[Mlir-commits] [mlir] [mlir][ArithToAMDGPU] Add option for saturating truncation to fp8 (PR #74153)

[Jakub Kuderski]

================
@@ -20,7 +20,8 @@ class Pass;
 #include "mlir/Conversion/Passes.h.inc"
 
 namespace arith {
-void populateArithToAMDGPUConversionPatterns(RewritePatternSet &patterns);
+void populateArithToAMDGPUConversionPatterns(RewritePatternSet &patterns,
+                                             bool saturateFP8Truncf);
----------------
kuhar wrote:

Could you add a documentation comment?
also nit:
```suggestion
void populateArithToAMDGPUConversionPatterns(RewritePatternSet &patterns,
                                             bool saturateFP8TruncF);
```

https://github.com/llvm/llvm-project/pull/74153