[BUG]: assertion failure in examples/basic/example.cu

[alephchang]

Is this a duplicate?

• I confirmed there appear to be no duplicate issues for this bug and that I agree to the Code of Conduct

Type of Bug

Runtime Error

Component

General CCCL

Describe the bug

build the example code and run on V100/A100/H100, but get assertion failure on A100.

How to Reproduce

1. under dir examples/basic/example
2. The compiling command: nvcc -I../../../cccl/thrust -I../../../cccl/libcudacxx/include -I../../../cccl/cub example.cu -o example -ccbin /depot/gcc-9.2.0/bin/g++ -gencode arch=compute_80,code=compute_80 -gencode arch=compute_90,code=compute_90 -gencode arch=compute_70,code=compute_70 -std=c++17
3. run the binary example on V100/H100 correctly, output

Sum: 1000

4. run the binary example on A100: assertion failure:

Sum: 512
example: example.cu:80: int main(): Assertion `result[0] == N' failed.
Abort (core dumped)

Expected behavior

the output on A100 should be like on V100/H100

Sum:1000

Reproduction link

No response

Operating System

AlmaLinux 8.4

nvidia-smi output

+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.183.06 Driver Version: 535.183.06 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA A100-SXM4-80GB On | 00000000:0A:00.0 Off | 0 |
| N/A 33C P0 64W / 400W | 0MiB / 81920MiB | 0% Default |
| | | Disabled |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| No running processes found |
+---------------------------------------------------------------------------------------+

NVCC version

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Tue_Jun_13_19:16:58_PDT_2023
Cuda compilation tools, release 12.2, V12.2.91
Build cuda_12.2.r12.2/compiler.32965470_0