[NVPTX] Enable AtomicExpandPass for NVPTX

This patch enables `AtomicExpandPass` for NVPTX.

Depend on D125652.

Reviewed By: tra

Differential Revision: https://reviews.llvm.org/D125639

mark getTargetTransformInfo and getTargetIRAnalysis as const

Seems like this can be const, since Passes shouldn't modify it.

Reviewed By: wsmoses

Differential Revision: https://reviews.llvm.org/D1

mark getTargetTransformInfo and getTargetIRAnalysis as const

Seems like this can be const, since Passes shouldn't modify it.

Reviewed By: wsmoses

Differential Revision: https://reviews.llvm.org/D120518

show more ...

[InferAddressSpaces] Support assumed addrspaces from addrspace predicates.

- CUDA cannot associate memory space with pointer types. Even though Clang could add extra attributes to specify the addres

[InferAddressSpaces] Support assumed addrspaces from addrspace predicates.

- CUDA cannot associate memory space with pointer types. Even though Clang could add extra attributes to specify the address space explicitly on a pointer type, it breaks the portability between Clang and NVCC.
- This change proposes to assume the address space from a pointer from the assumption built upon target-specific address space predicates, such as `__isGlobal` from CUDA. E.g.,

```
foo(float *p) {
__builtin_assume(__isGlobal(p));
// From there, we could assume p is a global pointer instead of a
// generic one.
}
```

This makes the code portable without introducing the implementation-specific features.

Note that NVCC starts to support __builtin_assume from version 11.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D112041

show more ...

[NVPTX] Add a late SROA pass which allows optimizing away more allocas.

Fixes performance regression https://bugs.llvm.org/show_bug.cgi?id=52037

Differential Revision: https://reviews.llvm.org/D111

[NVPTX] Add a late SROA pass which allows optimizing away more allocas.

Fixes performance regression https://bugs.llvm.org/show_bug.cgi?id=52037

Differential Revision: https://reviews.llvm.org/D111471

show more ...

Remove the verifyAfter mechanism that was replaced by D111397

Differential Revision: https://reviews.llvm.org/D111872

Move TargetRegistry.(h|cpp) from Support to MC

This moves the registry higher in the LLVM library dependency stack.
Every client of the target registry needs to link against MC anyway to
actually us

Move TargetRegistry.(h|cpp) from Support to MC

This moves the registry higher in the LLVM library dependency stack.
Every client of the target registry needs to link against MC anyway to
actually use the target, so we might as well move this out of Support.

This allows us to ensure that Support doesn't have includes from MC/*.

Differential Revision: https://reviews.llvm.org/D111454

show more ...

Take OptimizationLevel class out of Pass Builder

Pulled out the OptimizationLevel class from PassBuilder in order to be able to access it from within the PassManager and avoid include conflicts.

Re

Take OptimizationLevel class out of Pass Builder

Pulled out the OptimizationLevel class from PassBuilder in order to be able to access it from within the PassManager and avoid include conflicts.

Reviewed By: mtrofin

Differential Revision: https://reviews.llvm.org/D107025

show more ...

[NewPM] Hide pass manager debug logging behind -debug-pass-manager-verbose

Printing pass manager invocations is fairly verbose and not super
useful.

This allows us to remove DebugLogging from pass

[NewPM] Hide pass manager debug logging behind -debug-pass-manager-verbose

Printing pass manager invocations is fairly verbose and not super
useful.

This allows us to remove DebugLogging from pass managers and PassBuilder
since all logging (aside from analysis managers) goes through
instrumentation now.

This has the downside of never being able to print the top level pass
manager via instrumentation, but that seems like a minor downside.

Reviewed By: ychen

Differential Revision: https://reviews.llvm.org/D101797

show more ...

[NVPTX] Enable lowering of atomics on local memory

LLVM does not have valid assembly backends for atomicrmw on local memory. However, as this memory is thread local, we should be able to lower this

[NVPTX] Enable lowering of atomics on local memory

LLVM does not have valid assembly backends for atomicrmw on local memory. However, as this memory is thread local, we should be able to lower this to the relevant load/store.

Differential Revision: https://reviews.llvm.org/D98650

show more ...

Revert "[NVPTX] Enable lowering of atomics on local memory"

This reverts commit fede99d386ec9e7bab2762aa16cb10c0513ae464.

[NVPTX] Enable lowering of atomics on local memory

LLVM does not have valid assembly backends for atomicrmw on local memory. However, as this memory is thread local, we should be able to lower this

[NVPTX] Enable lowering of atomics on local memory

LLVM does not have valid assembly backends for atomicrmw on local memory. However, as this memory is thread local, we should be able to lower this to the relevant load/store.

Differential Revision: https://reviews.llvm.org/D98650

show more ...

[NVPTX][NewPM] Re-enable NVVMReflectPass

Disabled alongside NVVMIntrRangePass in https://reviews.llvm.org/D96166,
but turns out NVVMIntrRangePass was the issue.

Reviewed By: tra

Differential Revis

[NVPTX][NewPM] Re-enable NVVMReflectPass

Disabled alongside NVVMIntrRangePass in https://reviews.llvm.org/D96166,
but turns out NVVMIntrRangePass was the issue.

Reviewed By: tra

Differential Revision: https://reviews.llvm.org/D96291

show more ...

[NVPTX][NewPM] Temporarily disable NVPTX passes in new PM pipeline

These passes are causing numerical discrepancies after being added to
the pipeline. Disable while investigating.

Reviewed By: rupp

[NVPTX][NewPM] Temporarily disable NVPTX passes in new PM pipeline

These passes are causing numerical discrepancies after being added to
the pipeline. Disable while investigating.

Reviewed By: rupprecht

Differential Revision: https://reviews.llvm.org/D96166

show more ...

[NewPM][NVPTX] Port NVPTX opt passes

There are only two used in the IR optimization pipeline.
Port these and add them to the default pipeline.

Similar to https://reviews.llvm.org/D93863.

I added -

[NewPM][NVPTX] Port NVPTX opt passes

There are only two used in the IR optimization pipeline.
Port these and add them to the default pipeline.

Similar to https://reviews.llvm.org/D93863.

I added -mtriple to some tests since under the new PM, the passes are
only available when the TargetMachine is specified.

Reviewed By: rnk

Differential Revision: https://reviews.llvm.org/D93930

show more ...

CodeGen: Refactor regallocator command line and target selection

Make the sequence of passes to select and rewrite instructions to
physical registers be a target callback. This is to prepare to allo

CodeGen: Refactor regallocator command line and target selection

Make the sequence of passes to select and rewrite instructions to
physical registers be a target callback. This is to prepare to allow
targets to split register allocation into multiple phases.

show more ...

[NVPTX, LSV] Move the LSV optimization pass to later when the graph is cleaner

This allow it to recognize more loads as being consecutive when the load's address are complex at the start.

Different

[NVPTX, LSV] Move the LSV optimization pass to later when the graph is cleaner

This allow it to recognize more loads as being consecutive when the load's address are complex at the start.

Differential Revision: https://reviews.llvm.org/D74444

show more ...

Make llvm::StringRef to std::string conversions explicit.

This is how it should've been and brings it more in line with
std::string_view. There should be no functional change here.

This is mostly m

Make llvm::StringRef to std::string conversions explicit.

This is how it should've been and brings it more in line with
std::string_view. There should be no functional change here.

This is mostly mechanical from a custom clang-tidy check, with a lot of
manual fixups. It uncovers a lot of minor inefficiencies.

This doesn't actually modify StringRef yet, I'll do that in a follow-up.

show more ...

CMake: Make most target symbols hidden by default

Summary:
For builds with LLVM_BUILD_LLVM_DYLIB=ON and BUILD_SHARED_LIBS=OFF
this change makes all symbols in the target specific libraries hidden
by

CMake: Make most target symbols hidden by default

Summary:
For builds with LLVM_BUILD_LLVM_DYLIB=ON and BUILD_SHARED_LIBS=OFF
this change makes all symbols in the target specific libraries hidden
by default.

A new macro called LLVM_EXTERNAL_VISIBILITY has been added to mark symbols in these
libraries public, which is mainly needed for the definitions of the
LLVMInitialize* functions.

This patch reduces the number of public symbols in libLLVM.so by about
25%. This should improve load times for the dynamic library and also
make abi checker tools, like abidiff require less memory when analyzing
libLLVM.so

One side-effect of this change is that for builds with
LLVM_BUILD_LLVM_DYLIB=ON and LLVM_LINK_LLVM_DYLIB=ON some unittests that
access symbols that are no longer public will need to be statically linked.

Before and after public symbol counts (using gcc 8.2.1, ld.bfd 2.31.1):
nm before/libLLVM-9svn.so | grep ' [A-Zuvw] ' | wc -l
36221
nm after/libLLVM-9svn.so | grep ' [A-Zuvw] ' | wc -l
26278

Reviewers: chandlerc, beanz, mgorny, rnk, hans

Reviewed By: rnk, hans

Subscribers: merge_guards_bot, luismarques, smeenai, ldionne, lenary, s.egerton, pzheng, sameer.abuasal, MaskRay, wuzish, echristo, Jim, hiraditya, michaelplatings, chapuni, jholewinski, arsenm, dschuff, jyknight, dylanmckay, sdardis, nemanjai, jvesely, javed.absar, sbc100, jgravelle-google, aheejin, kbarton, fedor.sergeev, asb, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, jrtc27, zzheng, edward-jones, mgrang, atanasyan, rogfer01, MartinMosbeck, brucehoult, the_o, PkmX, jocewei, kristina, jsji, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D54439

show more ...

[llvm] Migrate llvm::make_unique to std::make_unique

Now that we've moved to C++14, we no longer need the llvm::make_unique
implementation from STLExtras.h. This patch is a mechanical replacement
of

[llvm] Migrate llvm::make_unique to std::make_unique

Now that we've moved to C++14, we no longer need the llvm::make_unique
implementation from STLExtras.h. This patch is a mechanical replacement
of (hopefully) all the llvm::make_unique instances across the monorepo.

llvm-svn: 369013

show more ...

Revert CMake: Make most target symbols hidden by default

This reverts r362990 (git commit 374571301dc8e9bc9fdd1d70f86015de198673bd)

This was causing linker warnings on Darwin:

ld: warning: direct

Revert CMake: Make most target symbols hidden by default

This reverts r362990 (git commit 374571301dc8e9bc9fdd1d70f86015de198673bd)

This was causing linker warnings on Darwin:

ld: warning: direct access in function 'llvm::initializeEvexToVexInstPassPass(llvm::PassRegistry&)'
from file '../../lib/libLLVMX86CodeGen.a(X86EvexToVex.cpp.o)' to global weak symbol
'void std::__1::__call_once_proxy<std::__1::tuple<void* (&)(llvm::PassRegistry&),
std::__1::reference_wrapper<llvm::PassRegistry>&&> >(void*)' from file '../../lib/libLLVMCore.a(Verifier.cpp.o)'
means the weak symbol cannot be overridden at runtime. This was likely caused by different translation
units being compiled with different visibility settings.

llvm-svn: 363028

show more ...

CMake: Make most target symbols hidden by default

Summary:
For builds with LLVM_BUILD_LLVM_DYLIB=ON and BUILD_SHARED_LIBS=OFF
this change makes all symbols in the target specific libraries hidden
by

CMake: Make most target symbols hidden by default

Summary:
For builds with LLVM_BUILD_LLVM_DYLIB=ON and BUILD_SHARED_LIBS=OFF
this change makes all symbols in the target specific libraries hidden
by default.

A new macro called LLVM_EXTERNAL_VISIBILITY has been added to mark symbols in these
libraries public, which is mainly needed for the definitions of the
LLVMInitialize* functions.

This patch reduces the number of public symbols in libLLVM.so by about
25%. This should improve load times for the dynamic library and also
make abi checker tools, like abidiff require less memory when analyzing
libLLVM.so

One side-effect of this change is that for builds with
LLVM_BUILD_LLVM_DYLIB=ON and LLVM_LINK_LLVM_DYLIB=ON some unittests that
access symbols that are no longer public will need to be statically linked.

Before and after public symbol counts (using gcc 8.2.1, ld.bfd 2.31.1):
nm before/libLLVM-9svn.so | grep ' [A-Zuvw] ' | wc -l
36221
nm after/libLLVM-9svn.so | grep ' [A-Zuvw] ' | wc -l
26278

Reviewers: chandlerc, beanz, mgorny, rnk, hans

Reviewed By: rnk, hans

Subscribers: Jim, hiraditya, michaelplatings, chapuni, jholewinski, arsenm, dschuff, jyknight, dylanmckay, sdardis, nemanjai, jvesely, nhaehnle, javed.absar, sbc100, jgravelle-google, aheejin, kbarton, fedor.sergeev, asb, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, jrtc27, zzheng, edward-jones, mgrang, atanasyan, rogfer01, MartinMosbeck, brucehoult, the_o, PkmX, jocewei, kristina, jsji, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D54439

llvm-svn: 362990

show more ...

[NVPTX] Create a TargetInfo header. NFC

Move the declarations of getThe<Name>Target() functions into a new header in
TargetInfo and make users of these functions include this new header.
This fixes

[NVPTX] Create a TargetInfo header. NFC

Move the declarations of getThe<Name>Target() functions into a new header in
TargetInfo and make users of these functions include this new header.
This fixes a layering problem.

llvm-svn: 360729

show more ...

CodeGen: Refactor regallocator command line and target selection

This will allow targets more flexibility to replace the
register allocator core passes. In a future commit,
AMDGPU will run the core

CodeGen: Refactor regallocator command line and target selection

This will allow targets more flexibility to replace the
register allocator core passes. In a future commit,
AMDGPU will run the core register assignment passes
twice, and will also want to disallow using the
standard -regalloc option.

llvm-svn: 356506

show more ...

Update the file headers across all of the LLVM projects in the monorepo
to reflect the new license.

We understand that people may be surprised that we're moving the header
entirely to discuss the ne

Update the file headers across all of the LLVM projects in the monorepo
to reflect the new license.

We understand that people may be surprised that we're moving the header
entirely to discuss the new license. We checked this carefully with the
Foundation's lawyer and we believe this is the correct approach.

Essentially, all code in the project is now made available by the LLVM
project under our new license, so you will see that the license headers
include that license only. Some of our contributors have contributed
code under our old license, and accordingly, we have retained a copy of
our old license notice in the top-level files in each project and
repository.

llvm-svn: 351636

show more ...

[NVPTX] Allow libcalls that are defined in the current module.

The patch adds a possibility to make library calls on NVPTX.

An important thing about library functions - they must be defined within

[NVPTX] Allow libcalls that are defined in the current module.

The patch adds a possibility to make library calls on NVPTX.

An important thing about library functions - they must be defined within
the current module. This basically should guarantee that we produce a
valid PTX assembly (without calls to not defined functions). The one who
wants to use the libcalls is probably will have to link against
compiler-rt or any other implementation.

Currently, it's completely impossible to make library calls because of
error LLVM ERROR: Cannot select: i32 = ExternalSymbol '...'. But we can
lower ExternalSymbol to TargetExternalSymbol and verify if the function
definition is available.

Also, there was an issue with a DAG during legalisation. When we expand
instruction into libcall, the inner call-chain isn't being "integrated"
into outer chain. Since the last "data-flow" (call retval load) node is
located in call-chain earlier than CALLSEQ_END node, the latter becomes
a leaf and therefore a dead node (and is being removed quite fast).
Proposed here solution relies on another data-flow pseudo nodes
(ProxyReg) which purpose is only to keep CALLSEQ_END at legalisation and
instruction selection phases - we remove the pseudo instructions before
register scheduling phase.

Patch by Denys Zariaiev!

Differential Revision: https://reviews.llvm.org/D34708

llvm-svn: 350069

show more ...