From bf2f85331ff81618ff51635179765653d508716f Mon Sep 17 00:00:00 2001 From: Tim Rogers Date: Sat, 23 Feb 2013 11:36:21 -0800 Subject: Udating the changes file to be more accurate [git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 15313] --- CHANGES | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'CHANGES') diff --git a/CHANGES b/CHANGES index 8de6271..8fb6d6a 100644 --- a/CHANGES +++ b/CHANGES @@ -31,6 +31,7 @@ Version 3.2.0+edits (development branch) versus 3.2.0 - Added support in ptx_instruction to return a std::string which returns the ptx/ptxplus line. - Added a Greedy Then Oldest (GTO) warp scheduler as described by Rogers et al.(Cache-Conscious Wavefront Scheduling - MICRO 45). +- Set the GTO scheduler as the default in the GTX480 configuration. - Bug Fixes: - Applied patch from Kito Cheng to update libopencl for checking NULL error code pointer. @@ -49,8 +50,6 @@ Version 3.2.0+edits (development branch) versus 3.2.0 denoted by "_". This has been fixed. - Fixed the implementation of the two level scheduler. Previously testing if an instruction was dependent on a long latency operation was broken - - Cleaned up some inefficent code in the ptx_instruction to_string() - - Fixed an error generted by valgrind due to forgetting to initialize a member variable Version 3.2.0 versus 3.1.2 - Added GPUWattch GPGPU power model based on McPAT 0.8beta. -- cgit v1.3