[clang] [llvm] [clang][OpenMP] Add no-loop SPMD kernel promotion (PR #224041)

[Dhruva Chakrabarti via cfe-commits]

================
@@ -3934,6 +3961,55 @@ emitInnerParallelForWhenCombined(CodeGenFunction &CGF,
         HasCancel = D->hasCancel();
     }
     CodeGenFunction::OMPCancelStackRAII CancelRegion(CGF, EKind, HasCancel);
+
+    CodeGenModule &CGM = CGF.CGM;
+    if (CGM.getOpenMPRuntime().canPromoteToNoLoop()) {
----------------
dhruvachak wrote:

The loop directive is available, so there is no reason to require a cache.

https://github.com/llvm/llvm-project/pull/224041