[mlir][GPU][NFC] Add ShuffleOp builder for constant offset/width

mlir/include/mlir/Dialect/GPU/GPUOps.td

let description = [{
     is smaller than %width. Otherwise it returns an unspecified value and
     `false`. A lane is the index of an invocation relative to its subgroup.
 
     The width specifies the number of invocations that participate in the
     shuffle. The width needs to be the same for all invocations that participate
     in the shuffle. Exactly the first `width` invocations of a subgroup need to
     execute this op in convergence.
   }];
+  let builders = [
+    // Helper function that creates a shuffle with constant offset/width.
+    OpBuilder<(ins "Value":$value, "int32_t":$offset, "int32_t":$width,
+                   "ShuffleMode":$mode)>
+  ];
   let assemblyFormat = "$mode $value `,` $offset `,` $width attr-dict `:` type($value)";
 }
 
 def GPU_BarrierOp : GPU_Op<"barrier"> {
   let summary = "Synchronizes all work items of a workgroup.";
   let description = [{
     The "barrier" op synchronizes all work items of a workgroup. It is used
     to coordinate communication between the work items of the workgroup.

mlir/lib/Dialect/GPU/IR/GPUDialect.cpp

llvm::interleaveComma(llvm::zip(operands, types), printer,
                         [&](const auto &pair) {
                           printer.printOperand(std::get<0>(pair));
                           printer << " : ";
                           printer.printType(std::get<1>(pair));
                         });
   printer << ")";
 }
 
+//
+
+//===----------------------------------------------------------------------===//
+// ShuffleOp
+//===----------------------------------------------------------------------===//
+
+void ShuffleOp::build(OpBuilder &builder, OperationState &result, Value value,
+                      int32_t offset, int32_t width, ShuffleMode mode) {
+  build(builder, result, value,
+        builder.create<arith::ConstantOp>(result.location,
+                                          builder.getI32IntegerAttr(offset)),
+        builder.create<arith::ConstantOp>(result.location,
+                                          builder.getI32IntegerAttr(width)),
+        mode);
+}
+
 //===----------------------------------------------------------------------===//
 // GPUFuncOp
 //===----------------------------------------------------------------------===//
 
 /// Adds a new block argument that corresponds to buffers located in
 /// workgroup memory.
 BlockArgument GPUFuncOp::addWorkgroupAttribution(Type type, Location loc) {
   auto attrName = getNumWorkgroupAttributionsAttrName();