[llvm] [AMDGPU] Fix a potential integer overflow in GCNRegPressure when true16 is enabled (PR #144968)

[Shilei Tian via llvm-commits]

================
@@ -66,7 +66,23 @@ void GCNRegPressure::inc(unsigned Reg,
       Value[TupleIdx] += Sign * TRI->getRegClassWeight(RC).RegWeight;
     }
     // Pressure scales with number of new registers covered by the new mask.
-    Sign *= SIRegisterInfo::getNumCoveredRegs(~PrevMask & NewMask);
+    // Note that, when true16 is enabled, we can no longer use the following
+    // code to calculate the difference of number of 32-bit registers between
+    // the two mask:
+    //
+    // Sign *= SIRegisterInfo::getNumCoveredRegs(~PrevMask & NewMask);
+    //
+    // The reason is, the new mask `~PrevMask & NewMask` doesn't treat a 16-bit
+    // register use as a whole 32-bit register use.
----------------
shiltian wrote:

`getNumCoveredRegs` is not the issue here. `~PrevMask & NewMask` is and it doesn't account for 16-bit use.

https://github.com/llvm/llvm-project/pull/144968