[flang][rt] Add noinline attributes for CUDA compile path for successful compilation (#161760)

NVCC does more aggressive inlining than Clang/GCC causing the exported
functions in extrema.cpp and findloc.cpp to become extremely large from
function specializations leading to compilation timeouts. Marking the 2
functions in this change as noinline for NVCC alleviates this problem as
it removes the worst of the cross-matrix argument specializations.

Also remove the workaround in
https://github.com/llvm/llvm-project/pull/156542 that opted out
findloc.cpp from the CUDA flang-rt build

Testing:
ninja flang-rt builds in ~30 minutes, these 2 files build in ~3 minutes

3 files changed, 13 insertions, 10 deletions

diff --git a/flang-rt/lib/runtime/CMakeLists.txt b/flang-rt/lib/runtime/CMakeLists.txt
index 6548ec955b2b..e8f70bd544e0 100644
--- a/flang-rt/lib/runtime/CMakeLists.txt
+++ b/flang-rt/lib/runtime/CMakeLists.txt
@@ -178,9 +178,6 @@ endif ()
 if ("${LLVM_RUNTIMES_TARGET}" MATCHES "^amdgcn|^nvptx")
   set(sources ${gpu_sources})
 elseif(FLANG_RT_EXPERIMENTAL_OFFLOAD_SUPPORT STREQUAL "CUDA")
-  # findloc.cpp has some issues with higher compute capability. Remove it
-  # from CUDA build until we can lower its memory footprint.
-  list(REMOVE_ITEM supported_sources findloc.cpp)
   set(sources ${supported_sources})
 else ()
   set(sources ${supported_sources} ${host_sources} ${f128_sources})
diff --git a/flang-rt/lib/runtime/extrema.cpp b/flang-rt/lib/runtime/extrema.cpp
index 9846529665e8..c4575cced901 100644
--- a/flang-rt/lib/runtime/extrema.cpp
+++ b/flang-rt/lib/runtime/extrema.cpp
@@ -397,9 +397,12 @@ template <TypeCategory CAT, bool IS_MAX,
     template <typename, bool, bool> class COMPARE>
 struct DoPartialMaxOrMinLocHelper {
   template <int KIND> struct Functor {
-    RT_API_ATTRS void operator()(const char *intrinsic, Descriptor &result,
-        const Descriptor &x, int kind, int dim, const Descriptor *mask,
-        bool back, Terminator &terminator) const {
+    // NVCC inlines more aggressively which causes too many specializations of
+    // this function to be inlined causing compiler timeouts. Set as
+    // noinline to allow compilation to complete.
+    RT_API_ATTRS RT_DEVICE_NOINLINE void operator()(const char *intrinsic,
+        Descriptor &result, const Descriptor &x, int kind, int dim,
+        const Descriptor *mask, bool back, Terminator &terminator) const {
       DoPartialMaxOrMinLoc<CAT, KIND, IS_MAX, COMPARE>(
           intrinsic, result, x, kind, dim, mask, back, terminator);
     }
diff --git a/flang-rt/lib/runtime/findloc.cpp b/flang-rt/lib/runtime/findloc.cpp
index 5485f4b97bd2..b5031ec95508 100644
--- a/flang-rt/lib/runtime/findloc.cpp
+++ b/flang-rt/lib/runtime/findloc.cpp
@@ -153,10 +153,13 @@ template <TypeCategory CAT,
     class HELPER>
 struct NumericFindlocHelper {
   template <int KIND> struct Functor {
-    RT_API_ATTRS void operator()(TypeCategory targetCat, int targetKind,
-        Descriptor &result, const Descriptor &x, const Descriptor &target,
-        int kind, int dim, const Descriptor *mask, bool back,
-        Terminator &terminator) const {
+    // NVCC inlines more aggressively which causes too many specializations of
+    // this function to be inlined causing compiler timeouts. Set as
+    // noinline to allow compilation to complete.
+    RT_API_ATTRS RT_DEVICE_NOINLINE void operator()(TypeCategory targetCat,
+        int targetKind, Descriptor &result, const Descriptor &x,
+        const Descriptor &target, int kind, int dim, const Descriptor *mask,
+        bool back, Terminator &terminator) const {
       switch (targetCat) {
       case TypeCategory::Integer:
       case TypeCategory::Unsigned: