8000 Inconsistent overflow handling in `torch.clamp_min` between CPU and CUDA for float16 tensors · Issue #153187 · pytorch/pytorch · GitHub
[go: up one dir, main page]
Skip to content

Inconsistent overflow handling in torch.clamp_min between CPU and CUDA for float16 tensors #153187

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
SilentTester73 opened this issue May 8, 2025 · 1 comment
Open

Inconsistent overflow handling in torch.clamp_min between CPU and CUDA for float16 tensors #153187

SilentTester73 opened this issue May 8, 2025 · 1 comment
Labels
module: edge cases Adversarial inputs unlikely to occur in practice triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module

Comments

@SilentTester73
Copy link

🐛 Describe the bug

Description

There is an inconsistency in how torch.clamp_min handles large values that exceed float16 range between CPU and CUDA implementations:

  • On CPU: When using a value that exceeds float16 range, an exception is raised with the message "value cannot be converted to type at::Half without overflow"
  • On CUDA: The same operation silently succeeds and converts all values to infinity

Reproduction

import torch

# Simple test case
tensor_data = [
    [1.0, float('nan')],
    [-1.0, 0.0]
]

# Test on CPU - raises exception
try:
    cpu_tensor = torch.tensor(tensor_data, dtype=torch.float16)
    result = torch.clamp_min(cpu_tensor, 4.35294e+26)
    print("CPU result:", result)
except RuntimeError as e:
    print(f"CPU error: {e}")

# Test on CUDA - silently succeeds with inf values
if torch.cuda.is_available():
    cuda_tensor = torch.tensor(tensor_data, device='cuda', dtype=torch.float16)
    result = torch.clamp_min(cuda_tensor, 4.35294e+26)
    print("CUDA result:", result)

Output

CPU error: value cannot be converted to type at::Half without overflow
CUDA result: tensor([[inf, nan],
        [inf, inf]], device='cuda:0', dtype=torch.float16)

Colab Notebook

A complete reproduction is available in this Colab notebook: https://colab.research.google.com/drive/1Tgb1jxqCO0eAWXDDTufCm5wg9PuhIYkH?usp=sharing

Versions

Collecting environment information...
PyTorch version: 2.7.0+cu126
Is debug build: False
CUDA used to build PyTorch: 12.6
ROCM used to build PyTorch: N/A

OS: Ubuntu 24.04.1 LTS (x86_64)
GCC version: (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
Clang version: 18.1.8 (++20240731025043+3b5b5c1ec4a3-1~exp1~20240731145144.92)
CMake version: version 4.0.0
Libc version: glibc-2.39

Python version: 3.12.3 (main, Feb  4 2025, 14:48:35) [GCC 13.3.0] (64-bit runtime)
Python platform: Linux-6.8.0-59-generic-x86_64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: 12.8.93
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 4090
Nvidia driver version: 570.133.20
cuDNN version: Could not collect
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:                        39 bits physical, 48 bits virtual
Byte Order:                           Little Endian
CPU(s):                               32
On-line CPU(s) list:                  0-31
Vendor ID:                            GenuineIntel
Model name:                           13th Gen Intel(R) Core(TM) i9-13900F
CPU family:                           6
Model:                                183
Thread(s) per core:                   2
Core(s) per socket:                   24
Socket(s):                            1
Stepping:                             1
CPU(s) scaling MHz:                   20%
CPU max MHz:                          5600.0000
CPU min MHz:                          800.0000
BogoMIPS:                             3993.60
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 tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 sdbg fma cx16 xtpr pdcm sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb intel_pt sha_ni xsaveopt xsavec xgetbv1 xsaves split_lock_detect user_shstk avx_vnni dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp hwp_pkg_req hfi vnmi umip pku ospke waitpkg gfni vaes vpclmulqdq rdpid movdiri movdir64b fsrm md_clear serialize arch_lbr ibt flush_l1d arch_capabilities
Virtualization:                       VT-x
L1d cache:                            896 KiB (24 instances)
L1i cache:                            1.3 MiB (24 instances)
L2 cache:                             32 MiB (12 instances)
L3 cache:                             36 MiB (1 instance)
NUMA node(s):                         1
NUMA node0 CPU(s):                    0-31
Vulnerability Gather data sampling:   Not affected
Vulnerability Itlb multihit:          Not affected
Vulnerability L1tf:                   Not affected
Vulnerability Mds:                    Not affected
Vulnerability Meltdown:               Not affected
Vulnerability Mmio stale data:        Not affected
Vulnerability Reg file data sampling: Mitigation; Clear Register File
Vulnerability Retbleed:               Not affected
Vulnerability Spec rstack overflow:   Not affected
Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[pip3] numpy==2.2.5
[pip3] nvidia-cublas-cu12==12.6.4.1
[pip3] nvidia-cuda-cupti-cu12==12.6.80
[pip3] nvidia-cuda-nvrtc-cu12==12.6.77
[pip3] nvidia-cuda-runtime-cu12==12.6.77
[pip3] nvidia-cudnn-cu12==9.5.1.17
[pip3] nvidia-cufft-cu12==11.3.0.4
[pip3] nvidia-curand-cu12==10.3.7.77
[pip3] nvidia-cusolver-cu12==11.7.1.2
[pip3] nvidia-cusparse-cu12==12.5.4.2
[pip3] nvidia-cusparselt-cu12==0.6.3
[pip3] nvidia-nccl-cu12==2.26.2
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvtx-cu12==12.6.77
[pip3] optree==0.15.0
[pip3] torch==2.7.0
[pip3] triton==3.3.0
[conda] Could not collect
@ngimel ngimel added the module: edge cases Adversarial inputs unlikely to occur in practice label May 9, 2025
@colesbury colesbury added the triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module label May 13, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
module: edge cases Adversarial inputs unlikely to occur in practice triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@colesbury @ngimel @SilentTester73
0