[llvm] AMDGPU: Fix packed 16-bit inline constants (PR #76522)

[Nicolai Hähnle via llvm-commits]

================
@@ -532,7 +560,24 @@ void AMDGPUInstPrinter::printImmediate32(uint32_t Imm,
            STI.hasFeature(AMDGPU::FeatureInv2PiInlineImm))
     O << "0.15915494";
   else
-    O << formatHex(static_cast<uint64_t>(Imm));
+    return false;
----------------
nhaehnle wrote:

This one doesn't have the casting problem, but I wanted to keep consistency between the two methods.

https://github.com/llvm/llvm-project/pull/76522