summaryrefslogtreecommitdiff
path: root/cuobjdump_to_ptxplus
AgeCommit message (Collapse)Author
2016-07-05ADD: initial support for instruction group used by CDPJin Wang
2015-06-05Adding in changes to put generated code files in the build directory instead ↵tgrogers
of the source directory - since this causes issues for parallel buildwq
2014-08-14-Forcing make clean to remove all automatically generated files by parsers ↵Ahmed El-Shafiey
(should fix regressions). -remove some printfs that were there for debugging [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 18480]
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]
2014-08-14Removing a slew of code still compiled with gcc and the need for a bunch of ↵Tim Rogers
external C linkage [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15912]
2014-08-14Fix for bug 47 - only comparing ".nv.global", ignoring trailing characters ↵Tayler Hetherington
(such as ".nv.global.init") [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15562]
2014-08-14MergingTim Rogers
//depot/gpgpu_sim_research/fermi_tim/... to //depot/gpgpu_sim_research/fermi/... Integrating CLs up to 15295. Descriptions of these CL's are included. *** A couple changes to aeriel-vision for warp issue plot support *** More arielvision changes to support the variable-entry length stacked bar chart *** Properly printing the right resolution of dynamic warp ids ***. Generalized the scheduler code and added detailed statistics for which warps issue each cycle. Verified the execution of the LRR scheduler - still have to get the two level scheduler to work. *** Implementing the 2lvl scehduler has it has been originally coded. LRR on both the inner and outer levels *** Adding in a debug tracing system to GPGPU-Sim. I am sick of writing debug code - then having to comment out, ifdef out or delete it to checkin. This also allows for print streams so the user can decided which traces they would like to see. Every print in GPGPU-Sim should go through this system - then it will be really easy to only get the information you want and more importantly people will (a) write and (b) checkin code that actually profiles what they are building. Reading tracefiles is superiour in many ways to single stepping since you can print the world and just vet the logfile for what you need. This also fascilitates advice from the Debugging Rules! book which states that you should never throw away a debugging tool. Having debug prints that don't get thrown away is big. *** Allowing the trace to be specified in the Make. Run Make TRACE=0 to compile the code without any traces *** Allowing prints from the performance sim to get the actual ptx instruction text *** Getting the two level scheduler to actaully work... What is released in fermi does not work at all - it effectively performs "static warp limit" from my CCWS paper. Warps are never demoted from the active list since the functionality checking to see if they are waiting on a longop is completly broken. Maybe if the original author had access to the tracing functions this would not have happened. The islongop test was completely broken. It did not mark the register as used, it marked the register number in the instruction as used. For example if this instruction was creating a long op: ld r6 [r1] It would mark register 0 as waiting for a long op (since it is register 0 of the two registers in this instruction), not register 6. Additionally, whenever ANY instruction from a warp releases registers, ALL the longops being tracked for this warp get cleared.... The only way anyone ever thought this worked is if they did not test it.... *** Reworking the warp schedulers to share common code. Making the GTX480 use gto by default. I am not sure wht they really use, but it really can't be LRR. Also adding in a new file for custom shared trace defines. These are useful when you want a print that has some additional criteria or information printed. Verified that the schedulers all work to a first order based on traces. *** Making it so you can run the stats collection scripts from any directory. Also allow the caller to specify a stats file instead of just assume its always the same one [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15296]
2014-08-14Extended PTX parser to recognize the .ptr .shared directive and allocate ↵Wilson Fung
shared memory buffer to those pointers. This is required to support OpenCL local memorywith the newer NVIDIA driver. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 14565]
2014-08-14Several changes to ptxplus towards getting the sphyraena benchmark to work. ↵Jimmy Kwa
Add .false modifier to cuobjdump_to_ptxplus. It isn't supported in gpgpusim yet since we don't know what it does. Fixed most of the issues with global (const14) variable not being declared properly. Added "BRX" instruction to cuobjdump_to_ptxplus and some support for it in gpgpusim. There are other issues with it that still need to be worked out. Added support for translating IADD.CARRY sass instruction into ptxplus addp instructions. Fixed a bug with generating ".half" modifiers on instructions so the ptxplus instruction addresses should match sass addresses now. Separated ssy instructions from nop. However, they are still simulated as nop in gpgpusim. Sometime cuobjdump generate a blank link that takes up an address slot. This was changed to a nop. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 14001]
2014-08-14Adding single element vector operands to support tex.1d instructions in CUDA ↵Wilson Fung
4.1 and later. KMN-FT should pass with this changelist. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13833]
2014-08-14add LIB-FT to (rodinia-ft) ans add it to rodinia-ft regression test, we have ↵Ahmed El-Shafiey
to decide whether to add another folder for ispass-ft or add all functionally tested benchmarks together ? -forgot to integrate some part last time [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13766]
2014-08-14Fixing bugs 169, 170, 171Ahmed El-Shafiey
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13761]
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]
2014-08-14Fix for bug #154-internal and #8-externalAndrew M. B. Boktor
Adding support for double destination to mad instruction Fixing broken madp instruction Adding a patch to cuobjdump_to_ptxplus to work around the C3 problem (Documented in bug #154 internal). [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13349]
2014-08-14Now makedepend doesn't have to interfere with our commits anymore.Andrew M. B. Boktor
makedepend generates the dependencies in Makefile.makedepend that is generated dynamically and cleaned with "make clean" Next step is to use gcc's "-M" option and get rid of makedepend altogether. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13292]
2014-08-14Fixing one of the problems discovered for bug 154 (internal).Wilson Fung
- Output of 16-bit integer multiplication (IMUL.U16) writes to the entire 32-bit register if a full register (i.e. not half register such as R1L) is specified as the destination. Before, it was only storing the lower 16-bit of the product into the full register. - Modified function header to declare at least 4 predicates in cuobjdump_to_ptxplus. This will mask out the problem with the predicate registers used before initialized. - Modified register value print out: now unsigned integers display their decimal values as well. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13246]
2014-08-14Fixing a condition mistake it the previous commitAndrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13093]
2014-08-14Using std::string instead of char*Andrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13092]
2014-08-14Removing stringList and replacing it with std::listAndrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12799]
2014-08-14Again fixing abs. The result should be a u32 for an I2I instruction. Using ↵Andrew M. B. Boktor
the detault. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12784]
2014-08-14Handling the case for absAndrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12783]
2014-08-14Trying to get around the problem of having more than 2 modifiers (two on the ↵Andrew M. B. Boktor
instruction and one on a memory operand). In this case, replace the modifier on the instruction with that of the memory operand. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12782]
2014-08-14I forgot that this is needed to calculate the offset since the offset is ↵Andrew M. B. Boktor
defined as multiple of access width Back out revision 8 from //depot/gpgpu_sim_research/fermi/distribution/cuobjdump_to_ptxplus/sass.y [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12781]
2014-08-14Not acting on type modifiers for memory operandsAndrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12775]
2014-08-14Removing a couple of memory corruptionsAndrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12761]
2014-08-14Cleaning up the output by cuobjdump_to_ptxplusAndrew M. B. Boktor
Fixing ptxplus with AES [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12737]
2014-08-14Removing a variable that's never usedAndrew M. B. Boktor
Fixing shift/reduce conflicts [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12630]
2014-08-14Removing warningsAndrew M. B. Boktor
A bit of cleanup [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12627]
2014-08-14Re-wrote the intermediate structure for the output of cuobjdump using C++ ↵Andrew M. B. Boktor
classes Some changes to remove warnings [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12609]
2014-08-14Adding copyright notices and updating CHANGESAndrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12552]
2014-08-14Deleting a file I missedAndrew M. B. Boktor
Cleaner make clean [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12546]
2014-08-14Merging decuda_to_ptxplus with cuobjdump_to_ptxplusAndrew M. B. Boktor
Major rework for the Makefile Deleting decuda_to_ptxplus Removing all dependencies on boost and removing it from the dependencies of the simulator [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12545]
2014-08-14Adding support for some more stuffAndrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12517]
2014-08-14Bugfix for bug#162Andrew M. B. Boktor
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12431]
2014-08-14Adding support for a big number of instructions and modifiers that were not ↵Andrew M. B. Boktor
supported before [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12372]
2014-08-141. Functional test for NNCAndrew M. B. Boktor
2. Adding NNC to include.list.rodinia-ft 3. Seems the fix I had added for it was lost through the merge (re-implemented it) 4. Added the commandline options an the corresponding gold file [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12298]
2014-08-14Adding support in the simulator for addition with carry specified in a given ↵Andrew M. B. Boktor
predicate register (calling it addp) Adding support in cuobjdump_to_ptxplus for IADD.CARRY* which translates to the above Now power benchmarks should work [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12266]
2014-08-14Moving things where they belongAndrew M. B. Boktor
cubojdump.l/.y are used to parse the output of cuobjdump, and thus should be part of libcuda not cuobjdump_to_ptxplus Included are also modifications to Makefiles [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12255]
2014-08-14Renamed "ST" token to "SASS_ST" and "LD" token to "SASS_LD". This avoids ↵Wilson Fung
identifier collision with boost::regex header. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12237]
2014-08-14MergingAndrew M. B. Boktor
//depot/gpgpu_sim_research/fermi-test/cuobjdump_to_ptxplus/... to //depot/gpgpu_sim_research/fermi/distribution/cuobjdump_to_ptxplus/... [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12022]
generated by cgit v1.3 (git 2.53.0) at 2026-07-10 23:45:21 +0000