Stub abstract interpretation support

Author: vchuravy

src/driver.jl

@@ -130,6 +130,9 @@ function codegen(output::Symbol, @nospecialize(job::CompilerJob);
     error("Unknown compilation output $output")
 end
 
+@noinline function var"gpuc.deferred"(f, args...) end
+@noinline function var"gpuc.lookup"(mi, f, args...) end
+
 # primitive mechanism for deferred compilation, for implementing CUDA dynamic parallelism.
 # this could both be generalized (e.g. supporting actual function calls, instead of
 # returning a function pointer), and be integrated with the nonrecursive codegen.

src/jlgen.jl

@@ -435,6 +435,17 @@ function CC.concrete_eval_eligible(interp::GPUInterpreter,
     return ret
 end
 
+function CC.abstract_call_known(interp::GPUInterpreter, @nospecialize(f),
+        arginfo::CC.ArgInfo, si::CC.StmtInfo, sv::CC.AbsIntState,
+        max_methods::Int = CC.get_max_methods(interp, f, sv))
+    if f === var"gpuc.deferred" ||
+       f === var"gpuc.lookup"
+        return CC.CallMeta(Ptr{Cvoid}, Union{}, CC.Effects(), CC.NoCallInfo())
+    end
+    return @invoke CC.abstract_call_known(interp::CC.AbstractInterpreter, f,
+        arginfo::CC.ArgInfo, si::CC.StmtInfo, sv::CC.AbsIntState,
+        max_methods::Int)
+end
 
 ## world view of the cache
 using Core.Compiler: WorldView