Allowing modern GPU configrations to properly run PTXPLUS.

There are several problems with this:

1) To get proper occupancy, based on register file usage, you must querry ptxas with
   the sm version that corresponds to the register usage in the config file. To enable this,
   a new config option has been added that determines what sm version you pass to ptxas to compute reg-usage.
   This configuration option is always required in the gpgpusim.config file
2) If you are running PTXPLUS with a modern card (i.e. volta/pascal), you need ptxas from CUDA 9.1.
   However since PTXPLUS only supports sm_13 - you need a version of CUDA where cudaobjectdump
   supports sm_1x. This ended at CUDA 5 - and PTXPLUS requires CUDA 4.2. Therefore, to run PTXPLUS
   on a modern card, you need CUDA 4.2 + modern CUDA installed. To fascilitate this, a new envronment
   varaible is added and the setup envrionment script prints an appropraite warning if you are using a newer CUDA.

We have tried to make this as fail-proof as possible - and die appropraitely when something is wrong.

6 files changed, 10 insertions, 1 deletions

diff --git a/configs/GTX480/gpgpusim.config b/configs/GTX480/gpgpusim.config
index 436cb41..ee90c12 100644
--- a/configs/GTX480/gpgpusim.config
+++ b/configs/GTX480/gpgpusim.config
@@ -22,6 +22,7 @@
 
 # shader core pipeline config
 -gpgpu_shader_registers 32768
+-gpgpu_occupancy_sm_number 20
 
 # This implies a maximum of 48 warps/SM
 -gpgpu_shader_core_pipeline 1536:32 
diff --git a/configs/GeForceGTX1080Ti/gpgpusim.config b/configs/GeForceGTX1080Ti/gpgpusim.config
index 47c2b6a..fb044c6 100644
--- a/configs/GeForceGTX1080Ti/gpgpusim.config
+++ b/configs/GeForceGTX1080Ti/gpgpusim.config
@@ -3,7 +3,7 @@
 # functional simulator specification
 -gpgpu_ptx_instruction_classification 0
 -gpgpu_ptx_sim_mode 0
--gpgpu_ptx_force_max_capability 20 
+-gpgpu_ptx_force_max_capability 60
 
 # SASS execution (only supported with CUDA >= 4.0)
 -gpgpu_ptx_convert_to_ptxplus 0
@@ -23,6 +23,7 @@
 
 # shader core pipeline config
 -gpgpu_shader_registers 65536
+-gpgpu_occupancy_sm_number 60
 
 # This implies a maximum of 64 warps/SM
 -gpgpu_shader_core_pipeline 2048:32 
diff --git a/configs/GeForceGTX750Ti/gpgpusim.config b/configs/GeForceGTX750Ti/gpgpusim.config
index 8b030b6..c675aab 100644
--- a/configs/GeForceGTX750Ti/gpgpusim.config
+++ b/configs/GeForceGTX750Ti/gpgpusim.config
@@ -21,6 +21,7 @@
 
 # shader core pipeline config
 -gpgpu_shader_registers 65536
+-gpgpu_occupancy_sm_number 52
 
 # This implies a maximum of 64 warps/SM
 -gpgpu_shader_core_pipeline 2048:32 
diff --git a/configs/QuadroFX5600/gpgpusim.config b/configs/QuadroFX5600/gpgpusim.config
index cb87b65..6f836ee 100644
--- a/configs/QuadroFX5600/gpgpusim.config
+++ b/configs/QuadroFX5600/gpgpusim.config
@@ -11,6 +11,9 @@
 
 # shader core pipeline config
 -gpgpu_shader_registers 16384
+-gpgpu_occupancy_sm_number 12
+
+-gpgpu_occupancy_sm_number 12
 #8192 (registers per block as written by device Query and which used in this option in our other configurations but this break some benchmarks execution! it does not affect performance modeling though)
 -gpgpu_shader_core_pipeline 768:32 
 -gpgpu_shader_cta 8
diff --git a/configs/QuadroFX5800/gpgpusim.config b/configs/QuadroFX5800/gpgpusim.config
index 82243c2..fef1110 100644
--- a/configs/QuadroFX5800/gpgpusim.config
+++ b/configs/QuadroFX5800/gpgpusim.config
@@ -11,6 +11,8 @@
 
 # shader core pipeline config
 -gpgpu_shader_registers 16384
+-gpgpu_occupancy_sm_number 13
+
 -gpgpu_shader_core_pipeline 1024:32 
 -gpgpu_shader_cta 8
 -gpgpu_simd_model 1
diff --git a/configs/TeslaC2050/gpgpusim.config b/configs/TeslaC2050/gpgpusim.config
index 442ab8b..6ac2c12 100644
--- a/configs/TeslaC2050/gpgpusim.config
+++ b/configs/TeslaC2050/gpgpusim.config
@@ -25,6 +25,7 @@
 
 # shader core pipeline config
 -gpgpu_shader_registers 32768
+-gpgpu_occupancy_sm_number 20
 
 # This implies a maximum of 48 warps/SM
 -gpgpu_shader_core_pipeline 1536:32