[clang] [clang][CodeGen] Emit atomic IR in place of optimized libcalls. (PR #73176)

[James Y Knight via cfe-commits]

================
@@ -1047,122 +1019,19 @@ RValue CodeGenFunction::EmitAtomicExpr(AtomicExpr *E) {
       Dest = Atomics.castToAtomicIntPointer(Dest);
   }
 
-  // Use a library call.  See: http://gcc.gnu.org/wiki/Atomic/GCCMM/LIbrary .
-  if (UseLibcall) {
-    bool UseOptimizedLibcall = false;
-    switch (E->getOp()) {
-    case AtomicExpr::AO__c11_atomic_init:
-    case AtomicExpr::AO__opencl_atomic_init:
-      llvm_unreachable("Already handled above with EmitAtomicInit!");
-
-    case AtomicExpr::AO__atomic_fetch_add:
-    case AtomicExpr::AO__atomic_fetch_and:
-    case AtomicExpr::AO__atomic_fetch_max:
-    case AtomicExpr::AO__atomic_fetch_min:
-    case AtomicExpr::AO__atomic_fetch_nand:
-    case AtomicExpr::AO__atomic_fetch_or:
-    case AtomicExpr::AO__atomic_fetch_sub:
-    case AtomicExpr::AO__atomic_fetch_xor:
-    case AtomicExpr::AO__atomic_add_fetch:
-    case AtomicExpr::AO__atomic_and_fetch:
-    case AtomicExpr::AO__atomic_max_fetch:
-    case AtomicExpr::AO__atomic_min_fetch:
-    case AtomicExpr::AO__atomic_nand_fetch:
-    case AtomicExpr::AO__atomic_or_fetch:
-    case AtomicExpr::AO__atomic_sub_fetch:
-    case AtomicExpr::AO__atomic_xor_fetch:
-    case AtomicExpr::AO__c11_atomic_fetch_add:
-    case AtomicExpr::AO__c11_atomic_fetch_and:
-    case AtomicExpr::AO__c11_atomic_fetch_max:
-    case AtomicExpr::AO__c11_atomic_fetch_min:
-    case AtomicExpr::AO__c11_atomic_fetch_nand:
-    case AtomicExpr::AO__c11_atomic_fetch_or:
-    case AtomicExpr::AO__c11_atomic_fetch_sub:
-    case AtomicExpr::AO__c11_atomic_fetch_xor:
-    case AtomicExpr::AO__hip_atomic_fetch_add:
-    case AtomicExpr::AO__hip_atomic_fetch_and:
-    case AtomicExpr::AO__hip_atomic_fetch_max:
-    case AtomicExpr::AO__hip_atomic_fetch_min:
-    case AtomicExpr::AO__hip_atomic_fetch_or:
-    case AtomicExpr::AO__hip_atomic_fetch_sub:
-    case AtomicExpr::AO__hip_atomic_fetch_xor:
-    case AtomicExpr::AO__opencl_atomic_fetch_add:
-    case AtomicExpr::AO__opencl_atomic_fetch_and:
-    case AtomicExpr::AO__opencl_atomic_fetch_max:
-    case AtomicExpr::AO__opencl_atomic_fetch_min:
-    case AtomicExpr::AO__opencl_atomic_fetch_or:
-    case AtomicExpr::AO__opencl_atomic_fetch_sub:
-    case AtomicExpr::AO__opencl_atomic_fetch_xor:
-    case AtomicExpr::AO__scoped_atomic_fetch_add:
-    case AtomicExpr::AO__scoped_atomic_fetch_and:
-    case AtomicExpr::AO__scoped_atomic_fetch_max:
-    case AtomicExpr::AO__scoped_atomic_fetch_min:
-    case AtomicExpr::AO__scoped_atomic_fetch_nand:
-    case AtomicExpr::AO__scoped_atomic_fetch_or:
-    case AtomicExpr::AO__scoped_atomic_fetch_sub:
-    case AtomicExpr::AO__scoped_atomic_fetch_xor:
-    case AtomicExpr::AO__scoped_atomic_add_fetch:
-    case AtomicExpr::AO__scoped_atomic_and_fetch:
-    case AtomicExpr::AO__scoped_atomic_max_fetch:
-    case AtomicExpr::AO__scoped_atomic_min_fetch:
-    case AtomicExpr::AO__scoped_atomic_nand_fetch:
-    case AtomicExpr::AO__scoped_atomic_or_fetch:
-    case AtomicExpr::AO__scoped_atomic_sub_fetch:
-    case AtomicExpr::AO__scoped_atomic_xor_fetch:
-      // For these, only library calls for certain sizes exist.
-      UseOptimizedLibcall = true;
-      break;
-
-    case AtomicExpr::AO__atomic_load:
-    case AtomicExpr::AO__atomic_store:
-    case AtomicExpr::AO__atomic_exchange:
-    case AtomicExpr::AO__atomic_compare_exchange:
-    case AtomicExpr::AO__scoped_atomic_load:
-    case AtomicExpr::AO__scoped_atomic_store:
-    case AtomicExpr::AO__scoped_atomic_exchange:
-    case AtomicExpr::AO__scoped_atomic_compare_exchange:
-      // Use the generic version if we don't know that the operand will be
-      // suitably aligned for the optimized version.
-      if (Misaligned)
-        break;
-      [[fallthrough]];
-    case AtomicExpr::AO__atomic_load_n:
-    case AtomicExpr::AO__atomic_store_n:
-    case AtomicExpr::AO__atomic_exchange_n:
-    case AtomicExpr::AO__atomic_compare_exchange_n:
-    case AtomicExpr::AO__c11_atomic_load:
-    case AtomicExpr::AO__c11_atomic_store:
-    case AtomicExpr::AO__c11_atomic_exchange:
-    case AtomicExpr::AO__c11_atomic_compare_exchange_weak:
-    case AtomicExpr::AO__c11_atomic_compare_exchange_strong:
-    case AtomicExpr::AO__hip_atomic_load:
-    case AtomicExpr::AO__hip_atomic_store:
-    case AtomicExpr::AO__hip_atomic_exchange:
-    case AtomicExpr::AO__hip_atomic_compare_exchange_weak:
-    case AtomicExpr::AO__hip_atomic_compare_exchange_strong:
-    case AtomicExpr::AO__opencl_atomic_load:
-    case AtomicExpr::AO__opencl_atomic_store:
-    case AtomicExpr::AO__opencl_atomic_exchange:
-    case AtomicExpr::AO__opencl_atomic_compare_exchange_weak:
-    case AtomicExpr::AO__opencl_atomic_compare_exchange_strong:
-    case AtomicExpr::AO__scoped_atomic_load_n:
-    case AtomicExpr::AO__scoped_atomic_store_n:
-    case AtomicExpr::AO__scoped_atomic_exchange_n:
-    case AtomicExpr::AO__scoped_atomic_compare_exchange_n:
-      // Only use optimized library calls for sizes for which they exist.
-      // FIXME: Size == 16 optimized library functions exist too.
-      if (Size == 1 || Size == 2 || Size == 4 || Size == 8)
-        UseOptimizedLibcall = true;
-      break;
-    }
+  bool PowerOf2Size = (Size & (Size - 1)) == 0;
+  bool UseLibcall = !PowerOf2Size | (Size > 16);
 
+  // Use a library call.  See: http://gcc.gnu.org/wiki/Atomic/GCCMM/Library.
----------------
jyknight wrote:

Suggestion for updated comment:

> For atomics larger than 16 bytes, emit a libcall from the frontend. This avoids the overhead of dealing with excessively-large value types in IR. Non-power-of-2 values also lower to libcall here, as they are not currently permitted in IR instructions (although that constraint could be relaxed in the future). For other cases where a libcall is required on a given platform, we let the backend handle it (this includes handling for all of the size-optimized libcall variants, which are only valid up to 16 bytes.)
>
> See: https://llvm.org/docs/Atomics.html#libcalls-atomic


https://github.com/llvm/llvm-project/pull/73176