reduction got accuracy issue on large tensor cases #2008
Description
🐛 Describe the bug
Platform: PVC Linux
Cases:
test/test_nn.py::TestNNDeviceTypeXPU::test_avg_pool_large_tensor2_xpu || op_ut
test/test_nn.py::TestNNDeviceTypeXPU::test_nll_loss_large_tensor_reduction_mean_xpu || op_ut
test/test_nn.py::TestNNDeviceTypeXPU::test_nll_loss_large_tensor_reduction_sum_xpu || op_ut
test/test_nn.py::TestNNDeviceTypeXPU::test_reductions_large_half_tensors_xpu_complex32 || op_ut
025-09-01T23:24:56.1459400Z ______ TestNNDeviceTypeXPU.test_nll_loss_large_tensor_reduction_mean_xpu _______
2025-09-01T23:24:56.1459778Z [gw4] linux -- Python 3.10.18 /tmp/xpu-tool/Python/3.10.18/x64/bin/python
2025-09-01T23:24:56.1460070Z Traceback (most recent call last):
2025-09-01T23:24:56.1460609Z File "/__w/torch-xpu-ops/torch-xpu-ops/pytorch/third_party/torch-xpu-ops/test/xpu/../../../../test/test_nn.py", line 12100, in test_nll_loss_large_tensor
2025-09-01T23:24:56.1461192Z self.assertTrue(torch.allclose(out.cpu(), out_cpu, rtol=rtol, atol=atol))
2025-09-01T23:24:56.1461640Z File "/tmp/xpu-tool/Python/3.10.18/x64/lib/python3.10/unittest/case.py", line 687, in assertTrue
2025-09-01T23:24:56.1462015Z raise self.failureException(msg)
2025-09-01T23:24:56.1462253Z AssertionError: False is not true
2025-09-01T23:24:56.1462392Z
2025-09-01T23:24:56.1463839Z _______ TestNNDeviceTypeXPU.test_nll_loss_large_tensor_reduction_sum_xpu _______
2025-09-01T23:24:56.1464215Z [gw4] linux -- Python 3.10.18 /tmp/xpu-tool/Python/3.10.18/x64/bin/python
2025-09-01T23:24:56.1464493Z Traceback (most recent call last):
2025-09-01T23:24:56.1464985Z File "/__w/torch-xpu-ops/torch-xpu-ops/pytorch/third_party/torch-xpu-ops/test/xpu/../../../../test/test_nn.py", line 12100, in test_nll_loss_large_tensor
2025-09-01T23:24:56.1465531Z self.assertTrue(torch.allclose(out.cpu(), out_cpu, rtol=rtol, atol=atol))
2025-09-01T23:24:56.1465978Z File "/tmp/xpu-tool/Python/3.10.18/x64/lib/python3.10/unittest/case.py", line 687, in assertTrue
2025-09-01T23:24:56.1466337Z raise self.failureException(msg)
2025-09-01T23:24:56.1466571Z AssertionError: False is not true
2025-09-01T23:24:56.1466708Z
2025-09-01T23:29:03.2092139Z ______ TestReductionsXPU.test_reductions_large_half_tensors_xpu_complex32 ______
2025-09-01T23:29:03.2092503Z [gw5] linux -- Python 3.10.18 /tmp/xpu-tool/Python/3.10.18/x64/bin/python
2025-09-01T23:29:03.2092780Z Traceback (most recent call last):
2025-09-01T23:29:03.2093292Z File "/__w/torch-xpu-ops/torch-xpu-ops/pytorch/third_party/torch-xpu-ops/test/xpu/../../../../test/test_reductions.py", line 3731, in test_reductions_large_half_tensors
2025-09-01T23:29:03.2093840Z self.assertEqual(torch.sum(t), expected)
2025-09-01T23:29:03.2094302Z File "/tmp/xpu-tool/Python/3.10.18/x64/lib/python3.10/site-packages/torch/testing/_internal/common_utils.py", line 4179, in assertEqual
2025-09-01T23:29:03.2094802Z raise error_metas.pop()[0].to_error( # type: ignore[index]
2025-09-01T23:29:03.2095071Z AssertionError: Scalars are not close!
2025-09-01T23:29:03.2095213Z
2025-09-01T23:29:03.2095327Z Expected 0j but got (inf+0j).
2025-09-01T23:29:03.2095555Z Absolute difference: inf (up to 1e-05 allowed)
2025-09-01T23:29:03.2095809Z Relative difference: inf (up to 0.001 allowed)
Versions
Versions
branch: main
Collecting environment information...
PyTorch version: 2.9.0a0+git6737e2c
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.5 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 4.0.0
Libc version: glibc-2.35
Python version: 3.10.18 | packaged by conda-forge | (main, Jun 4 2025, 14:45:41) [GCC 13.3.0] (64-bit runtime)
Python platform: Linux-5.15.0-73-generic-x86_64-with-glibc2.35
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
Is XPU available: True
XPU used to build PyTorch: 20250201
Intel GPU driver version:
- libze1: 1.20.2.0-1098~22.04
- intel-opencl-icd: 25.05.32567.19-1099~22.04
- level-zero: 1.0.0-92~u22.04
Intel GPU models onboard: - Intel(R) Data Center GPU Max 1550
Intel GPU models detected: - [0] _XpuDeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) oneAPI Unified Runtime over Level-Zero', type='gpu', device_id=0xBD5, driver_version='1.6.32567+19', total_memory=65536MB, max_compute_units=512, gpu_eu_count=512, gpu_subslice_count=64, max_work_group_size=1024, max_num_sub_groups=64, sub_group_sizes=[16 32], has_fp16=1, has_fp64=1, has_atomic64=1)
- [1] _XpuDeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) oneAPI Unified Runtime over Level-Zero', type='gpu', device_id=0xBD5, driver_version='1.6.32567+19', total_memory=65536MB, max_compute_units=512, gpu_eu_count=512, gpu_subslice_count=64, max_work_group_size=1024, max_num_sub_groups=64, sub_group_sizes=[16 32], has_fp16=1, has_fp64=1, has_atomic64=1)
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 48
On-line CPU(s) list: 0-47
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Gold 6342 CPU @ 2.80GHz
CPU family: 6
Model: 106
Thread(s) per core: 2
Core(s) per socket: 24
Socket(s): 1
Stepping: 6
CPU max MHz: 3500.0000
CPU min MHz: 800.0000
BogoMIPS: 5600.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 invpcid_single intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 1.1 MiB (24 instances)
L1i cache: 768 KiB (24 instances)
L2 cache: 30 MiB (24 instances)
L3 cache: 36 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-47
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Retbleed: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] dpcpp-cpp-rt==2025.2.1
[pip3] impi-rt==2021.16.1
[pip3] intel-cmplr-lib-rt==2025.2.1
[pip3] intel-cmplr-lib-ur==2025.2.1
[pip3] intel-cmplr-lic-rt==2025.2.1
[pip3] intel-opencl-rt==2025.2.1
[pip3] intel-openmp==2025.2.1
[pip3] intel-pti==0.13.1
[pip3] intel-sycl-rt==2025.2.1
[pip3] mkl==2025.2.0
[pip3] mypy==1.16.0
[pip3] mypy_extensions==1.1.0
[pip3] numpy==1.22.4
[pip3] oneccl==2021.16.1
[pip3] oneccl-devel==2021.16.1
[pip3] onemkl-sycl-blas==2025.2.0
[pip3] onemkl-sycl-dft==2025.2.0
[pip3] onemkl-sycl-lapack==2025.2.0
[pip3] onemkl-sycl-rng==2025.2.0
[pip3] onemkl-sycl-sparse==2025.2.0
[pip3] onnx==1.18.0
[pip3] onnx-ir==0.1.7
[pip3] onnxscript==0.4.0
[pip3] optree==0.13.0
[pip3] pytorch-triton-xpu==3.4.0+gitd0e80f39
[pip3] tbb==2022.2.0
[pip3] tcmlib==1.4.0
[pip3] torch==2.9.0a0+git6737e2c
[pip3] torchaudio==2.8.0a0+1c66402
[pip3] torchvision==0.22.0a0+966da7e
[pip3] umf==0.11.0
[conda] dpcpp-cpp-rt 2025.2.1 pypi_0 pypi
[conda] impi-rt 2021.16.1 pypi_0 pypi
[conda] intel-cmplr-lib-rt 2025.2.1 pypi_0 pypi
[conda] intel-cmplr-lib-ur 2025.2.1 pypi_0 pypi
[conda] intel-cmplr-lic-rt 2025.2.1 pypi_0 pypi
[conda] intel-opencl-rt 2025.2.1 pypi_0 pypi
[conda] intel-openmp 2025.2.1 pypi_0 pypi
[conda] intel-pti 0.13.1 pypi_0 pypi
[conda] intel-sycl-rt 2025.2.1 pypi_0 pypi
[conda] mkl 2025.2.0 pypi_0 pypi
[conda] numpy 1.22.4 pypi_0 pypi
[conda] oneccl 2021.16.1 pypi_0 pypi
[conda] oneccl-devel 2021.16.1 pypi_0 pypi
[conda] onemkl-sycl-blas 2025.2.0 pypi_0 pypi
[conda] onemkl-sycl-dft 2025.2.0 pypi_0 pypi
[conda] onemkl-sycl-lapack 2025.2.0 pypi_0 pypi
[conda] onemkl-sycl-rng 2025.2.0 pypi_0 pypi
[conda] onemkl-sycl-sparse 2025.2.0 pypi_0 pypi
[conda] optree 0.13.0 pypi_0 pypi
[conda] pytorch-triton-xpu 3.4.0+gitd0e80f39 pypi_0 pypi
[conda] tbb 2022.2.0 pypi_0 pypi
[conda] tcmlib 1.4.0 pypi_0 pypi
[conda] torch 2.9.0a0+git6737e2c pypi_0 pypi
[conda] torchaudio 2.8.0a0+1c66402 pypi_0 pypi
[conda] torchvision 0.22.0a0+966da7e pypi_0 pypi
[conda] umf 0.11.0 pypi_0 pypi