| Age | Commit message (Collapse) | Author |
|---|
|
with spaces (e.g., using templates)
|
|
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]
|
|
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]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 14317]
|
|
solves the problem of underminitstic kernel finish detection
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 14206]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10697]
|
|
cudasim.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10695]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 10013]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 9872]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 9687]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 8389]
|
|
Parameters are finalized at kernel launch, which means the contents
of parameter memory are initialized. Kernel arguement names have a
fixed order, hence same address should be assigned on subsequent
kernel launches of same kernel in other streams provided the data size
param_t::size of arguments for each kernel launch is identical (an
assertion has been added to check this is true).
- passing regression
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 8303]
|
|
OpenCL)
This changelist adds full support for streams supported by a new class,
stream_manager and enables concurrent execution of kernels from different
streams.
- fast_regression.sh fails for simpleMultiCopy, simpleStreams (other tests
passing)
** Known issues **
- Kernel parameter passing is not done correctly for concurrent kernel execution
(somehow concurrentKernels is not affected by this): the parameters are
stored inside function_info, which is shared among parallel kernel launches
so that the values passed into the launch are likely to get overwritten if
multiple grids are launched in parallel streams.
- Statistics are printed out whenever the simulation thread runs out of
cuda commands (doesn't make sense to print out when a kernel ends during
concurrent kernel execution). This will probably require further tweaking
so as to be more compatible with data collection scripts.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 8302]
|
