type RGBA struct {
	// Pix holds the image's pixels, in R, G, B, A order. The pixel at
	// (x, y) starts at Pix[(y-Rect.Min.Y)*Stride + (x-Rect.Min.X)*4].
	Pix []uint8
	// Stride is the Pix stride (in bytes) between vertically adjacent pixels.
	Stride int
	// Rect is the image's bounds.
	Rect Rectangle
}

func (p *RGBA) ColorModel() color.Model { return color.RGBAModel }

                            /*padding*/(GetAvgPoolOpPadAttr $old_val),
                            /*stride_h*/(GetI32At<0> (GetAsVectorAttr<"stride"> $attrs)),
                            /*stride_w*/(GetI32At<1> (GetAsVectorAttr<"stride"> $attrs)),
                            /*fused_activation_function*/TFL_AF_None,
                            (returnType (GetNhwcReturnTypeFromNchw $old_val))), 

			}
			if r <= range_.Hi {
				return range_.Stride == 1 || (r-range_.Lo)%range_.Stride == 0
			}
		}
		return false
	}

	// binary search over ranges
	lo := 0
	hi := len(ranges)
	for lo < hi {
		m := int(uint(lo+hi) >> 1)
		range_ := &ranges[m]
		if range_.Lo <= r && r <= range_.Hi {
			return range_.Stride == 1 || (r-range_.Lo)%range_.Stride == 0
		}
		if r < range_.Lo {
			hi = m

		ddelta = dst.Stride
		sdelta = src.Stride
		i0, i1, idelta = 0, dx*4, +4
	} else {
		// If the source start point is higher than the destination start point, or equal height but to the left,
		// then we compose the rows in right-to-left, bottom-up order instead of left-to-right, top-down.
		d0 += (dy - 1) * dst.Stride
		s0 += (dy - 1) * src.Stride
		ddelta = -dst.Stride
		sdelta = -src.Stride

  // CHECK-DAG: %[[result:.*]] = chlo.broadcast_add %[[conv]], %[[combined]]
  // CHECK: return %[[result]]
  %0 = mhlo.convolution(%lhs, %rhs)
      dim_numbers = [b, 0, 1, f]x[0, 1, i, o]->[b, 0, 1, f],
      window = {stride = [1, 1], pad = [[0, 0], [0, 0]],
      lhs_dilate = [1, 1], rhs_dilate = [1, 1]}
      {batch_group_count = 1 : i64, feature_group_count = 1 : i64}
    : (tensor<?x3x2x1xi8>, tensor<2x1x1x1xi8>) -> tensor<?x2x2x1xi32>

		srcPix = src.(*image.Gray).Pix
		dstPix, stride, rect = target.Pix, target.Stride, target.Rect
		bytesPerPixel = 1
	case *image.Gray16:
		srcPix = src.(*image.Gray16).Pix
		dstPix, stride, rect = target.Pix, target.Stride, target.Rect
		bytesPerPixel = 2
	case *image.NRGBA:
		srcPix = src.(*image.NRGBA).Pix
		dstPix, stride, rect = target.Pix, target.Stride, target.Rect
		bytesPerPixel = 4
	case *image.NRGBA64:

  // CHECK-DAG: %[[RESULT:.+]] = mhlo.convolution(%[[INPUT]], %[[NEW_FILTER]]) dim_numbers = [b, 0, 1, f]x[0, 1, i, o]->[b, 0, 1, f], window = {stride = [1, 1], pad = {{\[\[}}0, 0], [0, 0]], rhs_dilate = [1, 1]} {batch_group_count = 1 : i64, feature_group_count = 1 : i64} : (tensor<1x256x256x3xf32>, tensor<1x1x3x2xf32>) -> tensor<1x256x256x2xf32>

type blas64_Triangular struct {
	Stride int
	Uplo   int
}

// TriDense represents an upper or lower triangular matrix in dense storage
// format.
type TriDense struct {
	mat blas64_Triangular
}

func NewTriDense() *TriDense {
	return &TriDense{
		mat: blas64_Triangular{
			Stride: 3,
			Uplo:   blas_Upper,
		},
	}
}

func (t *TriDense) isUpper() bool {

		}
	}
}

func TestDumper(t *testing.T) {
	var in [40]byte
	for i := range in {
		in[i] = byte(i + 30)
	}

	for stride := 1; stride < len(in); stride++ {
		var out bytes.Buffer
		dumper := Dumper(&out)
		done := 0
		for done < len(in) {
			todo := done + stride
			if todo > len(in) {
				todo = len(in)
			}
			dumper.Write(in[done:todo])
			done = todo
		}

		dumper.Close()

  Value stride_value = CreateScalarConstValue<int32_t>(builder, loc, stride);
  Value dilation_rate_value =
      CreateScalarConstValue<int32_t>(builder, loc, dilation_rate);

  Value effective_filter_size_op = scalar_add(
      scalar_mul(dilation_rate_value, scalar_sub(filter_size, one)), one);

  // output_size = (input_size + stride - 1) / stride
  Value output_size = scalar_div(