Skip to content

RowToColumnTests.Biggest OOM on A3000 Laptop GPU with 6 GiB  #2070

Description

@gerashegalov

Repro:

./build/build-in-docker clean install \
  -DGPU_ARCHS=NATIVE \
  -DBUILD_TESTS=ON  \
  -DskipTests  \
  -Dlibcudf.clean.skip=false

Log file contet

RowToColumnTests.Biggest
unknown file: Failure
C++ exception with description "std::bad_alloc: out_of_memory: CUDA error at: /home/user/gits/NVIDIA/spark-rapids-jni/target/libcudf-install/include/rmm/mr/device/cuda_memory_resource.hpp:60: cudaErrorMemoryAllocation out of memory" thrown in the test body.

The same test passes on Quadro RTX 6000 with 24GiB

The test hard-codes a pretty large table in absolute terms: https://github.com/NVIDIA/spark-rapids-jni/blob/6d682161683d4d0c9d72c19eab09713d2268445b/src/main/cpp/tests/row_conversion.cpp#L412-L418

(2 * 1024 * 1024) rows * 128 cols * 4 = 1GiB

which is then replicated by conversion. Presumably the smaller GPU cannot pass this test as is.

The test should fail or be skipped with a clear message indicating that the GPU under test is too small.

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions