Add preliminary implementation for GPGPU code generation.

Translate the selected parallel loop body into a ptx string and run it with the
cuda driver API. We limit this preliminary implementation to target the
following special test cases:

  - Support only 2-dimensional parallel loops with or without only one innermost
    non-parallel loop.
  - Support write memory access to only one array in a SCoP.

The patch was committed with smaller changes to the build system:

There is now a flag to enable gpu code generation explictly. This was required
as we need the llvm.codegen() patch applied on the llvm sources, to compile this
feature correctly. Also, enabling gpu code generation does not require cuda.
This requirement was removed to allow 'make polly-test' runs, even without an
installed cuda runtime.

Contributed by:  Yabin Hu  <yabin.hwu@gmail.com>

llvm-svn: 161239

1 files changed, 13 insertions, 0 deletions

diff --git a/polly/autoconf/configure.ac b/polly/autoconf/configure.ac
index 7780055..63df358 100644
--- a/polly/autoconf/configure.ac
+++ b/polly/autoconf/configure.ac
@@ -120,7 +120,20 @@ fi
 AC_SUBST(scoplib_rpath)
 
 dnl Check if CUDA lib there
+dnl Disable the build of polly, even if it is checked out into tools/polly.
+AC_ARG_ENABLE(polly_gpu_codegen,
+              AS_HELP_STRING([--enable-polly-gpu-codegen],
+                             [Enable GPU code generation in Polly(default is NO)]),,
+                             enableval=default)
+case "$enableval" in
+  yes) AC_DEFINE([GPU_CODEGEN],[1], [Define if gpu codegen is enabled]) ;;
+  no)  AC_DEFINE([GPU_CODEGEN],[0], [Define if gpu codegen is enabled]) ;;
+  default) AC_DEFINE([GPU_CODEGEN],[0],  [Define if gpu codegen is enabled]) ;;
+  *) AC_MSG_ERROR([Invalid setting for --enable-polly-gpu-codegen. Use "yes" or "no"]) ;;
+esac
+
 find_lib_and_headers([cuda], [cuda.h], [cuda])
+
 AS_IF([test "x$cuda_found" = "xyes"],
   [AC_DEFINE([CUDALIB_FOUND],[1],[Define if cudalib found])])