%0 = "vhlo.reduce_window_v1"(%arg0, %arg1) <{base_dilations = #vhlo.tensor_v1<dense<1> : tensor<3xi64>>,
        padding = #vhlo.tensor_v1<dense<[[0, 0], [159, 0], [0, 0]]> : tensor<3x2xi64>>,
        window_dilations = #vhlo.tensor_v1<dense<1> : tensor<3xi64>>,
        window_dimensions = #vhlo.tensor_v1<dense<[1, 160, 1]> : tensor<3xi64>>,
        window_strides = #vhlo.tensor_v1<dense<1> : tensor<3xi64>>}> ({

				for j := 0; j < hi*vi; j++ {
					// The blocks are traversed one MCU at a time. For 4:2:0 chroma
					// subsampling, there are four Y 8x8 blocks in every 16x16 MCU.
					//
					// For a sequential 32x16 pixel image, the Y blocks visiting order is:
					//	0 1 4 5
					//	2 3 6 7
					//
					// For progressive images, the interleaved scans (those with nComp > 1)