File gcc-amdfam10-suse-9.patch of Package gcc41
Index: gcc/config/i386/athlon.md
===================================================================
--- gcc/config/i386/athlon.md.orig
+++ gcc/config/i386/athlon.md
@@ -133,18 +133,22 @@
;; Jump instructions are executed in the branch unit completely transparent to us
(define_insn_reservation "athlon_branch" 0
- (and (eq_attr "cpu" "athlon,k8,generic64")
+ (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10")
(eq_attr "type" "ibr"))
"athlon-direct,athlon-ieu")
(define_insn_reservation "athlon_call" 0
(and (eq_attr "cpu" "athlon,k8,generic64")
(eq_attr "type" "call,callv"))
"athlon-vector,athlon-ieu")
+(define_insn_reservation "athlon_call_amdfam10" 0
+ (and (eq_attr "cpu" "amdfam10")
+ (eq_attr "type" "call,callv"))
+ "athlon-double,athlon-ieu")
;; Latency of push operation is 3 cycles, but ESP value is available
;; earlier
(define_insn_reservation "athlon_push" 2
- (and (eq_attr "cpu" "athlon,k8,generic64")
+ (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10")
(eq_attr "type" "push"))
"athlon-direct,athlon-agu,athlon-store")
(define_insn_reservation "athlon_pop" 4
@@ -155,12 +159,16 @@
(and (eq_attr "cpu" "k8,generic64")
(eq_attr "type" "pop"))
"athlon-double,(athlon-ieu+athlon-load)")
+(define_insn_reservation "athlon_pop_amdfam10" 3
+ (and (eq_attr "cpu" "amdfam10")
+ (eq_attr "type" "pop"))
+ "athlon-direct,(athlon-ieu+athlon-load)")
(define_insn_reservation "athlon_leave" 3
(and (eq_attr "cpu" "athlon")
(eq_attr "type" "leave"))
"athlon-vector,(athlon-ieu+athlon-load)")
(define_insn_reservation "athlon_leave_k8" 3
- (and (eq_attr "cpu" "k8,generic64")
+ (and (eq_attr "cpu" "k8,generic64,amdfam10")
(eq_attr "type" "leave"))
"athlon-double,(athlon-ieu+athlon-load)")
@@ -169,6 +177,11 @@
(and (eq_attr "cpu" "athlon,k8,generic64")
(eq_attr "type" "lea"))
"athlon-direct,athlon-agu,nothing")
+;; Lea executes in AGU unit with 1 cycle latency on AMDFAM10
+(define_insn_reservation "athlon_lea_amdfam10" 1
+ (and (eq_attr "cpu" "amdfam10")
+ (eq_attr "type" "lea"))
+ "athlon-direct,athlon-agu,nothing")
;; Mul executes in special multiplier unit attached to IEU0
(define_insn_reservation "athlon_imul" 5
@@ -178,29 +191,35 @@
"athlon-vector,athlon-ieu0,athlon-mult,nothing,nothing,athlon-ieu0")
;; ??? Widening multiply is vector or double.
(define_insn_reservation "athlon_imul_k8_DI" 4
- (and (eq_attr "cpu" "k8,generic64")
+ (and (eq_attr "cpu" "k8,generic64,amdfam10")
(and (eq_attr "type" "imul")
(and (eq_attr "mode" "DI")
(eq_attr "memory" "none,unknown"))))
"athlon-direct0,athlon-ieu0,athlon-mult,nothing,athlon-ieu0")
(define_insn_reservation "athlon_imul_k8" 3
- (and (eq_attr "cpu" "k8,generic64")
+ (and (eq_attr "cpu" "k8,generic64,amdfam10")
(and (eq_attr "type" "imul")
(eq_attr "memory" "none,unknown")))
"athlon-direct0,athlon-ieu0,athlon-mult,athlon-ieu0")
+(define_insn_reservation "athlon_imul_amdfam10_HI" 4
+ (and (eq_attr "cpu" "amdfam10")
+ (and (eq_attr "type" "imul")
+ (and (eq_attr "mode" "HI")
+ (eq_attr "memory" "none,unknown"))))
+ "athlon-vector,athlon-ieu0,athlon-mult,nothing,athlon-ieu0")
(define_insn_reservation "athlon_imul_mem" 8
(and (eq_attr "cpu" "athlon")
(and (eq_attr "type" "imul")
(eq_attr "memory" "load,both")))
"athlon-vector,athlon-load,athlon-ieu,athlon-mult,nothing,nothing,athlon-ieu")
(define_insn_reservation "athlon_imul_mem_k8_DI" 7
- (and (eq_attr "cpu" "k8,generic64")
+ (and (eq_attr "cpu" "k8,generic64,amdfam10")
(and (eq_attr "type" "imul")
(and (eq_attr "mode" "DI")
(eq_attr "memory" "load,both"))))
"athlon-vector,athlon-load,athlon-ieu,athlon-mult,nothing,athlon-ieu")
(define_insn_reservation "athlon_imul_mem_k8" 6
- (and (eq_attr "cpu" "k8,generic64")
+ (and (eq_attr "cpu" "k8,generic64,amdfam10")
(and (eq_attr "type" "imul")
(eq_attr "memory" "load,both")))
"athlon-vector,athlon-load,athlon-ieu,athlon-mult,athlon-ieu")
@@ -211,21 +230,23 @@
;; other instructions.
;; ??? Experiments show that the idiv can overlap with roughly 6 cycles
;; of the other code
+;; Using the same heuristics for amdfam10 as K8 with idiv
(define_insn_reservation "athlon_idiv" 6
- (and (eq_attr "cpu" "athlon,k8,generic64")
+ (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10")
(and (eq_attr "type" "idiv")
(eq_attr "memory" "none,unknown")))
"athlon-vector,(athlon-ieu0*6+(athlon-fpsched,athlon-fvector))")
(define_insn_reservation "athlon_idiv_mem" 9
- (and (eq_attr "cpu" "athlon,k8,generic64")
+ (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10")
(and (eq_attr "type" "idiv")
(eq_attr "memory" "load,both")))
"athlon-vector,((athlon-load,athlon-ieu0*6)+(athlon-fpsched,athlon-fvector))")
;; The parallelism of string instructions is not documented. Model it same way
;; as idiv to create smaller automata. This probably does not matter much.
+;; Using the same heuristics for amdfam10 as K8 with idiv
(define_insn_reservation "athlon_str" 6
- (and (eq_attr "cpu" "athlon,k8,generic64")
+ (and (eq_attr "cpu" "athlon,k8,generic64,amdfam10")
(and (eq_attr "type" "str")
(eq_attr "memory" "load,both,store")))
"athlon-vector,athlon-load,athlon-ieu0*6")