OpenCores
URL https://opencores.org/ocsvn/zipcpu/zipcpu/trunk

Subversion Repositories zipcpu

[/] [zipcpu/] [trunk/] [rtl/] [cpudefs.v] - Blame information for rev 65

Go to most recent revision | Details | Compare with Previous | View Log

Line No. Rev Author Line
1 56 dgisselq
///////////////////////////////////////////////////////////////////////////////
2
//
3
// Filename:    cpudefs.v
4
//
5
// Project:     Zip CPU -- a small, lightweight, RISC CPU soft core
6
//
7
// Purpose:     Some architectures have some needs, others have other needs.
8
//              Some of my projects need a Zip CPU with pipelining, others
9
//      can't handle the timing required to get the answer from the ALU
10
//      back into the input for the ALU.  As each different projects has
11
//      different needs, I can either 1) reconfigure my entire baseline prior
12
//      to building each project, or 2) host a configuration file which contains
13
//      the information regarding each baseline.  This file is that
14
//      configuration file.  It controls how the CPU (not the system,
15
//      peripherals, or other) is defined and implemented.  Several options
16
//      are available within here, making the Zip CPU pipelined or not,
17
//      able to handle a faster clock with more stalls or a slower clock with
18
//      no stalls, etc.
19
//
20
//      This file encapsulates those control options.
21
//
22
//      The number of LUTs the Zip CPU uses varies dramatically with the
23
//      options defined in this file.
24
//
25
//
26
// Creator:     Dan Gisselquist, Ph.D.
27
//              Gisselquist Tecnology, LLC
28
//
29
///////////////////////////////////////////////////////////////////////////////
30
//
31
// Copyright (C) 2015, Gisselquist Technology, LLC
32
//
33
// This program is free software (firmware): you can redistribute it and/or
34
// modify it under the terms of  the GNU General Public License as published
35
// by the Free Software Foundation, either version 3 of the License, or (at
36
// your option) any later version.
37
//
38
// This program is distributed in the hope that it will be useful, but WITHOUT
39
// ANY WARRANTY; without even the implied warranty of MERCHANTIBILITY or
40
// FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
41
// for more details.
42
//
43
// License:     GPL, v3, as defined and found on www.gnu.org,
44
//              http://www.gnu.org/licenses/gpl.html
45
//
46
//
47
///////////////////////////////////////////////////////////////////////////////
48
`ifndef CPUDEFS_H
49
`define CPUDEFS_H
50
//
51
//
52
// The first couple options control the Zip CPU instruction set, and how
53
// it handles various instructions within the set:
54
//
55
//
56
// OPT_CONDITIONAL_FLAGS controls whether or not a conditional instruction
57
// is allowed to set flags.  If conditional instructions can set flags, then
58
// strings of conditional instructions will die whenever a flag setting 
59
// instruction is executed.  If they cannot, then you can execute a string
60
// of functions with no further conditions in them.  Set this flag to enable
61
// strings of instructions, as these can be a lot cheaper than the pipeline
62
// stalls associated with a conditional branch.
63
//
64
// This option will likely be changed in the future so that "CMP" and "TST"
65
// instructions set the flags even if they are conditional, to allow multiple
66
// conditions to be tested at once.
67
//
68
// I recommend setting this flag
69
//
70
`define OPT_CONDITIONAL_FLAGS
71
//
72
//
73
//
74
// OPT_ILLEGAL_INSTRUCTION is part of a new section of code that is supposed
75
// to recognize illegal instructions and interrupt the CPU whenever one such
76
// instruction is encountered.  The goal is to create a soft floating point
77
// unit via this approach, that can then be replaced with a true floating point
78
// unit.  As I'm not there yet, it just catches illegal instructions and
79
// interrupts the CPU on any such instruction--when defined.  Otherwise,
80
// illegal instructions are quietly ignored and their behaviour is ...
81
// undefined. (Many get treated like NOOPs ...)
82
//
83
// I recommend setting this flag, although it can be taken out if area is
84
// critical ...
85
//
86
`define OPT_ILLEGAL_INSTRUCTION
87
//
88
//
89
//
90
// OPT_MULTIPLY controls whether or not the multiply is built and included
91
// in the ALU by default.  Set this option and a parameter will be set that
92
// includes the multiply.  (This parameter may still be overridden, as with
93
// any parameter ...)  If the multiply is not included and
94
// OPT_ILLEGAL_INSTRUCTION is set, then the multiply will create an illegal
95
// instruction that will then trip the illegal instruction trap.
96
//
97
//
98
`define OPT_MULTIPLY
99
//
100
//
101
//
102
// OPT_SINGLE_FETCH controls whether or not the prefetch has a cache, and 
103
// whether or not it can issue one instruction per clock.  When set, the
104
// prefetch has no cache, and only one instruction is fetched at a time.
105
// This effectively sets the CPU so that only one instruction is ever 
106
// in the pipeline at once, and hence you may think of this as a "kill 
107
// pipeline" option.  However, since the pipelined fetch component uses so
108
// much area on the FPGA, this is an important option to use in trimming down
109
// used area if necessary.  Hence, it needs to be maintained for that purpose.
110
// Be aware, though, it will drop your performance by a factor between 2x and
111
// 3x.
112
//
113 64 dgisselq
// We can either pipeline our fetches, or issue one fetch at a time.  Pipelined
114
// fetches are more complicated and therefore use more FPGA resources, while
115
// single fetches will cause the CPU to stall for about 5 stalls each 
116
// instruction cycle, effectively reducing the instruction count per clock to
117
// about 0.2.  However, the area cost may be worth it.  Consider:
118
//
119
//      Slice LUTs              ZipSystem       ZipCPU
120
//      Single Fetching         2521            1734
121
//      Pipelined fetching      2796            2046
122
//      (These numbers may be dated, but should still be representative ...)
123
//
124 56 dgisselq
// I recommend only defining this if you "need" to, if area is tight and
125
// speed isn't as important.  Otherwise, just leave this undefined.
126
//
127
// `define      OPT_SINGLE_FETCH
128
//
129
//
130
//
131
// The next several options are pipeline optimization options.  They make no
132
// sense in a single instruction fetch mode, hence we #ifndef them so they
133
// are only defined if we are in a full pipelined mode (i.e. OPT_SINGLE_FETCH
134
// is not defined).
135
//
136
`ifndef OPT_SINGLE_FETCH
137
//
138
//
139
//
140
// OPT_PRECLEAR_BUS allows an upcoming, unconditional, LOD/STO instruction
141
// to kick the prefetch off the memory bus so that the LOD/STO instruction may
142
// use the bus without waiting for the prefetch cycle to complete.  While it
143
// sounds like this should speed things up, it isn't clear that it speeds up
144
// programs that much--often the bus gets precleared for the LOD/STO, only
145
// to have the next instruction stall because it wasn't loaded in time.
146
//
147
// While I recommend setting this flag, that recommendation may change in the
148
// future.
149
//
150
`define OPT_PRECLEAR_BUS
151
//
152
//
153
//
154
// OPT_EARLY_BRANCHING is an attempt to execute a BRA statement as early
155
// as possible, to avoid as many pipeline stalls on a branch as possible.
156
// It's not tremendously successful yet--BRA's suffer 3 stalls instead of 5,
157
// but I intend to keep working on this approach until the number of stalls
158
// gets down to one or (ideally) zero.  That way a "BRA" can be used as the
159
// compiler's branch prediction optimizer: BRA's don't stall, while branches on 
160
// conditions will always suffer about 5 stalls or so.
161
//
162
// I recommend setting this flag, so as to turn early branching on.
163
//
164
`define OPT_EARLY_BRANCHING
165
//
166
//
167
//
168
// OPT_PIPELINED_BUS_ACCESS controls whether or not LOD/STO instructions
169
// can take advantaged of pipelined bus instructions.  To be eligible, the
170
// operations must be identical (cannot pipeline loads and stores, just loads
171
// only or stores only), and the addresses must either be identical or one up
172
// from the previous address.  Further, the load/store string must all have
173
// the same conditional.  This approach gains the must use, in my humble
174
// opinion, when saving registers to or restoring registers from the stack
175
// at the beginning/end of a procedure, or when doing a context swap.
176
//
177
// I recommend setting this flag, for performance reasons, especially if your
178
// wishbone bus can handle pipelined bus accesses.
179
//
180
`define OPT_PIPELINED_BUS_ACCESS
181
//
182
//
183
//
184
// OPT_SINGLE_CYCLE controls how the Zip CPU handles operations where the
185
// second of two instructions uses a register output from the first of the
186
// two.  If set, there will be no stalling between such a pair of instructions.
187
// If not set, the CPU will insert a stall between such a pair to give the
188
// result time to propagate to the second instruction.  Other than the existence
189
// of a stall, the CPU will still yield the same results for the same
190
// instructions.
191
//
192
// The purpose of this is really timing: With this option defined, a logical
193
// or combinatorial mux is placed prior to the input of the ALU.  This mux,
194
// together with whatever ALU operation is to take place, must both fit within
195
// one clock cycle.  If they cannot be made to fit within the one clock cycle,
196
// then either the clock must be slowed down so that they can fit, or this
197
// flag needs to be turned off (not set) to get rid of the mux--hence speeding
198
// up the clock while slowing down some instructions.
199
//
200
`define OPT_SINGLE_CYCLE
201
//
202
//
203
`endif  // OPT_SINGLE_FETCH
204
//
205
//
206
`endif  // CPUDEFS_H

powered by: WebSVN 2.1.0

© copyright 1999-2024 OpenCores.org, equivalent to Oliscience, all rights reserved. OpenCores®, registered trademark.