merged with memory subsytem. Regression is passing but tensorcore kernel is stuck in deadlock

1 files changed, 8 insertions, 2 deletions

diff --git a/README b/README
index 6e2d734..7eaae5d 100644
--- a/README
+++ b/README
@@ -5,8 +5,8 @@ AerialVision and a configurable and extensible energy model called GPUWattch.
 GPGPU-Sim and GPUWattch have been rigorously validated with performance and
 power measurements of real hardware GPUs. 
 
-This version of GPGPU-Sim has been tested with CUDA version 2.3, 3.1, 4.0, 
-5.0, 5.5, 6.0 and 7.5.
+This version of GPGPU-Sim has been tested with CUDA version 4.2,
+5.0, 5.5, 6.0 and 7.5, 8.0, 9.0, 9.1
 
 Please see the copyright notice in the file COPYRIGHT distributed with this
 release in the same directory as this file.
@@ -18,6 +18,12 @@ Analyzing CUDA Workloads Using a Detailed GPU Simulator, in IEEE International
 Symposium on Performance Analysis of Systems and Software (ISPASS), Boston, MA,
 April 19-21, 2009.
 
+If you use the memory system in GPGPU-Sim, or the Volta/Pascal models,
+please cite:
+Mahmoud Khairy, Jain Akshay, Tor Aamodt, Timothy G Rogers,
+Exploring Modern GPU Memory System Design Challenges through Accurate Modeling, arXiv:1810.07269, 
+https://arxiv.org/abs/1810.07269
+
 If you use the GPUWattch energy model in your research, please cite:
 
 Jingwen Leng, Tayler Hetherington, Ahmed ElTantawy, Syed Gilani, Nam Sung Kim,