aboutsummaryrefslogtreecommitdiff
path: root/src/cuda-sim/instructions.cc
AgeCommit message (Collapse)Author
2014-08-14This changelist implements the following:Andrew M. B. Boktor
1. Adds support for using cuobjdump for both ptx and ptxplus execution. This has been tested with CUDA 4.0 . Ptxplus is no longer supported through decuda/decuda_to_ptxplus 2. Adds support for converting the SASS output by cuobjdump to ptxplus. This has been tested with CUDA 4.0 . The old path that extracts ptx from cubin files is still preserved 3. Adds a bank group model. (WARNING: memory config has changed, please adapt yours). To disable the bank groups model, set nbkgrp to 1 and tCCDL and tRTPL to 0 Diff the configuration files to learn about how to use those new options. Merging //depot/gpgpu_sim_research/fermi-test/distribution/... to //depot/gpgpu_sim_research/fermi/distribution/... [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 12023]
2014-08-14Adding 64-bit support for atomicAdd, atomicExch, atomicCAS and created a ↵Wilson Fung
brief directed test. Added floating point support for atomicAdd without testing. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11894]
2014-08-14Integration change. Fix for div_impl with 32-bit and smaller integers.Wilson Fung
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11310]
2014-08-14Integrating the pure functional simulationAyub Gubran
Merging //depot/gpgpu_sim_research/fermi_ayoub/distribution/src/cuda-sim/cuda-sim.cc //depot/gpgpu_sim_research/fermi_ayoub/distribution/src/cuda-sim/cuda-sim.h //depot/gpgpu_sim_research/fermi_ayoub/distribution/src/cuda-sim/instructions.cc //depot/gpgpu_sim_research/fermi_ayoub/distribution/src/cuda-sim/ptx_sim.h to //depot/gpgpu_sim_research/fermi/distribution/src/cuda-sim/... [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11288]
2014-08-14change copyright notice to include authorsTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 9872]
2011-06-29changing copyright to BSDTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 9687]
2010-12-15Added next instruction type to ptxplus, ".ff64". It's the same as ".f64" ↵Jimmy Kwa
except it reads and stores from two adjacent registers instead of a single 64 bit register. ".ff64" instructions are now printed in decuda_to_ptxplus. Support in the simulator for ".ff64" has been added but it is untested. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 8278]
2010-10-240.9756 correlation. Set L1T line size to 128 bytes... problem wasTor Aamodt
stalling to send four requests per warp into L1T tag lookup. If L1T is really 32B blocks (as per Henry's paper), this suggests banking of L1T needs to be modeled. Other changes: 1. bug fix in memory access generation for texture/const cache access 2. adding back memory latency measurement for visualizer [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7913]
2010-10-22enables global loads/stores for ptxplusTor Aamodt
passing CUDA 3.1 and ptxplus correlation correlation back to around 0.89 on ptxplus vs quadro fx5800 [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7898]
2010-10-121. adding simt_core_cluster, which models a TPC or (for fermi) GPC...Tor Aamodt
this gives us a place to stick caches shared among shader cores but on the shader side of the interconnect... maybe move the clock boundary code here? after integrating booksim 2 code? 2. added a pending write table to ldst_unit rather than scoreboard ... rationale is that ld/st unit needs to process register writes once it is done it can notify scoreboard once. 3. re-enabled shared memory delay (use pipeline within ldst_unit) 4. re-enabling operand collector writeback for all instruction types 5. disable MSHRs in this change list passing CUDA 3.1 regression next? texture cache, then redo mshrs? [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7845]
2010-10-09refactoring: moving texture reference mappings into gpgpu_t Tor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7835]
2010-10-081. refactoring cuda api code for loading PTX (removing external PTX loading ↵Tor Aamodt
entirely) 2. some bug fixes for warp_inst_t 3. creating a new class, gpgpu_t, which contains the functional "memory" state visible to all threads running on a GPU (doing this as part of my continuing effort to hunt down and eradicate every global variable that is not the top level "the gpu") 4. other misc. changes Almost passing CUDA 3.1 regression? oclHistogram keeps failing under torque, but does not fail when run on the command line from the same directory. [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7827]
2010-10-05broken change list: builds, but does not run, yetTor Aamodt
refactoring: create warp_inst_t that provides notion of a group of scalar instructions traveling down the pipeline. delete DWF delete MIMD delete warp_tracker delete old writeback stage, replace it with a stub that just writes back everything delete old pipeline model current status: MSHR's need to change to deal with the new structure [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7814]
2010-10-01integrating recent changes from fermi-test into fermiTor Aamodt
(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]
2010-08-30integrating CL 7421-7434 from fermi-test Tor Aamodt
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]
2010-08-29- integrate changes from fermi-test (CL's under that path in range 7261-7418).Tor Aamodt
(add scoreboard logic from ptxplus branch and modified operand collector with parallel ALU/SFU pipelines) passing regressions [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7419]
2010-08-23- add '-keep' option to keep intermediate files (used for OpenCL only right now)Tor Aamodt
- remove redundant initialization code of options (which confuses new users) - make bool option variables bool type - remove some more extern decls [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7247]
2010-08-08refactoring: moving PTX parsing functions into ptx_parser.*Tor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7167]
2010-08-08refactoring: moving 'loading' operations into ptx_loader.*Tor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7166]
2010-08-07watchpoint facility for ptx debuggingTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 7160]
2010-07-21- reduce 3.1 sdk regression test runtimes (as per 2.3 sdk versions)Tor Aamodt
- 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]
2010-07-19OpenCL running on simulator w/ CUDA 3.1 and nvidia driver 256.35Tor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6907]
2010-07-18finished refactor+implement call/return passing (now working on simple ↵Tor Aamodt
example included in this CL) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6886]
2010-07-18more refactoring of param passingTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6885]
2010-07-18continuing refactoring Tor Aamodt
modify template to actually do a function call (for testing real function call, not printf) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6884]
2010-07-18refactoring call/return ABI code (want unified interface for call/return ↵Tor Aamodt
reg/param) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6883]
2010-07-18finished moving cuda printf stuff to seperate file (step 2)Tor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6882]
2010-07-18refactoringTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6880]
2010-07-18- simple device printf support added (supports %u, %d, %f)Tor Aamodt
- add support to call_impl for passing values in through local param space (need to add support for return) - track local framesize during ptx parsing / update local stack-pointer during call/return - detect appropriate param space for ld.param (and st.param) depending upon address symbol's scope - putting back the crazy math for local mem allocation (seems to be required) - bug fix for global byte array initialization - force ld and st w/o space specifier to be generic_space - make type_decode method of type_info_key - adjust debug printing so listing of code and CFG information requires higher numbers (100 and 50) - local param ld/st accesses treated like local ld/st for timing model [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6878]
2010-07-17- added *implied* local memory stack pointer for functional execution Tor Aamodt
(still need to determine framesize during parsing, and need to support alternate mode were stack pointer is explicit register a la zev...) - define local param mapping to local memory for functional execution [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6875]
2010-07-17param space updates for correct parsing (still need to allocate thread Tor Aamodt
local storage for local param memory) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6871]
2010-07-17- adding new memory_space_t type to enable differentiation of differentTor Aamodt
parameter spaces (kernel parameters are conceptually different from function parameters, but PTX only has one .param keyword) - removing more dead code [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6870]
2010-07-17integrating Wilson's bugfixes from release branchTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6869]
2010-07-17- add support for ld/st with generic addressesTor Aamodt
- add support for parsing cache operators (still need to pass to timing model) [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6868]
2010-07-17- add support for cvta and isspacep instructions (currently assumingTor Aamodt
a fixed address mapping between shared,local to generic that depends upon hardware thread context used... might be interesting to explore tradeoffs at some point) - remove util.h... we don't need TRUE, FALSE anymore now that everything is C++ - remove some dead code from shader_decode [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6867]
2010-07-16- integrate Wilson's bug fixes from release Tor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6852]
2010-07-16- adding placeholders for new builtin registersTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6848]
2010-07-16- add placeholders for new (e.g., PTX 2.x) directives and instructionsTor Aamodt
- 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]
2010-07-16- BlackScholes passing on CUDA 3.1Tor Aamodt
- 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]
2010-07-15compiles with CUDA 3.1 (but, nothing tested)Tor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6832]
2010-07-15creating branch for adding support for CUDA 3.x and FermiTor Aamodt
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6829]
generated by cgit v1.3 (git 2.53.0) at 2026-07-13 21:25:06 +0000