[Flang] Compilation of DATA statement for large COMPLEX arrays needs a lot of memory #63610
Description
This is an issue from Fujitsu testsuite.
Flang-new terminates abnormally when compiling the following program.
When I checked with the top command, %MEM gradually increased to 100%.
It seems that a lot of memory was used.
There is no problem with gfortran compiling on the same machine.
The following are the test program, Flang-new and gfortran compilation result, and the stack trace of Flang-new.
! test.f90
complex(kind=8),dimension(1000) :: a8
complex(kind=8),dimension(1000,1000) :: b8
complex(kind=16),dimension(1000) :: a16
complex(kind=16),dimension(1000,1000) :: b16
data a8/1000*(0.0,0.0)/,a16/1000*(0.0,0.0)/
data b8/1000000*(0.0,0.0)/,b16/1000000*(0.0,0.0)/
end$ flang-new -v test.f90
flang-new version 17.0.0 (https://github.com/llvm/llvm-project.git 93af6bdcaf4d499e9d4c1da5aa82f92f0acc1dbd)
Target: aarch64-unknown-linux-gnu
Thread model: posix
InstalledDir: /path/to/install/bin
Found candidate GCC installation: /usr/lib/gcc/aarch64-redhat-linux/8
Selected GCC installation: /usr/lib/gcc/aarch64-redhat-linux/8
Candidate multilib: .;@m64
Selected multilib: .;@m64
"/path/to/install/bin/flang-new" -fc1 -triple aarch64-unknown-linux-gnu -emit-obj -fcolor-diagnostics -mrelocation-model pic -pic-level 2 -pic-is-pie -target-cpu generic -target-feature +neon -target-feature +v8a -o /tmp/test-6a351b.o -x f95-cpp-input test.f90
flang-new: error: unable to execute command: Killed
flang-new: error: flang frontend command failed due to signal (use -v to see invocation)
flang-new version 17.0.0 (https://github.com/llvm/llvm-project.git 93af6bdcaf4d499e9d4c1da5aa82f92f0acc1dbd)
Target: aarch64-unknown-linux-gnu
Thread model: posix
InstalledDir: /path/to/install/bin
flang-new: note: diagnostic msg:
********************
PLEASE ATTACH THE FOLLOWING FILES TO THE BUG REPORT:
Preprocessed source(s) and associated run script(s) are located at:
flang-new: note: diagnostic msg: /tmp/test-7d3e84
flang-new: note: diagnostic msg: /tmp/test-7d3e84.sh
flang-new: note: diagnostic msg:
********************
$ gfortran -v test.f90
Driving: gfortran -v test.f90 -l gfortran -l m -shared-libgcc
Using built-in specs.
COLLECT_GCC=gfortran
COLLECT_LTO_WRAPPER=/usr/libexec/gcc/aarch64-redhat-linux/8/lto-wrapper
Target: aarch64-redhat-linux
Configured with: ../configure --enable-bootstrap --enable-languages=c,c++,fortran,lto --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-shared --enable-threads=posix --enable-checking=release --enable-multilib --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-gnu-unique-object --enable-linker-build-id --with-gcc-major-version-only --with-linker-hash-style=gnu --enable-plugin --enable-initfini-array --with-isl --disable-libmpx --enable-gnu-indirect-function --build=aarch64-redhat-linux
Thread model: posix
gcc version 8.3.1 20190507 (Red Hat 8.3.1-4) (GCC)
:
$
#0 llvm::rotr<unsigned long, void> (V=2994594782533612773, R=44)
at /path/to/llvm-project/llvm/include/llvm/ADT/bit.h:378
#1 0x00007ffff0406d07 in llvm::hashing::detail::hash_state::mix_32_bytes (s=0x555573085270 "0\272eXUU",
a=@0x7fffffffa0a8: 2994594782533612773, b=@0x7fffffffa0b0: 2397334626997450193)
at /path/to/llvm-project/llvm/include/llvm/ADT/Hashing.h:295
#2 0x00007ffff0406ec3 in llvm::hashing::detail::hash_state::mix (this=0x7fffffffa090, s=0x555573085270 "0\272eXUU")
at /path/to/llvm-project/llvm/include/llvm/ADT/Hashing.h:310
#3 0x00007ffff0406c30 in llvm::hashing::detail::hash_state::create (s=0x555573085270 "0\272eXUU",
seed=18397679294719823053) at /path/to/llvm-project/llvm/include/llvm/ADT/Hashing.h:283
#4 0x00007ffff04a1366 in llvm::hashing::detail::hash_combine_range_impl<llvm::Constant* const> (first=0x555573085270,
last=0x5555730871b0) at /path/to/llvm-project/llvm/include/llvm/ADT/Hashing.h:468
#5 0x00007ffff049c677 in llvm::hash_combine_range<llvm::Constant* const*> (first=0x555573085270, last=0x5555730871b0)
at /path/to/llvm-project/llvm/include/llvm/ADT/Hashing.h:492
#6 0x00007ffff04a7c86 in llvm::ConstantAggrKeyType<llvm::ConstantArray>::getHash (this=0x7fffffffa1b8)
at /path/to/llvm-project/llvm/lib/IR/ConstantsContext.h:338
#7 0x00007ffff04a274b in llvm::ConstantUniqueMap<llvm::ConstantArray>::MapInfo::getHashValue (Val={...})
at /path/to/llvm-project/llvm/lib/IR/ConstantsContext.h:549
#8 0x00007ffff049d449 in llvm::ConstantUniqueMap<llvm::ConstantArray>::getOrCreate (this=0x5555555d8b70,
Ty=0x555558681880, V=...) at /path/to/llvm-project/llvm/lib/IR/ConstantsContext.h:599
#9 0x00007ffff048abd7 in llvm::ConstantArray::get (Ty=0x555558681880, V=...)
at /path/to/llvm-project/llvm/lib/IR/Constants.cpp:1238
#10 0x00007ffff0467493 in llvm::ConstantFoldInsertValueInstruction (Agg=0x555a2c3138e0, Val=0x55555852ccd0, Idxs=...)
at /path/to/llvm-project/llvm/lib/IR/ConstantFold.cpp:802
#11 0x00007ffff062802a in llvm::ConstantFolder::FoldInsertValue (this=0x7fffffffba78, Agg=0x555a2c3138e0,
Val=0x55555852ccd0, IdxList=...) at /path/to/llvm-project/llvm/include/llvm/IR/ConstantFolder.h:145
#12 0x00007fffe1460a71 in llvm::IRBuilderBase::CreateInsertValue (this=0x7fffffffba00, Agg=0x555a2c3138e0,
Val=0x55555852ccd0, Idxs=..., Name=...) at /path/to/llvm-project/llvm/include/llvm/IR/IRBuilder.h:2436
#13 0x00007fffe1436283 in convertOperationImpl (opInst=..., builder=..., moduleTranslation=...)
at /path/to/install/tools/mlir/include/mlir/Dialect/LLVMIR/LLVMConversions.inc:207
#14 0x00007fffe144f82d in (anonymous namespace)::LLVMDialectLLVMIRTranslationInterface::convertOperation (
this=0x5555555ee360, op=0x555563908280, builder=..., moduleTranslation=...)
at /path/to/llvm-project/mlir/lib/Target/LLVMIR/Dialect/LLVMIR/LLVMToLLVMIRTranslation.cpp:384
#15 0x00007fffe550ed13 in mlir::LLVM::ModuleTranslation::convertOperation (this=0x7fffffffbcc0, op=..., builder=...)
at /path/to/llvm-project/mlir/lib/Target/LLVMIR/ModuleTranslation.cpp:612
#16 0x00007fffe550fb60 in mlir::LLVM::ModuleTranslation::convertGlobals (this=0x7fffffffbcc0)
at /path/to/llvm-project/mlir/lib/Target/LLVMIR/ModuleTranslation.cpp:760
#17 0x00007fffe551435a in mlir::translateModuleToLLVMIR (module=0x5555584d0a10, llvmContext=..., name=...)
at /path/to/llvm-project/mlir/lib/Target/LLVMIR/ModuleTranslation.cpp:1403
#18 0x00007ffff6c74542 in Fortran::frontend::CodeGenAction::generateLLVMIR (this=0x5555555a1080)
at /path/to/llvm-project/flang/lib/Frontend/FrontendActions.cpp:721
#19 0x00007ffff6c75b4a in Fortran::frontend::CodeGenAction::executeAction (this=0x5555555a1080)
at /path/to/llvm-project/flang/lib/Frontend/FrontendActions.cpp:965
#20 0x00007ffff6c6d1d8 in Fortran::frontend::FrontendAction::execute (this=0x5555555a1080)
at /path/to/llvm-project/flang/lib/Frontend/FrontendAction.cpp:112
#21 0x00007ffff6c46f01 in Fortran::frontend::CompilerInstance::executeAction (this=0x55555558e630, act=...)
at /path/to/llvm-project/flang/lib/Frontend/CompilerInstance.cpp:167
#22 0x00007ffff7566a35 in Fortran::frontend::executeCompilerInvocation (flang=0x55555558e630)
at /path/to/llvm-project/flang/lib/FrontendTool/ExecuteCompilerInvocation.cpp:174
#23 0x00005555555631a0 in fc1_main (argv=...,
argv0=0x7fffffffe30f "/path/to/install/bin/flang-new")
at /path/to/llvm-project/flang/tools/flang-driver/fc1_main.cpp:67
#24 0x0000555555558031 in executeFC1Tool (argV=...)
at /path/to/llvm-project/flang/tools/flang-driver/driver.cpp:68
#25 0x0000555555558506 in main (argc=22, argv=0x7fffffffdfe8)
at /path/to/llvm-project/flang/tools/flang-driver/driver.cpp:111
The following is a similar program but an array size is smaller.
! small_test.f90
complex :: a(100)
data a/100*(0.0,0.0)/
endThat can be compiled normally, but Flang generates large MLIR with LLVM dialect.
I suspect this is the cause of the abnormal termination.
$ flang-new -Xflang -save-temps small_test.f90
$ cat small_test-llvmir.mlir
module attributes {dlti.dl_spec = #dlti.dl_spec<#dlti.dl_entry<i16, dense<[16, 32]> : vector<2xi32>>, #dlti.dl_entry<i64, dense<64> : vector<2xi32>>, #dlti.dl_entry<i128, dense<128> : vector<2xi32>>, #dlti.dl_entry<!llvm.ptr, dense<64> : vector<4xi32>>, #dlti.dl_entry<i1, dense<8> : vector<2xi32>>, #dlti.dl_entry<f16, dense<16> : vector<2xi32>>, #dlti.dl_entry<i32, dense<32> : vector<2xi32>>, #dlti.dl_entry<f64, dense<64> : vector<2xi32>>, #dlti.dl_entry<i8, dense<[8, 32]> : vector<2xi32>>, #dlti.dl_entry<f128, dense<128> : vector<2xi32>>, #dlti.dl_entry<"dlti.stack_alignment", 128 : i32>, #dlti.dl_entry<"dlti.endianness", "little">>, fir.defaultkind = "a1c4d8i4l4r4", fir.kindmap = "", llvm.data_layout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128", llvm.target_triple = "aarch64-unknown-linux-gnu"} {
llvm.func @_QQmain() {
llvm.return
}
llvm.mlir.global internal @_QFEa() {addr_space = 0 : i32} : !llvm.array<100 x struct<(f32, f32)>> {
%0 = llvm.mlir.constant(0.000000e+00 : f32) : f32
%1 = llvm.mlir.undef : !llvm.array<100 x struct<(f32, f32)>>
%2 = llvm.mlir.undef : !llvm.struct<(f32, f32)>
%3 = llvm.insertvalue %0, %2[0] : !llvm.struct<(f32, f32)>
%4 = llvm.insertvalue %0, %3[1] : !llvm.struct<(f32, f32)>
%5 = llvm.insertvalue %4, %1[0] : !llvm.array<100 x struct<(f32, f32)>>
%6 = llvm.insertvalue %4, %5[1] : !llvm.array<100 x struct<(f32, f32)>>
%7 = llvm.insertvalue %4, %6[2] : !llvm.array<100 x struct<(f32, f32)>>
%8 = llvm.insertvalue %4, %7[3] : !llvm.array<100 x struct<(f32, f32)>>
%9 = llvm.insertvalue %4, %8[4] : !llvm.array<100 x struct<(f32, f32)>>
%10 = llvm.insertvalue %4, %9[5] : !llvm.array<100 x struct<(f32, f32)>>
%11 = llvm.insertvalue %4, %10[6] : !llvm.array<100 x struct<(f32, f32)>>
:
%103 = llvm.insertvalue %4, %102[98] : !llvm.array<100 x struct<(f32, f32)>>
%104 = llvm.insertvalue %4, %103[99] : !llvm.array<100 x struct<(f32, f32)>>
llvm.return %104 : !llvm.array<100 x struct<(f32, f32)>>
}
llvm.mlir.global external constant @_QQEnvironmentDefaults() {addr_space = 0 : i32} : !llvm.ptr<struct<(i32, ptr<array<0 x struct<(ptr<i8>, ptr<i8>)>>>)>> {
%0 = llvm.mlir.null : !llvm.ptr<struct<(i32, ptr<array<0 x struct<(ptr<i8>, ptr<i8>)>>>)>>
llvm.return %0 : !llvm.ptr<struct<(i32, ptr<array<0 x struct<(ptr<i8>, ptr<i8>)>>>)>>
}
llvm.func @llvm.stacksave() -> !llvm.ptr<i8> attributes {sym_visibility = "private"}
llvm.func @llvm.stackrestore(!llvm.ptr<i8>) attributes {sym_visibility = "private"}
}