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
|
2011-09-05 Ramana Radhakrishnan <ramana.radhakrishnan@linaro.org>
Backport from mainline.
2011-08-26 Ramana Radhakrishnan <ramana.radhakrishnan@arm.com>
* config/arm/cortex-a9.md ("cortex_a9_mult_long"): New.
("cortex_a9_multiply_long"): New and use above. Handle all
long multiply cases.
("cortex_a9_multiply"): Handle smmul and smmulr.
("cortex_a9_mac"): Handle smmla.
=== modified file 'gcc/config/arm/cortex-a9.md'
--- old/gcc/config/arm/cortex-a9.md 2011-01-18 15:28:08 +0000
+++ new/gcc/config/arm/cortex-a9.md 2011-08-26 08:52:15 +0000
@@ -68,7 +68,8 @@
"cortex_a9_mac_m1*2, cortex_a9_mac_m2, cortex_a9_p0_wb")
(define_reservation "cortex_a9_mac"
"cortex_a9_multcycle1*2 ,cortex_a9_mac_m2, cortex_a9_p0_wb")
-
+(define_reservation "cortex_a9_mult_long"
+ "cortex_a9_mac_m1*3, cortex_a9_mac_m2, cortex_a9_p0_wb")
;; Issue at the same time along the load store pipeline and
;; the VFP / Neon pipeline is not possible.
@@ -139,29 +140,35 @@
(eq_attr "insn" "smlaxy"))
"cortex_a9_mac16")
-
(define_insn_reservation "cortex_a9_multiply" 4
(and (eq_attr "tune" "cortexa9")
- (eq_attr "insn" "mul"))
+ (eq_attr "insn" "mul,smmul,smmulr"))
"cortex_a9_mult")
(define_insn_reservation "cortex_a9_mac" 4
(and (eq_attr "tune" "cortexa9")
- (eq_attr "insn" "mla"))
+ (eq_attr "insn" "mla,smmla"))
"cortex_a9_mac")
+(define_insn_reservation "cortex_a9_multiply_long" 5
+ (and (eq_attr "tune" "cortexa9")
+ (eq_attr "insn" "smull,umull,smulls,umulls,smlal,smlals,umlal,umlals"))
+ "cortex_a9_mult_long")
+
;; An instruction with a result in E2 can be forwarded
;; to E2 or E1 or M1 or the load store unit in the next cycle.
(define_bypass 1 "cortex_a9_dp"
"cortex_a9_dp_shift, cortex_a9_multiply,
cortex_a9_load1_2, cortex_a9_dp, cortex_a9_store1_2,
- cortex_a9_mult16, cortex_a9_mac16, cortex_a9_mac, cortex_a9_store3_4, cortex_a9_load3_4")
+ cortex_a9_mult16, cortex_a9_mac16, cortex_a9_mac, cortex_a9_store3_4, cortex_a9_load3_4,
+ cortex_a9_multiply_long")
(define_bypass 2 "cortex_a9_dp_shift"
"cortex_a9_dp_shift, cortex_a9_multiply,
cortex_a9_load1_2, cortex_a9_dp, cortex_a9_store1_2,
- cortex_a9_mult16, cortex_a9_mac16, cortex_a9_mac, cortex_a9_store3_4, cortex_a9_load3_4")
+ cortex_a9_mult16, cortex_a9_mac16, cortex_a9_mac, cortex_a9_store3_4, cortex_a9_load3_4,
+ cortex_a9_multiply_long")
;; An instruction in the load store pipeline can provide
;; read access to a DP instruction in the P0 default pipeline
@@ -212,7 +219,7 @@
(define_bypass 1
"cortex_a9_fps"
- "cortex_a9_fadd, cortex_a9_fps, cortex_a9_fcmp, cortex_a9_dp, cortex_a9_dp_shift, cortex_a9_multiply")
+ "cortex_a9_fadd, cortex_a9_fps, cortex_a9_fcmp, cortex_a9_dp, cortex_a9_dp_shift, cortex_a9_multiply, cortex_a9_multiply_long")
;; Scheduling on the FP_ADD pipeline.
(define_reservation "ca9fp_add" "ca9_issue_vfp_neon + ca9fp_add1, ca9fp_add2, ca9fp_add3, ca9fp_add4")
|
