[AMDGPU] Combine s_or_saveexec, s_xor instructions.

This patch merges a consecutive sequence of

s_or_saveexec s_o, s_i
s_xor exec, exec, s_o

into a single

s_andn2_saveexec s_o, s_i instruction.
T

[AMDGPU] Combine s_or_saveexec, s_xor instructions.

This patch merges a consecutive sequence of

s_or_saveexec s_o, s_i
s_xor exec, exec, s_o

into a single

s_andn2_saveexec s_o, s_i instruction.
This patch also cleans up the SIOptimizeExecMasking pass a bit.

Reviewed By: nhaehnle

Differential Revision: https://reviews.llvm.org/D129073

show more ...

[AMDGPU] Do not generate ELF symbols for the local branch target labels

The compiler was generating symbols in the final code object for local
branch target labels. This bloats the code object, slow

[AMDGPU] Do not generate ELF symbols for the local branch target labels

The compiler was generating symbols in the final code object for local
branch target labels. This bloats the code object, slows down the loader,
and is only used to simplify disassembly.

Use '--symbolize-operands' with llvm-objdump to improve readability of the
branch target operands in disassembly.

Fixes: SWDEV-312223

Reviewed By: scott.linder

Differential Revision: https://reviews.llvm.org/D114273

show more ...

[AMDGPU] Don't handle export done when unify exit nodes

This patch aims to revert the changes introduced by D70781 D71192 D76364

D70781 was introduced to fix hardware hang where we do not insert ex

[AMDGPU] Don't handle export done when unify exit nodes

This patch aims to revert the changes introduced by D70781 D71192 D76364

D70781 was introduced to fix hardware hang where we do not insert exp-
null-done for a kill inside infinit loop. At that time we have not added
exp-null-done for kill early termination, but I believe as for now, we will
always add the exp-null-done for early termination case in LaterBranchLowering.

D71192 was introduced to handle the only_kill case, which is also been
handled by the kill early termination work.

D76364 was used to fix a regression by D71192, where we cleared the done
bit of the export in the existing program and not let the normal return
block branching to the new unified return block.

With this change, we just trust frontends have setup exp-done correctly
which is true for all existing frontends. The backend only inserts
exp-null-done for the kill cases which is handled in SILateBranchLowering.cpp.

Reviewed by: critson

Differential Revision: https://reviews.llvm.org/D105610

show more ...

[NFC][AMDGPU] autogenerate kill-infinite-loop.ll checks

This would help us to track the assembly changes to these tests.

Reviewed by: foad

Differential Revision: https://reviews.llvm.org/D105609

[AMDGPU] Rename SIInsertSkips Pass

Pass no longer handles skips. Pass now removes unnecessary
unconditional branches and lowers early termination branches.
Hence rename to SILateBranchLowering.

Mo

[AMDGPU] Rename SIInsertSkips Pass

Pass no longer handles skips. Pass now removes unnecessary
unconditional branches and lowers early termination branches.
Hence rename to SILateBranchLowering.

Move code to handle returns to epilog from SIPreEmitPeephole
into SILateBranchLowering. This means SIPreEmitPeephole only
contains optional optimisations, and all required transforms
are in SILateBranchLowering.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D98915

show more ...

[AMDGPU][SimplifyCFG] Teach AMDGPUUnifyDivergentExitNodes to preserve {,Post}DomTree

This is a (last big?) part of the patch series to make SimplifyCFG
preserve DomTree. Currently, it still does not

[AMDGPU][SimplifyCFG] Teach AMDGPUUnifyDivergentExitNodes to preserve {,Post}DomTree

This is a (last big?) part of the patch series to make SimplifyCFG
preserve DomTree. Currently, it still does not actually preserve it,
even thought it is pretty much fully updated to preserve it.

Once the default is flipped, a valid DomTree must be passed into
simplifyCFG, which means that whatever pass calls simplifyCFG,
should also be smart about DomTree's.

As far as i can see from `check-llvm` with default flipped,
this is the last LLVM test batch (other than bugpoint tests)
that needed fixes to not break with default flipped.

The changes here are boringly identical to the ones i did
over 42+ times/commits recently already,
so while AMDGPU is outside of my normal ecosystem,
i'm going to go for post-commit review here,
like in all the other 42+ changes.

Note that while the pass is taught to preserve {,Post}DomTree,
it still doesn't do that by default, because simplifycfg
still doesn't do that by default, and flipping default
in this pass will implicitly flip the default for simplifycfg.
That will happen, but not right now.

show more ...

[NFC][CodeGen][Tests] Mark all tests that fail to preserve DomTree for SimplifyCFG as such

These tests start to fail when the SimplifyCFG's default regarding DomTree
updating is switched on, so mark

[NFC][CodeGen][Tests] Mark all tests that fail to preserve DomTree for SimplifyCFG as such

These tests start to fail when the SimplifyCFG's default regarding DomTree
updating is switched on, so mark them as needing changes.

show more ...

[AMDGPU] Insert PS early exit at end of control flow

Exit early if the exec mask is zero at the end of control flow.
Mark the ends of control flow during control flow lowering and
convert these to e

[AMDGPU] Insert PS early exit at end of control flow

Exit early if the exec mask is zero at the end of control flow.
Mark the ends of control flow during control flow lowering and
convert these to exits during the insert skips pass.

Reviewed By: nhaehnle

Differential Revision: https://reviews.llvm.org/D82737

show more ...

Revert "[AMDGPU] Insert PS early exit at end of control flow"

This reverts commit 2bfcacf0ad362956277a1c2c9ba00ddc453a42ce.

There appears to be an issue to analysis preservation.

[AMDGPU] Insert PS early exit at end of control flow

Exit early if the exec mask is zero at the end of control flow.
Mark the ends of control flow during control flow lowering and
convert these to e

[AMDGPU] Insert PS early exit at end of control flow

Exit early if the exec mask is zero at the end of control flow.
Mark the ends of control flow during control flow lowering and
convert these to exits during the insert skips pass.

Reviewed By: nhaehnle

Differential Revision: https://reviews.llvm.org/D82737

show more ...

AMDGPU: Fix AMDGPUUnifyDivergentExitNodes with no normal returns

Summary:
The code was assuming in a few places that if there was only one exit
from the function that it was a normal return, which i

AMDGPU: Fix AMDGPUUnifyDivergentExitNodes with no normal returns

Summary:
The code was assuming in a few places that if there was only one exit
from the function that it was a normal return, which is invalid. It
could be an infinite loop, in which case we still need to insert the
usual fake edge so that the null export happens. This fixes shaders that
end with an infinite loop that discards.

Reviewers: arsenm, nhaehnle, critson

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

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D71192

show more ...

AMDGPU: Fix handling of infinite loops in fragment shaders

Summary:
Due to the fact that kill is just a normal intrinsic, even though it's
supposed to terminate the thread, we can end up with provab

AMDGPU: Fix handling of infinite loops in fragment shaders

Summary:
Due to the fact that kill is just a normal intrinsic, even though it's
supposed to terminate the thread, we can end up with provably infinite
loops that are actually supposed to end successfully. The
AMDGPUUnifyDivergentExitNodes pass breaks up these loops, but because
there's no obvious place to make the loop branch to, it just makes it
return immediately, which skips the exports that are supposed to happen
at the end and hangs the GPU if all the threads end up being killed.

While it would be nice if the fact that kill terminates the thread were
modeled in the IR, I think that the structurizer as-is would make a mess if we
did that when the kill is inside control flow. For now, we just add a null
export at the end to make sure that it always exports something, which fixes
the immediate problem without penalizing the more common case. This means that
we sometimes do two "done" exports when only some of the threads enter the
discard loop, but from tests the hardware seems ok with that.

This fixes dEQP-VK.graphicsfuzz.while-inside-switch with radv.

Reviewers: arsenm, nhaehnle

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

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D70781

show more ...

Revert "AMDGPU: Fix AMDGPUUnifyDivergentExitNodes with no normal returns"

This reverts commit 323bfde20c5f3e63db3d6b385b394ed38542abe6.

AMDGPU: Fix AMDGPUUnifyDivergentExitNodes with no normal returns

Summary:
The code was assuming in a few places that if there was only one exit
from the function that it was a normal return, which i

AMDGPU: Fix AMDGPUUnifyDivergentExitNodes with no normal returns

Summary:
The code was assuming in a few places that if there was only one exit
from the function that it was a normal return, which is invalid. It
could be an infinite loop, in which case we still need to insert the
usual fake edge so that the null export happens. This fixes shaders that
end with an infinite loop that discards.

Reviewers: arsenm, nhaehnle, critson

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

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D71192

show more ...

AMDGPU: Fix handling of infinite loops in fragment shaders

Summary:
Due to the fact that kill is just a normal intrinsic, even though it's
supposed to terminate the thread, we can end up with provab

AMDGPU: Fix handling of infinite loops in fragment shaders

Summary:
Due to the fact that kill is just a normal intrinsic, even though it's
supposed to terminate the thread, we can end up with provably infinite
loops that are actually supposed to end successfully. The
AMDGPUUnifyDivergentExitNodes pass breaks up these loops, but because
there's no obvious place to make the loop branch to, it just makes it
return immediately, which skips the exports that are supposed to happen
at the end and hangs the GPU if all the threads end up being killed.

While it would be nice if the fact that kill terminates the thread were
modeled in the IR, I think that the structurizer as-is would make a mess if we
did that when the kill is inside control flow. For now, we just add a null
export at the end to make sure that it always exports something, which fixes
the immediate problem without penalizing the more common case. This means that
we sometimes do two "done" exports when only some of the threads enter the
discard loop, but from tests the hardware seems ok with that.

This fixes dEQP-VK.graphicsfuzz.while-inside-switch with radv.

Reviewers: arsenm, nhaehnle

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

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D70781

show more ...