| Age | Commit message (Collapse) | Author |
|
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]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13761]
|
|
- 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]
|
|
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]
|
|
- 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]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13093]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13092]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12799]
|
|
the detault.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12784]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12783]
|
|
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]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12761]
|
|
Fixing ptxplus with AES
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12737]
|
|
A bit of cleanup
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12627]
|
|
classes
Some changes to remove warnings
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12609]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12552]
|
|
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]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12517]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12431]
|
|
supported before
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12372]
|
|
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]
|
|
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]
|
|
//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]
|