summaryrefslogtreecommitdiff
path: root/setup_environment
AgeCommit message (Collapse)Author
2018-11-16changes for cuda 4.2 supportDeval Shah
2018-11-09required environment variablesDeval Shah
2018-10-11Merging the latest dev from the public branchtgrogers
2018-06-30oops - you should set this if it does not exist, not the other way around...tgrogers
2018-06-30Adding in a check to not blow away the PTXAS variable if you already had it settgrogers
2018-06-30Cleaning up the setup env message a bit and having the simulator properly ↵tgrogers
dump to stderr on error
2018-06-30Preventing bad git commit numbers from printing when you run setup_env from ↵tgrogers
a dir that is not the gpgpusim_distr dir
2018-06-30changing the flow s.t. you cannot compile the simulator with a different ↵tgrogers
version of CUDA from the app.
2018-06-29Fixing the PTXPLUS + new CUDA execution case.tgrogers
2018-06-29Allowing modern GPU configrations to properly run PTXPLUS.tgrogers
There are several problems with this: 1) To get proper occupancy, based on register file usage, you must querry ptxas with the sm version that corresponds to the register usage in the config file. To enable this, a new config option has been added that determines what sm version you pass to ptxas to compute reg-usage. This configuration option is always required in the gpgpusim.config file 2) If you are running PTXPLUS with a modern card (i.e. volta/pascal), you need ptxas from CUDA 9.1. However since PTXPLUS only supports sm_13 - you need a version of CUDA where cudaobjectdump supports sm_1x. This ended at CUDA 5 - and PTXPLUS requires CUDA 4.2. Therefore, to run PTXPLUS on a modern card, you need CUDA 4.2 + modern CUDA installed. To fascilitate this, a new envronment varaible is added and the setup envrionment script prints an appropraite warning if you are using a newer CUDA. We have tried to make this as fail-proof as possible - and die appropraitely when something is wrong.
2018-04-11This build status line was broken when there were cached filestgrogers
2018-03-25Merging with updates in the public repotgrogers
2018-03-20Adding in some setupscript stuff to properly print the build version and get ↵tgrogers
rid of this not fully tested warning
2018-02-22run all the configs, do 9.1 on the sdk and stop the setup environment from ↵tgrogers
complaining about cuda version
2017-12-12support for 9.1tgrogers
2017-07-12Getting jenkins to work by changing the error on shell type to a warning. ↵tgrogers
The way we detect the shell is not fool-proof and fails for jenkins, although we are using bash
2016-10-28support for CUDA 8.0 PTXAhmed ElTantawy
2016-05-12updating Makefile and setup environment for 7.5 supportAhmed ElTantawy
2015-03-05update setup_environment to reflect the levels of support of CUDA versionsAhmed ElTantawy
2015-03-04initial support for CUDA 5.0, 5.5, 6.0 to get template from SDK runningAhmed ElTantawy
2014-08-14Review: 76001: Setup environment quick fix for ubuntuDongdong Li
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16725]
2014-08-14Review 69001:Dongdong Li
More support for setup environment 1. More general solution to get CC_VERSION, work for Linux(OpenSUSE, Ubuntu, Debian) and OSX 2. Add zsh support, change == to = to make it compatible with bash, zsh and sh 3. Fix a bug in Makefile [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16640]
2014-08-14Adding a wildcard to the end of the GCC sed string parser to handle gcc ↵Tim Rogers
prints that print more information about their version numbers Review ID: 59001. lgtm: 1 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16549]
2014-08-14 Changing the make flow so all the generated files, both object and code ↵Tim Rogers
generated go in a directory independent of the source directory [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16503]
2014-08-14Fixing a bug that was trashing the LD_LIBRARY_PATH if GPGPUSIM_ROOT was not ↵Tim Rogers
the first entry in the list [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15422]
2014-08-14simplify bash checkTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15169]
2014-08-14verify user is using bashTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15168]
2014-08-14enable CUBIN parsing on Mac OS XTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 14882]
2014-08-14Updating setup_environment and Makefile to use gpuwattch instead of mcpatTayler Hetherington
(src/mcpat -> src/gpuwattch) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 14799]
2014-08-14a bit more cleaningTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 14797]
2014-08-14clean up setup_environmentTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 14796]
2014-08-14Merging Power model into FermiTayler Hetherington
//depot/gpgpu_sim_research/fermi_power/distribution/... to //depot/gpgpu_sim_research/fermi/distribution/... [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 14723]
2014-08-14testing submission policy checking script; enable CUDA 4.2 for testingTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13576]
2014-08-14Fixing Tor's clean up. Seems like we have 2 version string kicking around ↵Tim Rogers
One that looks like "3010" cause we have to use this value in a C macro. And one that looks like "3.1" cause that makes more sense as a stand alone string. Removing the reference to "3.1" in the simulator code build since it just make things confusing. The benchmarks still use the "3.1" style string but these two flows are reasonably seperate. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13574]
2014-08-14cleaning Tim's edits up so can work on MacOS and avoid duplicating effort ↵Tor Aamodt
done by version_detection.mk [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13573]
2014-08-14Setting the path earlier so nvcc is the right version when we fill in the ↵Tim Rogers
build env vars. This is useful if you are building one version of the sdk, change your CUDA_INSTALL_PATH then source setup_environment again. Now things will be properly setup for the latter SDK after your source [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13572]
2014-08-14Putting GPGPU-sim into nvcc version specific build and lib folders.Tim Rogers
Also changing the cuobjdump_to_ptxplus build to into the build directory instead of inline with the src [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13567]
2014-08-14- can compile on MacOSX (tested on Lion)... no regression testing done on MacTor Aamodt
- ptxplus ... edits to eliminate some warnings with older gcc about printfs without string literal - eliminate warning about map (just too annoying while testing on Mac) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13560]
2014-08-14also print out build number (perforce change list)Tor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13556]
2014-08-14Fixing broken build.Tim Rogers
Using a variable with the same name in two different bash scripts causes some issues.... Removing the redundnat declaration of THIS_DIR [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13555]
2014-08-14Editing the version print code to allow setup_environment to be run from any ↵Tim Rogers
directory [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13554]
2014-08-14tell new user what version of GPGPU-Sim this is while trying to build (i.e., ↵Tor Aamodt
in case they can't even get it to build) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13549]
2014-08-14Correct typosTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13511]
2014-08-14More beginner instructionsTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13510]
2014-08-14additional checking for setup_environment...Tor Aamodt
attempting to get GPGPU-Sim to run on MacOSX again (no joy) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13509]
2014-08-14move check for nvcc after we set PATHTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13085]
2014-08-14make sure CUDA_INSTALL_PATH points to a valid directory and that "which" can ↵Tor Aamodt
find nvcc [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13084]
2014-08-14- Update README file to be slightly more user friendly (i.e., try not to ↵Tor Aamodt
imply user should bugger off and stop asking developer for help) - Remove ridiculously long and cryptic comment from setup_environment. Most people will use CUDA_INSTALL_PATH. - Remove decuda targets from Makefile - Add check to Makefile to insist that setup_environment was run first - Add version file (eliminate redundancy) and remove version strings from src/cuda-sim/cuda-sim.cc [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12874]
2014-08-14- adding clearer documentation to setup_environmentTor Aamodt
- removing an assert that gets triggered when using CUDA 4.2 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12865]
2014-08-14do NOT let setup_environment quietly return if CUDA Toolkit not foundTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12863]
generated by cgit v1.3 (git 2.53.0) at 2026-07-11 18:00:50 +0000