[Openmp-commits] [PATCH] D65836: Factor architecture dependent code out of loop.cu

[Jon Chesterfield via Phabricator via Openmp-commits]

JonChesterfield marked 2 inline comments as done.
JonChesterfield added inline comments.


================
Comment at: openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.h:17-18
+
+#define FORCEINLINE __forceinline__ __device__
+
+FORCEINLINE void __kmpc_impl_unpack(int64_t val, int32_t *lo, int32_t *hi) {
----------------
ABataev wrote:
> JonChesterfield wrote:
> > ABataev wrote:
> > > Better to use original `INLINE` macro defined in the project rather than to define the new one.
> > I'd prefer that too, but INLINE maps to `__inline__`, rather than `__forceinline__`, and that leaves calls to these functions in the bitcode library for nvptx.
> Then better to fix original `INLINE` macro and replace `__inline__` with `__forceinline__`. I assume we'd like to inline all the functions.
That works for me. I suspect everything marked INLINE was intended to be inlined. Diff at D65876.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D65836/new/

https://reviews.llvm.org/D65836