[llvm] [AMDGPU][GlobalISel] Fix assert on APInt creation. (PR #124608)

[Daniil Fukalov via llvm-commits]

================
@@ -56,7 +56,7 @@ AMDGPU::getBaseWithConstantOffset(MachineRegisterInfo &MRI, Register Reg,
 
   Register Base;
   if (KnownBits && mi_match(Reg, MRI, m_GOr(m_Reg(Base), m_ICst(Offset))) &&
-      KnownBits->maskedValueIsZero(Base, APInt(32, Offset)))
+      KnownBits->maskedValueIsZero(Base, APInt(32, Offset, /*isSigned=*/true)))
----------------
dfukalov wrote:

Jay suggested to use APInt in the same case use https://github.com/llvm/llvm-project/pull/122251#discussion_r1908574869

@jayfoad?

https://github.com/llvm/llvm-project/pull/124608