Add copy_contender benchmark, Makefile, and copy_testbench header

Benchmark supports:
=> Generating a chain of copies in a single context
    - No timing pause between copies
=> Copies to, from, or between device(s)
=> Variable size and number of copies
=> Logging how many milliseconds each copy takes

*** Warning ***
* Relies on implicit synchronization of unidirectional copies across
* streams. Verify that this is still the case with CUDA before
* trusting results. One can check by verifying that the runtime for
* one iteration roughly matches the time for each iteration in a
* multi-iteration run.
***

1 files changed, 3 insertions, 0 deletions

diff --git a/copy_experiments/Makefile b/copy_experiments/Makefile
new file mode 100644
index 0000000..2358c60
--- /dev/null
+++ b/copy_experiments/Makefile
@@ -0,0 +1,3 @@
+
+copy_contender: copy_contender.cu copy_testbench.h
+        /usr/local/cuda/bin/nvcc copy_contender.cu -o $@ -lcuda -g