From 555cce395bb8457a209b26f6f7ff62cc09839fdf Mon Sep 17 00:00:00 2001 From: bftf Date: Mon, 11 Nov 2019 12:29:15 -0800 Subject: Enabled CUDA 10. Added implementations for __cudaPushCallConfiguration and __cudaPopCallConfiguration, neither of which are documented in the CUDA API but they preceed any cudaLaunchKernel() call and push the call configuration on a stack which is then popped when cudaLaunchKernel() is called. Currently the max stack size is 1, an assert will be triggered when this is violated. --- CHANGES | 1 + 1 file changed, 1 insertion(+) (limited to 'CHANGES') diff --git a/CHANGES b/CHANGES index 2a4222b..31ae672 100644 --- a/CHANGES +++ b/CHANGES @@ -37,6 +37,7 @@ Version 4.0.0 (development branch) versus 3.2.3 3- Addig new system stats: gpu occupancy, L2BW, etc -Library: 1 Enabled CUTLASS Library on GPGPU-Sim +2 Enabled CUDA 10 -Regression: 1- Added TensorCore Regression Kernel -Configs: -- cgit v1.3 From e9e9fcf5957530ecb927aecb5ea238e4b78a4f45 Mon Sep 17 00:00:00 2001 From: tgrogers Date: Tue, 21 Apr 2020 14:50:53 -0400 Subject: some additional changes descriptions --- CHANGES | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'CHANGES') diff --git a/CHANGES b/CHANGES index 31ae672..0c48a3d 100644 --- a/CHANGES +++ b/CHANGES @@ -44,6 +44,10 @@ Version 4.0.0 (development branch) versus 3.2.3 Adding the Pascal and Volta config files that has been correlated against real hardware. See the correlation website here: https://engineering.purdue.edu/tgrogers/group/correlator.html +-General: +1 - Applied a code formatting standard +2 - Minimized number of global variables (to make the simulator parallelizable across multiple threads or multiple processes). +All previous, independent global variables are now members of an object at some level. Version 3.2.3+edits (development branch) versus 3.2.3 - Support for running regression tests using Travis -- cgit v1.3