AMDGPU: Don't check constant address space for atomic stores

[arsenm]

Summary

We define a separate list for storable address spaces. This saves
entry in the matcher table address space list.

[rampitec]

LGTM

[arsenm]

84e035d8f1d635d202692e3c38c9c96aa1e08088

llvm/lib/Target/AMDGPU/AMDGPUInstructions.td

def atomic_load_32_#as : PatFrag<(ops node:$ptr), (atomic_load_32 node:$ptr)> {
   let IsAtomic = 1;
   let MemoryVT = i32;
 }
 
 def atomic_load_64_#as : PatFrag<(ops node:$ptr), (atomic_load_64 node:$ptr)> {
   let IsAtomic = 1;
   let MemoryVT = i64;
 }
+} // End let AddressSpaces
+} // End foreach as
 
+
+foreach as = [ "global", "flat", "local", "private", "region" ] in {
+let AddressSpaces = !cast<AddressSpaceList>("StoreAddress_"#as).AddrSpaces in {
 def store_#as : PatFrag<(ops node:$val, node:$ptr),
                     (unindexedstore node:$val, node:$ptr)> {
   let IsStore = 1;
   let IsTruncStore = 0;
 }
 
 // truncstore fragments.
 def truncstore_#as : PatFrag<(ops node:$val, node:$ptr),

 }
 
 def store_hi16_#as : StoreHi16 <truncstorei16>;
 def truncstorei8_hi16_#as : StoreHi16<truncstorei8>;
 def truncstorei16_hi16_#as : StoreHi16<truncstorei16>;
 
 defm atomic_store_#as : binary_atomic_op<atomic_store>;
 
-} // End let AddressSpaces = ...
-} // End foreach AddrSpace
+} // End let AddressSpaces
+} // End foreach as
 
 
 multiclass ret_noret_binary_atomic_op<SDNode atomic_op, bit IsInt = 1> {
   foreach as = [ "global", "flat", "constant", "local", "private", "region" ] in {
     let AddressSpaces = !cast<AddressSpaceList>("LoadAddress_"#as).AddrSpaces in {
       defm "_"#as : binary_atomic_op<atomic_op, IsInt>;
 
       let PredicateCode = [{return (SDValue(N, 0).use_empty());}] in {