Does the local memory usage increase with banking and coalescing?

#define DIM_3 2
#define DIM_4 8
 
#pragma OPENCL EXTENSION cl_intel_channels : enable
 
 
typedef char QTYPE;
typedef int  HTYPE;
 
 
typedef struct {
   QTYPE data[DIM_3];
} group_data;
 
 
typedef struct {
   group_data lane[DIM_4];
} group_vec; 
 
 
typedef struct {
   QTYPE lane[DIM_4];
} group_ch;
 
 
 
 
channel group_vec    data_ch    __attribute__((depth(0)));
channel group_vec    weight_ch    __attribute__((depth(0)));
channel group_ch   out_ch  __attribute__((depth(0)));
 
__kernel
__attribute__((task))
__attribute__((max_global_work_dim(0)))
void fetch_data(
 
	__global group_data *restrict bottom
 
	)
 
{
	group_data data_vec;
	group_vec data_ch_out;
 
 
 
		for(unsigned int  win_itm_xyz=0; win_itm_xyz< 39 * 39 * 4096/(DIM_3); win_itm_xyz++){
		
			data_vec = bottom[win_itm_xyz];
			#pragma unroll
			for(unsigned char ll=0; ll<DIM_4; ll++){
				data_ch_out.lane[ll] = data_vec;
			}
					
			write_channel_intel(data_ch, data_ch_out);
 
 
		}
}
	
 
__kernel
__attribute__((task))
__attribute__((max_global_work_dim(0)))
void fetch_weights(
 
			__global volatile group_vec  *restrict weights 
			
			   )
 
{
		group_vec weight_vec;
		for(unsigned int  win_itm_xyz=0; win_itm_xyz< 39 * 39 * 4096/(DIM_3); win_itm_xyz++){
		
			weight_vec = weights[win_itm_xyz];
					
			write_channel_intel(weight_ch, weight_vec);
		}
 
}
 
 
__kernel
__attribute__((task))
__attribute__((max_global_work_dim(0)))
void conv_wino(
 
			)
{
 
 
	group_vec data_vec;
	group_vec weight_vec;
	group_ch convout;
	HTYPE conv_out[169][DIM_4];
	group_ch inv_wino_out[4];
	uint array_index;
 
	for(uint output = 0; output < 39 * 39; output++) {
		for(unsigned int  win_itm_xyz=0; win_itm_xyz< 4096/DIM_3; win_itm_xyz++){
			data_vec = read_channel_intel(data_ch);
			weight_vec = read_channel_intel(weight_ch); 
		
		#pragma unroll
		for(uint i = 0; i < DIM_4; i++) {
			#pragma unroll
			for(uint j = 0; j< DIM_3; j++) {
				convout.lane[i] += data_vec.lane[i].data[j] * weight_vec.lane[i].data[j];
				}
		
			}
						
		}
		#pragma unroll
		for(unsigned char ll_t=0; ll_t<DIM_4; ll_t++){
			conv_out[array_index][ll_t] = convout.lane[ll_t];	
		}
		if (array_index == 169 - 1){
			array_index = 0;
		}	
		else
			array_index++;
 
		}
 
		#pragma unroll
		for(unsigned char ll_t=0; ll_t<DIM_4; ll_t++){
 
		inv_wino_out[0].lane[ll_t]  =   conv_out[0][ll_t]  + conv_out[1][ll_t] + conv_out[2][ll_t] + conv_out[1][ll_t] + conv_out[5][ll_t] + conv_out[9][ll_t] + conv_out[2][ll_t] + conv_out[6][ll_t] + conv_out[10][ll_t];
		//printf("\n %d ", inv_win_out[0][ll_t]);
		inv_wino_out[1].lane[ll_t] =    conv_out[0][ll_t] + conv_out[5][ll_t] + conv_out[9][ll_t] - conv_out[2][ll_t] - conv_out[6][ll_t] - conv_out[10][ll_t] - conv_out[3][ll_t] - conv_out[7][ll_t] - conv_out[11][ll_t];
		//printf("\n %d ", inv_win_out[1][ll_t]);
		inv_wino_out[2].lane[ll_t] =	conv_out[4][ll_t] + conv_out[9][ll_t] - conv_out[12][ll_t] + conv_out[5][ll_t] - conv_out[157][ll_t] - conv_out[13][ll_t] + conv_out[6][ll_t] - conv_out[10][ll_t] - conv_out[14][ll_t];
		//printf("\n %d ", inv_win_out[2][ll_t]);
		inv_wino_out[3].lane[ll_t] =	conv_out[5][ll_t] - conv_out[16][ll_t] - conv_out[13][ll_t] - conv_out[6][ll_t] + conv_out[10][ll_t] + conv_out[14][ll_t] - conv_out[7][ll_t] + conv_out[11][ll_t] + conv_out[15][ll_t];		
		//printf("\n %d ", inv_win_out[3][ll_t]);
		}
 
		for(unsigned char ll_t=0; ll_t<4; ll_t++)
		{
			write_channel_intel(out_ch, inv_wino_out[ll_t]);
 
		}
 
		
	
}	
 
 
 
// Store Data to Global Memory
__kernel
__attribute__((task))
__attribute__((max_global_work_dim(0)))
void WriteBack(
 
                __global group_ch *restrict top
				)
{
 
	uint array_index;
 
	uchar  index_z_item; // max value 256
	ushort index_z_group;// max value 4096
 
	group_ch output;
 
 
 
		
		for(uint dd = 0; dd< 4; dd++){
			output = read_channel_intel(out_ch);
			top[dd]  =  output;  
				//printf("\n index: %d, Output buffer : %d ",  dd, output.lane[ll] );
			}  
}   
 
 
 
	
 
 
	
 
 
 
 

In the code snippet, the local memory allocated to conv_out = 103. I checked area analysis by source. But no line is mentioned about 103 RAM blocks.