| Age | Commit message (Collapse) | Author |
|
it was always hardcoded to 2).
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11742]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11728]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11725]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11724]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11589]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11588]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11587]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11586]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11577]
|
|
because one can have 4 input operands and 4 register operands in a surface store instruction.
Fixed arch_regs for memory instructions being ignored in the pre-decode statge.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11576]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11575]
|
|
partitions will not lead to address aliasing.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11574]
|
|
predecode. See Bug 138
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11573]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11571]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11570]
|
|
136 for details.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11530]
|
|
and set the line to modified at fill (when it misses the cache).
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11527]
|
|
before (totals to 115 cycles of latency). Changing the Fermi config to specify the different latency parameters.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11523]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11522]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11521]
|
|
MAX_THREAD_PER_SM. Also decreased LOCAL_MEM_SIZE_MAX to 8kB to make it fit within our allotted memory space (otherwise the simulator may mistaken global memory access as local memory accesses).
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11520]
|
|
the total amount of L2
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11519]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11518]
|
|
this in the config)
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11517]
|
|
interconnect for Fermi. Halved the dram buswidth option to properly model the peak DRAM bandwidth. Changed L2 cache line to 256B.
Also further shortened the bandwidth test to speed up measurement.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11516]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11514]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11511]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11510]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11508]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11507]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11495]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11493]
|
|
Merging
//depot/gpgpu_sim_research/fermi-test/distribution/configs/Fermi/...
to //depot/gpgpu_sim_research/fermi/distribution/configs/Fermi/...
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11492]
|
|
the order in which cores are simulator per cycle. Also adding support for calling function with empty parameter list.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11489]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11486]
|
|
and observed the over-count for vector memory instruction. The fix eliminates the over-count.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11481]
|
|
shader_core_ctx. Now m_num_sim_insn counts scalar thread instructions. A new counter is added for warp instructions.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11472]
|
|
ISPASS paper.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11471]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11470]
|
|
everything related to building and setting up the simulator should be in the README and the wiki should only refer to that
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11467]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11461]
|
|
detail. For verification, I added a directed test with a pre-calculated number of shared memory instructions.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11454]
|
|
(expected). The key is that the missing function is now in place. Also removed reference to print_shader_cycle_distro() (this is deprecated by AerialVision).
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11346]
|
|
have the correct predefines.
Added the cleandocs target to the clean target.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11345]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11344]
|
|
disabled, it was trying to print its content, even though.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11340]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11334]
|
|
comments
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11333]
|
|
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11329]
|
|
simulation.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11327]
|