Avimitin wrote:
I encountered a clang compiler crash (segmentation fault) when attempting to
compile the `utf8_count.c` benchmark from the `rvv-bench` project
([https://github.com/camel-cdr/rvv-bench/blob/main/bench/utf8\_count.c](https://github.com/camel-cdr/rvv-bench/blob/main/bench/utf8_count.c))
using clang build from this branch. The crash occurs during the 'RISC-V
DAG-\>DAG Pattern Instruction Selection' pass.
**Steps to Reproduce:**
1. Obtain the `utf8_count.c` file from the `rvv-bench` project (or use the
minimal C code provided below).
2. Compile the C code with the following command:
```bash
riscv32-none-elf-clang -mabi=ilp32f
-march=rv32imafc_xsfmm128t_zve32f_zvl2048b -mno-relax -static -nostartfiles
-mcmodel=medany -fvisibility=hidden -fno-PIC -g -O3 -fno-rtti -fno-exceptions
-fno-threadsafe-statics -c utf8_count.c -o utf8_count.o
```
**Error Log:**
<details>
<summary>Compiler Error Output</summary>
```console
$ riscv32-none-elf-clang -mabi=ilp32f
-march=rv32imafc_xsfmm128t_zve32f_zvl2048b -mno-relax -static -nostartfiles
-mcmodel=medany -fvisibility=hidden -fno-PIC -g -O3 -fno-rtti -fno-exceptions
-fno-threadsafe-statics -c test.c -o test.o
PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and
include the crash backtrace, preprocessed source, and associated run script.
Stack dump:
0. Program arguments:
/nix/store/4b17xsrdcyd2bnm91pdclfw2wz3g0ikg-clang-21.0.0-unstable-2025-03-23/bin/clang
@/tmp/nix-shell.VojIba/cc-params.249Z4g
1. <eof> parser at end of file
2. Code generation
3. Running pass 'Function Pass Manager' on module 'utf8_count.c'.
4. Running pass 'RISC-V DAG->DAG Pattern Instruction Selection' on
function '@utf8_count_SWAR_popc_bithack_autovec'
Stack dump without symbol names (ensure you have llvm-symbolizer in your PATH
or set the environment var `LLVM_SYMBOLIZER_PATH` to point to it):
0 libLLVM.so.21.0git 0x00007fffea78aa0c
llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) + 60
1 libLLVM.so.21.0git 0x00007fffea788774
llvm::sys::CleanupOnSignal(unsigned long) + 148
2 libLLVM.so.21.0git 0x00007fffea668a88
3 libc.so.6 0x00007fffe8e40f30
4 libLLVM.so.21.0git 0x00007fffea9f4454
llvm::ScalableVectorType::get(llvm::Type*, unsigned int) + 20
5 libLLVM.so.21.0git 0x00007fffeb0d2c50
llvm::EVT::getExtendedVectorVT(llvm::LLVMContext&, llvm::EVT,
llvm::ElementCount) + 48
6 libLLVM.so.21.0git 0x00007fffeb35a250
7 libLLVM.so.21.0git 0x00007fffeb35c008
8 libLLVM.so.21.0git 0x00007fffeb2fd970
9 libLLVM.so.21.0git 0x00007fffeb2fe3a9
llvm::SelectionDAG::LegalizeTypes() + 1321
10 libLLVM.so.21.0git 0x00007fffeb47af5f
llvm::SelectionDAGISel::CodeGenAndEmitDAG() + 271
11 libLLVM.so.21.0git 0x00007fffeb47dc5a
llvm::SelectionDAGISel::SelectAllBasicBlocks(llvm::Function const&) + 5274
12 libLLVM.so.21.0git 0x00007fffeb47fb99
llvm::SelectionDAGISel::runOnMachineFunction(llvm::MachineFunction&) + 217
13 libLLVM.so.21.0git 0x00007fffeb46e8e9
llvm::SelectionDAGISelLegacy::runOnMachineFunction(llvm::MachineFunction&) + 409
14 libLLVM.so.21.0git 0x00007fffead5e853
15 libLLVM.so.21.0git 0x00007fffea972d89
llvm::FPPassManager::runOnFunction(llvm::Function&) + 1705
16 libLLVM.so.21.0git 0x00007fffea972f3c
llvm::FPPassManager::runOnModule(llvm::Module&) + 44
17 libLLVM.so.21.0git 0x00007fffea971f69
llvm::legacy::PassManagerImpl::run(llvm::Module&) + 1081
18 libclang-cpp.so.21.0git 0x00007ffff5cc47f4
clang::emitBackendOutput(clang::CompilerInstance&, clang::CodeGenOptions&,
llvm::StringRef, llvm::Module*, clang::BackendAction,
llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem>,
std::unique_ptr<llvm::raw_pwrite_stream,
std::default_delete<llvm::raw_pwrite_stream>>, clang::BackendConsumer*) + 2772
19 libclang-cpp.so.21.0git 0x00007ffff60764bc
clang::BackendConsumer::HandleTranslationUnit(clang::ASTContext&) + 1692
20 libclang-cpp.so.21.0git 0x00007ffff4616eec clang::ParseAST(clang::Sema&,
bool, bool) + 1212
21 libclang-cpp.so.21.0git 0x00007ffff6a79928 clang::FrontendAction::Execute()
+ 40
22 libclang-cpp.so.21.0git 0x00007ffff69eec13
clang::CompilerInstance::ExecuteAction(clang::FrontendAction&) + 1475
23 libclang-cpp.so.21.0git 0x00007ffff6b1b11b
clang::ExecuteCompilerInvocation(clang::CompilerInstance*) + 539
24 clang 0x000000000041670a cc1_main(llvm::ArrayRef<char
const*>, char const*, void*) + 7306
25 clang 0x000000000040e8f3
26 libclang-cpp.so.21.0git 0x00007ffff65d9a99
27 libLLVM.so.21.0git 0x00007fffea668e93
llvm::CrashRecoveryContext::RunSafely(llvm::function_ref<void ()>) + 35
28 libclang-cpp.so.21.0git 0x00007ffff65da545
29 libclang-cpp.so.21.0git 0x00007ffff659966c
clang::driver::Compilation::ExecuteCommand(clang::driver::Command const&,
clang::driver::Command const*&, bool) const + 172
30 libclang-cpp.so.21.0git 0x00007ffff659a652
clang::driver::Compilation::ExecuteJobs(clang::driver::JobList const&,
llvm::SmallVectorImpl<std::pair<int, clang::driver::Command const*>>&, bool)
const + 146
31 libclang-cpp.so.21.0git 0x00007ffff65b017c
clang::driver::Driver::ExecuteCompilation(clang::driver::Compilation&,
llvm::SmallVectorImpl<std::pair<int, clang::driver::Command const*>>&) + 364
32 clang 0x00000000004132f4 clang_main(int, char**,
llvm::ToolContext const&) + 8308
33 clang 0x000000000040e2b4 main + 100
34 libc.so.6 0x00007fffe8e2a1fe
35 libc.so.6 0x00007fffe8e2a2b9 __libc_start_main + 137
36 clang 0x000000000040e315 _start + 37
clang: error: clang frontend command failed with exit code 139 (use -v to see
invocation)
clang version 21.0.0git
Target: riscv32-unknown-none-elf
Thread model: posix
InstalledDir:
/nix/store/4b17xsrdcyd2bnm91pdclfw2wz3g0ikg-clang-21.0.0-unstable-2025-03-23/bin
clang: note: diagnostic msg:
********************
PLEASE ATTACH THE FOLLOWING FILES TO THE BUG REPORT:
Preprocessed source(s) and associated run script(s) are located at:
clang: note: diagnostic msg: /tmp/nix-shell.VojIba/utf8_count-cefc8d.c
clang: note: diagnostic msg: /tmp/nix-shell.VojIba/utf8_count-cefc8d.sh
clang: note: diagnostic msg:
********************
```
</details>
**Minimal Reproducible C Code:**
The crash appears to be triggered by the `utf8_count_SWAR_popc_bithack_autovec`
function.
<details>
<summary>Reproduce C code (test.c)</summary>
```c
#include <limits.h>
#include <stdint.h>
#include <stddef.h>
#include <float.h>
typedef uint32_t ux;
static inline int upopcnt(ux x)
{
x -= (x >> 1) & (-(ux)1/3);
x = (x & (-(ux)1/15*3)) + ((x >> 2) & (-(ux)1/15*3));
x = (x + (x >> 4)) & (-(ux)1/255*15);
({__asm volatile("" : "+r"(x) : "r"(x) : "memory");});
x += (x >> 8);
x += (x >> 16);
;
return x & 127;
}
size_t utf8_count_SWAR_popc_bithack_autovec(char const *str, size_t len) {
ux const __attribute__((__may_alias__)) * u;
size_t count = 0, tail = 0;
uint8_t const *u8 = (uint8_t const *)str;
if (len < sizeof *u) {
tail = len;
goto skip;
}
tail = sizeof *u - (uintptr_t)str % sizeof *u;
len -= tail;
while (tail--)
count += (*u8++ & 0xC0) != 0x80, (void)0;
u = (ux const *)u8;
tail = len % sizeof *u;
for (len /= sizeof *u; len--; ++u) {
ux b1 = ~*u & (ux)0x80808080;
ux b2 = *u & (ux)0x40404040;
count += upopcnt((b1 >> 1) | b2);
(void)0;
}
u8 = (uint8_t const *)u;
skip:
while (tail--)
count += (*u8++ & 0xC0) != 0x80, (void)0;
return count;
}
```
</details>
**Compiler Flags Used:**
```text
-mabi=ilp32f -march=rv32imafc_xsfmm128t_zve32f_zvl2048b -mno-relax -static
-nostartfiles -mcmodel=medany -fvisibility=hidden -fno-PIC -g -O3 -fno-rtti
-fno-exceptions -fno-threadsafe-statics
```
https://github.com/llvm/llvm-project/pull/133031
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
