From: vekumar Date: Wed, 10 Oct 2012 09:19:11 +0000 (+0000) Subject: Fix for PR51109 X-Git-Tag: upstream/4.9.2~10051 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=51179f0a04b382fb3ad875b08f48d699b1d0efc6;p=platform%2Fupstream%2Flinaro-gcc.git Fix for PR51109 git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@192296 138bc75d-0d04-0410-961f-82ee72b054a4 --- diff --git a/gcc/ChangeLog b/gcc/ChangeLog index c21398d..9840736 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,9 @@ +2012-10-10 Ganesh Gopalasubramanian + + PR target/51109 + * gcc/config/i386/bdver1.md (bdver1_int): Automaton has been + split to reduce state transitions. + 2012-10-10 Richard Biener PR middle-end/54876 diff --git a/gcc/config/i386/bdver1.md b/gcc/config/i386/bdver1.md index 2367785..1680e2e 100644 --- a/gcc/config/i386/bdver1.md +++ b/gcc/config/i386/bdver1.md @@ -36,7 +36,7 @@ (define_attr "bdver1_decode" "direct,vector,double" (const_string "direct")) -(define_automaton "bdver1,bdver1_int,bdver1_load,bdver1_mult,bdver1_fp") +(define_automaton "bdver1,bdver1_ieu,bdver1_load,bdver1_fp,bdver1_agu") (define_cpu_unit "bdver1-decode0" "bdver1") (define_cpu_unit "bdver1-decode1" "bdver1") @@ -71,12 +71,12 @@ | (nothing,(bdver1-decode1 + bdver1-decode2)))") -(define_cpu_unit "bdver1-ieu0" "bdver1_int") -(define_cpu_unit "bdver1-ieu1" "bdver1_int") +(define_cpu_unit "bdver1-ieu0" "bdver1_ieu") +(define_cpu_unit "bdver1-ieu1" "bdver1_ieu") (define_reservation "bdver1-ieu" "(bdver1-ieu0 | bdver1-ieu1)") -(define_cpu_unit "bdver1-agu0" "bdver1_int") -(define_cpu_unit "bdver1-agu1" "bdver1_int") +(define_cpu_unit "bdver1-agu0" "bdver1_agu") +(define_cpu_unit "bdver1-agu1" "bdver1_agu") (define_reservation "bdver1-agu" "(bdver1-agu0 | bdver1-agu1)") (define_cpu_unit "bdver1-mult" "bdver1_mult") @@ -93,6 +93,12 @@ ;; 128bit SSE instructions issue two stores at once. (define_reservation "bdver1-store2" "(bdver1-load0 + bdver1-load1)") +;; vectorpath (microcoded) instructions are single issue instructions. +;; So, they occupy all the integer units. +(define_reservation "bdver1-ivector" "bdver1-ieu0+bdver1-ieu1+ + bdver1-agu0+bdver1-agu1+ + bdver1-load0+bdver1-load1") + ;; The FP operations start to execute at stage 12 in the pipeline, while ;; integer operations start to execute at stage 9 for athlon and 11 for K8 ;; Compensate the difference for athlon because it results in significantly @@ -125,7 +131,7 @@ (define_insn_reservation "bdver1_call" 0 (and (eq_attr "cpu" "bdver1,bdver2") (eq_attr "type" "call,callv")) - "bdver1-double,bdver1-agu,bdver1-ieu") + "bdver1-double,bdver1-agu") ;; PUSH mem is double path. (define_insn_reservation "bdver1_push" 1 (and (eq_attr "cpu" "bdver1,bdver2") @@ -135,17 +141,17 @@ (define_insn_reservation "bdver1_pop" 1 (and (eq_attr "cpu" "bdver1,bdver2") (eq_attr "type" "pop")) - "bdver1-direct,(bdver1-ieu+bdver1-load)") + "bdver1-direct,bdver1-ivector") ;; LEAVE no latency info so far, assume same with amdfam10. (define_insn_reservation "bdver1_leave" 3 (and (eq_attr "cpu" "bdver1,bdver2") (eq_attr "type" "leave")) - "bdver1-vector,(bdver1-ieu+bdver1-load)") + "bdver1-vector,bdver1-ivector") ;; LEA executes in AGU unit with 1 cycle latency on BDVER1. (define_insn_reservation "bdver1_lea" 1 (and (eq_attr "cpu" "bdver1,bdver2") (eq_attr "type" "lea")) - "bdver1-direct,bdver1-agu,nothing") + "bdver1-direct,bdver1-agu") ;; MUL executes in special multiplier unit attached to IEU1. (define_insn_reservation "bdver1_imul_DI" 6 @@ -153,23 +159,23 @@ (and (eq_attr "type" "imul") (and (eq_attr "mode" "DI") (eq_attr "memory" "none,unknown")))) - "bdver1-direct1,bdver1-ieu1,bdver1-mult,nothing,bdver1-ieu1") + "bdver1-direct1,bdver1-ieu1") (define_insn_reservation "bdver1_imul" 4 (and (eq_attr "cpu" "bdver1,bdver2") (and (eq_attr "type" "imul") (eq_attr "memory" "none,unknown"))) - "bdver1-direct1,bdver1-ieu1,bdver1-mult,bdver1-ieu1") + "bdver1-direct1,bdver1-ieu1") (define_insn_reservation "bdver1_imul_mem_DI" 10 (and (eq_attr "cpu" "bdver1,bdver2") (and (eq_attr "type" "imul") (and (eq_attr "mode" "DI") (eq_attr "memory" "load,both")))) - "bdver1-direct1,bdver1-load,bdver1-ieu,bdver1-mult,nothing,bdver1-ieu") + "bdver1-direct1,bdver1-load,bdver1-ieu1") (define_insn_reservation "bdver1_imul_mem" 8 (and (eq_attr "cpu" "bdver1,bdver2") (and (eq_attr "type" "imul") (eq_attr "memory" "load,both"))) - "bdver1-direct1,bdver1-load,bdver1-ieu,bdver1-mult,bdver1-ieu") + "bdver1-direct1,bdver1-load,bdver1-ieu1") ;; IDIV cannot execute in parallel with other instructions. Dealing with it ;; as with short latency vector instruction is good approximation avoiding