases with multiple
returns creating regions with multiple exits.
Create a copy of UnifyFunctionExitNodes that only
unifies exit nodes that skips exit nodes
with uniform branch sources.
llvm-svn: 298729
- Rename runtime metadata -> code object metadata
- Make metadata not flow
- Switch enums to use ScalarEnumerationTraits
- Cleanup and move AMDGPUCodeObjectMetadata.h to AMDGPU/MCTargetDesc
- Introduce in-memory representation for attributes
- Code object metadata streamer
- Create metadata for isa and printf during EmitStartOfAsmFile
- Create metadata for kernel during EmitFunctionBodyStart
- Finalize and emit metadata to .note during EmitEndOfAsmFile
- Other minor improvements/bug fixes
Differential Revision: https://reviews.llvm.org/D29948
llvm-svn: 298552
This is used for a specific type of return to a shader part's
epilog code. Rename to try avoiding confusion from a true
call's return.
llvm-svn: 298452
This adds a parameter to @llvm.objectsize that makes it return
conservative values if it's given null.
This fixes PR23277.
Differential Revision: https://reviews.llvm.org/D28494
llvm-svn: 298430
Summary:
This class is a list of AttributeSetNodes corresponding the function
prototype of a call or function declaration. This class used to be
called ParamAttrListPtr, then AttrListPtr, then AttributeSet. It is
typically accessed by parameter and return value index, so
"AttributeList" seems like a more intuitive name.
Rename AttributeSetImpl to AttributeListImpl to follow suit.
It's useful to rename this class so that we can rename AttributeSetNode
to AttributeSet later. AttributeSet is the set of attributes that apply
to a single function, argument, or return value.
Reviewers: sanjoy, javed.absar, chandlerc, pete
Reviewed By: pete
Subscribers: pete, jholewinski, arsenm, dschuff, mehdi_amini, jfb, nhaehnle, sbc100, void, llvm-commits
Differential Revision: https://reviews.llvm.org/D31102
llvm-svn: 298393
Summary:
First iteration of SDWA peephole.
This pass tries to combine several instruction into one SDWA instruction. E.g. it converts:
'''
V_LSHRREV_B32_e32 %vreg0, 16, %vreg1
V_ADD_I32_e32 %vreg2, %vreg0, %vreg3
V_LSHLREV_B32_e32 %vreg4, 16, %vreg2
'''
Into:
'''
V_ADD_I32_sdwa %vreg4, %vreg1, %vreg3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
'''
Pass structure:
1. Iterate over machine instruction in basic block and try to apply "SDWA patterns" to each of them. SDWA patterns match machine instruction into either source or destination SDWA operand. E.g. ''' V_LSHRREV_B32_e32 %vreg0, 16, %vreg1''' is matched to source SDWA operand '''%vreg1 src_sel:WORD_1'''.
2. Iterate over found SDWA operands and find instruction that could be potentially coverted into SDWA. E.g. for source SDWA operand potential instruction are all instruction in this basic block that uses '''%vreg0'''
3. Iterate over all potential instructions and check if they can be converted into SDWA.
4. Convert instructions to SDWA.
This review contains basic implementation of SDWA peephole pass. This pass requires additional testing fot both correctness and performance (no performance testing done).
There are several ways this pass can be improved:
1. Make this pass work on whole function not only basic block. As I can see this can be done right now without changes to pass.
2. Introduce more SDWA patterns
3. Introduce mnemonics to limit when SDWA patterns should apply
Reviewers: vpykhtin, alex-t, arsenm, rampitec
Subscribers: wdng, nhaehnle, mgorny
Differential Revision: https://reviews.llvm.org/D30038
llvm-svn: 298365
This is direct port of HSAILAliasAnalysis pass, just cleaned for
style and renamed.
Differential Revision: https://reviews.llvm.org/D31103
llvm-svn: 298172
If the loop condition was an i1 phi with a constantexpr input, this
would add a loop intrinsic fed by a phi dependent on a call to
if.break in the same block. Insert the call in the loop header.
llvm-svn: 298121
Move backend internal intrinsics along with the rest of the
normal intrinsics, and use the Intrinsic::getDeclaration
API instead of manually constructing the type list.
It's surprising this was working before. fdiv.fast had
the wrong number of parameters. The control flow intrinsic
declaration attributes were not being applied, and
their types were inconsistent. The actual IR use types
did not match the declaration, and were closer to the
types used for the patterns. The brcond lowering
was changing the types, so introduce new nodes for those.
llvm-svn: 298119
Loop unswitching can be extremely harmful for a SIMT target. In case
if hoisted condition is not uniform a SIMT machine will execute both
clones of a loop sequentially. Therefor LoopUnswitch checks if the
condition is non-divergent.
Since DivergenceAnalysis adds an expensive PostDominatorTree analysis
not needed for non-SIMT targets a new option is added to avoid unneded
analysis initialization. The method getAnalysisUsage is called when
TargetTransformInfo is not yet available and we cannot use it here.
For that reason a new field DivergentTarget is added to PassManagerBuilder
to control the behavior and set this field from a target.
Differential Revision: https://reviews.llvm.org/D30796
llvm-svn: 298104
We can mark functions to always inline early in the opt. Since we do not have
call support this early inlining creates opportunities for inter-procedural
optimizations which would not occur otherwise.
Differential Revision: https://reviews.llvm.org/D31016
llvm-svn: 297958
computeKnownBits didn't handle fp_to_fp16 to report
the high bits as 0. ARM maps the generic node to an instruction
that does not modify the high bits of the register, so introduce
a target node where the high bits are known 0.
llvm-svn: 297873
Since v_max_f32_e64/v_max_f16_e64 can be folded if the target
instruction supports the clamp bit, we also need to maintain
modifiers when converting v_mac to v_mad.
This fixes a rendering issue with Dirt Rally because a v_mac
instruction with the clamp bit set was converted to a v_mad
but that bit was lost during the conversion.
Fixes: e184e01dd79 ("AMDGPU: Fold FP clamp as modifier bit")
Patch by Samuel Pitoiset <samuel.pitoiset@gmail.com>
llvm-svn: 297556
This method inverts the Reason field of a scheduling candidate.
It does right comparison between RegCritical and RegExcess, but
everything else is broken. In fact it can prefer less strong reason
such as Weak over RegCritical because Weak > -RegCritical.
The CandReason enum is properly sorted, so just remove artificial
ranking.
Differential Revision: https://reviews.llvm.org/D30557
llvm-svn: 297536
If there is only one successor, and that successor only
has one predecessor the wait can obviously be delayed until
uses or the end of the next block. This avoids code quality
regressions when there are trivial fallthrough blocks inserted
for structurization.
llvm-svn: 297251
Summary:
This will allow future patches to inspect the details of the LLT. The implementation is now split between
the Support and CodeGen libraries to allow TableGen to use this class without introducing layering concerns.
Thanks to Ahmed Bougacha for finding a reasonable way to avoid the layering issue and providing the version of this patch without that problem.
The problem with the previous commit appears to have been that TableGen was including CodeGen/LowLevelType.h instead of Support/LowLevelTypeImpl.h.
Reviewers: t.p.northover, qcolombet, rovka, aditya_nandakumar, ab, javed.absar
Subscribers: arsenm, nhaehnle, mgorny, dberris, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D30046
llvm-svn: 297241
More module problems. This time it only showed up in the stage 2 compile of
clang-x86_64-linux-selfhost-modules-2 but not the stage 1 compile.
Somehow, this change causes the build to need Attributes.gen before it's been
generated.
llvm-svn: 297188
Summary:
This will allow future patches to inspect the details of the LLT. The implementation is now split between
the Support and CodeGen libraries to allow TableGen to use this class without introducing layering concerns.
Thanks to Ahmed Bougacha for finding a reasonable way to avoid the layering issue and providing the version of this patch without that problem.
Reviewers: t.p.northover, qcolombet, rovka, aditya_nandakumar, ab, javed.absar
Subscribers: arsenm, nhaehnle, mgorny, dberris, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D30046
llvm-svn: 297177
Added code to check constant bus restrictions for VOP formats (only one SGPR value or literal-constant may be used by the instruction).
Note that the same checks are performed by SIInstrInfo::verifyInstruction (used by lowering code).
Added LIT tests.
llvm-svn: 296873
It's not clear to me if this is always better than
doing ds_write2_b64 This adds the constraint of
a 128-bit register input instead of a pair of
64-bit.
llvm-svn: 296512
If during scheduling we have identified that we cannot keep optimistic
occupancy increase critical register pressure limit and try scheduling
of the whole function again. In this case blocks with smaller pressure
will have a chance for better scheduling.
Differential Revision: https://reviews.llvm.org/D30442
llvm-svn: 296506
This change introduces new method to estimate register pressure in
GCNScheduler. Standard RPTracker gives huge error due to the following
reasons:
1. It does not account for live-ins or live-outs if value is not used
in the region itself. That creates a huge error in a very common case
if there are a lot of live-thu registers.
2. It does not properly count subregs.
3. It assumes a register used as an input operand can be reused as an
output. This is not always possible by itself, this is not what RA
will finally do in many cases for various reasons not limited to RA's
inability to do so, and this is not so if the value is actually a
live-thu.
In addition we can now see clear separation between live-in pressure
which we cannot change with the scheduling and tentative pressure
which we can change.
Differential Revision: https://reviews.llvm.org/D30439
llvm-svn: 296491
If two subregs of the same register are defined and we need to revert
schedule changing def order, we will end up with both instructions
having def,read-undef flags because adjustLaneLiveness() will only set
this flag but will not remove it.
Fix this by removing read-undef flags before calling adjustLaneLiveness.
Differential Revision: https://reviews.llvm.org/D30428
llvm-svn: 296484
Summary:
This will allow future patches to inspect the details of the LLT. The implementation is now split between
the Support and CodeGen libraries to allow TableGen to use this class without introducing layering concerns.
Thanks to Ahmed Bougacha for finding a reasonable way to avoid the layering issue and providing the version of this patch without that problem.
Reviewers: t.p.northover, qcolombet, rovka, aditya_nandakumar, ab, javed.absar
Subscribers: arsenm, nhaehnle, mgorny, dberris, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D30046
llvm-svn: 296474
- Verify that runtime metadata is actually valid runtime metadata when assembling, otherwise we could accept the following when assembling, but ocl runtime will reject it:
.amdgpu_runtime_metadata
{ amd.MDVersion: [ 2, 1 ], amd.RandomUnknownKey, amd.IsaInfo: ...
- Make IsaInfo optional, and always emit it.
Differential Revision: https://reviews.llvm.org/D30349
llvm-svn: 296324
This reverts commit r296009. It broke one out of tree target and also
does not account for all partial lines added or removed when calculating
PressureDiff.
llvm-svn: 296182
If a subreg is used in an instruction it counts as a whole superreg
for the purpose of register pressure calculation. This patch corrects
improper register pressure calculation by examining operand's lane mask.
Differential Revision: https://reviews.llvm.org/D29835
llvm-svn: 296009
Implement isLegalToVectorizeLoadChain for AMDGPU to avoid
producing private address spaces accesses that will need to be
split up later. This was doing the wrong thing in the case
where the queried chain was an even number of elements.
A possible <4 x i32> store was being split into
store <2 x i32>
store i32
store i32
rather than
store <2 x i32>
store <2 x i32>
when legal.
llvm-svn: 295933
The manual is unclear on the details of this. It's not
clear to me if denormals are not allowed with clamp,
or if that is only omod. Not allowing denorms for
fp16 or fp64 isn't useful so I also question if that
is really a restriction. Same with whether this is valid
without IEEE mode enabled.
llvm-svn: 295905
This should avoid reporting any stack needs to be allocated in the
case where no stack is truly used. An unused stack slot is still
left around in other cases where there are real stack objects
but no spilling occurs.
llvm-svn: 295891
This allows us to ensure that 0 is never a valid pointer
to a user object, and ensures that the offset is always legal
without needing a register to access it. This comes at the cost
of usable offsets and wasted stack space.
llvm-svn: 295877
Change implementation to use max instead of add.
min/max/med3 do not flush denormals regardless of the mode,
so it is OK to use it whether or not they are enabled.
Also allow using clamp with f16, and use knowledge
of dx10_clamp.
llvm-svn: 295788
Before frame offsets are calculated, try to eliminate the
frame indexes used by SGPR spills. Then we can delete them
after.
I think for now we can be sure that no other instruction
will be re-using the same frame indexes. It should be easy
to notice if this assumption ever breaks since everything
asserts if it tries to use a dead frame index later.
The unused emergency stack slot seems to still be left behind,
so an additional 4 bytes is still wasted.
llvm-svn: 295753
This patch reverts region's scheduling to the original untouched state
in case if we have have decreased occupancy.
In addition it switches to use TargetRegisterInfo occupancy callback
for pressure limits instead of gradually increasing limits which were
just passed by. We are going to stay with the best schedule so we do
not need to tolerate worsened scheduling anymore.
Differential Revision: https://reviews.llvm.org/D29971
llvm-svn: 295206
This patch corrects the maximum workgroups per CU if we have big
workgroups (more than 128). This calculation contributes to the
occupancy calculation in respect to LDS size.
Differential Revision: https://reviews.llvm.org/D29974
llvm-svn: 295134
This change returns empty PSet list for M0 register. Otherwise its
PSet as defined by tablegen is SReg_32. This results in incorrect
register pressure calculation every time an instruction uses M0.
Such uses count as SReg_32 PSet and inadequately increase pressure
on SGPRs.
Differential Revision: https://reviews.llvm.org/D29798
llvm-svn: 294691
Summary:
Convert all obvious node_begin/node_end and child_begin/child_end
pairs to range based for.
Sending for review in case someone has a good idea how to make
graph_children able to be inferred. It looks like it would require
changing GraphTraits to be two argument or something. I presume
inference does not happen because it would have to check every
GraphTraits in the world to see if the noderef types matched.
Note: This change was 3-staged with clang as well, which uses
Dominators/etc from LLVM.
Reviewers: chandlerc, tstellarAMD, dblaikie, rsmith
Subscribers: arsenm, llvm-commits, nhaehnle
Differential Revision: https://reviews.llvm.org/D29767
llvm-svn: 294620
Implement getRegPressureLimit and getRegPressureSetLimit callbacks in
SIRegisterInfo.
This makes standard converge scheduler to behave almost the same as
GCNScheduler, sometime slightly better sometimes a bit worse.
In gerenal that is also possible to switch GCNScheduler to use these
callbacks instead of getMaxWaves(), which also makes GCNScheduler
slightly better on some tests and slightly worse on another. A big
win is behavior with converge scheduler.
Note, these are used not only by scheduling, but in places like
MachineLICM.
Differential Revision: https://reviews.llvm.org/D29700
llvm-svn: 294518
For amdgcn target Clang generates addrspacecast to represent null pointers in private and local address spaces.
In LLVM codegen, the static variable initializer is lowered by virtual function AsmPrinter::lowerConstant which is target generic. Since addrspacecast is target specific, AsmPrinter::lowerConst
This patch overrides AsmPrinter::lowerConstant with AMDGPUAsmPrinter::lowerConstant, which is able to lower the target-specific addrspacecast in the null pointer representation so that -1 is co
Differential Revision: https://reviews.llvm.org/D29284
llvm-svn: 294265
This has quite positive performance impact according to measurements.
Before previous fixes to limit the optimization that was too high
and blowed compile time and scratch usage, but now this is gone and
we can bump the threshold.
Differential Revision: https://reviews.llvm.org/D29505
llvm-svn: 294032
Exit loop analysis early if suitable private access found.
Do not account for GEPs which are invariant to loop induction variable.
Do not account for Allocas which are too big to fit into register file anyway.
Add option for tuning: -amdgpu-unroll-threshold-private.
Differential Revision: https://reviews.llvm.org/D29473
llvm-svn: 293991
Recommiting after fixing X86 inc/dec chain bug.
* Simplify Consecutive Merge Store Candidate Search
Now that address aliasing is much less conservative, push through
simplified store merging search and chain alias analysis which only
checks for parallel stores through the chain subgraph. This is cleaner
as the separation of non-interfering loads/stores from the
store-merging logic.
When merging stores search up the chain through a single load, and
finds all possible stores by looking down from through a load and a
TokenFactor to all stores visited.
This improves the quality of the output SelectionDAG and the output
Codegen (save perhaps for some ARM cases where we correctly constructs
wider loads, but then promotes them to float operations which appear
but requires more expensive constant generation).
Some minor peephole optimizations to deal with improved SubDAG shapes (listed below)
Additional Minor Changes:
1. Finishes removing unused AliasLoad code
2. Unifies the chain aggregation in the merged stores across code
paths
3. Re-add the Store node to the worklist after calling
SimplifyDemandedBits.
4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is
arbitrary, but seems sufficient to not cause regressions in
tests.
5. Remove Chain dependencies of Memory operations on CopyfromReg
nodes as these are captured by data dependence
6. Forward loads-store values through tokenfactors containing
{CopyToReg,CopyFromReg} Values.
7. Peephole to convert buildvector of extract_vector_elt to
extract_subvector if possible (see
CodeGen/AArch64/store-merge.ll)
8. Store merging for the ARM target is restricted to 32-bit as
some in some contexts invalid 64-bit operations are being
generated. This can be removed once appropriate checks are
added.
This finishes the change Matt Arsenault started in r246307 and
jyknight's original patch.
Many tests required some changes as memory operations are now
reorderable, improving load-store forwarding. One test in
particular is worth noting:
CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store
forwarding converts a load-store pair into a parallel store and
a memory-realized bitcast of the same value. However, because we
lose the sharing of the explicit and implicit store values we
must create another local store. A similar transformation
happens before SelectionDAG as well.
Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle
llvm-svn: 293893
The operand types were defined to fit the fp16_to_fp node, which
has the half as an integer type. v_cvt_f32_f16 does support
source modifiers, so change this to have an FP type and modifiers.
For targets without legal f16, this requires recognizing the
bit operations and trying to produce them.
llvm-svn: 293857
Functions matching LDS use to occupancy return results for a workgroup
of 64 workitems. The numbers has to be adjusted for bigger workgroups.
For example a workgroup of size 256 already occupies 4 waves just by
itself. Given that all numbers of LDS use in the compiler are per
workgroup, occupancy shall be multiplied by 4 in this case. Each 64
workitems still limited by the same number, but 4 subrgoups 64 workitems
each can afford 4 times more LDS to get the same occupancy.
In addition change initializes LDS size in the subtarget to a real value
for SI+ targets. This is required since LDS size is a variable in these
calculations.
Differential Revision: https://reviews.llvm.org/D29423
llvm-svn: 293837
These were simply preserving the flags of the original operation,
which was too conservative in most cases and incorrect for mul.
nsw/nuw may be needed for some combines to cleanup messes when
intermediate sext_inregs are introduced later.
Tested valid combinations with alive.
llvm-svn: 293776
Summary:
For some reason instructions are being inserted in the wrong order with some
builds. I'm not sure why this is happening.
Reviewers: arsenm
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, tony-tye, tpr, llvm-commits
Differential Revision: https://reviews.llvm.org/D29325
llvm-svn: 293639
I think this is safe as long as no inputs are known to ever
be nans.
Also add an intrinsic for fmed3 to be able to handle all safe
math cases.
llvm-svn: 293598
For now just port some of the existing NVPTX tests
and from an old HSAIL optimization pass which
approximately did the same thing.
Don't enable the pass yet until more testing is done.
llvm-svn: 293580
Since we have no call support and late linking we can produce code
only for used symbols. This saves compilation time, size of the final
executable, and size of any intermediate dumps.
Run Internalize pass early in the opt pipeline followed by global
DCE pass. To enable it RT can pass -amdgpu-internalize-symbols option.
Differential Revision: https://reviews.llvm.org/D29214
llvm-svn: 293549
This is worse if the original constant is an inline immediate.
This should also be done for 64-bit adds, but requires fixing
operand folding bugs first.
llvm-svn: 293540
We had various variants of defining dump() functions in LLVM. Normalize
them (this should just consistently implement the things discussed in
http://lists.llvm.org/pipermail/cfe-dev/2014-January/034323.html
For reference:
- Public headers should just declare the dump() method but not use
LLVM_DUMP_METHOD or #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
- The definition of a dump method should look like this:
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
LLVM_DUMP_METHOD void MyClass::dump() {
// print stuff to dbgs()...
}
#endif
llvm-svn: 293359
Coverage/smoke Gfx7/8 tests were committed r292922 but then reverted
by r292974 due to AddressSanitizer failure, which is fixed by this patch.
Tests to be re-committed soon.
llvm-svn: 293338
Accomplishes what r292982 was supposed to, which ended up
only really making the necessary test changes.
This should be applied to the 4.0 branch.
Patch by Vedran Miletić <vedran@miletic.net>
llvm-svn: 293310
With the adjustPassManager interface that is now possible to use
custom early module passes.
Differential Revision: https://reviews.llvm.org/D29189
llvm-svn: 293300
This change introduces adjustPassManager target callback giving a
target an opportunity to tweak PassManagerBuilder before pass
managers are populated.
This generalizes and replaces addEarlyAsPossiblePasses target
callback. In particular that can be used to add custom passes to
extension points other than EP_EarlyAsPossible.
Differential Revision: https://reviews.llvm.org/D28336
llvm-svn: 293189
* Simplify Consecutive Merge Store Candidate Search
Now that address aliasing is much less conservative, push through
simplified store merging search and chain alias analysis which only
checks for parallel stores through the chain subgraph. This is cleaner
as the separation of non-interfering loads/stores from the
store-merging logic.
When merging stores search up the chain through a single load, and
finds all possible stores by looking down from through a load and a
TokenFactor to all stores visited.
This improves the quality of the output SelectionDAG and the output
Codegen (save perhaps for some ARM cases where we correctly constructs
wider loads, but then promotes them to float operations which appear
but requires more expensive constant generation).
Some minor peephole optimizations to deal with improved SubDAG shapes (listed below)
Additional Minor Changes:
1. Finishes removing unused AliasLoad code
2. Unifies the chain aggregation in the merged stores across code
paths
3. Re-add the Store node to the worklist after calling
SimplifyDemandedBits.
4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is
arbitrary, but seems sufficient to not cause regressions in
tests.
5. Remove Chain dependencies of Memory operations on CopyfromReg
nodes as these are captured by data dependence
6. Forward loads-store values through tokenfactors containing
{CopyToReg,CopyFromReg} Values.
7. Peephole to convert buildvector of extract_vector_elt to
extract_subvector if possible (see
CodeGen/AArch64/store-merge.ll)
8. Store merging for the ARM target is restricted to 32-bit as
some in some contexts invalid 64-bit operations are being
generated. This can be removed once appropriate checks are
added.
This finishes the change Matt Arsenault started in r246307 and
jyknight's original patch.
Many tests required some changes as memory operations are now
reorderable, improving load-store forwarding. One test in
particular is worth noting:
CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store
forwarding converts a load-store pair into a parallel store and
a memory-realized bitcast of the same value. However, because we
lose the sharing of the explicit and implicit store values we
must create another local store. A similar transformation
happens before SelectionDAG as well.
Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle
llvm-svn: 293184
Leave early ifcvt disabled for now since there are some
shader-db regressions.
This causes some immediate improvements, but could be better.
The cost checking that the pass does is based on critical path
length for out of order CPUs which we do not want so it skips out
on many cases we want.
llvm-svn: 293016
Summary:
This lets you select which sort of spilling you want, either s[0:1] or 64-bit loads from s[0:1].
Patch By: Dave Airlie
Reviewers: nhaehnle, arsenm, tstellarAMD
Reviewed By: arsenm
Subscribers: mareko, llvm-commits, kzhuravl, wdng, yaxunl, tony-tye
Differential Revision: https://reviews.llvm.org/D25428
llvm-svn: 293000
The sequence like this:
v_cmpx_le_f32_e32 vcc, 0, v0
s_branch BB0_30
s_cbranch_execnz BB0_30
; BB#29:
exp null off, off, off, off done vm
s_endpgm
BB0_30:
; %endif110
is likely wrong. The s_branch instruction will unconditionally jump
to BB0_30 and the skip block (exp done + endpgm) inserted for
performing the kill instruction will never be executed. This results
in a GPU hang with Star Ruler 2.
The s_branch instruction is added during the "Control Flow Optimizer"
pass which seems to re-organize the basic blocks, and we assume
that SI_KILL_TERMINATOR is always the last instruction inside a
basic block. Thus, after inserting a skip block we just go to the
next BB without looking at the subsequent instructions after the
kill, and the s_branch op is never removed.
Instead, we should remove the unconditional out branches and let
skip the two instructions if the exec mask is non-zero.
This patch fixes the GPU hang and doesn't introduce any regressions
with "make check".
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=99019
Patch by Samuel Pitoiset <samuel.pitoiset@gmail.com>
llvm-svn: 292985
This switches to the workaround that HSA defaults to
for the mesa path.
This should be applied to the 4.0 branch.
Patch by Vedran Miletić <vedran@miletic.net>
llvm-svn: 292982
Regalloc creates COPY instructions which do not formally use VALU.
That results in v_mov instructions displaced after exec mask modification.
One pass which do it is SIOptimizeExecMasking, but potentially it can be
done by other passes too.
This patch adds a pass immediately after regalloc to add implicit exec
use operand to all VGPR copy instructions.
Differential Revision: https://reviews.llvm.org/D28874
llvm-svn: 292956
Inline spiller can decide to move a spill as early as possible in the basic block.
It will skip phis and label, but we also need to make sure it skips instructions
in the basic block prologue which restore exec mask.
Added isPositionLike callback in TargetInstrInfo to detect instructions which
shall be skipped in addition to common phis, labels etc.
Differential Revision: https://reviews.llvm.org/D27997
llvm-svn: 292554
This instruction is missing from LiveIntervals.
I'm not aware of any problems because of this though.
Differential Revision: https://reviews.llvm.org/D28879
llvm-svn: 292521
For -(x + y) -> (-x) + (-y), if x == -y, this would
change the result from -0.0 to 0.0. Since the fma/fmad
combine is an extension of this problem it also
applies there.
fmul should be fine, and I don't think any of the unary
operators or conversions should be a problem either.
llvm-svn: 292473
Limit register coalescer by not allowing it to artificially increase
size of registers beyond dword. Such super-registers are in fact
register sequences and not distinct HW registers.
With more super-regs we would need to allocate adjacent registers
and constraint regalloc more than needed. Moreover, our super
registers are overlapping. For instance we have VGPR0_VGPR1_VGPR2,
VGPR1_VGPR2_VGPR3, VGPR2_VGPR3_VGPR4 etc, which complicates registers
allocation even more, resulting in excessive spilling.
Differential Revision: https://reviews.llvm.org/D28782
llvm-svn: 292413
Rename from addOperand to just add, to match the other method that has been
added to MachineInstrBuilder for adding more than just 1 operand.
See https://reviews.llvm.org/D28057 for the whole discussion.
Differential Revision: https://reviews.llvm.org/D28556
llvm-svn: 291891
This produces worse code when i16 is legal, mostly
due to combines getting confused by conversions inserted
for uniform 16-bit operations.
llvm-svn: 291717
updated instructions:
pmulld, pmullw, pmulhw, mulsd, mulps, mulpd, divss, divps, divsd, divpd, addpd and subpd.
special optimization case which replaces pmulld with pmullw\pmulhw\pshuf seq.
In case if the real operands bitwidth <= 16.
Differential Revision: https://reviews.llvm.org/D28104
llvm-svn: 291657
For i16 zeroext arguments when i16 was a legal type, the
known bits information from the truncate was lost. Insert
a zeroext so the known bits optimizations work with the 32-bit
loads.
Fixes code quality regressions vs. SI in min.ll test.
llvm-svn: 291461
Among other stuff, this allows to use predefined .option.machine_version_major
/minor/stepping symbols in the directive.
Relevant test expanded at once (also file renamed for clarity).
Differential Revision: https://reviews.llvm.org/D28140
llvm-svn: 290710
The feature allows for conditional assembly, filling the entries
of .amd_kernel_code_t etc.
Symbols are defined with value 0 at the beginning of each kernel scope.
After each register usage, the respective symbol is set to:
value = max( value, ( register index + 1 ) )
Thus, at the end of scope the value represents a count of used registers.
Kernel scopes begin at .amdgpu_hsa_kernel directive, end at the
next .amdgpu_hsa_kernel (or EOF, whichever comes first). There is also
dummy scope that lies from the beginning of source file til the
first .amdgpu_hsa_kernel.
Test added.
Differential Revision: https://reviews.llvm.org/D27859
llvm-svn: 290608
Canonicalize a select with a constant to the false side. This
enables more instruction shrinking opportunities since an
inline immediate can be used for the false side of v_cndmask_b32_e32.
This seems to usually be better but causes some code size regressions
in some tests.
llvm-svn: 290372
Summary: This is needed for later SDWA support in CodeGen.
Reviewers: vpykhtin, tstellarAMD
Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, tony-tye
Differential Revision: https://reviews.llvm.org/D27412
llvm-svn: 290338
Summary: Real instruction should copy constraints from real instruction. This allows auto-generated disassembler to correctly process tied operands.
Reviewers: nhaustov, vpykhtin, tstellarAMD
Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, tony-tye
Differential Revision: https://reviews.llvm.org/D27847
llvm-svn: 290336
When the instruction is processed the first time, it may be
deleted resulting in crashes. While the new test adds the same
user to the worklist twice, this particular case doesn't crash
but I'm not sure why.
llvm-svn: 290191
Summary:
Without a MachineMemOperand, the scheduler was assuming MIMG instructions
were ordered memory references, so no loads or stores could be reordered
across them.
Reviewers: arsenm
Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, tony-tye
Differential Revision: https://reviews.llvm.org/D27536
llvm-svn: 290179
Summary:
Added pair of directives .hsa_code_object_metadata/.end_hsa_code_object_metadata.
Between them user can put YAML string that would be directly put to the generated note. E.g.:
'''
.hsa_code_object_metadata
{
amd.MDVersion: [ 2, 0 ]
}
.end_hsa_code_object_metadata
'''
Based on D25046
Reviewers: vpykhtin, nhaustov, yaxunl, tstellarAMD
Subscribers: arsenm, kzhuravl, wdng, nhaehnle, mgorny, tony-tye
Differential Revision: https://reviews.llvm.org/D27619
llvm-svn: 290097
Jonas Paulsson