diff options
| author | Yvan Roux <yvan.roux@linaro.org> | 2016-09-04 14:30:49 +0200 |
|---|---|---|
| committer | Yvan Roux <yvan.roux@linaro.org> | 2016-09-07 22:08:41 +0200 |
| commit | 3d5553db199eba2a88dc3923cbe953b0895d643e (patch) | |
| tree | 11e4556e8292c5a3845f343792d34ae1dd289d1a | |
| parent | b52a5acf8da6ba25c9b0eef20c9fe6b59dd68128 (diff) | |
gcc/
Backport from trunk r239772.
2016-08-26 Kyrylo Tkachov <kyrylo.tkachov@arm.com>
PR target/70473
* config/arm/cortex-a8-neon.md (cortex_a8_vfp_muld): Reduce
reservation duration to 15 cycles.
(cortex_a8_vfp_macs): Likewise.
(cortex_a8_vfp_macd): Likewise.
(cortex_a8_vfp_divs): Likewise.
(cortex_a8_vfp_divd): Likewise.
Change-Id: I5af61ce70108b3bff57dba89c8cdd07ab628792d
| -rw-r--r-- | gcc/config/arm/cortex-a8-neon.md | 14 |
1 files changed, 9 insertions, 5 deletions
diff --git a/gcc/config/arm/cortex-a8-neon.md b/gcc/config/arm/cortex-a8-neon.md index 45f861f6c6f..b16c29974a7 100644 --- a/gcc/config/arm/cortex-a8-neon.md +++ b/gcc/config/arm/cortex-a8-neon.md @@ -357,30 +357,34 @@ (eq_attr "type" "fmuls")) "cortex_a8_vfp,cortex_a8_vfplite*11") +;; Don't model a reservation for more than 15 cycles as this explodes the +;; state space of the automaton for little gain. It is unlikely that the +;; scheduler will find enough instructions to hide the full latency of the +;; instructions. (define_insn_reservation "cortex_a8_vfp_muld" 17 (and (eq_attr "tune" "cortexa8") (eq_attr "type" "fmuld")) - "cortex_a8_vfp,cortex_a8_vfplite*16") + "cortex_a8_vfp,cortex_a8_vfplite*15") (define_insn_reservation "cortex_a8_vfp_macs" 21 (and (eq_attr "tune" "cortexa8") (eq_attr "type" "fmacs,ffmas")) - "cortex_a8_vfp,cortex_a8_vfplite*20") + "cortex_a8_vfp,cortex_a8_vfplite*15") (define_insn_reservation "cortex_a8_vfp_macd" 26 (and (eq_attr "tune" "cortexa8") (eq_attr "type" "fmacd,ffmad")) - "cortex_a8_vfp,cortex_a8_vfplite*25") + "cortex_a8_vfp,cortex_a8_vfplite*15") (define_insn_reservation "cortex_a8_vfp_divs" 37 (and (eq_attr "tune" "cortexa8") (eq_attr "type" "fdivs, fsqrts")) - "cortex_a8_vfp,cortex_a8_vfplite*36") + "cortex_a8_vfp,cortex_a8_vfplite*15") (define_insn_reservation "cortex_a8_vfp_divd" 65 (and (eq_attr "tune" "cortexa8") (eq_attr "type" "fdivd, fsqrtd")) - "cortex_a8_vfp,cortex_a8_vfplite*64") + "cortex_a8_vfp,cortex_a8_vfplite*15") ;; Comparisons can actually take 7 cycles sometimes instead of four, ;; but given all the other instructions lumped into type=ffarith that |