- 16 Aug, 2018 1 commit
-
-
Sven-Bodo Scholz authored
-
- 15 Aug, 2018 2 commits
-
-
Sven-Bodo Scholz authored
trace g traces GPU actions; currently only kernel launches will be reported.
-
Sven-Bodo Scholz authored
-
- 09 Mar, 2018 1 commit
-
-
Hans-Nikolai Viessmann authored
The CUDA runtime system and driver provide very little in the way of helpful or clear error messages. Especially in the case of kernel dimensions being out-of-bound. Depending on what CUDA-CC one uses (e.g. 2.0, 3.5, 5.0, etc.) there is a max-limit to how large the X, Y, and Z dimensions can be for the kernel. This patch adds a check which will error out if we generate a dimension greater than permitted by the CUDA-CC. Furthermore a test is provided.
-
- 21 Mar, 2016 1 commit
-
-
Hans-Nikolai Viessmann authored
-
- 19 Mar, 2016 1 commit
-
-
Max Baird authored
Improved GPU error checking reporting. GPU errors are now specific to CUDA API calls and include the file name and line number.
-
- 18 Jan, 2016 1 commit
-
-
Max Baird authored
-
- 27 Mar, 2014 1 commit
-
-
Artem Shinkarov authored
We introduce DBUG_UNREACHABLE macro to mark the places in the code that must not happen. We produce an error message stating that we hit such a place in the code. * debug.[ch]: DBUG_UNREACHABLE macro defined for both DBUG_OFF and !DBUG_OFF cases. exit_function was moved outside of !DBUG_OFF region. * ctinfo.[ch]: Removed CTIterminateCompilationSilient in favour of existing CTIexit and replaced occurences. * main.c Adjusted comments to match doxygen style, set exit_function unconditionally to DBUG_OFF.
-
- 19 Oct, 2012 1 commit
-
-
Artem Shinkarov authored
Final changes which eliminate almost almost all statement-passing macros, and replace long fprintf-s with `out` and `indout`. There are some more icm2c_xxx files, where the fprintf replacement can be done. Let's leave it for a future refactoring.
-
- 11 Aug, 2012 1 commit
-
-
Miguel Sousa Diogo authored
scafolding work would be required otherwise, as they can only be compiled by the NVidia compiler, and I don't have the time for that now. Provided macros for cudahybrid related ICMs. Expanded the number and arguments of cudahybrid primitive functions to better match the required ICMs, specifically distinctions between host and device transfers and arguments for setting ownership of data. Created specific ICM for (de)allocation and reference counting of distributed variables. Modified kernel launches to make use of streams on cudahybrid backend.
-
- 11 Oct, 2011 1 commit
-
-
Jing Guo authored
1) loopallocopt.c to lift allocation out of a for loop 2) reusewithregion.c to perform memory reuse base on polyhedral model.
-
- 03 Jul, 2011 1 commit
-
-
Artem Shinkarov authored
-
- 02 Jun, 2011 1 commit
-
-
Jing Guo authored
a scalar. Withloop scalarizing is applied to the fold withloops (uncompleted)
-
- 27 May, 2011 1 commit
-
-
Jing Guo authored
-
- 07 Jan, 2011 1 commit
-
-
Jing Guo authored
No commit message
-
- 27 Dec, 2010 1 commit
-
-
Jing Guo authored
-
- 16 Dec, 2010 1 commit
-
-
Jing Guo authored
-
- 28 Oct, 2010 2 commits
- 29 Sep, 2010 1 commit
-
-
Jing Guo authored
No commit message
-
- 14 Sep, 2010 1 commit
-
-
Jing Guo authored
No commit message
-
- 07 Sep, 2010 1 commit
-
-
Jing Guo authored
to compilation error. improve tag cuda execution mode.
-
- 15 Jun, 2010 1 commit
-
-
Jing Guo authored
-
- 05 May, 2010 1 commit
-
-
Jing Guo authored
-
- 27 Apr, 2010 1 commit
-
-
Jing Guo authored
-
- 26 Mar, 2010 1 commit
-
-
Jing Guo authored
No commit message
-
- 26 Nov, 2009 1 commit
-
-
Jing Guo authored
-
- 02 Nov, 2009 1 commit
-
-
Jing Guo authored
No commit message
-
- 23 Oct, 2009 1 commit
-
-
Jing Guo authored
-
- 14 Sep, 2009 1 commit
-
-
Jing Guo authored
-
- 06 Sep, 2009 1 commit
-
-
Jing Guo authored
-
- 13 Aug, 2009 1 commit
-
-
Carl Joslin authored
-
- 12 Aug, 2009 1 commit
-
-
Jing Guo authored
-