Card GTX 280
Compute Capability: 1.3
CUDA environment : v 3.0 beta
While I was debugging a kernel through cuda-gdb, I got following error after continuing from the break point.
The main problem is that I couldn’t use the cuda-gdb for any other kernel. It reports following error.
On skimming over google, I found out the such error can occur in normal gdb too.
But gdb is working fine, only cuda-gdb reports error.
Die: DW_TAG_padding (abbrev = 0, offset = 0)
has children: FALSE
attributes:
Dwarf Error: Cannot find type of die [in module /tmp/tmp_cudagdb_elf_7220_7283_1528136088.o]
Can someone please let me know how to fix this issue or any work around to get back cuda-gdb working.
Thanks in Advance!
[murugand@cerberus chk]$ cuda-gdb cg_new
NVIDIA ® CUDA Debugger
BETA release
Portions Copyright © 2008,2009 NVIDIA Corporation
GNU gdb 6.6
Copyright © 2006 Free Software Foundation, Inc.
GDB is free software, covered by the GNU General Public License, and you are
welcome to change it and/or distribute copies of it under certain conditions.
Type “show copying” to see the conditions.
There is absolutely no warranty for GDB. Type “show warranty” for details.
This GDB was configured as “x86_64-unknown-linux-gnu”…
Using host libthread_db library “/lib64/libthread_db.so.1”.
(cuda-gdb) b CG_kernel
Breakpoint 1 at 0x4017f1: file cg_new.cu, line 219.
(cuda-gdb) r
Starting program: /home/murugand/cuda/chk/cg_new
Breakpoint 1 at 0x4017d2: file /tmp/tmpxft_000019d1_00000000-1_cg_new.cudafe1.stub.c, line 11.
Breakpoint 1 at 0x4017f1: file cg_new.cu, line 219.
[Thread debugging using libthread_db enabled]
[New process 7284]
[New Thread 47247946829728 (LWP 7284)]
Die: DW_TAG_padding (abbrev = 0, offset = 0)
has children: FALSE
attributes:
Dwarf Error: Cannot find type of die [in module /tmp/tmp_cudagdb_elf_7220_7283_1528136088.o]
(cuda-gdb)