| Age | Commit message (Collapse) | Author |
|---|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 18452]
|
|
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]
|
|
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]
|
|
need to modify carry and overflow flags.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13317]
|
|
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]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 9872]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 9687]
|
|
(i'll use "fermi" for more disruptive changes to the pipeline model such
as updating the MSHRs and getting rid of the warp tracker, ripping out DWF, etc...)
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7805]
|
|
this integrates the ptxplus functional model changes, but has only been
verified with CUDA 3.1 PTX regressions (which pass)
still need to verify ptxplus itself is working in this branch
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7435]
|
|
- add ldu support (just use ld for now)
- get rid of asserts for .const[n]
- status:
cuda sdk 3.1 dct8x8, eigenvalues, MersenneTwister, reduction, scan still running (too slow)
ocl sdk 3.1 oclQuasirandomGenerator still running (too slow)
ocl sdk 3.1 oclReduction fail comparison (cuda 3.1)
ocl sdk 3.1 oclMatrixMul exits mid computation
ocl sdk 3.1 oclTranspose hits "clCreateBuffer - buffer already created for this host variable"
ocl sdk 3.1 oclSortingNetworks fails w/ message about min workgroup size
remaining 30 tests pass
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6927]
|
|
- update regression script to use compute sdk location for cuda (both
distributed in one download now)
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6846]
|
|
- Added fma operation by simply calling mad, however in reality fma is supposed to
be more accurate than mad. For now, properly emulating fma (to get the extra
precision) isn't a priority.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6839]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6829]
|
