File gcc-amdfam10-suse-8.patch of Package gcc41
Index: gcc/config/i386/athlon.md
===================================================================
--- gcc/config/i386/athlon.md.orig
+++ gcc/config/i386/athlon.md
@@ -518,6 +518,23 @@
(and (eq_attr "type" "mmxmov,ssemov")
(eq_attr "memory" "load")))
"athlon-direct,athlon-fploadk8,athlon-fstore")
+;; On AMDFAM10 all double, single and integer packed and scalar SSEx data
+;; loads generated are direct path, latency of 2 and do not use any FP
+;; executions units. No seperate entries for movlpx/movhpx loads, which
+;; are direct path, latency of 4 and use the FADD/FMUL FP execution units,
+;; as they will not be generated.
+(define_insn_reservation "athlon_sseld_amdfam10" 2
+ (and (eq_attr "cpu" "amdfam10")
+ (and (eq_attr "type" "ssemov")
+ (eq_attr "memory" "load")))
+ "athlon-direct,athlon-fploadk8")
+;; On AMDFAM10 MMX data loads generated are direct path, latency of 4
+;; and can use any FP executions units
+(define_insn_reservation "athlon_mmxld_amdfam10" 4
+ (and (eq_attr "cpu" "amdfam10")
+ (and (eq_attr "type" "mmxmov")
+ (eq_attr "memory" "load")))
+ "athlon-direct,athlon-fploadk8, athlon-fany")
(define_insn_reservation "athlon_mmxssest" 3
(and (eq_attr "cpu" "k8,generic64")
(and (eq_attr "type" "mmxmov,ssemov")
@@ -535,6 +552,25 @@
(and (eq_attr "type" "mmxmov,ssemov")
(eq_attr "memory" "store,both")))
"athlon-direct,(athlon-fpsched+athlon-agu),(athlon-fstore+athlon-store)")
+;; On AMDFAM10 all double, single and integer packed SSEx data stores
+;; generated are all double path, latency of 2 and use the FSTORE FP
+;; execution unit. No entries seperate for movupx/movdqu, which are
+;; vector path, latency of 3 and use the FSTORE*2 FP execution unit,
+;; as they will not be generated.
+(define_insn_reservation "athlon_ssest_amdfam10" 2
+ (and (eq_attr "cpu" "amdfam10")
+ (and (eq_attr "type" "ssemov")
+ (and (eq_attr "mode" "V4SF,V2DF,TI")
+ (eq_attr "memory" "store,both"))))
+ "athlon-double,(athlon-fpsched+athlon-agu),((athlon-fstore+athlon-store)*2)")
+;; On AMDFAM10 all double, single and integer scalar SSEx and MMX
+;; data stores generated are all direct path, latency of 2 and use
+;; the FSTORE FP execution unit
+(define_insn_reservation "athlon_mmxssest_short_amdfam10" 2
+ (and (eq_attr "cpu" "amdfam10")
+ (and (eq_attr "type" "mmxmov,ssemov")
+ (eq_attr "memory" "store,both")))
+ "athlon-direct,(athlon-fpsched+athlon-agu),(athlon-fstore+athlon-store)")
(define_insn_reservation "athlon_movaps_k8" 2
(and (eq_attr "cpu" "k8,generic64")
(and (eq_attr "type" "ssemov")