<html>
    <head>
      <base href="https://bugs.llvm.org/">
    </head>
    <body><table border="1" cellspacing="0" cellpadding="8">
        <tr>
          <th>Bug ID</th>
          <td><a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - LLVM 11.0 & Pytorch HIP: Cannot select: t14: v2f64 = extract_subvector t11, Constant:i32<2>"
   href="https://bugs.llvm.org/show_bug.cgi?id=46067">46067</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>LLVM 11.0 & Pytorch HIP: Cannot select: t14: v2f64 = extract_subvector t11, Constant:i32<2>
          </td>
        </tr>

        <tr>
          <th>Product</th>
          <td>clang
          </td>
        </tr>

        <tr>
          <th>Version</th>
          <td>trunk
          </td>
        </tr>

        <tr>
          <th>Hardware</th>
          <td>PC
          </td>
        </tr>

        <tr>
          <th>OS</th>
          <td>Linux
          </td>
        </tr>

        <tr>
          <th>Status</th>
          <td>NEW
          </td>
        </tr>

        <tr>
          <th>Severity</th>
          <td>normal
          </td>
        </tr>

        <tr>
          <th>Priority</th>
          <td>P
          </td>
        </tr>

        <tr>
          <th>Component</th>
          <td>Driver
          </td>
        </tr>

        <tr>
          <th>Assignee</th>
          <td>unassignedclangbugs@nondot.org
          </td>
        </tr>

        <tr>
          <th>Reporter</th>
          <td>jmschrack@gmail.com
          </td>
        </tr>

        <tr>
          <th>CC</th>
          <td>llvm-bugs@lists.llvm.org, neeilans@live.com, richard-llvm@metafoo.co.uk
          </td>
        </tr></table>
      <p>
        <div>
        <pre>Built LLVM from Github source.
Trying to build a Hip-ified PyTorch from source.

[3878/4644] Building HIPCC object
caffe2/CMakeFiles/torch_hip.dir/operators/hip/torch_hip_generated_generate_proposals_op_util_nms_gpu.hip.o
FAILED:
caffe2/CMakeFiles/torch_hip.dir/operators/hip/torch_hip_generated_generate_proposals_op_util_nms_gpu.hip.o 
cd /home/skullcrab/pytorch/build/caffe2/CMakeFiles/torch_hip.dir/operators/hip
&& /usr/bin/cmake -E make_directory
/home/skullcrab/pytorch/build/caffe2/CMakeFiles/torch_hip.dir/operators/hip/.
&& /usr/bin/cmake -D verbose:BOOL=OFF -D build_configuration:STRING=RELEASE -D
generated_file:STRING=/home/skullcrab/pytorch/build/caffe2/CMakeFiles/torch_hip.dir/operators/hip/./torch_hip_generated_generate_proposals_op_util_nms_gpu.hip.o
-P
/home/skullcrab/pytorch/build/caffe2/CMakeFiles/torch_hip.dir/operators/hip/torch_hip_generated_generate_proposals_op_util_nms_gpu.hip.o.cmake
LLVM ERROR: Cannot select: t14: v2f64 = extract_subvector t11, Constant:i32<2>
  t11: v4f64,ch = CopyFromReg t0, Register:v4f64 %365
    t10: v4f64 = Register %365
  t12: i32 = Constant<2>
In function:
_ZN6caffe25utils12_GLOBAL__N_116RotatedNMSKernelEPKNS0_10RotatedBoxEifiPi
PLEASE submit a bug report to <a href="https://bugs.llvm.org/">https://bugs.llvm.org/</a> and include the crash
backtrace.
Stack dump:
0.      Program arguments: /opt/rocm-3.3.0/llvm/bin/llc
/tmp/generate_proposals_op_util_nms_gpu-45ebbd-gfx803-optimized-66393e.bc -O3
-mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -filetype=obj
-amdgpu-early-inline-all=true -amdgpu-function-calls=false -o
/tmp/generate_proposals_op_util_nms_gpu-45ebbd-gfx803-0c705d.o 
1.      Running pass 'CallGraph Pass Manager' on module
'/tmp/generate_proposals_op_util_nms_gpu-45ebbd-gfx803-optimized-66393e.bc'.
2.      Running pass 'AMDGPU DAG->DAG Pattern Instruction Selection' on
function
'@_ZN6caffe25utils12_GLOBAL__N_116RotatedNMSKernelEPKNS0_10RotatedBoxEifiPi'
 #0 0x0000000001a92a44 PrintStackTraceSignalHandler(void*)
(/opt/rocm-3.3.0/llvm/bin/llc+0x1a92a44)
 #1 0x0000000001a9052e llvm::sys::RunSignalHandlers()
(/opt/rocm-3.3.0/llvm/bin/llc+0x1a9052e)
 #2 0x0000000001a92d6c SignalHandler(int)
(/opt/rocm-3.3.0/llvm/bin/llc+0x1a92d6c)
 #3 0x00007fe28d07c890 __restore_rt
(/lib/x86_64-linux-gnu/libpthread.so.0+0x12890)
 #4 0x00007fe28bd42e97 raise
/build/glibc-OTsEL5/glibc-2.27/signal/../sysdeps/unix/sysv/linux/raise.c:51:0
 #5 0x00007fe28bd44801 abort /build/glibc-OTsEL5/glibc-2.27/stdlib/abort.c:81:0
 #6 0x0000000001a211e0
llvm::report_fatal_error(std::__cxx11::basic_string<char,
std::char_traits<char>, std::allocator<char> > const&, bool)
(/opt/rocm-3.3.0/llvm/bin/llc+0x1a211e0)
 #7 0x0000000001a211f7 (/opt/rocm-3.3.0/llvm/bin/llc+0x1a211f7)
 #8 0x00000000018f79a2 llvm::SelectionDAGISel::CannotYetSelect(llvm::SDNode*)
(/opt/rocm-3.3.0/llvm/bin/llc+0x18f79a2)
 #9 0x00000000018f6bee llvm::SelectionDAGISel::SelectCodeCommon(llvm::SDNode*,
unsigned char const*, unsigned int) (/opt/rocm-3.3.0/llvm/bin/llc+0x18f6bee)
#10 0x0000000000876b6a (anonymous
namespace)::AMDGPUDAGToDAGISel::Select(llvm::SDNode*)
(/opt/rocm-3.3.0/llvm/bin/llc+0x876b6a)
#11 0x00000000018ed73e llvm::SelectionDAGISel::DoInstructionSelection()
(/opt/rocm-3.3.0/llvm/bin/llc+0x18ed73e)
#12 0x00000000018ec5da llvm::SelectionDAGISel::CodeGenAndEmitDAG()
(/opt/rocm-3.3.0/llvm/bin/llc+0x18ec5da)
#13 0x00000000018ea1d5
llvm::SelectionDAGISel::SelectAllBasicBlocks(llvm::Function const&)
(/opt/rocm-3.3.0/llvm/bin/llc+0x18ea1d5)
#14 0x00000000018e6666
llvm::SelectionDAGISel::runOnMachineFunction(llvm::MachineFunction&)
(/opt/rocm-3.3.0/llvm/bin/llc+0x18e6666)
#15 0x0000000000875c54 (anonymous
namespace)::AMDGPUDAGToDAGISel::runOnMachineFunction(llvm::MachineFunction&)
(/opt/rocm-3.3.0/llvm/bin/llc+0x875c54)
#16 0x0000000000fe24ba
llvm::MachineFunctionPass::runOnFunction(llvm::Function&)
(/opt/rocm-3.3.0/llvm/bin/llc+0xfe24ba)
#17 0x00000000013a43de llvm::FPPassManager::runOnFunction(llvm::Function&)
(/opt/rocm-3.3.0/llvm/bin/llc+0x13a43de)
#18 0x0000000000c5c22c (anonymous
namespace)::CGPassManager::runOnModule(llvm::Module&)
(/opt/rocm-3.3.0/llvm/bin/llc+0xc5c22c)
#19 0x00000000013a4daf llvm::legacy::PassManagerImpl::run(llvm::Module&)
(/opt/rocm-3.3.0/llvm/bin/llc+0x13a4daf)
#20 0x000000000067e527 main (/opt/rocm-3.3.0/llvm/bin/llc+0x67e527)
#21 0x00007fe28bd25b97 __libc_start_main
/build/glibc-OTsEL5/glibc-2.27/csu/../csu/libc-start.c:344:0
#22 0x000000000067c05a _start (/opt/rocm-3.3.0/llvm/bin/llc+0x67c05a)
clang-11: error: unable to execute command: Aborted (core dumped)
clang-11: error: amdgcn-link command failed due to signal (use -v to see
invocation)
clang version 11.0.0 (<a href="https://github.com/llvm/llvm-project.git">https://github.com/llvm/llvm-project.git</a>
efa70843aa711802d57d1600d705a5bb51b4c740)
Target: x86_64-unknown-linux-gnu
Thread model: posix
InstalledDir: /opt/rocm-3.3.0/llvm/bin
clang-11: note: diagnostic msg: Error generating preprocessed source(s).
CMake Error at
torch_hip_generated_generate_proposals_op_util_nms_gpu.hip.o.cmake:174
(message):
  Error generating file
 
/home/skullcrab/pytorch/build/caffe2/CMakeFiles/torch_hip.dir/operators/hip/./torch_hip_generated_generate_proposals_op_util_nms_gpu.hip.o</pre>
        </div>
      </p>


      <hr>
      <span>You are receiving this mail because:</span>

      <ul>
          <li>You are on the CC list for the bug.</li>
      </ul>
    </body>
</html>