| Age | Commit message (Collapse) | Author |
|
http://www.gpgpu-sim.org/bugs/show_bug.cgi?id=81
Review ID: 173001
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 18179]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 17739]
|
|
http://www.gpgpu-sim.org/bugs/show_bug.cgi?id=78
review: 123001, LGTM: 2
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 17692]
|
|
Code Review Issue: 113001
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 17414]
|
|
Code Review: Issue 103001
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 17411]
|
|
- Warning fixed
- Unused file deleted
- Add support for node map configuration.
Code Review: Issue 93001
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 17410]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 17315]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 17183]
|
|
fix dram clock energy scaling
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 17124]
|
|
Review ID: 89001
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 17086]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 17048]
|
|
Fixing the alignment of all types of memory so that it's aligned to size or 128byte whichever is smaller
Refactoring out the padding code
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 17047]
|
|
write-allocation policy. Also added description for the write-allocation fix implemented by Tayler.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16914]
|
|
is used.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16904]
|
|
1. Decouple the constructor of interconnect interface
2. Some type changed to unsigned from int
Fixed Bug: wrong variable in InterconnectInterface::Busy()
Review: 83001
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16877]
|
|
Review ID: 75001 lgtm: 2
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16758]
|
|
Details: See Review 80001 https://gpgpu-sim-code-review.appspot.com/80001/
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16747]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16725]
|
|
and the data port in each bank is limited to 32B/cycle.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16700]
|
|
icnt_config_islip.txt to use icnt_config_islip.icnt. This will not affect any of the regressions/correlations as they overwrite this with the correct configuration file name. Reviewed with Myrice.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16684]
|
|
for specific caches.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16683]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16671]
|
|
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]
|
|
keep the DRAM utilized. Also extended the state printing function to print out mem_fetch entries inside the DRAM delay queue.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16639]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16635]
|
|
partition. Each L2 cache banks has its own connection to the interconnection network to allow L2 bandwidth to scale without increase the number of memory parttiion units.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16613]
|
|
still caching data from local memory space.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16601]
|
|
Main contribution is a static warp limiting scheduler.
There is also some minor cleanup to the heirarchy of the cache code and removal some excessively long lines
Review ID: 36001 lgtm: 1
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16580]
|
|
"WarpIssueDynamicIdBreakdown" are being printed in the visualization files without any data.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16572]
|
|
contains no data. Instead of crashing, it prints out an warning and proceeds.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16569]
|
|
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]
|
|
Correct the extension of the QuadroFX5600 interconnect config file
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16534]
|
|
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]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16505]
|
|
generated go in a directory independent of the source directory
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16503]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16496]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16495]
|
|
simulation liveness printout (default to 1 per second in wall clock time).
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16482]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16480]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16479]
|
|
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]
|
|
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]
|
|
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]
|
|
increment HIT_RESERVED). Reviewed in person by Tim.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16460]
|
|
for Quadro config).
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16457]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16456]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16453]
|
|
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]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16437]
|
|
lex.ptxinfo_.c file is built
review:42002 lgtm:1
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 16432]
|