I make an editor for own game engine and I used for 2d rendering Direct2D but I wanted to render a directx texture

on window in editor, I didn't find convenient way to convert directx texture to direct2d bitmap. I decided to make own 2d render on directx 11 and I made that but I have poor performance. I knew that my realization to be slower

than direct2d but not in 4 times, how I can make better performance. I made simple profiling, more time to take

call DrawIndexed from directx 11 I don't understand why drawing is so slow. which optimization can I make ?

My 2d render pipeline looks simple. When call draw_rect fucntion function generates vertices and indices for a rect

than a struct which holds vertices and indices is added to na array this from the array draw_primitives takes data and

gets started to render and in the end of frame the array is reseted.

void Render_2D::draw_primitives()
{
	if (total_vertex_count == 0) {
		return;
	}

	static u32 privious_total_vertex_count;
	static u32 privious_total_index_count;

	if (!vertex_buffer || (privious_total_vertex_count != total_vertex_count)) {
		privious_total_vertex_count = total_vertex_count;
		
		free_com_object(vertex_buffer);
		
		vertex_buffer = make_vertex_buffer(sizeof(Vertex_XC), total_vertex_count, NULL, D3D11_USAGE_DYNAMIC, D3D11_CPU_ACCESS_WRITE);
	}

	if (!index_buffer || (privious_total_index_count != total_index_count)) {
		privious_total_index_count = total_index_count;

		free_com_object(index_buffer);
		
		index_buffer = make_index_buffer(total_index_count, NULL, D3D11_USAGE_DYNAMIC, D3D11_CPU_ACCESS_WRITE);
	}

	D3D11_MAPPED_SUBRESOURCE buffer;
	ZeroMemory(&buffer, sizeof(D3D11_MAPPED_SUBRESOURCE));
		
	HR(directx11.device_context->Map(vertex_buffer, 0, D3D11_MAP_WRITE_DISCARD, 0, &buffer));

	D3D11_MAPPED_SUBRESOURCE i_buffer;
	ZeroMemory(&i_buffer, sizeof(D3D11_MAPPED_SUBRESOURCE));

	HR(directx11.device_context->Map(index_buffer, 0, D3D11_MAP_WRITE_DISCARD, 0, &i_buffer));

	Vertex_XC *p1 = (Vertex_XC *)buffer.pData;
	u32 *p2 = (u32 *)i_buffer.pData;
	
	Primitive_2D *primitive = NULL;
	For(primitives, primitive) {

		memcpy((void *)p1, primitive->vertices.items, primitive->vertices.count * sizeof(Vertex_XC));
		memcpy((void *)p2, primitive->indices.items, primitive->indices.count * sizeof(u32));
		p1 += primitive->vertex_offset;
		p2 += primitive->index_offset;
	}

	directx11.device_context->Unmap(index_buffer, 0);
	directx11.device_context->Unmap(vertex_buffer, 0);

	Fx_Shader *shader = fx_shader_manager.get_shader("color");
	shader->bind("world_view_projection", &render_sys.view_info->orthogonal_matrix);
	shader->attach("draw_vertex_on_screen");


	D3D11_DEPTH_STENCIL_DESC depth_stencil;
	ZeroMemory(&depth_stencil, sizeof(D3D11_DEPTH_STENCIL_DESC));
	depth_stencil.DepthEnable = false;
	depth_stencil.DepthFunc = D3D11_COMPARISON_ALWAYS;
	depth_stencil.DepthWriteMask = D3D11_DEPTH_WRITE_MASK_ALL;
	depth_stencil.StencilEnable = false;

	ID3D11DepthStencilState *state = NULL;
	directx11.device->CreateDepthStencilState(&depth_stencil, &state);

	directx11.device_context->OMSetDepthStencilState(state, 0);

	primitive = NULL;
	For(primitives, primitive) {
		draw_indexed_traingles(vertex_buffer, sizeof(Vertex_XC), "vertex_color", index_buffer, primitive->indices.count, primitive->vertex_offset, primitive->index_offset);
	}

	directx11.device_context->RSSetState(0);
}

you seem to be hammering the api and the memory system for no reason.

if (!vertex_buffer || (privious_total_vertex_count != total_vertex_count)) {
to:
if ((!vertex_buffer) || (privious_total_vertex_count <= total_vertex_count)) {

if (!index_buffer || (privious_total_index_count != total_index_count)) {
to

if ((!index_buffer) || (privious_total_index_count <= total_index_count)) {

the first two zeromemory on buffers is even required? you seem to overwrite the memory anyway.