summaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Collapse)Author
2014-08-14Adding the ability to querry the WARPSZ flag from the ptx script.Tim Rogers
Also changed some initialization code when cores are created in both the funcational and perfromance simulator review:3001 lgtm:5 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16506]
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]
2014-08-14Interconnection traffic breakdown stats (integration from TM branch).Wilson Fung
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16495]
2014-08-14Adding new option '-liveness_message_freq', which throttles the frequency of ↵Wilson Fung
simulation liveness printout (default to 1 per second in wall clock time). [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16482]
2014-08-14Fixing ":" to "=" in shader_print_cache_stats. This will not affect the ↵Tayler Hetherington
regressions butwill cause the correlation to fail due to a change in the output - need to update gold files on failure. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16477]
2014-08-14Review: 47001. Fixing bug in CL16463. When streams are actually used, ↵Tayler Hetherington
kernels can complete while other kernels are still running. The fix in CL16463 caused the GPU to re-initialize when a kernel completes, which may occur while another kernel is still running. Added a check to test if the GPU is also inactive when a kernel completes in order to re-initialize. simpleStreams CUDA SDK now passes with CUDA 3.1. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16469]
2014-08-14Review: 46001. Fixing a source of non-determinism in GPGPU-Sim (Bug 174). ↵Tayler Hetherington
Not sure if this is the only issue, but this was definitely a source of non-determinism (checked with many of the <rodinia>-FT benchmarks). In gpgpu_sim_thread_concurrent() (gpgpusim_entrypoint.cc), the inner do{...}while(active); only breaks when the gpu is not active. As a result, the gpu is only initialized when the gpu becomes momentarily inactive. If one kernel completes while another kernel is currently pending in the stream's queue, the next kernel will start running immediately causing the GPU to not be reinitialized (which includes resetting per-kernel stats). The fix simply recognizes that a kernel has completed and breaks from the loop prior to starting the next operation. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16463]
2014-08-14Fixing pending_hit bug (Access is supposed to return MISS, but stats should ↵Tayler Hetherington
increment HIT_RESERVED). Reviewed in person by Tim. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16460]
2014-08-14Fixing bug in printing - Not checking if cache was instantiated (i.e., L1D ↵Tayler Hetherington
for Quadro config). [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16457]
2014-08-14Fixing deadlock bug for CL16452Tayler Hetherington
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16456]
2014-08-14Fixing compilation bug in CL16452. Tested with gcc version 4.2.1 and 4.3.4.Tayler Hetherington
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16453]
2014-08-14Review: 33001. Updating/cleaning up the cache statistics. Moving the ↵Tayler Hetherington
statistics from the tag array to the cache access functions. Added cache_stats class to record all memory accesses and access outcomes to each cache. Removed L2CacheAccessBreakdown_t. Cleaned up power_stats to reflect changes in the cache stats. Updated the cache stats printing. This will cause the performance gold files to change as the output format has been changed. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16452]
2014-08-14Further cleaning up power stats - Continuation of issue 35001.Tayler Hetherington
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16437]
2014-08-14Adding a dependency so the ptxinto.tab.h file is generated before the ↵Tim Rogers
lex.ptxinfo_.c file is built review:42002 lgtm:1 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16432]
2014-08-14Fixing interconnect stats bugTayler Hetherington
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16428]
2014-08-14Fixing 2 bugs & small code clean up:Tayler Hetherington
1: 'Constant dynamic' power not included in average/min/max power values. 2: Average/min/max per-kernel powers not being reset at kernel boundaries, causing incorrect per-kernel values. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16405]
2014-08-14Fixing bug 59 + cleaning some code related to the power modelAhmed El-Shafiey
Review ID:32001 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16205]
2014-08-14Fixing the broken valgrind build.Tim Rogers
review:28002 lgtm:0 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15957]
2014-08-14force power log files to be readable by group and othersAhmed El-Shafiey
(Review ID: 21001) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15927]
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]
2014-08-14Restoring the functional simulation entry function for OpenCL, which was ↵Ayub Gubran
undone in CL 12023 probably by mistake. Reveiw ID: 17001 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15885]
2014-08-14make sure L1 cache is flushed at a configuration change between kernels, ↵Ahmed El-Shafiey
even if flushing L1 cache between kernels option is not set [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15834]
2014-08-14 Removing the default printing of the dynamic warp distribution histogram ↵Tim Rogers
at the end of every kenerl [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15830]
2014-08-14initialize the shared_memory_sizeAhmed El-Shafiey
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15817]
2014-08-14 - Adding support for cudaFuncSetCacheConfig API, that allows changing theAhmed El-Shafiey
L1 Cache and Shared Memory configurations across kernels. The support enable the user to specify two more configurations (Preferred L1) or (Preferred Shared Memory) besides the default config. If the cudaFuncSetCacheConfig API is used to set the cache configuration of a specific kernel to either of these configuration (cudaFuncCachePreferShared, cudaFuncCachePreferL1), the simulator will change the cache configuration at kernel launch accordingly, if there is no alternative configurations provided to the simulator it will use the default configurations with a warning message display [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15816]
2014-08-14Updating ICNT stat collectionTayler Hetherington
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15788]
2014-08-14Replaced the legacy L2 cache access stats with more meaningful breakdown ↵Wilson Fung
that categorize access by their access type (global memory read/write, local memory read/write, instruction read, ... etc.). [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15784]
2014-08-14fixing a bug in the interconnect stats was introduced in CL15746Ahmed El-Shafiey
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15781]
2014-08-14Updating gpuwattch makefilesTayler Hetherington
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15761]
2014-08-14Updating mem_fetch::get_num_flits() to work with atomicsTayler Hetherington
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15760]
2014-08-14Cleaning up interconnection network memory partition to core statistics. Now ↵Tayler Hetherington
counting the number of flits arriving at the cores instead of the number of flits leaving each memory partition. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15746]
2014-08-14Cleaning up the interconnection core to memory partition statisticsTayler Hetherington
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15745]
2014-08-14-another fix to resolve valigrind complains.Ahmed El-Shafiey
-sumbittig new power gold files for chages in CL15668 and CL15674 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15722]
2014-08-14this should fix valigrid compais after fixing the wire initilization bugAhmed El-Shafiey
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15714]
2014-08-14correcting the allocation of n_simt_to_mem/n_mem_to_simt statsAhmed El-Shafiey
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15699]
2014-08-14Fix incorrect initialization of wire_length variable in cacti/wire.cc - ↵Tayler Hetherington
causing incorrect per-access cache energy Adding 32bit/64bit check to Cacti's Makefile. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15668]
2014-08-14fix from JigwenAhmed El-Shafiey
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15629]
2014-08-14Fixing GPUWattch McPAT Makefile to use -m32 for 32 bit and -m64 for 64 bit LinuxTayler Hetherington
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15583]
2014-08-14Fixing bug in reseting code - looping over # of power values, not number of ↵Tayler Hetherington
performance counters to reset performance counters [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15577]
2014-08-14Fixing bug in power counter resetTayler Hetherington
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15539]
2014-08-14Integrate mov.pred fix from TM branch.Wilson Fung
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15538]
2014-08-14This should fix the NNC undefined memory locations bug. It turned out that ↵Ahmed El-Shafiey
the main problem is in the benchmark code itself. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15537]
2014-08-14Adding other power stats to reset functionTayler Hetherington
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15522]
2014-08-14fixing bugs that were revealed by automated power correlation results.Ahmed El-Shafiey
1- reset the per kernel average power per component every kernel. 2- chage the font size of the x ticks in fial figure [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15521]
2014-08-14fixing some assignment in the "get_operand_value" function where unsigned ↵Ahmed El-Shafiey
were assigned to unions! Also, do proper initialization in the constructors of operand_info, therse among places where valgrind complaining from NNC, but still it is not fixed. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15503]
2014-08-14GPUWattch bug fix: Performance counters not being correctly reset at kernel ↵Tayler Hetherington
completion. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15413]
2014-08-14Okay, both the crash and the valgrind complaint are caused by the non-type ↵Tim Rogers
safeness of fprintf. Fix is to explicitly tell fprintf that the to_string.c_str() result is a string. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15312]
2014-08-14Fixed at least one error in the valgrind build. Forgot to initial a member ↵Tim Rogers
variable. I thought the init() function where dynamic_warp_id is initialized was called on construction. It is not. Added a default value in the constructor. Maybe a code review would have caught this :) Also cleaned up some weird code I had in the ptx_instruction::to_string(). Also trimmed out tabs from our stored source line string so it is much more readable on print [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15310]
2014-08-14Fixing a bug exposed by the fix for bug 42.Tim Rogers
The "_" "null" register potentially generated by ptx and intentionally generated by ptxplus was being initialized without a type. This caused the parser to think it was not a register. Fix is to allow the parser to think of it as register, but ensure the arch-sim does not by adding a flag indicating that it is special. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15305]
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]
generated by cgit v1.3 (git 2.53.0) at 2026-07-11 00:49:22 +0000