SWDEV-322605 - Fix infinite loop condition

If GlobalMemCacheLine reported is 0, runtime may run into an
infinite loop as the KernelSegmentAlignment is chosen as size of the
cache line.

Change-Id: Ide547940cc0407f16fab10ee210b4fd3ae4eaafc

rocclr/device/rocm/rockernel.cpp

@@ -56,7 +56,9 @@ bool LightningKernel::postLoad() {
     symbolName_ = name();
   }
   kernargSegmentAlignment_ =
-      amd::alignUp(std::max(kernargSegmentAlignment_, 128u), device().info().globalMemCacheLineSize_);
+      amd::alignUp(std::max(kernargSegmentAlignment_, 128u),
+                   device().info().globalMemCacheLineSize_ > 0 ?
+                       device().info().globalMemCacheLineSize_ : 64);
 
   // Set the workgroup information for the kernel
   workGroupInfo_.availableLDSSize_ = device().info().localMemSizePerCU_;