Integration from TM-311 branch.

- Updated PTX parser to support CUDA 4.1 and 4.2.
  - Revised fatbin workaround to a more robust version (with comments explaining it).
  - Added print_simulation_time() in gpgpu_sim_thread_concurrent().

[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 13789]

1 files changed, 8 insertions, 3 deletions

diff --git a/CHANGES b/CHANGES
index 33ceee2..f077145 100644
--- a/CHANGES
+++ b/CHANGES
@@ -1,20 +1,25 @@
 CHANGE LOG:
 
 Version 3.1.1+edits (development branch) versus 3.1.1
+- Added support for CUDA 4.1 and 4.2 (PTX 3.0). 
 - Added an improved and less brittle support for associating fatbins to
   sections from the output of cuobjdump
+- Added raw simulation time printout back for CUDA.  
+- Revived support for PTX file override via environment variables for CUDA 4.0
+  onwards. 
 - Bug Fixes:
     - Fixed a compile error that happens with newer gcc/g++ versions (4.7.1)
-    - Fixed a bug with the association between cuobjdump output and cubin 
+    - Fixed a bug with the association between cuobjdump output and cubin
       handles (Bug #7 external)
     - Adding support for atomic operations with generic memory space.  Before
       this, atomic operations can only work on global memory space.  (Bug #14
       external)
-    - Fixed a bug in conversion to ptxplus that was causing local memory store 
+    - Fixed a bug in conversion to ptxplus that was causing local memory store
       or load instruction to be ignored.
     - Adding support for direct addressing using immediate values for the load
       and store instructions.
-    - Fixed a bug that was causing inconsistency in local memory address calculations
+    - Fixed a bug that was causing inconsistency in local memory address
+      calculations
 
 Version 3.1.1 versus 3.1.0
 - Add checks to top level makefile to ensure setup_environment is run and checks to