techlibs/common/mul2dsp.v


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
pre { line-height: 125%; margin: 0; }
td.linenos pre { color: #000000; background-color: #f0f0f0; padding: 0 5px 0 5px; }
span.linenos { color: #000000; background-color: #f0f0f0; padding: 0 5px 0 5px; }
td.linenos pre.special { color: #000000; background-color: #ffffc0; padding: 0 5px 0 5px; }
span.linenos.special { color: #000000; background-color: #ffffc0; padding: 0 5px 0 5px; }
.highlight .hll { background-color: #ffffcc }
.highlight { background: #ffffff; }
.highlight .c { color: #888888 } /* Comment */
.highlight .err { color: #a61717; background-color: #e3d2d2 } /* Error */
.highlight .k { color: #008800; font-weight: bold } /* Keyword */
.highlight .ch { color: #888888 } /* Comment.Hashbang */
.highlight .cm { color: #888888 } /* Comment.Multiline */
.highlight .cp { color: #cc0000; font-weight: bold } /* Comment.Preproc */
.highlight .cpf { color: #888888 } /* Comment.PreprocFile */
.highlight .c1 { color: #888888 } /* Comment.Single */
.highlight .cs { color: #cc0000; font-weight: bold; background-color: #fff0f0 } /* Comment.Special */
.highlight .gd { color: #000000; background-color: #ffdddd } /* Generic.Deleted */
.highlight .ge { font-style: italic } /* Generic.Emph */
.highlight .gr { color: #aa0000 } /* Generic.Error */
.highlight .gh { color: #333333 } /* Generic.Heading */
.highlight .gi { color: #000000; background-color: #ddffdd } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #555555 } /* Generic.Prompt */
.highlight .gs { font-weight: bold } /* Generic.Strong */
.highlight .gu { color: #666666 } /* Generic.Subheading */
.highlight .gt { color: #aa0000 } /* Generic.Traceback */
.highlight .kc { color: #008800; font-weight: bold } /* Keyword.Constant */
.highlight .kd { color: #008800; font-weight: bold } /* Keyword.Declaration */
.highlight .kn { color: #008800; font-weight: bold } /* Keyword.Namespace */
.highlight .kp { color: #008800 } /* Keyword.Pseudo */
.highlight .kr { color: #008800; font-weight: bold } /* Keyword.Reserved */
.highlight .kt { color: #888888; font-weight: bold } /* Keyword.Type */
.highlight .m { color: #0000DD; font-weight: bold } /* Literal.Number */
.highlight .s { color: #dd2200; background-color: #fff0f0 } /* Literal.String */
.highlight .na { color: #336699 } /* Name.Attribute */
.highlight .nb { color: #003388 } /* Name.Builtin */
.highlight .nc { color: #bb0066; font-weight: bold } /* Name.Class */
.highlight .no { color: #003366; font-weight: bold } /* Name.Constant */
.highlight .nd { color: #555555 } /* Name.Decorator */
.highlight .ne { color: #bb0066; font-weight: bold } /* Name.Exception */
.highlight .nf { color: #0066bb; font-weight: bold } /* Name.Function */
.highlight .nl { color: #336699; font-style: italic } /* Name.Label */
.highlight .nn { color: #bb0066; font-weight: bold } /* Name.Namespace */
.highlight .py { color: #336699; font-weight: bold } /* Name.Property */
.highlight .nt { color: #bb0066; font-weight: bold } /* Name.Tag */
.highlight .nv { color: #336699 } /* Name.Variable */
.highlight .ow { color: #008800 } /* Operator.Word */
.highlight .w { color: #bbbbbb } /* Text.Whitespace */
.highlight .mb { color: #0000DD; font-weight: bold } /* Literal.Number.Bin */
.highlight .mf { color: #0000DD; font-weight: bold } /* Literal.Number.Float */
.highlight .mh { color: #0000DD; font-weight: bold } /* Literal.Number.Hex */
.highlight .mi { color: #0000DD; font-weight: bold } /* Literal.Number.Integer */
.highlight .mo { color: #0000DD; font-weight: bold } /* Literal.Number.Oct */
.highlight .sa { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Affix */
.highlight .sb { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Backtick */
.highlight .sc { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Char */
.highlight .dl { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Delimiter */
.highlight .sd { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Doc */
.highlight .s2 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Double */
.highlight .se { color: #0044dd; background-color: #fff0f0 } /* Literal.String.Escape */
.highlight .sh { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Heredoc */
.highlight .si { color: #3333bb; background-color: #fff0f0 } /* Literal.String.Interpol */
.highlight .sx { color: #22bb22; background-color: #f0fff0 } /* Literal.String.Other */
.highlight .sr { color: #008800; background-color: #fff0ff } /* Literal.String.Regex */
.highlight .s1 { color: #dd2200; background-color: #fff0f0 } /* Literal.String.Single */
.highlight .ss { color: #aa6600; background-color: #fff0f0 } /* Literal.String.Symbol */
.highlight .bp { color: #003388 } /* Name.Builtin.Pseudo */
.highlight .fm { color: #0066bb; font-weight: bold } /* Name.Function.Magic */
.highlight .vc { color: #336699 } /* Name.Variable.Class */
.highlight .vg { color: #dd7700 } /* Name.Variable.Global */
.highlight .vi { color: #3333bb } /* Name.Variable.Instance */
.highlight .vm { color: #336699 } /* Name.Variable.Magic */
.highlight .il { color: #0000DD; font-weight: bold } /* Literal.Number.Integer.Long */# Atmel AVR

QMK should run on any Atmel AVR processor with enough Flash. It has been tested on the following:

* ATmega32U4 ([PJRC Teensy 2.0](http://www.pjrc.com/teensy/))
* AT90USB1286 ([PJRC Teensy++ 2.0](http://www.pjrc.com/teensy/))
* AT90USB1287 ([Atmel USBKEY](http://www.atmel.com/tools/AT90USBKEY.aspx))
* ATmega168P with using [V-USB](http://www.obdev.at/products/vusb/index.html)
* ATmega328P with using [V-USB](http://www.obdev.at/products/vusb/index.html)
* ATmega32U2
* AT90USB1286, 646, 647 should work
* AT90USB162 testing...

NOTE: To enable full features of firmware you'll need 32KB flash size.

Please add any tested microcontrollers to this list.

# ARM

You can also use any ARM processor that [ChibiOS](http://www.chibios.org) supports. The following processors have been tested:

* [Kinetis MKL26Z64](http://www.nxp.com/products/microcontrollers-and-processors/arm-processors/kinetis-cortex-m-mcus/l-series-ultra-low-power-m0-plus/kinetis-kl2x-48-mhz-usb-ultra-low-power-microcontrollers-mcus-based-on-arm-cortex-m0-plus-core:KL2x)
* [Kinetis MK20DX128](http://www.nxp.com/assets/documents/data/en/data-sheets/K20P64M50SF0.pdf)
* [Kinetis MK20DX128](http://www.nxp.com/assets/documents/data/en/data-sheets/K20P64M50SF0.pdf)
* [Kinetis MK20DX256](http://www.nxp.com/products/microcontrollers-and-processors/arm-processors/kinetis-cortex-m-mcus/k-series-performance-m4/k2x-usb/kinetis-k20-72-mhz-full-speed-usb-mixed-signal-integration-microcontrollers-mcus-based-on-arm-cortex-m4-core:K20_72)
/*
 *  yosys -- Yosys Open SYnthesis Suite
 *
 *  Copyright (C) 2012  Clifford Wolf <clifford@clifford.at>
 *                2019  Eddie Hung    <eddie@fpgeh.com>
 *                2019  David Shah    <dave@ds0.me>
 *
 *  Permission to use, copy, modify, and/or distribute this software for any
 *  purpose with or without fee is hereby granted, provided that the above
 *  copyright notice and this permission notice appear in all copies.
 *
 *  THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
 *  WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
 *  MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
 *  ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
 *  WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
 *  ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
 *  OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 *
 *  ---
 *
 *  Tech-mapping rules for decomposing arbitrarily-sized $mul cells
 *  into an equivalent collection of smaller `DSP_NAME cells (with the 
 *  same interface as $mul) no larger than `DSP_[AB]_MAXWIDTH, attached 
 *  to $shl and $add cells.
 *
 */

`ifndef DSP_A_MAXWIDTH
$fatal(1, "Macro DSP_A_MAXWIDTH must be defined");
`endif
`ifndef DSP_B_MAXWIDTH
$fatal(1, "Macro DSP_B_MAXWIDTH must be defined");
`endif
`ifndef DSP_B_MAXWIDTH
$fatal(1, "Macro DSP_B_MAXWIDTH must be defined");
`endif
`ifndef DSP_A_MAXWIDTH_PARTIAL
`define DSP_A_MAXWIDTH_PARTIAL `DSP_A_MAXWIDTH
`endif
`ifndef DSP_B_MAXWIDTH_PARTIAL
`define DSP_B_MAXWIDTH_PARTIAL `DSP_B_MAXWIDTH
`endif

`ifndef DSP_NAME
$fatal(1, "Macro DSP_NAME must be defined");
`endif

`define MAX(a,b) (a > b ? a : b)
`define MIN(a,b) (a < b ? a : b)

(* techmap_celltype = "$mul $__mul" *)
module _80_mul (A, B, Y);
	parameter A_SIGNED = 0;
	parameter B_SIGNED = 0;
	parameter A_WIDTH = 1;
	parameter B_WIDTH = 1;
	parameter Y_WIDTH = 1;

	(* force_downto *)
	input [A_WIDTH-1:0] A;
	(* force_downto *)
	input [B_WIDTH-1:0] B;
	(* force_downto *)
	output [Y_WIDTH-1:0] Y;

	parameter _TECHMAP_CELLTYPE_ = "";

	generate
	if (0) begin end
`ifdef DSP_A_MINWIDTH
	else if (A_WIDTH < `DSP_A_MINWIDTH)
		wire _TECHMAP_FAIL_ = 1;
`endif
`ifdef DSP_B_MINWIDTH
	else if (B_WIDTH < `DSP_B_MINWIDTH)
		wire _TECHMAP_FAIL_ = 1;
`endif
`ifdef DSP_Y_MINWIDTH
	else if (Y_WIDTH < `DSP_Y_MINWIDTH)
		wire _TECHMAP_FAIL_ = 1;
`endif
`ifdef DSP_SIGNEDONLY
	else if (_TECHMAP_CELLTYPE_ == "$mul" && !A_SIGNED && !B_SIGNED)
		\$mul #(
			.A_SIGNED(1),
			.B_SIGNED(1),
			.A_WIDTH(A_WIDTH + 1),
			.B_WIDTH(B_WIDTH + 1),
			.Y_WIDTH(Y_WIDTH)
		) _TECHMAP_REPLACE_ (
			.A({1'b0, A}),
			.B({1'b0, B}),
			.Y(Y)
		);
`endif
	else if (_TECHMAP_CELLTYPE_ == "$mul" && A_WIDTH < B_WIDTH)
		\$mul #(
			.A_SIGNED(B_SIGNED),
			.B_SIGNED(A_SIGNED),
			.A_WIDTH(B_WIDTH),
			.B_WIDTH(A_WIDTH),
			.Y_WIDTH(Y_WIDTH)
		) _TECHMAP_REPLACE_ (
			.A(B),
			.B(A),
			.Y(Y)
		);
	else begin
		wire [1023:0] _TECHMAP_DO_ = "proc; clean";

`ifdef DSP_SIGNEDONLY
		localparam sign_headroom = 1;
`else
		localparam sign_headroom = 0;
`endif

		genvar i;
		if (A_WIDTH > `DSP_A_MAXWIDTH) begin
			localparam n = (A_WIDTH-`DSP_A_MAXWIDTH+`DSP_A_MAXWIDTH_PARTIAL-sign_headroom-1) / (`DSP_A_MAXWIDTH_PARTIAL-sign_headroom);
			localparam partial_Y_WIDTH = `MIN(Y_WIDTH, B_WIDTH+`DSP_A_MAXWIDTH_PARTIAL);
			localparam last_A_WIDTH = A_WIDTH-n*(`DSP_A_MAXWIDTH_PARTIAL-sign_headroom);
			localparam last_Y_WIDTH = B_WIDTH+last_A_WIDTH;
			if (A_SIGNED && B_SIGNED) begin : blk
				(* force_downto *)
				wire signed [partial_Y_WIDTH-1:0] partial [n-1:0];
				(* force_downto *)
				wire signed [last_Y_WIDTH-1:0] last_partial;
				(* force_downto *)
				wire signed [Y_WIDTH-1:0] partial_sum [n:0];
			end
			else begin : blk
				(* force_downto *)
				wire [partial_Y_WIDTH-1:0] partial [n-1:0];
				(* force_downto *)
				wire [last_Y_WIDTH-1:0] last_partial;
				(* force_downto *)
				wire [Y_WIDTH-1:0] partial_sum [n:0];
			end

			for (i = 0; i < n; i=i+1) begin:sliceA
				\$__mul #(
					.A_SIGNED(sign_headroom),
					.B_SIGNED(B_SIGNED),
					.A_WIDTH(`DSP_A_MAXWIDTH_PARTIAL),
					.B_WIDTH(B_WIDTH),
					.Y_WIDTH(partial_Y_WIDTH)
				) mul (
					.A({{sign_headroom{1'b0}}, A[i*(`DSP_A_MAXWIDTH_PARTIAL-sign_headroom) +: `DSP_A_MAXWIDTH_PARTIAL-sign_headroom]}),
					.B(B),
					.Y(blk.partial[i])
				);
				// TODO: Currently a 'cascade' approach to summing the partial
				//       products is taken here, but a more efficient 'binary
				//       reduction' approach also exists...
				if (i == 0)
					assign blk.partial_sum[i] = blk.partial[i];
				else
					assign blk.partial_sum[i] = (blk.partial[i] << (* mul2dsp *) i*(`DSP_A_MAXWIDTH_PARTIAL-sign_headroom)) + (* mul2dsp *) blk.partial_sum[i-1];
			end

			\$__mul #(
				.A_SIGNED(A_SIGNED),
				.B_SIGNED(B_SIGNED),
				.A_WIDTH(last_A_WIDTH),
				.B_WIDTH(B_WIDTH),
				.Y_WIDTH(last_Y_WIDTH)
			) sliceA.last (
				.A(A[A_WIDTH-1 -: last_A_WIDTH]),
				.B(B),
				.Y(blk.last_partial)
			);
			assign blk.partial_sum[n] = (blk.last_partial << (* mul2dsp *) n*(`DSP_A_MAXWIDTH_PARTIAL-sign_headroom)) + (* mul2dsp *) blk.partial_sum[n-1];
			assign Y = blk.partial_sum[n];
		end
		else if (B_WIDTH > `DSP_B_MAXWIDTH) begin
			localparam n = (B_WIDTH-`DSP_B_MAXWIDTH+`DSP_B_MAXWIDTH_PARTIAL-sign_headroom-1) / (`DSP_B_MAXWIDTH_PARTIAL-sign_headroom);
			localparam partial_Y_WIDTH = `MIN(Y_WIDTH, A_WIDTH+`DSP_B_MAXWIDTH_PARTIAL);
			localparam last_B_WIDTH = B_WIDTH-n*(`DSP_B_MAXWIDTH_PARTIAL-sign_headroom);
			localparam last_Y_WIDTH = A_WIDTH+last_B_WIDTH;
			if (A_SIGNED && B_SIGNED) begin : blk
				(* force_downto *)
				wire signed [partial_Y_WIDTH-1:0] partial [n-1:0];
				(* force_downto *)
				wire signed [last_Y_WIDTH-1:0] last_partial;
				(* force_downto *)
				wire signed [Y_WIDTH-1:0] partial_sum [n:0];
			end
			else begin : blk
				(* force_downto *)
				wire [partial_Y_WIDTH-1:0] partial [n-1:0];
				(* force_downto *)
				wire [last_Y_WIDTH-1:0] last_partial;
				(* force_downto *)
				wire [Y_WIDTH-1:0] partial_sum [n:0];
			end

			for (i = 0; i < n; i=i+1) begin:sliceB
				\$__mul #(
					.A_SIGNED(A_SIGNED),
					.B_SIGNED(sign_headroom),
					.A_WIDTH(A_WIDTH),
					.B_WIDTH(`DSP_B_MAXWIDTH_PARTIAL),
					.Y_WIDTH(partial_Y_WIDTH)
				) mul (
					.A(A),
					.B({{sign_headroom{1'b0}}, B[i*(`DSP_B_MAXWIDTH_PARTIAL-sign_headroom) +: `DSP_B_MAXWIDTH_PARTIAL-sign_headroom]}),
					.Y(blk.partial[i])
				);
				// TODO: Currently a 'cascade' approach to summing the partial
				//       products is taken here, but a more efficient 'binary
				//       reduction' approach also exists...
				if (i == 0)
					assign blk.partial_sum[i] = blk.partial[i];
				else
					assign blk.partial_sum[i] = (blk.partial[i] << (* mul2dsp *) i*(`DSP_B_MAXWIDTH_PARTIAL-sign_headroom)) + (* mul2dsp *) blk.partial_sum[i-1];
			end

			\$__mul #(
				.A_SIGNED(A_SIGNED),
				.B_SIGNED(B_SIGNED),
				.A_WIDTH(A_WIDTH),
				.B_WIDTH(last_B_WIDTH),
				.Y_WIDTH(last_Y_WIDTH)
			) mul_sliceB_last (
				.A(A),
				.B(B[B_WIDTH-1 -: last_B_WIDTH]),
				.Y(blk.last_partial)
			);
			assign blk.partial_sum[n] = (blk.last_partial << (* mul2dsp *) n*(`DSP_B_MAXWIDTH_PARTIAL-sign_headroom)) + (* mul2dsp *) blk.partial_sum[n-1];
			assign Y = blk.partial_sum[n];
		end
		else begin
			if (A_SIGNED) begin : blkA
				wire signed [`DSP_A_MAXWIDTH-1:0] Aext = $signed(A);
			end
			else begin : blkA
				wire [`DSP_A_MAXWIDTH-1:0] Aext = A;
			end
			if (B_SIGNED) begin : blkB
				wire signed [`DSP_B_MAXWIDTH-1:0] Bext = $signed(B);
			end
			else begin : blkB
				wire [`DSP_B_MAXWIDTH-1:0] Bext = B;
			end

			`DSP_NAME #(
				.A_SIGNED(A_SIGNED),
				.B_SIGNED(B_SIGNED),
				.A_WIDTH(`DSP_A_MAXWIDTH),
				.B_WIDTH(`DSP_B_MAXWIDTH),
				.Y_WIDTH(`MIN(Y_WIDTH,`DSP_A_MAXWIDTH+`DSP_B_MAXWIDTH)),
			) _TECHMAP_REPLACE_ (
				.A(blkA.Aext),
				.B(blkB.Bext),
				.Y(Y)
			);
		end
	end
	endgenerate
endmodule

(* techmap_celltype = "$mul $__mul" *)
module _90_soft_mul (A, B, Y);
	parameter A_SIGNED = 0;
	parameter B_SIGNED = 0;
	parameter A_WIDTH = 1;
	parameter B_WIDTH = 1;
	parameter Y_WIDTH = 1;

	(* force_downto *)
	input [A_WIDTH-1:0] A;
	(* force_downto *)
	input [B_WIDTH-1:0] B;
	(* force_downto *)
	output [Y_WIDTH-1:0] Y;

	// Indirection necessary since mapping
	//   back to $mul will cause recursion
	generate
	if (A_SIGNED && !B_SIGNED)
		\$__soft_mul #(
			.A_SIGNED(A_SIGNED),
			.B_SIGNED(1),
			.A_WIDTH(A_WIDTH),
			.B_WIDTH(B_WIDTH+1),
			.Y_WIDTH(Y_WIDTH)
		) _TECHMAP_REPLACE_ (
			.A(A),
			.B({1'b0,B}),
			.Y(Y)
		);
	else if (!A_SIGNED && B_SIGNED)
		\$__soft_mul #(
			.A_SIGNED(1),
			.B_SIGNED(B_SIGNED),
			.A_WIDTH(A_WIDTH+1),
			.B_WIDTH(B_WIDTH),
			.Y_WIDTH(Y_WIDTH)
		) _TECHMAP_REPLACE_ (
			.A({1'b0,A}),
			.B(B),
			.Y(Y)
		);
	else
		\$__soft_mul #(
			.A_SIGNED(A_SIGNED),
			.B_SIGNED(B_SIGNED),
			.A_WIDTH(A_WIDTH),
			.B_WIDTH(B_WIDTH),
			.Y_WIDTH(Y_WIDTH)
		) _TECHMAP_REPLACE_ (
			.A(A),
			.B(B),
			.Y(Y)
		);
	endgenerate
endmodule