[Mlir-commits] [mlir] [mlir] Check for int limits when converting gpu dims (PR #140747)

Adam Siemieniuk llvmlistbot at llvm.org
Tue May 20 08:33:55 PDT 2025


================
@@ -116,7 +116,9 @@ struct OpLowering : public ConvertOpToLLVMPattern<Op> {
 
     if (upperBound && intrType != IntrType::None) {
       int32_t min = (intrType == IntrType::Dim ? 1 : 0);
-      int32_t max = *upperBound + (intrType == IntrType::Id ? 0 : 1);
+      int32_t max = *upperBound == INT_MAX
----------------
adam-smnk wrote:

Fly-by nit: `INT32_MAX` or even better `std::numeric_limits`

https://github.com/llvm/llvm-project/pull/140747


More information about the Mlir-commits mailing list