The OpenMP runtime's cmake scripts do not correctly locate the
libdevice that the Debian/Ubuntu package nvidia-cuda-toolkit currently
includes, at least on my Ubuntu 18.04.1 installation. This patch
fixes that for me.
This problem was discussed at length in D55269. D40453 added a
similar adjustment in clang, but reviewers of D55269 concluded that,
for the OpenMP runtime, the right place to address this problem is in
cmake's CUDA support. However, it was also suggested we could add a
workaround to OpenMP's cmake scripts now. This patch contains such a
workaround, which I've tried to design so that it will have no harmful
effect if cmake improves in the future.
nvidia-cuda-toolkit also needs improvements because its intended
monolithic CUDA tree shim, /usr/lib/cuda, has many empty directories,
such as bin. I reported that at:
<https://bugs.launchpad.net/ubuntu/+source/nvidia-cuda-toolkit/+bug/1808999>
Reviewed By: grokos
Differential Revision: https://reviews.llvm.org/D55588
llvm-svn: 350377
Doing this late so we will prefer to fold the AND into a masked comparison first. That can be better for the live range of the mask register.
Differential Revision: https://reviews.llvm.org/D56246
llvm-svn: 350374
Summary:
- This adopts SwiftABIInfo as the base class for WebAssemblyABIInfo, which is in keeping with what is done for other targets for which Swift is supported.
- This is a minimal patch to unblock exploration of WASM support for Swift (https://bugs.swift.org/browse/SR-9307)
Reviewers: rjmccall, sunfish
Reviewed By: rjmccall
Subscribers: ahti, dschuff, sbc100, jgravelle-google, aheejin, cfe-commits
Differential Revision: https://reviews.llvm.org/D56188
llvm-svn: 350372
Summary:
Replace the 32-bit allocator with a 64-bit one with a non-constant
base address, and reduce both the number of size classes and the maximum
size of per-thread caches.
As measured on [1], this reduces average weighted memory overhead
(MaxRSS) from 26% to 12% over stock android allocator. These numbers
include overhead from code instrumentation and hwasan shadow (i.e. not a
pure allocator benchmark).
This switch also enables release-to-OS functionality, which is not
implemented in the 32-bit allocator. I have not seen any effect from
that on the benchmark.
[1] https://android.googlesource.com/platform/system/extras/+/master/memory_replay/
Reviewers: vitalybuka, kcc
Subscribers: kubamracek, cryptoad, llvm-commits
Differential Revision: https://reviews.llvm.org/D56239
llvm-svn: 350370
This would show up if we fix horizontal reductions to narrow as they go along,
but it's an improvement for size and/or Jaguar (fast-hops) independent of that.
We need to do this late to not interfere with other pattern matching of larger
horizontal sequences.
We can extend this to integer ops in a follow-up patch.
Differential Revision: https://reviews.llvm.org/D56011
llvm-svn: 350369
There is already in use:
lit/lit-lldb-init:
settings set symbols.enable-external-lookup false
packages/Python/lldbsuite/test/lldbtest.py:
self.runCmd('settings set symbols.enable-external-lookup false')
But those are not in effect during MI part of the testsuite. Another problem is
that symbols.enable-external-lookup (read by GetEnableExternalLookup) has been
currently read only by LocateMacOSXFilesUsingDebugSymbols and therefore it had
no effect on Linux.
On Red Hat platforms (Fedoras, RHEL-7) there is DWZ in use and so
MiSyntaxTestCase-test_lldbmi_output_grammar FAILs due to:
AssertionError: error: inconsistent pattern ''^.+?\n'' for state 0x5f
(matched string: warning: (x86_64) /lib64/libstdc++.so.6 unsupported
DW_FORM values: 0x1f20 0x1f21
It is the only testcase with this error. It happens due to:
(lldb) target create "/lib64/libstdc++.so.6"
Current executable set to '/lib64/libstdc++.so.6' (x86_64).
(lldb) b main
warning: (x86_64) /lib64/libstdc++.so.6 unsupported DW_FORM values: 0x1f20 0x1f21
Breakpoint 1: no locations (pending).
WARNING: Unable to resolve breakpoint to any actual locations.
which happens only with gcc-base-debuginfo rpm installed (similarly for other packages).
It should also speed up the testsuite as it no longer needs to read
/usr/lib/debug symbols which have no effect (and should not have any effect) on
the testsuite results.
Differential Revision: https://reviews.llvm.org/D55859
llvm-svn: 350368
Summary:
Irreducible control flow is not that rare, e.g. it happens in malloc and
3 other places in the libc portions linked in to a hello world program.
This patch improves how we handle that code: it emits a br_table to
dispatch to only the minimal necessary number of blocks. This reduces
the size of malloc by 33%, and makes it comparable in size to asm2wasm's
malloc output.
Added some tests, and verified this passes the emscripten-wasm tests run
on the waterfall (binaryen2, wasmobj2, other).
Reviewers: aheejin, sunfish
Subscribers: mgrang, jgravelle-google, sbc100, dschuff, llvm-commits
Differential Revision: https://reviews.llvm.org/D55467
Patch by Alon Zakai (kripken)
llvm-svn: 350367
Summary:
The previously introduced new operand type for br_table didn't have
a disassembler implementation, causing an assert.
Reviewers: dschuff, aheejin
Subscribers: sbc100, jgravelle-google, sunfish, llvm-commits
Differential Revision: https://reviews.llvm.org/D56227
llvm-svn: 350366
Summary:
Instead of asserting on certain kinds of malformed instructions, it
now still print, but instead adds an annotation indicating the
problem, and/or indicates invalid_type etc.
We're using the InstPrinter from many contexts that can't always
guarantee values are within range (e.g. the disassembler), where having
output is more valueable than asserting.
Reviewers: dschuff, aheejin
Subscribers: sbc100, jgravelle-google, sunfish, llvm-commits
Differential Revision: https://reviews.llvm.org/D56223
llvm-svn: 350365
In cmake 3.10.2, if (${VARIABLE_NAME}) seems to always be false no
matter what documentation says (or maybe I just failed at reading).
Anyway, if (VARIABLE_NAME) seems to do what this code intended.
llvm-svn: 350361
This tests a case where we need to be able to compute sign bits for two insert_subvectors that is a liveout of a basic block. The result is then used as a boolean vector in another basic block.
llvm-svn: 350359
These are similar patterns, but when you throw AVX512 onto the pile,
the number of variations explodes. For FP, we really don't care about
AVX1 vs. AVX2 for FP ops. There may be some superficial shuffle diffs,
but that's not what we're testing for here, so I removed those RUNs.
Separating by type also lets us specify 'sse3' for the FP file vs. 'ssse3'
for the integer file...because x86.
llvm-svn: 350357
As noted in PR39973 and D55558:
https://bugs.llvm.org/show_bug.cgi?id=39973
...this is a partial implementation of a fold that we do as an IR canonicalization in instcombine:
// extelt (binop X, Y), Index --> binop (extelt X, Index), (extelt Y, Index)
We want to have this in the DAG too because as we can see in some of the test diffs (reductions),
the pattern may not be visible in IR.
Given that this is already an IR canonicalization, any backend that would prefer a vector op over
a scalar op is expected to already have the reverse transform in DAG lowering (not sure if that's
a realistic expectation though). The transform is limited with a TLI hook because there's an
existing transform in CodeGenPrepare that tries to do the opposite transform.
Differential Revision: https://reviews.llvm.org/D55722
llvm-svn: 350354
Add omp_get_device_num() function for 5.0 which returns the number of the
device the current thread is running on. Currently, we are leaving it to the
compiler to handle this properly if it is called inside target.
Also, did some cleanup and updating of duplicate device API functions (in both
libomp and libomptarget) to make them into weak functions that check for the
symbol from libomptarget, and will call the version in libomptarget if it is
present. If any additional device API functions are implemented also in
libomptarget in the future, we should add the dlsym calls to the host functions.
Also, if the omp_target_* functions are to be implemented for the host (this has
been requested), they should attempt to call the libomptarget versions as well.
Patch by Terry Wilmarth
Differential Revision: https://reviews.llvm.org/D55578
llvm-svn: 350352
Detailed description: SIFoldOperands::foldInstOperand iterates over the
operand uses calling the function that changes def-use iteratorson the
way. As a result loop exits immediately when def-use iterator is
changed. Hence, the operand is folded to the very first use instruction
only. This makes VGPR live along the whole basic block and increases
register pressure significantly. The performance drop observed in SHOC
DeviceMemory test is caused by this bug.
Proposed fix: collect uses to separate container for further processing
in another loop.
Testing: make check-llvm
SHOC performance test.
Reviewers: rampitec, ronlieb
Differential Revision: https://reviews.llvm.org/D56161
llvm-svn: 350350
It was added in r257236 but then the one use was removed in r309517. Since no
test should call %host_cc, remove the pattern.
Differential Revision: https://reviews.llvm.org/D56200
llvm-svn: 350348
Use report_fatal_error in MCStreamer::EmitRawTextImpl instead of
using errs() and explain the rationale behind it not being
llvm_unreachable() to save confusion for any future maintainers.
Differential Revision: https://reviews.llvm.org/D56245
llvm-svn: 350342
Follow up for D53051
This patch introduces the tool associated with the ELF implementation of
TextAPI (previously llvm-tapi, renamed for better distinction). This
tool will house a number of features related to enalysis and
manipulation of shared object's exposed interfaces. The first major
feature for this tool is support for producing binary stubs that are
useful for compile-time linking of shared objects. This patch introduces
beginnings of support for reading binary ELF objects to work towards
that goal.
Added:
- elfabi tool.
- support for reading architecture from a binary ELF file into an
ELFStub.
- Support for writing .tbe files.
Differential Revision: https://reviews.llvm.org/D55352
llvm-svn: 350341
-plugin already prints an error if the name of an unknown plugin is passed.
-add-plugin used to silently ignore that, now it errors too.
Differential Revision: https://reviews.llvm.org/D56273
llvm-svn: 350340
This makes the target name consistent with how all the other unit tests are
named.
Differential Revision: https://reviews.llvm.org/D56216
llvm-svn: 350339
Summary:
Fix EntrySize, Size, and Align before doing layout calculation.
As a side cleanup, this removes a dependence on sizeof(Elf_Sym) within BinaryReader, so we can untemplatize that.
This unblocks a cleaner implementation of handling the -O<format> flag. See D53667 for a previous attempt. Actual implementation of the -O<format> flag will come in an upcoming commit, this is largely a NFC (although not _totally_ one, because alignment on binary input was actually wrong before).
Reviewers: jakehehrlich, jhenderson, alexshap, espindola
Reviewed By: jhenderson
Subscribers: emaste, arichardson, llvm-commits
Differential Revision: https://reviews.llvm.org/D56211
llvm-svn: 350336
NFC: This adds the dom tree verification under debug mode at a point
just before we start unrolling the loop. This allows us to verify dom
tree at a state where it is much smaller and before the unrolling
actually happens.
This also implies we do not need to run -verify-dom-info everytime to
see if the DT is in a valid state when we transform the loop for runtime
unrolling.
llvm-svn: 350334
Summary:
One of the LLVM optimizations, split critical edges, also clones tail
instructions. This is a dangerous operation for __syncthreads()
functions and this transformation leads to undefined behavior or
incorrect results. Patch fixes this problem by replacing __syncthreads()
function with the assembler instruction, which cost is too high and
wich cannot be copied.
Reviewers: grokos, gtbercea, kkwli0
Subscribers: guansong, openmp-commits, caomhin
Differential Revision: https://reviews.llvm.org/D56274
llvm-svn: 350333
Include CheckAtomic CMake module from LLVM in order to detect support
for atomics when building stand-alone. Otherwise,
the HAVE_CXX_ATOMICS64_WITHOUT_LIB variable is undefined and clangd
wrongly attempts to link -latomic on systems not using the library.
Original bug report: https://bugs.gentoo.org/667016
Differential Revision: https://reviews.llvm.org/D56061
llvm-svn: 350329
nvvm_barrier0.
Use runtime functions instead of the direct call to the nvvm intrinsics.
It allows to prevent some dangerous LLVM optimizations, that breaks the
code for the NVPTX target.
llvm-svn: 350328
Joel E. Denny