[libc] Fix using the `libcgpu.a` for NVPTX in non-LTO builds

[jhuber6]

Summary

CUDA requires a PTX feature to be compiled generally, because the
libcgpu.a archive contains LLVM-IR we need to have one present to
compile it. Currently, the wrapper fatbinary format we use to
incorporate these into single-source offloading languages has a special
option to provide this. Since this was not present in the builds, if the
user did not specify it via -foffload-lto it would not compile from
CUDA or OpenMP due to the missing PTX features. Fix this by passing it
to the packager invocation.

libc/cmake/modules/LLVMLibCObjectRules.cmake

foreach(gpu_arch ${LIBC_GPU_ARCHITECTURES})
           CXX_STANDARD ${ADD_GPU_OBJ_CXX_STANDARD}
       )
       if(ADD_GPU_OBJ_DEPENDS)
         add_dependencies(${gpu_target_name} ${ADD_GPU_OBJ_DEPENDS})
       endif()
 
       # Append this target to a list of images to package into a single binary.
       set(input_file $<TARGET_OBJECTS:${gpu_target_name}>)
+      if("${gpu_arch}" IN_LIST all_nvptx_architectures)
+        string(REGEX MATCH "\\+ptx[0-9]+" nvptx_ptx_feature ${nvptx_options})
+        list(APPEND packager_images
+             --image=file=${input_file},arch=${gpu_arch},triple=${gpu_target_triple},feature=${nvptx_ptx_feature})
+      else()
         list(APPEND packager_images
              --image=file=${input_file},arch=${gpu_arch},triple=${gpu_target_triple})
+       endif()
       list(APPEND gpu_target_names ${gpu_target_name})
     endforeach()
 
     # After building the target for the desired GPUs we must package the output
     # into a fatbinary, see https://clang.llvm.org/docs/OffloadingDesign.html for
     # more information.
     set(packaged_target_name ${fq_target_name}.${src_name}.__gpu__)
     set(packaged_output_name ${CMAKE_CURRENT_BINARY_DIR}/${fq_target_name}.${src_name}.gpubin)