7 files changed, 659 insertions, 240 deletions

diff --git a/.gitignore b/.gitignore
index 5f0fdbe..c42b364 100644
--- a/.gitignore
+++ b/.gitignore
@@ -8,6 +8,8 @@ libsmctrl_test_stream_mask
 libsmctrl_test_stream_mask_override
 libsmctrl_test_next_mask
 libsmctrl_test_next_mask_override
+libcuda.so.1
+nvtaskset
 *.pyc
 *.o
 .gdb_history
diff --git a/Makefile b/Makefile
index 62ec245..87a5708 100644
--- a/Makefile
+++ b/Makefile
@@ -3,9 +3,11 @@ CUDA ?= /usr/local/cuda
 # Note that CXX and CC are predefined as g++ and cc (respectively) by Make
 NVCC ?= $(CUDA)/bin/nvcc
 # Everything has to have -lcuda, as it's needed for libsmctrl
-LDFLAGS := -lcuda -I$(CUDA)/include -L$(CUDA)/lib64
+LDFLAGS := -ldl -lcuda -I$(CUDA)/include -L$(CUDA)/lib64
+ARCH = $(shell $(CC) -dumpmachine)
+CFLAGS := -Wall -Wno-parentheses
 
-.PHONY: clean tests all
+.PHONY: clean tests all install remove run_tests
 
 # ----- Main Library -----
 libsmctrl.so: libsmctrl.c libsmctrl.h
@@ -14,9 +16,14 @@ libsmctrl.so: libsmctrl.c libsmctrl.h
 # -fPIC is needed even if built as a static library, in case we are linked into
 # another shared library
 libsmctrl.a: libsmctrl.c libsmctrl.h
-        $(CC) $< -c -o libsmctrl.o -fPIC $(CFLAGS) $(LDFLAGS)
+        $(CC) $< -c -o libsmctrl.o -fPIC -DLIBSMCTRL_STATIC $(CFLAGS) $(LDFLAGS)
         ar rcs $@ libsmctrl.o
 
+# ----- CUDA Wrapper -----
+libcuda.so.1: libsmctrl.c libsmctrl.h
+        $(CC) $< -shared -o $@ -fPIC -DLIBSMCTRL_WRAPPER $(CFLAGS) $(LDFLAGS)
+        patchelf libcuda.so.1 --add-needed libcuda.so
+
 # ----- Utilities -----
 # Use static linking with tests to avoid LD_LIBRARY_PATH issues
 nvtaskset: nvtaskset.c libsmctrl.so libsmctrl.a
@@ -29,7 +36,7 @@ libsmctrl_test_gpc_info: libsmctrl_test_gpc_info.c libsmctrl.a testbench.h
 libsmctrl_test_mask_shared.o: libsmctrl_test_mask_shared.cu testbench.h
         $(NVCC) -ccbin $(CXX) $< -c -g
 
-libsmctrl_test_supreme_mask: libsmctrl_test_supreme_mask.c libsmctrl.a libsmctrl_test_mask_shared.o
+libsmctrl_test_supreme_mask: libsmctrl_test_supreme_mask.c libsmctrl.a libsmctrl_test_mask_shared.o libcuda.so.1 nvtaskset
         $(NVCC) -ccbin $(CXX) $@.c -o $@ libsmctrl_test_mask_shared.o -g -L. -l:libsmctrl.a $(LDFLAGS)
 
 libsmctrl_test_global_mask: libsmctrl_test_global_mask.c libsmctrl.a libsmctrl_test_mask_shared.o
@@ -52,7 +59,7 @@ tests: libsmctrl_test_gpc_info libsmctrl_test_supreme_mask \
        libsmctrl_test_stream_mask_override libsmctrl_test_next_mask \
        libsmctrl_test_next_mask_override
 
-all: libsmctrl.so nvtaskset tests
+all: libsmctrl.so libcuda.so.1 nvtaskset tests
 
 clean:
         rm -f libsmctrl.so libsmctrl.o libsmctrl.a libsmctrl_test_gpc_info \
@@ -60,4 +67,32 @@ clean:
               libsmctrl_test_global_mask \
               libsmctrl_test_stream_mask libsmctrl_test_stream_mask_override \
               libsmctrl_test_next_mask libsmctrl_test_next_mask_override \
-              nvtaskset
+              nvtaskset libcuda.so.1
+
+install: libcuda.so.1
+        @# Check that CUDA is installed first
+        test -f /lib/$(ARCH)/libcuda.so.*.*
+        @# Change libcuda.so link to bypass libcuda.so.1
+        sudo ln -sf /lib/$(ARCH)/libcuda.so.*.* /lib/$(ARCH)/libcuda.so
+        @# Remove libcuda.so.1 symlink
+        sudo rm /lib/$(ARCH)/libcuda.so.1
+        @# Install wrapper as libcuda.so.1
+        sudo cp libcuda.so.1 /lib/$(ARCH)/libcuda.so.1
+
+remove:
+        @# Test that our library in installed first
+        test ! -L /lib/$(ARCH)/libcuda.so.1
+        @# Overwrite install with original symlinks
+        sudo ln -sf libcuda.so.1 /lib/$(ARCH)/libcuda.so
+        sudo ln -sf /lib/$(ARCH)/libcuda.so.*.* /lib/$(ARCH)/libcuda.so.1
+
+run_tests: tests
+        ./libsmctrl_test_global_mask
+        ./libsmctrl_test_next_mask
+        ./libsmctrl_test_stream_mask
+        ./libsmctrl_test_next_mask_override
+        ./libsmctrl_test_stream_mask_override
+        @# Must set LD_LIBRARY_PATH in case make install has not been run
+        LD_LIBRARY_PATH=. ./libsmctrl_test_supreme_mask
+        ./libsmctrl_test_gpc_info
+        @ echo "All tests passed!"
diff --git a/README.md b/README.md
index f2be718..11ad153 100644
--- a/README.md
+++ b/README.md
@@ -13,16 +13,37 @@ Please cite this paper in any work which leverages our library. Here's the BibTe
   year={2023},
   month={May},
   pages={54--66},
+  doi={10.1109/RTAS58335.2023.00012},
   _series={RTAS}
 }
 ```
 
-Please see [the paper](https://www.cs.unc.edu/~jbakita/rtas23.pdf) and `libsmctrl.h` for details and examples of how to use this library.
+The ability for `libsmctrl` to work on unmodified tasks was developed as part of a follow-up paper:
+
+_J. Bakita and J. H. Anderson, "Hardware Compute Partitioning on NVIDIA GPUs for Composable Systems", Proceedings of the 37th Euromicro Conference on Real-Time Systems, pp. 18:1-18:24, July 2025._
+
+Please cite this paper in any work which uses this for partitioning unmodified tasks. Here's the BibTeX entry:
+```
+@inproceedings{bakita2025hardware,
+  title={Hardware Compute Partitioning on {NVIDIA} {GPUs} for Composable Systems},
+  author={Bakita, Joshua and Anderson, James H},
+  booktitle={Proceedings of the 37th Euromicro Conference on Real-Time Systems},
+  year={2025},
+  month={July},
+  pages={18:1--18:24},
+  doi={10.1109/ECRTS.2025.18},
+  _series={ECRTS}
+}
+```
+
+Please see [the first paper](https://www.cs.unc.edu/~jbakita/rtas23.pdf), [the second paper](https://www.cs.unc.edu/~jbakita/ecrts25.pdf) and `libsmctrl.h` for details and examples of how to use this library.
 We strongly encourage consulting those resources first; the below comments serve merely as an appendum.
 
 ## Run-time Dependencies
 `libcuda.so`, which is automatically installed by the NVIDIA GPU driver.
 
+(Technically `libdl` is also required, but this should never need to be manually installed. This is a dependency of CUDA, and is also part of the GNU C Standard Library starting with version 2.34.)
+
 ## Building
 To build, ensure that you have `gcc` installed and access to the CUDA SDK including `nvcc`. Then run:
 ```
@@ -66,8 +87,52 @@ nvcc benchmark.cu -o benchmark -I/playpen/libsmctl -lsmctrl -lcuda -L/playpen/li
 ```
 The resultant `benchmark` binary should be portable to any system with an equivalent or newer version of the NVIDIA GPU driver installed.
 
+## Use Without Application Modification
+As an alternative to modifying your application, `libsmctrl` can be installed system-wide, and partitions for each application can be set via the `nvtaskset` tool.
+The `nvtaskset` tool works very similarly to the Linux CPU-affinity-setting tool `taskset`.
+
+To install `libsmctrl` system-wide, such that all CUDA-using applications automatically load it, ensure that `patchelf` is installed (`sudo apt install patchelf`), and run:
+```
+make libcuda.so.1 install
+```
+Or, if you do not want to modify any system-wide state, and only want `libsmctrl` loaded as part of anything run from this console:
+```
+make libcuda.so.1
+export LD_LIBRARY_PATH=$(pwd)
+```
+(This works because CUDA is always dynamically loaded from `libcuda.so.1`, and `lbsmctrl` creates a "fake" `libcuda.so.1` in this directory that wraps CUDA.
+ Setting `LD_LIBRARY_PATH` ensures that the wrapped version is the first one loaded.
+ The only difference with running `make install` is that it copies our "fake" `libcuda.so.1` to a location where the loader will automatically find it.)
+
+And then to start an application within a specific TPC partition, e.g., the first 10 TPCs:
+```
+./nvtaskset -t 0-9 my_program my_args
+```
+Note that this will automatically start NVIDIA MPS, which is a prerequisite to co-run tasks on NVIDIA GPUs without timeslicing.
+
+And to change the TPCs available for a process ID 1234 to to the first 10 TPCs:
+```
+./nvtaskset -tp 0-9 1234
+```
+
+Or, to change a process of ID 1234 to only run on GPC 3:
+```
+./nvtaskset -gp 3 1234
+```
+
+To remove the system-wide installation of `libsmctrl`, run:
+```
+make remove
+```
+
 ## Run Tests
-To test partitioning:
+
+To run them all:
+```
+make run_tests
+```
+
+If you prefer to run them individually, to test partitioning:
 ```
 make tests
 ./libsmctrl_test_global_mask
@@ -82,18 +147,26 @@ make tests
 ./libsmctrl_test_next_mask_override
 ```
 
-And if `nvdebug` has been installed:
+To test that `nvtaskset` can dynamically change the mask of a running program:
 ```
-make tests
+make libsmctrl_test_supreme_mask
+./libsmctrl_test_supreme_mask
+```
+