[AMDGPU] Add GFX11 test coverage

Add GFX11 test coverage to a bunch of tests where it was easy to do so,
mostly because the checks are autogenerated and/or GFX11 can share the
same checks as GFX10.

[AMDGPU] Add GFX11 test coverage

Add GFX11 test coverage to a bunch of tests where it was easy to do so,
mostly because the checks are autogenerated and/or GFX11 can share the
same checks as GFX10.

Differential Revision: https://reviews.llvm.org/D129295

show more ...

[AMDGPU] Set most sched model resource's BufferSize to one

Using a BufferSize of one for memory ProcResources will result in better
ILP since it more accurately models the dependencies between memor

[AMDGPU] Set most sched model resource's BufferSize to one

Using a BufferSize of one for memory ProcResources will result in better
ILP since it more accurately models the dependencies between memory ops
and their consumers on an in-order processor. After this change, the
scheduler will treat the data edges from loads as blocking so that
stalls are guaranteed when waiting for data to be retreaved from memory.
Since we don't actually track waitcnt here, this should do a better job
at modeling their behavior.

Practically, this means that the scheduler will trigger the 'STALL'
heuristic more often.

This type of change needs to be evaluated experimentally. Preliminary
results are positive.

Fixes: SWDEV-282962

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D114777

show more ...

[AMDGPU] Switch PostRA sched to MachineSched

Use GCNHazardRecognizer in postra sched.
Updated tests for the new schedules.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D1095

[AMDGPU] Switch PostRA sched to MachineSched

Use GCNHazardRecognizer in postra sched.
Updated tests for the new schedules.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D109536

Change-Id: Ia86ba2ae168f12fb34b4d8efdab491f84d936cde

show more ...

AMDGPU: Try to eliminate clearing of high bits of 16-bit instructions

These used to consistently be zeroed pre-gfx9, but gfx9 made the
situation complicated since now some still do and some don't. T

AMDGPU: Try to eliminate clearing of high bits of 16-bit instructions

These used to consistently be zeroed pre-gfx9, but gfx9 made the
situation complicated since now some still do and some don't. This
also manages to pick up a few cases that the pattern fails to optimize
away.

We handle some cases with instruction patterns, but some get
through. In particular this improves the integer cases.

show more ...

[AMDGPU] Extend gfx10 test coverage. NFC.

Differential Revision: https://reviews.llvm.org/D99267

[AMDGPU] Update subtarget features for new target ID support

Support for XNACK and SRAMECC is not static on some GPUs. We must be able
to differentiate between different scenarios for these dynamic

[AMDGPU] Update subtarget features for new target ID support

Support for XNACK and SRAMECC is not static on some GPUs. We must be able
to differentiate between different scenarios for these dynamic subtarget
features.

The possible settings are:

- Unsupported: The GPU has no support for XNACK/SRAMECC.
- Any: Preference is unspecified. Use conservative settings that can run anywhere.
- Off: Request support for XNACK/SRAMECC Off
- On: Request support for XNACK/SRAMECC On

GCNSubtarget will track the four options based on the following criteria. If
the subtarget does not support XNACK/SRAMECC we say the setting is
"Unsupported". If no subtarget features for XNACK/SRAMECC are requested we
must support "Any" mode. If the subtarget features XNACK/SRAMECC exist in the
feature string when initializing the subtarget, the settings are "On/Off".

The defaults are updated to be conservatively correct, meaning if no setting
for XNACK or SRAMECC is explicitly requested, defaults will be used which
generate code that can be run anywhere. This corresponds to the "Any" setting.

Differential Revision: https://reviews.llvm.org/D85882

show more ...

[AMDGPU] Add volatile support to SIMemoryLegalizer

Treat a non-atomic volatile load and store as a relaxed atomic at
system scope for the address spaces accessed. This will ensure all
relevant cache

[AMDGPU] Add volatile support to SIMemoryLegalizer

Treat a non-atomic volatile load and store as a relaxed atomic at
system scope for the address spaces accessed. This will ensure all
relevant caches will be bypassed.

A volatile atomic is not changed and still only bypasses caches upto
the level specified by the SyncScope operand.

Differential Revision: https://reviews.llvm.org/D94214

show more ...

[NFC] Removed unused prefixes from CodeGen/AMDGPU

All the 'l'-starting tests.

Differential Revision: https://reviews.llvm.org/D94151

[MachineScheduler] Fix the TopDepth/BotHeightReduce latency heuristics

tryLatency compares two sched candidates. For the top zone it prefers
the one with lesser depth, but only if that depth is grea

[MachineScheduler] Fix the TopDepth/BotHeightReduce latency heuristics

tryLatency compares two sched candidates. For the top zone it prefers
the one with lesser depth, but only if that depth is greater than the
total latency of the instructions we've already scheduled -- otherwise
its latency would be hidden and there would be no stall.

Unfortunately it only tests the depth of one of the candidates. This can
lead to situations where the TopDepthReduce heuristic does not kick in,
but a lower priority heuristic chooses the other candidate, whose depth
*is* greater than the already scheduled latency, which causes a stall.

The fix is to apply the heuristic if the depth of *either* candidate is
greater than the already scheduled latency.

All this also applies to the BotHeightReduce heuristic in the bottom
zone.

Differential Revision: https://reviews.llvm.org/D72392

show more ...

[AMDGPU] Make v4i64/v4f64/v8i64/v8f64 legal

We can produce such vectors in the Promote Alloca pass,
but we are unable to use movrel to operate it and lower
via scratch. Making it legal makes SI_INDI

[AMDGPU] Make v4i64/v4f64/v8i64/v8f64 legal

We can produce such vectors in the Promote Alloca pass,
but we are unable to use movrel to operate it and lower
via scratch. Making it legal makes SI_INDIRECT patterns
work.

There is more work to do in subsequent changes:

1. We initialize m0 twice to access each dword. It shall
be possible to only do it once and increment base register
number instead.
2. We also need v16i64/v16f64 but these first need to be
added to tablegen.

Differential Revision: https://reviews.llvm.org/D79808

show more ...

AMDGPU: Remove denormal subtarget features

Switch to using the denormal-fp-math/denormal-fp-math-f32 attributes.

AMDGPU: Assume f32 denormals are enabled by default

This will likely introduce catastrophic performance regressions on
older subtargets, but should be correct. A follow up change will
remove the old

AMDGPU: Assume f32 denormals are enabled by default

This will likely introduce catastrophic performance regressions on
older subtargets, but should be correct. A follow up change will
remove the old fp32-denormals subtarget features, and switch to using
the new denormal-fp-math/denormal-fp-math-f32 attributes. Frontends
should be making sure to add the denormal-fp-math-f32 attribute when
appropriate to avoid performance regressions.

show more ...

[AMDGPU] Bundle loads before post-RA scheduler

We are relying on atrificial DAG edges inserted by the
MemOpClusterMutation to keep loads and stores together in the
post-RA scheduler. This does not w

[AMDGPU] Bundle loads before post-RA scheduler

We are relying on atrificial DAG edges inserted by the
MemOpClusterMutation to keep loads and stores together in the
post-RA scheduler. This does not work all the time since it
allows to schedule a completely independent instruction in the
middle of the cluster.

Removed the DAG mutation and added pass to bundle already
clustered instructions. These bundles are unpacked before the
memory legalizer because it does not work with bundles but also
because it allows to insert waitcounts in the middle of a store
cluster.

Removing artificial edges also allows a more relaxed scheduling.

Differential Revision: https://reviews.llvm.org/D72737

show more ...

[AMDGPU] Fix typo in SIInstrInfo::memOpsHaveSameBasePtr

Summary:
The typo has been present since memOpsHaveSameBasePtr was introduced in
r313208.

It caused SIInstrInfo::shouldClusterMemOps to clust

[AMDGPU] Fix typo in SIInstrInfo::memOpsHaveSameBasePtr

Summary:
The typo has been present since memOpsHaveSameBasePtr was introduced in
r313208.

It caused SIInstrInfo::shouldClusterMemOps to cluster more mem ops than
it was supposed to.

Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D71616

show more ...

DAG: Change behavior of fminnum/fmaxnum nodes

Introduce new versions that follow the IEEE semantics
to help with legalization that may need quieted inputs.

There are some regressions from inserting

DAG: Change behavior of fminnum/fmaxnum nodes

Introduce new versions that follow the IEEE semantics
to help with legalization that may need quieted inputs.

There are some regressions from inserting unnecessary
canonicalizes when these are matched from fast math
fcmp + select which should be fixed in a future commit.

llvm-svn: 344914

show more ...

AMDGPU: Add pass to lower kernel arguments to loads

This replaces most argument uses with loads, but for
now not all.

The code in SelectionDAG for calling convention lowering
is actively harmful fo

AMDGPU: Add pass to lower kernel arguments to loads

This replaces most argument uses with loads, but for
now not all.

The code in SelectionDAG for calling convention lowering
is actively harmful for amdgpu_kernel. It attempts to
split the argument types into register legal types, which
results in low quality code for arbitary types. Since
all kernel arguments are passed in memory, we just want the
raw types.

I've tried a couple of methods of mitigating this in SelectionDAG,
but it's easier to just bypass this problem alltogether. It's
possible to hack around the problem in the initial lowering,
but the real problem is the DAG then expects to be able to use
CopyToReg/CopyFromReg for uses of the arguments outside the block.

Exposing the argument loads in the IR also has the advantage
that the LoadStoreVectorizer can merge them.

I'm not sure the best approach to dealing with the IR
argument list is. The patch as-is just leaves the IR arguments
in place, so all the existing code will still compute the same
kernarg size and pointlessly lowers the arguments.

Arguably the frontend should emit kernels with an empty argument
list in the first place. Alternatively a dummy array could be
inserted as a single argument just to reserve space.

This does have some disadvantages. Local pointer kernel arguments can
no longer have AssertZext placed on them as the equivalent !range
metadata is not valid on pointer typed loads. This is mostly bad
for SI which needs to know about the known bits in order to use the
DS instruction offset, so in this case this is not done.

More importantly, this skips noalias arguments since this pass
does not yet convert this to the equivalent !alias.scope and !noalias
metadata. Producing this metadata correctly seems to be tricky,
although this logically is the same as inlining into a function which
doesn't exist. Additionally, exposing these loads to the vectorizer
may result in degraded aliasing information if a pointer load is
merged with another argument load.

I'm also not entirely sure this is preserving the current clover
ABI, although I would greatly prefer if it would stop widening
arguments and match the HSA ABI. As-is I think it is extending
< 4-byte arguments to 4-bytes but doesn't align them to 4-bytes.

llvm-svn: 335650

show more ...

AMDGPU: Fix missing test coverage for some 16-bit and packed ops

llvm-svn: 333024

AMDGPU: Fix -enable-var-scope violations

llvm-svn: 318004

AMDGPU: Cleanup subtarget features

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
in

AMDGPU: Cleanup subtarget features

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

show more ...

AMDGPU: Allow SIShrinkInstructions to work in non-SSA

Immediates can be folded as long as the immediate is a vreg.

Also undo commuting instructions if it didn't fold an immediate.

llvm-svn: 307575

[AMDGPU] Switch scalarize global loads ON by default
Differential revision: https://reviews.llvm.org/D34407

llvm-svn: 307097

Revert r307026, "[AMDGPU] Switch scalarize global loads ON by default"

It broke a testcase.

Failing Tests (1):
LLVM :: CodeGen/AMDGPU/alignbit-pat.ll

llvm-svn: 307054

[AMDGPU] Switch scalarize global loads ON by default

Differential revision: https://reviews.llvm.org/D34407

llvm-svn: 307026

[AMDGPU] Untangle SDWA pass from SIShrinkInstructions

Remove dependency of SDWA pass on SIShrinkInstructions.
The goal is to move SDWA even higher in the stack to avoid second run
of MachineLICM, Ma

[AMDGPU] Untangle SDWA pass from SIShrinkInstructions

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

show more ...

[AMDGPU] Allow SDWA in instructions with immediates and SGPRs

An encoding does not allow to use SDWA in an instruction with
scalar operands, either literals or SGPRs. That is however possible
to cop

[AMDGPU] Allow SDWA in instructions with immediates and SGPRs

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

show more ...