Commit | Line | Data |
---|---|---|
1da177e4 LT |
1 | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
2 | MOTOROLA MICROPROCESSOR & MEMORY TECHNOLOGY GROUP | |
3 | M68000 Hi-Performance Microprocessor Division | |
4 | M68060 Software Package | |
5 | Production Release P1.00 -- October 10, 1994 | |
6 | ||
96de0e25 | 7 | M68060 Software Package Copyright © 1993, 1994 Motorola Inc. All rights reserved. |
1da177e4 LT |
8 | |
9 | THE SOFTWARE is provided on an "AS IS" basis and without warranty. | |
10 | To the maximum extent permitted by applicable law, | |
11 | MOTOROLA DISCLAIMS ALL WARRANTIES WHETHER EXPRESS OR IMPLIED, | |
12 | INCLUDING IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE | |
13 | and any warranty against infringement with regard to the SOFTWARE | |
14 | (INCLUDING ANY MODIFIED VERSIONS THEREOF) and any accompanying written materials. | |
15 | ||
16 | To the maximum extent permitted by applicable law, | |
17 | IN NO EVENT SHALL MOTOROLA BE LIABLE FOR ANY DAMAGES WHATSOEVER | |
18 | (INCLUDING WITHOUT LIMITATION, DAMAGES FOR LOSS OF BUSINESS PROFITS, | |
19 | BUSINESS INTERRUPTION, LOSS OF BUSINESS INFORMATION, OR OTHER PECUNIARY LOSS) | |
20 | ARISING OF THE USE OR INABILITY TO USE THE SOFTWARE. | |
21 | Motorola assumes no responsibility for the maintenance and support of the SOFTWARE. | |
22 | ||
23 | You are hereby granted a copyright license to use, modify, and distribute the SOFTWARE | |
24 | so long as this entire notice is retained without alteration in any modified and/or | |
25 | redistributed versions, and that such modified versions are clearly identified as such. | |
26 | No licenses are granted by implication, estoppel or otherwise under any patents | |
27 | or trademarks of Motorola, Inc. | |
28 | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | |
29 | ||
30 | 68060 FLOATING-POINT SOFTWARE PACKAGE (Library version) | |
31 | -------------------------------------------------------- | |
32 | ||
33 | The file fplsp.sa contains the "Library version" of the | |
34 | 68060SP Floating-Point Software Package. The routines | |
35 | included in this module can be used to emulate the | |
36 | FP instructions not implemented in 68060 hardware. These | |
37 | instructions normally take exception vector #11 | |
38 | "FP Unimplemented Instruction". | |
39 | ||
40 | By re-compiling a program that uses these instructions, and | |
41 | making subroutine calls in place of the unimplemented | |
42 | instructions, a program can avoid the overhead associated | |
43 | with taking the exception. | |
44 | ||
45 | Release file format: | |
46 | -------------------- | |
47 | The file fplsp.sa is essentially a hexadecimal image of the | |
48 | release package. This is the ONLY format which will be supported. | |
49 | The hex image was created by assembling the source code and | |
50 | then converting the resulting binary output image into an | |
51 | ASCII text file. The hexadecimal numbers are listed | |
52 | using the Motorola Assembly Syntax assembler directive "dc.l" | |
53 | (define constant longword). The file can be converted to other | |
54 | assembly syntaxes by using any word processor with a global | |
55 | search and replace function. | |
56 | ||
57 | To assist in assembling and linking this module with other modules, | |
58 | the installer should add a symbolic label to the top of the file. | |
59 | This will allow calling routines to access the entry points | |
60 | of this package. | |
61 | ||
62 | The source code fplsp.s has also been included but only for | |
63 | documentation purposes. | |
64 | ||
65 | Release file structure: | |
66 | ----------------------- | |
67 | The file fplsp.sa contains an "Entry-Point" section and a | |
68 | code section. The FPLSP has no "Call-Out" section. The first section | |
69 | is the "Entry-Point" section. In order to access a function in the | |
70 | package, a program must "bsr" or "jsr" to the location listed | |
71 | below in "68060FPLSP entry points" that corresponds to the desired | |
72 | function. A branch instruction located at the selected entry point | |
73 | within the package will then enter the correct emulation code routine. | |
74 | ||
75 | The entry point addresses at the beginning of the package will remain | |
76 | fixed so that a program calling the routines will not have to be | |
77 | re-compiled with every new 68060FPLSP release. | |
78 | ||
79 | There are 3 entry-points for each instruction type: single precision, | |
80 | double precision, and extended precision. | |
81 | ||
82 | As an example, the "fsin" library instruction can be passed an | |
83 | extended precision operand if program executes: | |
84 | ||
85 | # fsin.x fp0 | |
86 | ||
87 | fmovm.x &0x01,-(%sp) # pass operand on stack | |
88 | bsr.l _060FPLSP_TOP+0x1a8 # branch to fsin routine | |
89 | add.l &0xc,%sp # clear operand from stack | |
90 | ||
91 | Upon return, fp0 holds the correct result. The FPSR is | |
92 | set correctly. The FPCR is unchanged. The FPIAR is undefined. | |
93 | ||
94 | Another example. This time, a dyadic operation: | |
95 | ||
96 | # frem.s %fp1,%fp0 | |
97 | ||
98 | fmov.s %fp1,-(%sp) # pass src operand | |
99 | fmov.s %fp0,-(%sp) # pass dst operand | |
100 | bsr.l _060FPLSP_TOP+0x168 # branch to frem routine | |
101 | addq.l &0x8,%sp # clear operands from stack | |
102 | ||
103 | Again, the result is returned in fp0. Note that BOTH operands | |
104 | are passed in single precision format. | |
105 | ||
106 | Exception reporting: | |
107 | -------------------- | |
108 | The package takes exceptions according to the FPCR value upon subroutine | |
109 | entry. If an exception should be reported, then the package forces | |
110 | this exception using implemented floating-point instructions. | |
111 | For example, if the instruction being emulated should cause a | |
112 | floating-point Operand Error exception, then the library routine | |
113 | executes an FMUL of a zero and an infinity to force the OPERR | |
114 | exception. Although the FPIAR will be undefined for the enabled | |
115 | Operand Error exception handler, the user will at least be able | |
116 | to record that the event occurred. | |
117 | ||
118 | Miscellaneous: | |
119 | -------------- | |
120 | The package does not attempt to correctly emulate instructions | |
121 | with Signalling NAN inputs. Use of SNANs should be avoided with | |
122 | this package. | |
123 | ||
124 | The fabs/fadd/fdiv/fint/fintrz/fmul/fneg/fsqrt/fsub entry points | |
125 | are provided for the convenience of older compilers that make | |
126 | subroutine calls for all fp instructions. The code does NOT emulate | |
127 | the instruction but rather simply executes it. | |
128 | ||
129 | 68060FPLSP entry points: | |
130 | ------------------------ | |
131 | _060FPLSP_TOP: | |
132 | 0x000: _060LSP__facoss_ | |
133 | 0x008: _060LSP__facosd_ | |
134 | 0x010: _060LSP__facosx_ | |
135 | 0x018: _060LSP__fasins_ | |
136 | 0x020: _060LSP__fasind_ | |
137 | 0x028: _060LSP__fasinx_ | |
138 | 0x030: _060LSP__fatans_ | |
139 | 0x038: _060LSP__fatand_ | |
140 | 0x040: _060LSP__fatanx_ | |
141 | 0x048: _060LSP__fatanhs_ | |
142 | 0x050: _060LSP__fatanhd_ | |
143 | 0x058: _060LSP__fatanhx_ | |
144 | 0x060: _060LSP__fcoss_ | |
145 | 0x068: _060LSP__fcosd_ | |
146 | 0x070: _060LSP__fcosx_ | |
147 | 0x078: _060LSP__fcoshs_ | |
148 | 0x080: _060LSP__fcoshd_ | |
149 | 0x088: _060LSP__fcoshx_ | |
150 | 0x090: _060LSP__fetoxs_ | |
151 | 0x098: _060LSP__fetoxd_ | |
152 | 0x0a0: _060LSP__fetoxx_ | |
153 | 0x0a8: _060LSP__fetoxm1s_ | |
154 | 0x0b0: _060LSP__fetoxm1d_ | |
155 | 0x0b8: _060LSP__fetoxm1x_ | |
156 | 0x0c0: _060LSP__fgetexps_ | |
157 | 0x0c8: _060LSP__fgetexpd_ | |
158 | 0x0d0: _060LSP__fgetexpx_ | |
159 | 0x0d8: _060LSP__fgetmans_ | |
160 | 0x0e0: _060LSP__fgetmand_ | |
161 | 0x0e8: _060LSP__fgetmanx_ | |
162 | 0x0f0: _060LSP__flog10s_ | |
163 | 0x0f8: _060LSP__flog10d_ | |
164 | 0x100: _060LSP__flog10x_ | |
165 | 0x108: _060LSP__flog2s_ | |
166 | 0x110: _060LSP__flog2d_ | |
167 | 0x118: _060LSP__flog2x_ | |
168 | 0x120: _060LSP__flogns_ | |
169 | 0x128: _060LSP__flognd_ | |
170 | 0x130: _060LSP__flognx_ | |
171 | 0x138: _060LSP__flognp1s_ | |
172 | 0x140: _060LSP__flognp1d_ | |
173 | 0x148: _060LSP__flognp1x_ | |
174 | 0x150: _060LSP__fmods_ | |
175 | 0x158: _060LSP__fmodd_ | |
176 | 0x160: _060LSP__fmodx_ | |
177 | 0x168: _060LSP__frems_ | |
178 | 0x170: _060LSP__fremd_ | |
179 | 0x178: _060LSP__fremx_ | |
180 | 0x180: _060LSP__fscales_ | |
181 | 0x188: _060LSP__fscaled_ | |
182 | 0x190: _060LSP__fscalex_ | |
183 | 0x198: _060LSP__fsins_ | |
184 | 0x1a0: _060LSP__fsind_ | |
185 | 0x1a8: _060LSP__fsinx_ | |
186 | 0x1b0: _060LSP__fsincoss_ | |
187 | 0x1b8: _060LSP__fsincosd_ | |
188 | 0x1c0: _060LSP__fsincosx_ | |
189 | 0x1c8: _060LSP__fsinhs_ | |
190 | 0x1d0: _060LSP__fsinhd_ | |
191 | 0x1d8: _060LSP__fsinhx_ | |
192 | 0x1e0: _060LSP__ftans_ | |
193 | 0x1e8: _060LSP__ftand_ | |
194 | 0x1f0: _060LSP__ftanx_ | |
195 | 0x1f8: _060LSP__ftanhs_ | |
196 | 0x200: _060LSP__ftanhd_ | |
197 | 0x208: _060LSP__ftanhx_ | |
198 | 0x210: _060LSP__ftentoxs_ | |
199 | 0x218: _060LSP__ftentoxd_ | |
200 | 0x220: _060LSP__ftentoxx_ | |
201 | 0x228: _060LSP__ftwotoxs_ | |
202 | 0x230: _060LSP__ftwotoxd_ | |
203 | 0x238: _060LSP__ftwotoxx_ | |
204 | ||
205 | 0x240: _060LSP__fabss_ | |
206 | 0x248: _060LSP__fabsd_ | |
207 | 0x250: _060LSP__fabsx_ | |
208 | 0x258: _060LSP__fadds_ | |
209 | 0x260: _060LSP__faddd_ | |
210 | 0x268: _060LSP__faddx_ | |
211 | 0x270: _060LSP__fdivs_ | |
212 | 0x278: _060LSP__fdivd_ | |
213 | 0x280: _060LSP__fdivx_ | |
214 | 0x288: _060LSP__fints_ | |
215 | 0x290: _060LSP__fintd_ | |
216 | 0x298: _060LSP__fintx_ | |
217 | 0x2a0: _060LSP__fintrzs_ | |
218 | 0x2a8: _060LSP__fintrzd_ | |
219 | 0x2b0: _060LSP__fintrzx_ | |
220 | 0x2b8: _060LSP__fmuls_ | |
221 | 0x2c0: _060LSP__fmuld_ | |
222 | 0x2c8: _060LSP__fmulx_ | |
223 | 0x2d0: _060LSP__fnegs_ | |
224 | 0x2d8: _060LSP__fnegd_ | |
225 | 0x2e0: _060LSP__fnegx_ | |
226 | 0x2e8: _060LSP__fsqrts_ | |
227 | 0x2f0: _060LSP__fsqrtd_ | |
228 | 0x2f8: _060LSP__fsqrtx_ | |
229 | 0x300: _060LSP__fsubs_ | |
230 | 0x308: _060LSP__fsubd_ | |
231 | 0x310: _060LSP__fsubx_ |