aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2014-08-14updating README and CHANGES with suggested editsTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11014]
2014-08-14Adding comment on Tayler's update to fermi branchTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11003]
2014-08-14set build number and update READMETor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11000]
2014-08-14Removing common.mk since it's not used anymoreTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10999]
2014-08-14Getting rid of outdated documentationTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10998]
2014-08-14point out difference in default configTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10988]
2014-08-14fixing OpenCL include path detection (compile for nvopencl_wrapper was ↵Tor Aamodt
breaking build on pc08) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10987]
2014-08-14- merge setup_environment_ptxplus into setup_environmentTor Aamodt
- detect if libOpenCL.so is installed in default location to enable OpenCL build (nvopencl_wrapper should be modified to detect if it is accessing an NVIDIA OpenCL implementation) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10985]
2014-08-14change version number to 3.0.1 build XYZTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10969]
2014-08-14Removing config_setup and changing setup_environment to allow for a better ↵Tim Rogers
way to enable the debug build [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10968]
2014-08-14Back out changelist 10951Hadi Jooybar
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10963]
2014-08-14Adding in a commentTim Rogers
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10962]
2014-08-14Should be tested.Hadi Jooybar
Does not support sm_20 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10951]
2014-08-14defeat perforce autoupdate of string parsingTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10936]
2014-08-14attempt to autoupdate version in READMETor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10935]
2014-08-14missing text needed to parse change list numberTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10934]
2014-08-14attempt to automatically embed perforce change list number in version numberTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10933]
2014-08-14fixed memory error in decuda_to_ptxplus that was causing the type modifier ↵Jimmy Kwa
for constants to not appear in some cases. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10931]
2014-08-14Bugfix. The script used to check the version of nvcc that is in the path, ↵Andrew M. B. Boktor
however, we use the one at $CUDA_INSTALL_PATH/bin. Now check and use the same thing. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10930]
2014-08-14Trying to fix the whitespace problem between ubuntu and opensuseAndrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10915]
2014-08-14Fixed copyright notice breaking compile of decuda's lex files.Inderpreet Singh
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10903]
2014-08-14More copyright notices addedAndrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10902]
2014-08-14Updated CHANGES with the differences since the last release.Andrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10900]
2014-08-14Making the default L2 something saneTim Rogers
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10899]
2014-08-14 - Fixing L1 Texture cache option (I updated the description to look like ↵Ali Bakhoda
the other L1 cache options) and change the default values to the one in Quadro config. The old default value could not even be parsed. - Removed the SIMD width option from the shader_core_pipeline_opt description and default value and Quadro config file. Also changed the default thread count from 256 to 1024. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10897]
2014-08-14Deleted ISPASS configs.Ali Bakhoda
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10896]
2014-08-14uncommenting the decuda target. This is not actually necessary for gcc 4.5 ↵Tim Rogers
as stated in the changlist this hapened in, it was an unintended side effect of integrating changes for gcc 4.5 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10893]
2014-08-14A few words about how to get it running on ubuntu in the README.Andrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10891]
2014-08-14Single whitespace change to work on ubuntuAndrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10884]
2014-08-14Adding back the whitespace. Comparison is broken without it.Andrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10877]
2014-08-14Fixed build fail when there is no openclAndrew M. B. Boktor
Now, you have to define both NVOPENCL_LIBDIR and NVOPENCL_INCDIR in the setupd_environment script to build with opencl. If any of them is not setup, gpgpu-sim will build will output a warning and built without opencl support. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10873]
2014-08-14Added a new target for doxygen in the makefile and updated the README with ↵Andrew M. B. Boktor
that info. "make docs" to build and "make cleandocs" to clean. You have to have doxygen and graphviz installed. The new docs target doesn't build with the simulator (you have to call it explicitly) to avoid giving unecessary errors to people. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10872]
2014-08-14Added all distribution/src as well as libcuda and libopencl to the documentationAndrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10871]
2014-08-14Disabled ptxplus by default and added a comment about the conditions needed ↵Andrew M. B. Boktor
for it to be enabled [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10870]
2014-08-14The simulator stops and outputs a message if it cannot find a cubin file ↵Andrew M. B. Boktor
while trying to convert to ptxplus [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10869]
2014-08-14Back out revision 2 from ↵Andrew M. B. Boktor
//depot/gpgpu_sim_research/fermi/distribution/setup_environment removed troublesome whitespaces around '=' [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10868]
2014-08-14Minor changes to READMEAndrew M. B. Boktor
removed ece specific code from setup_environment [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10866]
2014-08-14Rename/Move:Andrew M. B. Boktor
From: //depot/gpgpu_sim_research/fermi/distribution/setup_enviroment_ptxplus To: //depot/gpgpu_sim_research/fermi/distribution/setup_environment_ptxplus [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10865]
2014-08-14Rename/Move:Andrew M. B. Boktor
From: //depot/gpgpu_sim_research/fermi/distribution/setup_enviroment To: //depot/gpgpu_sim_research/fermi/distribution/setup_environment [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10864]
2014-08-14Integration change. 10658 - getting the benchmarks to build with gcc 4.5Tim Rogers
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10793]
2014-08-14Integrating documentation scripts into fermi.Andrew M. B. Boktor
Read comment on CL10779 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10780]
2014-08-14Actually fixing the atomic bugTim Rogers
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10756]
2014-08-14Warning refixTim Rogers
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10755]
2014-08-14Fixing the atomics I broke with the insn count fixTim Rogers
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10754]
2014-08-14Warnings cleanupTim Rogers
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10753]
2014-08-14Fixing the varying instruction count when the cache configuration changes.Tim Rogers
The problem was 2-fold: 1) If all the lanes hit, we were not incrementing the instruction count since the instruction did not progress to the WB stage, the scoreboard relasing is done in the ldst_unit::cycle function for cache hits. Added code there to increment the instrcution count. 2) Loads were some lanes hit in cache and some lanes do not were not being comepletely counted. Only the lanes sent off to the memory system were being counted because we were setting the warp's active lanes to the access's acrtive lanes.... I am not sure why this code was there... [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10737]
2014-08-14Removing some function inlining to make debugging easierTim Rogers
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10736]
2014-08-14Undoing the rest of files mistakly changed in CL10695, this change completes ↵Ayub Gubran
the work of CL10697 which undone the changes to one file (stream_manager.cc). Here I undo the changes for 4 make files and more importantly the setup_enviroment file where I uncommented the include path of openCL as the case before CL10695, and I kept Tim changes to the CUDA path done later in CL10723 which he made originally to undo the work I did but didn't uncommet the openCL path which I do here. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10730]
2014-08-14Adding a print guard if there is no cacheTim Rogers
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10728]
2014-08-14Integration change. - CL 9058 , adding the l1 cache stat print to the end of ↵Tim Rogers
execution [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10727]
generated by cgit v1.3 (git 2.53.0) at 2026-07-13 22:16:05 +0000