diff options
| author | Ahmed El-Shafiey <[email protected]> | 2012-12-10 11:42:55 -0800 |
|---|---|---|
| committer | Andrew Boktor <[email protected]> | 2014-08-14 13:49:22 -0700 |
| commit | 98ad7857d0722fc605e0b62f05bb1f23893cd6a0 (patch) | |
| tree | 675c4d201c58a25b8ca5368e8d0a0481cc58259b /CHANGES | |
| parent | ddad2b1ddd4dbd1c8641c90984b22cccf403dc4c (diff) | |
Adding a line to the CHANGES says we added a power model based on McPAT 0.8beta, now it is under (Version 3.1.2 versus 3.1.1) may be moved later if we decided to update the version
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 14779]
Diffstat (limited to 'CHANGES')
| -rw-r--r-- | CHANGES | 1 |
1 files changed, 1 insertions, 0 deletions
@@ -29,6 +29,7 @@ Version 3.1.2 versus 3.1.1 drivers newer than version 256.40. - nvopencl_wrapper now works on machine with both AMD and NVIDIA GPUs. It will automatically compile the OpenCL Kernels via the NVIDIA platform. +- Added a GPGPU power model based on McPAT 0.8beta. - 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 |