forked from antonblanchard/microwatt
-
Notifications
You must be signed in to change notification settings - Fork 0
/
fpu.vhdl
3592 lines (3440 loc) · 149 KB
/
fpu.vhdl
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
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
-- Floating-point unit for Microwatt
library ieee;
use ieee.std_logic_1164.all;
use ieee.numeric_std.all;
library work;
use work.insn_helpers.all;
use work.decode_types.all;
use work.crhelpers.all;
use work.helpers.all;
use work.common.all;
entity fpu is
port (
clk : in std_ulogic;
rst : in std_ulogic;
flush_in : in std_ulogic;
e_in : in Execute1ToFPUType;
e_out : out FPUToExecute1Type;
w_out : out FPUToWritebackType
);
end entity fpu;
architecture behaviour of fpu is
type fp_number_class is (ZERO, FINITE, INFINITY, NAN);
constant EXP_BITS : natural := 13;
constant UNIT_BIT : natural := 56;
constant QNAN_BIT : natural := UNIT_BIT - 1;
constant SP_LSB : natural := UNIT_BIT - 23;
constant SP_GBIT : natural := SP_LSB - 1;
constant SP_RBIT : natural := SP_LSB - 2;
constant DP_LSB : natural := UNIT_BIT - 52;
constant DP_GBIT : natural := DP_LSB - 1;
constant DP_RBIT : natural := DP_LSB - 2;
type fpu_reg_type is record
class : fp_number_class;
negative : std_ulogic;
denorm : std_ulogic;
exponent : signed(EXP_BITS-1 downto 0); -- unbiased
mantissa : std_ulogic_vector(63 downto 0); -- 8.56 format
end record;
type state_t is (IDLE, DO_ILLEGAL,
DO_MCRFS, DO_MTFSB, DO_MTFSFI, DO_MFFS, DO_MTFSF,
DO_FMR, DO_FMRG, DO_FCMP, DO_FTDIV, DO_FTSQRT,
DO_FCFID, DO_FCTI,
DO_FRSP, DO_FRI,
DO_FADD, DO_FMUL, DO_FDIV, DO_FSQRT, DO_FMADD,
DO_FRE, DO_FRSQRTE,
DO_FSEL,
DO_IDIVMOD,
FRI_1,
ADD_1, ADD_SHIFT, ADD_2, ADD_3,
CMP_1, CMP_2,
MULT_1,
FMADD_0, FMADD_1, FMADD_2, FMADD_3,
FMADD_4, FMADD_5, FMADD_6,
LOOKUP,
DIV_2, DIV_3, DIV_4, DIV_5, DIV_6,
FRE_1,
RSQRT_1,
FTDIV_1,
SQRT_1, SQRT_2, SQRT_3, SQRT_4,
SQRT_5, SQRT_6, SQRT_7, SQRT_8,
SQRT_9, SQRT_10, SQRT_11, SQRT_12,
INT_SHIFT, INT_ROUND, INT_ISHIFT,
INT_FINAL, INT_CHECK, INT_OFLOW,
FINISH, NORMALIZE,
ROUND_UFLOW, ROUND_OFLOW,
ROUNDING, ROUNDING_2, ROUNDING_3,
DENORM,
RENORM_A, RENORM_A2,
RENORM_B, RENORM_B2,
RENORM_C, RENORM_C2,
NAN_RESULT, EXC_RESULT,
IDIV_NORMB, IDIV_NORMB2, IDIV_NORMB3,
IDIV_CLZA, IDIV_CLZA2, IDIV_CLZA3,
IDIV_NR0, IDIV_NR1, IDIV_NR2, IDIV_USE0_5,
IDIV_DODIV, IDIV_SH32,
IDIV_DIV, IDIV_DIV2, IDIV_DIV3, IDIV_DIV4, IDIV_DIV5,
IDIV_DIV6, IDIV_DIV7, IDIV_DIV8, IDIV_DIV9,
IDIV_EXT_TBH, IDIV_EXT_TBH2, IDIV_EXT_TBH3,
IDIV_EXT_TBH4, IDIV_EXT_TBH5,
IDIV_EXTDIV, IDIV_EXTDIV1, IDIV_EXTDIV2, IDIV_EXTDIV3,
IDIV_EXTDIV4, IDIV_EXTDIV5, IDIV_EXTDIV6,
IDIV_MODADJ, IDIV_MODSUB, IDIV_DIVADJ, IDIV_OVFCHK, IDIV_DONE, IDIV_ZERO);
type decode32 is array(0 to 31) of state_t;
type decode8 is array(0 to 7) of state_t;
type reg_type is record
state : state_t;
busy : std_ulogic;
f2stall : std_ulogic;
instr_done : std_ulogic;
complete : std_ulogic;
do_intr : std_ulogic;
illegal : std_ulogic;
op : insn_type_t;
insn : std_ulogic_vector(31 downto 0);
instr_tag : instr_tag_t;
dest_fpr : gspr_index_t;
fe_mode : std_ulogic;
rc : std_ulogic;
fp_rc : std_ulogic;
is_cmp : std_ulogic;
single_prec : std_ulogic;
sp_result : std_ulogic;
fpscr : std_ulogic_vector(31 downto 0);
comm_fpscr : std_ulogic_vector(31 downto 0); -- committed FPSCR value
a : fpu_reg_type;
b : fpu_reg_type;
c : fpu_reg_type;
r : std_ulogic_vector(63 downto 0); -- 8.56 format
s : std_ulogic_vector(55 downto 0); -- extended fraction
x : std_ulogic;
p : std_ulogic_vector(63 downto 0); -- 8.56 format
y : std_ulogic_vector(63 downto 0); -- 8.56 format
result_sign : std_ulogic;
result_class : fp_number_class;
result_exp : signed(EXP_BITS-1 downto 0);
shift : signed(EXP_BITS-1 downto 0);
writing_fpr : std_ulogic;
write_reg : gspr_index_t;
complete_tag : instr_tag_t;
writing_cr : std_ulogic;
writing_xer : std_ulogic;
int_result : std_ulogic;
cr_result : std_ulogic_vector(3 downto 0);
cr_mask : std_ulogic_vector(7 downto 0);
old_exc : std_ulogic_vector(4 downto 0);
update_fprf : std_ulogic;
quieten_nan : std_ulogic;
nsnan_result : std_ulogic;
tiny : std_ulogic;
denorm : std_ulogic;
round_mode : std_ulogic_vector(2 downto 0);
is_subtract : std_ulogic;
exp_cmp : std_ulogic;
madd_cmp : std_ulogic;
add_bsmall : std_ulogic;
is_multiply : std_ulogic;
is_sqrt : std_ulogic;
first : std_ulogic;
count : unsigned(1 downto 0);
doing_ftdiv : std_ulogic_vector(1 downto 0);
opsel_a : std_ulogic_vector(1 downto 0);
use_a : std_ulogic;
use_b : std_ulogic;
use_c : std_ulogic;
invalid : std_ulogic;
negate : std_ulogic;
longmask : std_ulogic;
integer_op : std_ulogic;
divext : std_ulogic;
divmod : std_ulogic;
is_signed : std_ulogic;
int_ovf : std_ulogic;
div_close : std_ulogic;
inc_quot : std_ulogic;
a_hi : std_ulogic_vector(7 downto 0);
a_lo : std_ulogic_vector(55 downto 0);
m32b : std_ulogic;
oe : std_ulogic;
xerc : xer_common_t;
xerc_result : xer_common_t;
res_sign : std_ulogic;
end record;
type lookup_table is array(0 to 1023) of std_ulogic_vector(17 downto 0);
signal r, rin : reg_type;
signal fp_result : std_ulogic_vector(63 downto 0);
signal opsel_b : std_ulogic_vector(1 downto 0);
signal opsel_r : std_ulogic_vector(1 downto 0);
signal opsel_s : std_ulogic_vector(1 downto 0);
signal opsel_ainv : std_ulogic;
signal opsel_mask : std_ulogic;
signal opsel_binv : std_ulogic;
signal in_a : std_ulogic_vector(63 downto 0);
signal in_b : std_ulogic_vector(63 downto 0);
signal result : std_ulogic_vector(63 downto 0);
signal carry_in : std_ulogic;
signal lost_bits : std_ulogic;
signal r_hi_nz : std_ulogic;
signal r_lo_nz : std_ulogic;
signal r_gt_1 : std_ulogic;
signal s_nz : std_ulogic;
signal misc_sel : std_ulogic_vector(3 downto 0);
signal f_to_multiply : MultiplyInputType;
signal multiply_to_f : MultiplyOutputType;
signal msel_1 : std_ulogic_vector(1 downto 0);
signal msel_2 : std_ulogic_vector(1 downto 0);
signal msel_add : std_ulogic_vector(1 downto 0);
signal msel_inv : std_ulogic;
signal inverse_est : std_ulogic_vector(18 downto 0);
-- opsel values
constant AIN_R : std_ulogic_vector(1 downto 0) := "00";
constant AIN_A : std_ulogic_vector(1 downto 0) := "01";
constant AIN_B : std_ulogic_vector(1 downto 0) := "10";
constant AIN_C : std_ulogic_vector(1 downto 0) := "11";
constant BIN_ZERO : std_ulogic_vector(1 downto 0) := "00";
constant BIN_R : std_ulogic_vector(1 downto 0) := "01";
constant BIN_RND : std_ulogic_vector(1 downto 0) := "10";
constant BIN_PS8 : std_ulogic_vector(1 downto 0) := "11";
constant RES_SUM : std_ulogic_vector(1 downto 0) := "00";
constant RES_SHIFT : std_ulogic_vector(1 downto 0) := "01";
constant RES_MULT : std_ulogic_vector(1 downto 0) := "10";
constant RES_MISC : std_ulogic_vector(1 downto 0) := "11";
constant S_ZERO : std_ulogic_vector(1 downto 0) := "00";
constant S_NEG : std_ulogic_vector(1 downto 0) := "01";
constant S_SHIFT : std_ulogic_vector(1 downto 0) := "10";
constant S_MULT : std_ulogic_vector(1 downto 0) := "11";
-- msel values
constant MUL1_A : std_ulogic_vector(1 downto 0) := "00";
constant MUL1_B : std_ulogic_vector(1 downto 0) := "01";
constant MUL1_Y : std_ulogic_vector(1 downto 0) := "10";
constant MUL1_R : std_ulogic_vector(1 downto 0) := "11";
constant MUL2_C : std_ulogic_vector(1 downto 0) := "00";
constant MUL2_LUT : std_ulogic_vector(1 downto 0) := "01";
constant MUL2_P : std_ulogic_vector(1 downto 0) := "10";
constant MUL2_R : std_ulogic_vector(1 downto 0) := "11";
constant MULADD_ZERO : std_ulogic_vector(1 downto 0) := "00";
constant MULADD_CONST : std_ulogic_vector(1 downto 0) := "01";
constant MULADD_A : std_ulogic_vector(1 downto 0) := "10";
constant MULADD_RS : std_ulogic_vector(1 downto 0) := "11";
-- control signals and values for exponent data path
constant REXP1_ZERO : std_ulogic_vector(1 downto 0) := "00";
constant REXP1_R : std_ulogic_vector(1 downto 0) := "01";
constant REXP1_A : std_ulogic_vector(1 downto 0) := "10";
constant REXP1_BHALF : std_ulogic_vector(1 downto 0) := "11";
constant REXP2_CON : std_ulogic_vector(1 downto 0) := "00";
constant REXP2_NE : std_ulogic_vector(1 downto 0) := "01";
constant REXP2_C : std_ulogic_vector(1 downto 0) := "10";
constant REXP2_B : std_ulogic_vector(1 downto 0) := "11";
constant RECON2_ZERO : std_ulogic_vector(1 downto 0) := "00";
constant RECON2_UNIT : std_ulogic_vector(1 downto 0) := "01";
constant RECON2_BIAS : std_ulogic_vector(1 downto 0) := "10";
constant RECON2_MAX : std_ulogic_vector(1 downto 0) := "11";
signal re_sel1 : std_ulogic_vector(1 downto 0);
signal re_sel2 : std_ulogic_vector(1 downto 0);
signal re_con2 : std_ulogic_vector(1 downto 0);
signal re_neg1 : std_ulogic;
signal re_neg2 : std_ulogic;
signal re_set_result : std_ulogic;
constant RSH1_ZERO : std_ulogic_vector(1 downto 0) := "00";
constant RSH1_B : std_ulogic_vector(1 downto 0) := "01";
constant RSH1_NE : std_ulogic_vector(1 downto 0) := "10";
constant RSH1_S : std_ulogic_vector(1 downto 0) := "11";
constant RSH2_CON : std_ulogic := '0';
constant RSH2_A : std_ulogic := '1';
constant RSCON2_ZERO : std_ulogic_vector(3 downto 0) := "0000";
constant RSCON2_1 : std_ulogic_vector(3 downto 0) := "0001";
constant RSCON2_UNIT_52 : std_ulogic_vector(3 downto 0) := "0010";
constant RSCON2_64_UNIT : std_ulogic_vector(3 downto 0) := "0011";
constant RSCON2_32 : std_ulogic_vector(3 downto 0) := "0100";
constant RSCON2_52 : std_ulogic_vector(3 downto 0) := "0101";
constant RSCON2_UNIT : std_ulogic_vector(3 downto 0) := "0110";
constant RSCON2_63 : std_ulogic_vector(3 downto 0) := "0111";
constant RSCON2_64 : std_ulogic_vector(3 downto 0) := "1000";
constant RSCON2_MINEXP : std_ulogic_vector(3 downto 0) := "1001";
signal rs_sel1 : std_ulogic_vector(1 downto 0);
signal rs_sel2 : std_ulogic;
signal rs_con2 : std_ulogic_vector(3 downto 0);
signal rs_neg1 : std_ulogic;
signal rs_neg2 : std_ulogic;
signal rs_norm : std_ulogic;
constant arith_decode : decode32 := (
-- indexed by bits 5..1 of opcode
2#01000# => DO_FRI,
2#01100# => DO_FRSP,
2#01110# => DO_FCTI,
2#01111# => DO_FCTI,
2#10010# => DO_FDIV,
2#10100# => DO_FADD,
2#10101# => DO_FADD,
2#10110# => DO_FSQRT,
2#11000# => DO_FRE,
2#11001# => DO_FMUL,
2#11010# => DO_FRSQRTE,
2#11100# => DO_FMADD,
2#11101# => DO_FMADD,
2#11110# => DO_FMADD,
2#11111# => DO_FMADD,
others => DO_ILLEGAL
);
constant cmp_decode : decode8 := (
2#000# => DO_FCMP,
2#001# => DO_FCMP,
2#010# => DO_MCRFS,
2#100# => DO_FTDIV,
2#101# => DO_FTSQRT,
others => DO_ILLEGAL
);
constant misc_decode : decode32 := (
-- indexed by bits 10, 8, 4, 2, 1 of opcode
2#00010# => DO_MTFSB,
2#01010# => DO_MTFSFI,
2#10010# => DO_FMRG,
2#11010# => DO_FMRG,
2#10011# => DO_MFFS,
2#11011# => DO_MTFSF,
2#10110# => DO_FCFID,
2#11110# => DO_FCFID,
others => DO_ILLEGAL
);
-- Inverse lookup table, indexed by the top 8 fraction bits
-- The first 256 entries are the reciprocal (1/x) lookup table,
-- and the remaining 768 entries are the reciprocal square root table.
-- Output range is [0.5, 1) in 0.19 format, though the top
-- bit isn't stored since it is always 1.
-- Each output value is the inverse of the center of the input
-- range for the value, i.e. entry 0 is 1 / (1 + 1/512),
-- entry 1 is 1 / (1 + 3/512), etc.
constant inverse_table : lookup_table := (
-- 1/x lookup table
-- Unit bit is assumed to be 1, so input range is [1, 2)
18x"3fc01", 18x"3f411", 18x"3ec31", 18x"3e460", 18x"3dc9f", 18x"3d4ec", 18x"3cd49", 18x"3c5b5",
18x"3be2f", 18x"3b6b8", 18x"3af4f", 18x"3a7f4", 18x"3a0a7", 18x"39968", 18x"39237", 18x"38b14",
18x"383fe", 18x"37cf5", 18x"375f9", 18x"36f0a", 18x"36828", 18x"36153", 18x"35a8a", 18x"353ce",
18x"34d1e", 18x"3467a", 18x"33fe3", 18x"33957", 18x"332d7", 18x"32c62", 18x"325f9", 18x"31f9c",
18x"3194a", 18x"31303", 18x"30cc7", 18x"30696", 18x"30070", 18x"2fa54", 18x"2f443", 18x"2ee3d",
18x"2e841", 18x"2e250", 18x"2dc68", 18x"2d68b", 18x"2d0b8", 18x"2caee", 18x"2c52e", 18x"2bf79",
18x"2b9cc", 18x"2b429", 18x"2ae90", 18x"2a900", 18x"2a379", 18x"29dfb", 18x"29887", 18x"2931b",
18x"28db8", 18x"2885e", 18x"2830d", 18x"27dc4", 18x"27884", 18x"2734d", 18x"26e1d", 18x"268f6",
18x"263d8", 18x"25ec1", 18x"259b3", 18x"254ac", 18x"24fad", 18x"24ab7", 18x"245c8", 18x"240e1",
18x"23c01", 18x"23729", 18x"23259", 18x"22d90", 18x"228ce", 18x"22413", 18x"21f60", 18x"21ab4",
18x"2160f", 18x"21172", 18x"20cdb", 18x"2084b", 18x"203c2", 18x"1ff40", 18x"1fac4", 18x"1f64f",
18x"1f1e1", 18x"1ed79", 18x"1e918", 18x"1e4be", 18x"1e069", 18x"1dc1b", 18x"1d7d4", 18x"1d392",
18x"1cf57", 18x"1cb22", 18x"1c6f3", 18x"1c2ca", 18x"1bea7", 18x"1ba8a", 18x"1b672", 18x"1b261",
18x"1ae55", 18x"1aa50", 18x"1a64f", 18x"1a255", 18x"19e60", 18x"19a70", 18x"19686", 18x"192a2",
18x"18ec3", 18x"18ae9", 18x"18715", 18x"18345", 18x"17f7c", 18x"17bb7", 18x"177f7", 18x"1743d",
18x"17087", 18x"16cd7", 18x"1692c", 18x"16585", 18x"161e4", 18x"15e47", 18x"15ab0", 18x"1571d",
18x"1538e", 18x"15005", 18x"14c80", 18x"14900", 18x"14584", 18x"1420d", 18x"13e9b", 18x"13b2d",
18x"137c3", 18x"1345e", 18x"130fe", 18x"12da2", 18x"12a4a", 18x"126f6", 18x"123a7", 18x"1205c",
18x"11d15", 18x"119d2", 18x"11694", 18x"11359", 18x"11023", 18x"10cf1", 18x"109c2", 18x"10698",
18x"10372", 18x"10050", 18x"0fd31", 18x"0fa17", 18x"0f700", 18x"0f3ed", 18x"0f0de", 18x"0edd3",
18x"0eacb", 18x"0e7c7", 18x"0e4c7", 18x"0e1ca", 18x"0ded2", 18x"0dbdc", 18x"0d8eb", 18x"0d5fc",
18x"0d312", 18x"0d02b", 18x"0cd47", 18x"0ca67", 18x"0c78a", 18x"0c4b1", 18x"0c1db", 18x"0bf09",
18x"0bc3a", 18x"0b96e", 18x"0b6a5", 18x"0b3e0", 18x"0b11e", 18x"0ae5f", 18x"0aba3", 18x"0a8eb",
18x"0a636", 18x"0a383", 18x"0a0d4", 18x"09e28", 18x"09b80", 18x"098da", 18x"09637", 18x"09397",
18x"090fb", 18x"08e61", 18x"08bca", 18x"08936", 18x"086a5", 18x"08417", 18x"0818c", 18x"07f04",
18x"07c7e", 18x"079fc", 18x"0777c", 18x"074ff", 18x"07284", 18x"0700d", 18x"06d98", 18x"06b26",
18x"068b6", 18x"0664a", 18x"063e0", 18x"06178", 18x"05f13", 18x"05cb1", 18x"05a52", 18x"057f5",
18x"0559a", 18x"05342", 18x"050ed", 18x"04e9a", 18x"04c4a", 18x"049fc", 18x"047b0", 18x"04567",
18x"04321", 18x"040dd", 18x"03e9b", 18x"03c5c", 18x"03a1f", 18x"037e4", 18x"035ac", 18x"03376",
18x"03142", 18x"02f11", 18x"02ce2", 18x"02ab5", 18x"0288b", 18x"02663", 18x"0243d", 18x"02219",
18x"01ff7", 18x"01dd8", 18x"01bbb", 18x"019a0", 18x"01787", 18x"01570", 18x"0135b", 18x"01149",
18x"00f39", 18x"00d2a", 18x"00b1e", 18x"00914", 18x"0070c", 18x"00506", 18x"00302", 18x"00100",
-- 1/sqrt(x) lookup table
-- Input is in the range [1, 4), i.e. two bits to the left of the
-- binary point. Those 2 bits index the following 3 blocks of 256 values.
-- 1.0 ... 1.9999
18x"3fe00", 18x"3fa06", 18x"3f612", 18x"3f224", 18x"3ee3a", 18x"3ea58", 18x"3e67c", 18x"3e2a4",
18x"3ded2", 18x"3db06", 18x"3d73e", 18x"3d37e", 18x"3cfc2", 18x"3cc0a", 18x"3c85a", 18x"3c4ae",
18x"3c106", 18x"3bd64", 18x"3b9c8", 18x"3b630", 18x"3b29e", 18x"3af10", 18x"3ab86", 18x"3a802",
18x"3a484", 18x"3a108", 18x"39d94", 18x"39a22", 18x"396b6", 18x"3934e", 18x"38fea", 18x"38c8c",
18x"38932", 18x"385dc", 18x"3828a", 18x"37f3e", 18x"37bf6", 18x"378b2", 18x"37572", 18x"37236",
18x"36efe", 18x"36bca", 18x"3689a", 18x"36570", 18x"36248", 18x"35f26", 18x"35c06", 18x"358ea",
18x"355d4", 18x"352c0", 18x"34fb0", 18x"34ca4", 18x"3499c", 18x"34698", 18x"34398", 18x"3409c",
18x"33da2", 18x"33aac", 18x"337bc", 18x"334cc", 18x"331e2", 18x"32efc", 18x"32c18", 18x"32938",
18x"3265a", 18x"32382", 18x"320ac", 18x"31dd8", 18x"31b0a", 18x"3183e", 18x"31576", 18x"312b0",
18x"30fee", 18x"30d2e", 18x"30a74", 18x"307ba", 18x"30506", 18x"30254", 18x"2ffa4", 18x"2fcf8",
18x"2fa4e", 18x"2f7a8", 18x"2f506", 18x"2f266", 18x"2efca", 18x"2ed2e", 18x"2ea98", 18x"2e804",
18x"2e572", 18x"2e2e4", 18x"2e058", 18x"2ddce", 18x"2db48", 18x"2d8c6", 18x"2d646", 18x"2d3c8",
18x"2d14c", 18x"2ced4", 18x"2cc5e", 18x"2c9ea", 18x"2c77a", 18x"2c50c", 18x"2c2a2", 18x"2c038",
18x"2bdd2", 18x"2bb70", 18x"2b90e", 18x"2b6b0", 18x"2b454", 18x"2b1fa", 18x"2afa4", 18x"2ad4e",
18x"2aafc", 18x"2a8ac", 18x"2a660", 18x"2a414", 18x"2a1cc", 18x"29f86", 18x"29d42", 18x"29b00",
18x"298c2", 18x"29684", 18x"2944a", 18x"29210", 18x"28fda", 18x"28da6", 18x"28b74", 18x"28946",
18x"28718", 18x"284ec", 18x"282c4", 18x"2809c", 18x"27e78", 18x"27c56", 18x"27a34", 18x"27816",
18x"275fa", 18x"273e0", 18x"271c8", 18x"26fb0", 18x"26d9c", 18x"26b8a", 18x"2697a", 18x"2676c",
18x"26560", 18x"26356", 18x"2614c", 18x"25f46", 18x"25d42", 18x"25b40", 18x"2593e", 18x"25740",
18x"25542", 18x"25348", 18x"2514e", 18x"24f58", 18x"24d62", 18x"24b6e", 18x"2497c", 18x"2478c",
18x"2459e", 18x"243b0", 18x"241c6", 18x"23fde", 18x"23df6", 18x"23c10", 18x"23a2c", 18x"2384a",
18x"2366a", 18x"2348c", 18x"232ae", 18x"230d2", 18x"22efa", 18x"22d20", 18x"22b4a", 18x"22976",
18x"227a2", 18x"225d2", 18x"22402", 18x"22234", 18x"22066", 18x"21e9c", 18x"21cd2", 18x"21b0a",
18x"21944", 18x"2177e", 18x"215ba", 18x"213fa", 18x"21238", 18x"2107a", 18x"20ebc", 18x"20d00",
18x"20b46", 18x"2098e", 18x"207d6", 18x"20620", 18x"2046c", 18x"202b8", 18x"20108", 18x"1ff58",
18x"1fda8", 18x"1fbfc", 18x"1fa50", 18x"1f8a4", 18x"1f6fc", 18x"1f554", 18x"1f3ae", 18x"1f208",
18x"1f064", 18x"1eec2", 18x"1ed22", 18x"1eb82", 18x"1e9e4", 18x"1e846", 18x"1e6aa", 18x"1e510",
18x"1e378", 18x"1e1e0", 18x"1e04a", 18x"1deb4", 18x"1dd20", 18x"1db8e", 18x"1d9fc", 18x"1d86c",
18x"1d6de", 18x"1d550", 18x"1d3c4", 18x"1d238", 18x"1d0ae", 18x"1cf26", 18x"1cd9e", 18x"1cc18",
18x"1ca94", 18x"1c910", 18x"1c78c", 18x"1c60a", 18x"1c48a", 18x"1c30c", 18x"1c18e", 18x"1c010",
18x"1be94", 18x"1bd1a", 18x"1bba0", 18x"1ba28", 18x"1b8b2", 18x"1b73c", 18x"1b5c6", 18x"1b452",
18x"1b2e0", 18x"1b16e", 18x"1affe", 18x"1ae8e", 18x"1ad20", 18x"1abb4", 18x"1aa46", 18x"1a8dc",
-- 2.0 ... 2.9999
18x"1a772", 18x"1a608", 18x"1a4a0", 18x"1a33a", 18x"1a1d4", 18x"1a070", 18x"19f0c", 18x"19da8",
18x"19c48", 18x"19ae6", 18x"19986", 18x"19828", 18x"196ca", 18x"1956e", 18x"19412", 18x"192b8",
18x"1915e", 18x"19004", 18x"18eae", 18x"18d56", 18x"18c00", 18x"18aac", 18x"18958", 18x"18804",
18x"186b2", 18x"18562", 18x"18412", 18x"182c2", 18x"18174", 18x"18026", 18x"17eda", 18x"17d8e",
18x"17c44", 18x"17afa", 18x"179b2", 18x"1786a", 18x"17724", 18x"175de", 18x"17498", 18x"17354",
18x"17210", 18x"170ce", 18x"16f8c", 18x"16e4c", 18x"16d0c", 18x"16bcc", 18x"16a8e", 18x"16950",
18x"16814", 18x"166d8", 18x"1659e", 18x"16464", 18x"1632a", 18x"161f2", 18x"160ba", 18x"15f84",
18x"15e4e", 18x"15d1a", 18x"15be6", 18x"15ab2", 18x"15980", 18x"1584e", 18x"1571c", 18x"155ec",
18x"154bc", 18x"1538e", 18x"15260", 18x"15134", 18x"15006", 18x"14edc", 18x"14db0", 18x"14c86",
18x"14b5e", 18x"14a36", 18x"1490e", 18x"147e6", 18x"146c0", 18x"1459a", 18x"14476", 18x"14352",
18x"14230", 18x"1410c", 18x"13fea", 18x"13eca", 18x"13daa", 18x"13c8a", 18x"13b6c", 18x"13a4e",
18x"13930", 18x"13814", 18x"136f8", 18x"135dc", 18x"134c2", 18x"133a8", 18x"1328e", 18x"13176",
18x"1305e", 18x"12f48", 18x"12e30", 18x"12d1a", 18x"12c06", 18x"12af2", 18x"129de", 18x"128ca",
18x"127b8", 18x"126a6", 18x"12596", 18x"12486", 18x"12376", 18x"12266", 18x"12158", 18x"1204a",
18x"11f3e", 18x"11e32", 18x"11d26", 18x"11c1a", 18x"11b10", 18x"11a06", 18x"118fc", 18x"117f4",
18x"116ec", 18x"115e4", 18x"114de", 18x"113d8", 18x"112d2", 18x"111ce", 18x"110ca", 18x"10fc6",
18x"10ec2", 18x"10dc0", 18x"10cbe", 18x"10bbc", 18x"10abc", 18x"109bc", 18x"108bc", 18x"107be",
18x"106c0", 18x"105c2", 18x"104c4", 18x"103c8", 18x"102cc", 18x"101d0", 18x"100d6", 18x"0ffdc",
18x"0fee2", 18x"0fdea", 18x"0fcf0", 18x"0fbf8", 18x"0fb02", 18x"0fa0a", 18x"0f914", 18x"0f81e",
18x"0f72a", 18x"0f636", 18x"0f542", 18x"0f44e", 18x"0f35a", 18x"0f268", 18x"0f176", 18x"0f086",
18x"0ef94", 18x"0eea4", 18x"0edb4", 18x"0ecc6", 18x"0ebd6", 18x"0eae8", 18x"0e9fa", 18x"0e90e",
18x"0e822", 18x"0e736", 18x"0e64a", 18x"0e55e", 18x"0e474", 18x"0e38a", 18x"0e2a0", 18x"0e1b8",
18x"0e0d0", 18x"0dfe8", 18x"0df00", 18x"0de1a", 18x"0dd32", 18x"0dc4c", 18x"0db68", 18x"0da82",
18x"0d99e", 18x"0d8ba", 18x"0d7d6", 18x"0d6f4", 18x"0d612", 18x"0d530", 18x"0d44e", 18x"0d36c",
18x"0d28c", 18x"0d1ac", 18x"0d0cc", 18x"0cfee", 18x"0cf0e", 18x"0ce30", 18x"0cd54", 18x"0cc76",
18x"0cb9a", 18x"0cabc", 18x"0c9e0", 18x"0c906", 18x"0c82a", 18x"0c750", 18x"0c676", 18x"0c59c",
18x"0c4c4", 18x"0c3ea", 18x"0c312", 18x"0c23a", 18x"0c164", 18x"0c08c", 18x"0bfb6", 18x"0bee0",
18x"0be0a", 18x"0bd36", 18x"0bc62", 18x"0bb8c", 18x"0baba", 18x"0b9e6", 18x"0b912", 18x"0b840",
18x"0b76e", 18x"0b69c", 18x"0b5cc", 18x"0b4fa", 18x"0b42a", 18x"0b35a", 18x"0b28a", 18x"0b1bc",
18x"0b0ee", 18x"0b01e", 18x"0af50", 18x"0ae84", 18x"0adb6", 18x"0acea", 18x"0ac1e", 18x"0ab52",
18x"0aa86", 18x"0a9bc", 18x"0a8f0", 18x"0a826", 18x"0a75c", 18x"0a694", 18x"0a5ca", 18x"0a502",
18x"0a43a", 18x"0a372", 18x"0a2aa", 18x"0a1e4", 18x"0a11c", 18x"0a056", 18x"09f90", 18x"09ecc",
-- 3.0 ... 3.9999
18x"09e06", 18x"09d42", 18x"09c7e", 18x"09bba", 18x"09af6", 18x"09a32", 18x"09970", 18x"098ae",
18x"097ec", 18x"0972a", 18x"09668", 18x"095a8", 18x"094e8", 18x"09426", 18x"09368", 18x"092a8",
18x"091e8", 18x"0912a", 18x"0906c", 18x"08fae", 18x"08ef0", 18x"08e32", 18x"08d76", 18x"08cba",
18x"08bfe", 18x"08b42", 18x"08a86", 18x"089ca", 18x"08910", 18x"08856", 18x"0879c", 18x"086e2",
18x"08628", 18x"08570", 18x"084b6", 18x"083fe", 18x"08346", 18x"0828e", 18x"081d8", 18x"08120",
18x"0806a", 18x"07fb4", 18x"07efe", 18x"07e48", 18x"07d92", 18x"07cde", 18x"07c2a", 18x"07b76",
18x"07ac2", 18x"07a0e", 18x"0795a", 18x"078a8", 18x"077f4", 18x"07742", 18x"07690", 18x"075de",
18x"0752e", 18x"0747c", 18x"073cc", 18x"0731c", 18x"0726c", 18x"071bc", 18x"0710c", 18x"0705e",
18x"06fae", 18x"06f00", 18x"06e52", 18x"06da4", 18x"06cf6", 18x"06c4a", 18x"06b9c", 18x"06af0",
18x"06a44", 18x"06998", 18x"068ec", 18x"06840", 18x"06796", 18x"066ea", 18x"06640", 18x"06596",
18x"064ec", 18x"06442", 18x"0639a", 18x"062f0", 18x"06248", 18x"061a0", 18x"060f8", 18x"06050",
18x"05fa8", 18x"05f00", 18x"05e5a", 18x"05db4", 18x"05d0e", 18x"05c68", 18x"05bc2", 18x"05b1c",
18x"05a76", 18x"059d2", 18x"0592e", 18x"05888", 18x"057e4", 18x"05742", 18x"0569e", 18x"055fa",
18x"05558", 18x"054b6", 18x"05412", 18x"05370", 18x"052ce", 18x"0522e", 18x"0518c", 18x"050ec",
18x"0504a", 18x"04faa", 18x"04f0a", 18x"04e6a", 18x"04dca", 18x"04d2c", 18x"04c8c", 18x"04bee",
18x"04b50", 18x"04ab0", 18x"04a12", 18x"04976", 18x"048d8", 18x"0483a", 18x"0479e", 18x"04700",
18x"04664", 18x"045c8", 18x"0452c", 18x"04490", 18x"043f6", 18x"0435a", 18x"042c0", 18x"04226",
18x"0418a", 18x"040f0", 18x"04056", 18x"03fbe", 18x"03f24", 18x"03e8c", 18x"03df2", 18x"03d5a",
18x"03cc2", 18x"03c2a", 18x"03b92", 18x"03afa", 18x"03a62", 18x"039cc", 18x"03934", 18x"0389e",
18x"03808", 18x"03772", 18x"036dc", 18x"03646", 18x"035b2", 18x"0351c", 18x"03488", 18x"033f2",
18x"0335e", 18x"032ca", 18x"03236", 18x"031a2", 18x"03110", 18x"0307c", 18x"02fea", 18x"02f56",
18x"02ec4", 18x"02e32", 18x"02da0", 18x"02d0e", 18x"02c7c", 18x"02bec", 18x"02b5a", 18x"02aca",
18x"02a38", 18x"029a8", 18x"02918", 18x"02888", 18x"027f8", 18x"0276a", 18x"026da", 18x"0264a",
18x"025bc", 18x"0252e", 18x"024a0", 18x"02410", 18x"02384", 18x"022f6", 18x"02268", 18x"021da",
18x"0214e", 18x"020c0", 18x"02034", 18x"01fa8", 18x"01f1c", 18x"01e90", 18x"01e04", 18x"01d78",
18x"01cee", 18x"01c62", 18x"01bd8", 18x"01b4c", 18x"01ac2", 18x"01a38", 18x"019ae", 18x"01924",
18x"0189c", 18x"01812", 18x"01788", 18x"01700", 18x"01676", 18x"015ee", 18x"01566", 18x"014de",
18x"01456", 18x"013ce", 18x"01346", 18x"012c0", 18x"01238", 18x"011b2", 18x"0112c", 18x"010a4",
18x"0101e", 18x"00f98", 18x"00f12", 18x"00e8c", 18x"00e08", 18x"00d82", 18x"00cfe", 18x"00c78",
18x"00bf4", 18x"00b70", 18x"00aec", 18x"00a68", 18x"009e4", 18x"00960", 18x"008dc", 18x"00858",
18x"007d6", 18x"00752", 18x"006d0", 18x"0064e", 18x"005cc", 18x"0054a", 18x"004c8", 18x"00446",
18x"003c4", 18x"00342", 18x"002c2", 18x"00240", 18x"001c0", 18x"00140", 18x"000c0", 18x"00040"
);
-- Left and right shifter with 120 bit input and 64 bit output.
-- Shifts inp left by shift bits and returns the upper 64 bits of
-- the result. The shift parameter is interpreted as a signed
-- number in the range -64..63, with negative values indicating
-- right shifts.
function shifter_64(inp: std_ulogic_vector(119 downto 0);
shift: std_ulogic_vector(6 downto 0))
return std_ulogic_vector is
variable s1 : std_ulogic_vector(94 downto 0);
variable s2 : std_ulogic_vector(70 downto 0);
variable shift_result : std_ulogic_vector(63 downto 0);
begin
case shift(6 downto 5) is
when "00" =>
s1 := inp(119 downto 25);
when "01" =>
s1 := inp(87 downto 0) & "0000000";
when "10" =>
s1 := x"0000000000000000" & inp(119 downto 89);
when others =>
s1 := x"00000000" & inp(119 downto 57);
end case;
case shift(4 downto 3) is
when "00" =>
s2 := s1(94 downto 24);
when "01" =>
s2 := s1(86 downto 16);
when "10" =>
s2 := s1(78 downto 8);
when others =>
s2 := s1(70 downto 0);
end case;
case shift(2 downto 0) is
when "000" =>
shift_result := s2(70 downto 7);
when "001" =>
shift_result := s2(69 downto 6);
when "010" =>
shift_result := s2(68 downto 5);
when "011" =>
shift_result := s2(67 downto 4);
when "100" =>
shift_result := s2(66 downto 3);
when "101" =>
shift_result := s2(65 downto 2);
when "110" =>
shift_result := s2(64 downto 1);
when others =>
shift_result := s2(63 downto 0);
end case;
return shift_result;
end;
-- Generate a mask with 0-bits on the left and 1-bits on the right which
-- selects the bits will be lost in doing a right shift. The shift
-- parameter is the bottom 6 bits of a negative shift count,
-- indicating a right shift.
function right_mask(shift: unsigned(5 downto 0)) return std_ulogic_vector is
variable mask_result: std_ulogic_vector(63 downto 0);
begin
mask_result := (others => '0');
if is_X(shift) then
mask_result := (others => 'X');
return mask_result;
end if;
for i in 0 to 63 loop
if i >= shift then
mask_result(63 - i) := '1';
end if;
end loop;
return mask_result;
end;
-- Split a DP floating-point number into components and work out its class.
-- If is_int = 1, the input is considered an integer
function decode_dp(fpr: std_ulogic_vector(63 downto 0); is_fp: std_ulogic;
is_32bint: std_ulogic; is_signed: std_ulogic) return fpu_reg_type is
variable reg : fpu_reg_type;
variable exp_nz : std_ulogic;
variable exp_ao : std_ulogic;
variable frac_nz : std_ulogic;
variable low_nz : std_ulogic;
variable cls : std_ulogic_vector(2 downto 0);
begin
reg.negative := fpr(63);
reg.denorm := '0';
exp_nz := or (fpr(62 downto 52));
exp_ao := and (fpr(62 downto 52));
frac_nz := or (fpr(51 downto 0));
low_nz := or (fpr(31 downto 0));
if is_fp = '1' then
reg.denorm := frac_nz and not exp_nz;
reg.exponent := signed(resize(unsigned(fpr(62 downto 52)), EXP_BITS)) - to_signed(1023, EXP_BITS);
if exp_nz = '0' then
reg.exponent := to_signed(-1022, EXP_BITS);
end if;
reg.mantissa := std_ulogic_vector(shift_left(resize(unsigned(exp_nz & fpr(51 downto 0)), 64),
UNIT_BIT - 52));
cls := exp_ao & exp_nz & frac_nz;
case cls is
when "000" => reg.class := ZERO;
when "001" => reg.class := FINITE; -- denormalized
when "010" => reg.class := FINITE;
when "011" => reg.class := FINITE;
when "110" => reg.class := INFINITY;
when others => reg.class := NAN;
end case;
elsif is_32bint = '1' then
reg.negative := fpr(31);
reg.mantissa(31 downto 0) := fpr(31 downto 0);
reg.mantissa(63 downto 32) := (others => (is_signed and fpr(31)));
reg.exponent := (others => '0');
if low_nz = '1' then
reg.class := FINITE;
else
reg.class := ZERO;
end if;
else
reg.mantissa := fpr;
reg.exponent := (others => '0');
if (fpr(63) or exp_nz or frac_nz) = '1' then
reg.class := FINITE;
else
reg.class := ZERO;
end if;
end if;
return reg;
end;
-- Construct a DP floating-point result from components
function pack_dp(negative: std_ulogic; class: fp_number_class; exp: signed(EXP_BITS-1 downto 0);
mantissa: std_ulogic_vector; single_prec: std_ulogic; quieten_nan: std_ulogic)
return std_ulogic_vector is
variable dp_result : std_ulogic_vector(63 downto 0);
begin
dp_result := (others => '0');
case class is
when ZERO =>
when FINITE =>
if mantissa(UNIT_BIT) = '1' then
-- normalized number
dp_result(62 downto 52) := std_ulogic_vector(resize(exp, 11) + 1023);
end if;
dp_result(51 downto 29) := mantissa(UNIT_BIT - 1 downto SP_LSB);
if single_prec = '0' then
dp_result(28 downto 0) := mantissa(SP_LSB - 1 downto DP_LSB);
end if;
when INFINITY =>
dp_result(62 downto 52) := "11111111111";
when NAN =>
dp_result(62 downto 52) := "11111111111";
dp_result(51) := quieten_nan or mantissa(QNAN_BIT);
dp_result(50 downto 29) := mantissa(QNAN_BIT - 1 downto SP_LSB);
if single_prec = '0' then
dp_result(28 downto 0) := mantissa(SP_LSB - 1 downto DP_LSB);
end if;
end case;
dp_result(63) := negative;
return dp_result;
end;
-- Determine whether to increment when rounding
-- Returns rounding_inc & inexact
-- If single_prec = 1, assumes x includes the bottom 31 (== SP_LSB - 2)
-- bits of the mantissa already (usually arranged by setting set_x = 1 earlier).
function fp_rounding(mantissa: std_ulogic_vector(63 downto 0); x: std_ulogic;
single_prec: std_ulogic; rn: std_ulogic_vector(2 downto 0);
sign: std_ulogic)
return std_ulogic_vector is
variable grx : std_ulogic_vector(2 downto 0);
variable ret : std_ulogic_vector(1 downto 0);
variable lsb : std_ulogic;
begin
if single_prec = '0' then
grx := mantissa(DP_GBIT downto DP_RBIT) & (x or (or mantissa(DP_RBIT - 1 downto 0)));
lsb := mantissa(DP_LSB);
else
grx := mantissa(SP_GBIT downto SP_RBIT) & x;
lsb := mantissa(SP_LSB);
end if;
ret(1) := '0';
ret(0) := or (grx);
case rn(1 downto 0) is
when "00" => -- round to nearest
if grx = "100" and rn(2) = '0' then
ret(1) := lsb; -- tie, round to even
else
ret(1) := grx(2);
end if;
when "01" => -- round towards zero
when others => -- round towards +/- inf
if rn(0) = sign then
-- round towards greater magnitude
ret(1) := ret(0);
end if;
end case;
return ret;
end;
-- Determine result flags to write into the FPSCR
function result_flags(sign: std_ulogic; class: fp_number_class; unitbit: std_ulogic)
return std_ulogic_vector is
begin
case class is
when ZERO =>
return sign & "0010";
when FINITE =>
return (not unitbit) & sign & (not sign) & "00";
when INFINITY =>
return '0' & sign & (not sign) & "01";
when NAN =>
return "10001";
end case;
end;
begin
fpu_multiply_0: entity work.multiply
port map (
clk => clk,
m_in => f_to_multiply,
m_out => multiply_to_f
);
fpu_0: process(clk)
begin
if rising_edge(clk) then
if rst = '1' or flush_in = '1' then
r.state <= IDLE;
r.busy <= '0';
r.f2stall <= '0';
r.instr_done <= '0';
r.complete <= '0';
r.illegal <= '0';
r.do_intr <= '0';
r.writing_fpr <= '0';
r.writing_cr <= '0';
r.writing_xer <= '0';
r.fpscr <= (others => '0');
r.write_reg <= (others =>'0');
r.complete_tag.valid <= '0';
r.cr_mask <= (others =>'0');
r.cr_result <= (others =>'0');
r.instr_tag.valid <= '0';
if rst = '1' then
r.fpscr <= (others => '0');
r.comm_fpscr <= (others => '0');
elsif r.do_intr = '0' then
-- flush_in = 1 and not due to us generating an interrupt,
-- roll back to committed fpscr
r.fpscr <= r.comm_fpscr;
end if;
else
assert not (r.state /= IDLE and e_in.valid = '1') severity failure;
r <= rin;
end if;
end if;
end process;
-- synchronous reads from lookup table
lut_access: process(clk)
variable addrhi : std_ulogic_vector(1 downto 0);
variable addr : std_ulogic_vector(9 downto 0);
begin
if rising_edge(clk) then
if r.is_sqrt = '1' then
addrhi := r.b.mantissa(UNIT_BIT + 1 downto UNIT_BIT);
else
addrhi := "00";
end if;
addr := addrhi & r.b.mantissa(UNIT_BIT - 1 downto UNIT_BIT - 8);
if is_X(addr) then
inverse_est <= (others => 'X');
else
inverse_est <= '1' & inverse_table(to_integer(unsigned(addr)));
end if;
end if;
end process;
e_out.busy <= r.busy;
e_out.f2stall <= r.f2stall;
e_out.exception <= r.fpscr(FPSCR_FEX);
-- Note that the cycle where r.complete = 1 for an instruction can be as
-- late as the second cycle of the following instruction (i.e. in the state
-- following IDLE state). Hence it is important that none of the fields of
-- r that are used below are modified in IDLE state.
w_out.valid <= r.complete;
w_out.instr_tag <= r.complete_tag;
w_out.write_enable <= r.writing_fpr and r.complete;
w_out.write_reg <= r.write_reg;
w_out.write_data <= fp_result;
w_out.write_cr_enable <= r.writing_cr and r.complete;
w_out.write_cr_mask <= r.cr_mask;
w_out.write_cr_data <= r.cr_result & r.cr_result & r.cr_result & r.cr_result &
r.cr_result & r.cr_result & r.cr_result & r.cr_result;
w_out.write_xerc <= r.writing_xer and r.complete;
w_out.xerc <= r.xerc_result;
w_out.interrupt <= r.do_intr;
w_out.intr_vec <= 16#700#;
w_out.srr1 <= (47-44 => r.illegal, 47-43 => not r.illegal, others => '0');
fpu_1: process(all)
variable v : reg_type;
variable adec : fpu_reg_type;
variable bdec : fpu_reg_type;
variable cdec : fpu_reg_type;
variable fpscr_mask : std_ulogic_vector(31 downto 0);
variable j, k : integer;
variable flm : std_ulogic_vector(7 downto 0);
variable fpin_a : std_ulogic;
variable fpin_b : std_ulogic;
variable fpin_c : std_ulogic;
variable is_32bint : std_ulogic;
variable mask : std_ulogic_vector(63 downto 0);
variable in_a0 : std_ulogic_vector(63 downto 0);
variable in_b0 : std_ulogic_vector(63 downto 0);
variable misc : std_ulogic_vector(63 downto 0);
variable shift_res : std_ulogic_vector(63 downto 0);
variable round : std_ulogic_vector(1 downto 0);
variable update_fx : std_ulogic;
variable arith_done : std_ulogic;
variable invalid : std_ulogic;
variable zero_divide : std_ulogic;
variable mant_nz : std_ulogic;
variable min_exp : signed(EXP_BITS-1 downto 0);
variable max_exp : signed(EXP_BITS-1 downto 0);
variable bias_exp : signed(EXP_BITS-1 downto 0);
variable new_exp : signed(EXP_BITS-1 downto 0);
variable exp_tiny : std_ulogic;
variable exp_huge : std_ulogic;
variable clz : std_ulogic_vector(5 downto 0);
variable set_x : std_ulogic;
variable mshift : signed(EXP_BITS-1 downto 0);
variable need_check : std_ulogic;
variable msb : std_ulogic;
variable is_add : std_ulogic;
variable set_a : std_ulogic;
variable set_a_exp : std_ulogic;
variable set_a_mant : std_ulogic;
variable set_a_hi : std_ulogic;
variable set_a_lo : std_ulogic;
variable set_b : std_ulogic;
variable set_b_mant : std_ulogic;
variable set_c : std_ulogic;
variable set_y : std_ulogic;
variable set_s : std_ulogic;
variable qnan_result : std_ulogic;
variable px_nz : std_ulogic;
variable pcmpb_eq : std_ulogic;
variable pcmpb_lt : std_ulogic;
variable pcmpc_eq : std_ulogic;
variable pcmpc_lt : std_ulogic;
variable pshift : std_ulogic;
variable renorm_sqrt : std_ulogic;
variable sqrt_exp : signed(EXP_BITS-1 downto 0);
variable shiftin : std_ulogic;
variable shiftin0 : std_ulogic;
variable mulexp : signed(EXP_BITS-1 downto 0);
variable maddend : std_ulogic_vector(127 downto 0);
variable sum : std_ulogic_vector(63 downto 0);
variable round_inc : std_ulogic_vector(63 downto 0);
variable rbit_inc : std_ulogic;
variable mult_mask : std_ulogic;
variable sign_bit : std_ulogic;
variable rnd_b32 : std_ulogic;
variable rexp_in1 : signed(EXP_BITS-1 downto 0);
variable rexp_in2 : signed(EXP_BITS-1 downto 0);
variable rexp_cin : std_ulogic;
variable rexp_sum : signed(EXP_BITS-1 downto 0);
variable rsh_in1 : signed(EXP_BITS-1 downto 0);
variable rsh_in2 : signed(EXP_BITS-1 downto 0);
variable exec_state : state_t;
variable opcbits : std_ulogic_vector(4 downto 0);
variable int_result : std_ulogic;
variable illegal : std_ulogic;
variable rsign : std_ulogic;
begin
v := r;
v.complete := '0';
v.do_intr := '0';
is_32bint := '0';
exec_state := IDLE;
if r.complete = '1' or r.do_intr = '1' then
v.instr_done := '0';
v.writing_fpr := '0';
v.writing_cr := '0';
v.writing_xer := '0';
v.comm_fpscr := r.fpscr;
v.illegal := '0';
end if;
-- capture incoming instruction
if e_in.valid = '1' then
v.insn := e_in.insn;
v.op := e_in.op;
v.instr_tag := e_in.itag;
v.fe_mode := or (e_in.fe_mode);
v.dest_fpr := e_in.frt;
v.single_prec := e_in.single;
v.is_signed := e_in.is_signed;
v.rc := e_in.rc;
v.fp_rc := '0';
v.is_cmp := e_in.out_cr;
v.oe := e_in.oe;
v.m32b := e_in.m32b;
v.xerc := e_in.xerc;
v.longmask := '0';
v.integer_op := '0';
v.divext := '0';
v.divmod := '0';
v.is_sqrt := '0';
v.is_multiply := '0';
fpin_a := '0';
fpin_b := '0';
fpin_c := '0';
v.use_a := e_in.valid_a;
v.use_b := e_in.valid_b;
v.use_c := e_in.valid_c;
v.round_mode := '0' & r.fpscr(FPSCR_RN+1 downto FPSCR_RN);
case e_in.op is
when OP_FP_ARITH =>
fpin_a := e_in.valid_a;
fpin_b := e_in.valid_b;
fpin_c := e_in.valid_c;
v.longmask := e_in.single;
v.fp_rc := e_in.rc;
exec_state := arith_decode(to_integer(unsigned(e_in.insn(5 downto 1))));
if e_in.insn(5 downto 1) = "11001" or e_in.insn(5 downto 3) = "111" then
v.is_multiply := '1';
end if;
if e_in.insn(5 downto 1) = "10110" or e_in.insn(5 downto 1) = "11010" then
v.is_sqrt := '1';
end if;
if e_in.insn(5 downto 1) = "01111" then
v.round_mode := "001";
end if;
when OP_FP_CMP =>
fpin_a := e_in.valid_a;
fpin_b := e_in.valid_b;
exec_state := cmp_decode(to_integer(unsigned(e_in.insn(8 downto 6))));
when OP_FP_MISC =>
v.fp_rc := e_in.rc;
opcbits := e_in.insn(10) & e_in.insn(8) & e_in.insn(4) & e_in.insn(2) & e_in.insn(1);
exec_state := misc_decode(to_integer(unsigned(opcbits)));
when OP_FP_MOVE =>
v.fp_rc := e_in.rc;
fpin_a := e_in.valid_a;
fpin_b := e_in.valid_b;
fpin_c := e_in.valid_c;
if e_in.insn(5) = '0' then
exec_state := DO_FMR;
else
exec_state := DO_FSEL;
end if;
when OP_DIV =>
v.integer_op := '1';
is_32bint := e_in.single;
exec_state := DO_IDIVMOD;
when OP_DIVE =>
v.integer_op := '1';
v.divext := '1';
is_32bint := e_in.single;
exec_state := DO_IDIVMOD;
when OP_MOD =>
v.integer_op := '1';
v.divmod := '1';
is_32bint := e_in.single;
exec_state := DO_IDIVMOD;
when others =>
exec_state := DO_ILLEGAL;
end case;
v.quieten_nan := '1';
v.tiny := '0';
v.denorm := '0';
v.is_subtract := '0';
v.add_bsmall := '0';
v.doing_ftdiv := "00";
v.int_ovf := '0';
v.div_close := '0';
adec := decode_dp(e_in.fra, fpin_a, is_32bint, e_in.is_signed);
bdec := decode_dp(e_in.frb, fpin_b, is_32bint, e_in.is_signed);
cdec := decode_dp(e_in.frc, fpin_c, '0', '0');
v.a := adec;
v.b := bdec;
v.c := cdec;
v.exp_cmp := '0';
if adec.exponent > bdec.exponent then
v.exp_cmp := '1';
end if;
v.madd_cmp := '0';
if (adec.exponent + cdec.exponent + 1) >= bdec.exponent then
v.madd_cmp := '1';
end if;
v.a_hi := 8x"0";
v.a_lo := 56x"0";
end if;
r_hi_nz <= or (r.r(UNIT_BIT + 1 downto SP_LSB));
r_lo_nz <= or (r.r(SP_LSB - 1 downto DP_LSB));
r_gt_1 <= or (r.r(63 downto 1));
s_nz <= or (r.s);
if r.single_prec = '0' then
if r.doing_ftdiv(1) = '0' then
max_exp := to_signed(1023, EXP_BITS);
else
max_exp := to_signed(1020, EXP_BITS);
end if;
if r.doing_ftdiv(0) = '0' then
min_exp := to_signed(-1022, EXP_BITS);
else
min_exp := to_signed(-1021, EXP_BITS);
end if;
bias_exp := to_signed(1536, EXP_BITS);
else
max_exp := to_signed(127, EXP_BITS);
min_exp := to_signed(-126, EXP_BITS);
bias_exp := to_signed(192, EXP_BITS);