CUDA Toolkit 4.1/4.2: nvcc Crashes with an Access Violation

Question

I am developing a CUDA application for GTX 580 with Visual Studio 2010 Professional on Windows 7 64bit. My project builds fine with CUDA Toolkit 4.0, but nvcc crashes when I choose CUDA Toolkit 4.1 or 4.2 with the following error:

1> Stack dump:
1> 0. Running pass 'Promote Constant Global' on module 'moduleOutput'.
1>CUDACOMPILE : nvcc error : 'cicc' died with status 0xC0000005 (ACCESS_VIOLATION)

Strangely enough, the program compiles OK with "compute_10,sm_10" specified for "Code Generation", but "compute_20,sm_20" does not work. The code in question can be downloaded here:

http://www.meriken2ch.com/files/CUDA_SHA-1_Tripper_MERIKENs_Branch_0.04_Alpha_1.zip

(README.txt is in Japanese, but comments in source files are in English.)

I am suspecting a newly introduced bug in CUDA Toolkit 4.1/4.2. Has anybody encountered this issue? Is there any workaround for it? Any kind of help will be much appreciated.

Can you please try the publicly available CUDA 5.0 RC to see if this problem still exists and report back? — harrism, Sep 03 '12 at 03:56

score 1 · Accepted Answer · answered Sep 04 '12 at 00:23

1

This appears to have been a compiler bug in CUDA 4.x that is fixed in CUDA 5.0 (according to a comment from @meriken2ch, the project builds fine with CUDA 5.0 RC).

answered Sep 04 '12 at 00:23

harrism

26,505
2
57
88

CUDA Toolkit 4.1/4.2: nvcc Crashes with an Access Violation

1 Answers1