[PATCH 2/3] AArch64: Add FULLY_PIPELINED_FMA to tune baseline

[Wilco Dijkstra]

Add FULLY_PIPELINED_FMA to tune baseline - this is a generic feature that is
already enabled for some cores, but benchmarking it shows it is faster on all
modern cores (SPECFP improves ~0.17% on Neoverse V1 and 0.04% on Neoverse N1).

Passes regress & bootstrap, OK for commit?

gcc/ChangeLog:

        * config/aarch64/aarch64-tuning-flags.def (AARCH64_EXTRA_TUNE_BASE): 
Add AARCH64_EXTRA_TUNE_FULLY_PIPELINED_FMA.        
        * config/aarch64/tuning_models/ampere1b.h: Remove redundant 
AARCH64_EXTRA_TUNE_FULLY_PIPELINED_FMA.
        * config/aarch64/tuning_models/neoversev2.h: Likewise.

---

diff --git a/gcc/config/aarch64/aarch64-tuning-flags.def 
b/gcc/config/aarch64/aarch64-tuning-flags.def
index 
ffbff20e29c78c00fc211adbba962c20827370aa..1d8abee1e263706e3930e4d39c59faefef8cfe41
 100644
--- a/gcc/config/aarch64/aarch64-tuning-flags.def
+++ b/gcc/config/aarch64/aarch64-tuning-flags.def
@@ -51,6 +51,7 @@ AARCH64_EXTRA_TUNING_OPTION ("fully_pipelined_fma", 
FULLY_PIPELINED_FMA)
 AARCH64_EXTRA_TUNING_OPTION ("avoid_pred_rmw", AVOID_PRED_RMW)
 
 /* Baseline tuning settings suitable for all modern cores.  */
-#define AARCH64_EXTRA_TUNE_BASE (AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND)
+#define AARCH64_EXTRA_TUNE_BASE (AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND \
+                                | AARCH64_EXTRA_TUNE_FULLY_PIPELINED_FMA)
 
 #undef AARCH64_EXTRA_TUNING_OPTION
diff --git a/gcc/config/aarch64/tuning_models/ampere1b.h 
b/gcc/config/aarch64/tuning_models/ampere1b.h
index 
936fe7ad390edbf70f670d50843bc5caa4fa55e5..340f7b0b47943a43ac57342a464c9267d9912f28
 100644
--- a/gcc/config/aarch64/tuning_models/ampere1b.h
+++ b/gcc/config/aarch64/tuning_models/ampere1b.h
@@ -103,8 +103,7 @@ static const struct tune_params ampere1b_tunings =
   0,   /* max_case_values.  */
   tune_params::AUTOPREFETCHER_STRONG,  /* autoprefetcher_model.  */
   (AARCH64_EXTRA_TUNE_BASE
-   | AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA
-   | AARCH64_EXTRA_TUNE_FULLY_PIPELINED_FMA), /* tune_flags.  */
+   | AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA), /* tune_flags.  */
   &ampere1b_prefetch_tune,
   AARCH64_LDP_STP_POLICY_ALIGNED,   /* ldp_policy_model.  */
   AARCH64_LDP_STP_POLICY_ALIGNED    /* stp_policy_model.  */
diff --git a/gcc/config/aarch64/tuning_models/neoversev2.h 
b/gcc/config/aarch64/tuning_models/neoversev2.h
index 
40af5f47f4f62757e8e374abbb29cec5d1a8f7f3..43baeafd646bafadb739376160eaaf268d0542a8
 100644
--- a/gcc/config/aarch64/tuning_models/neoversev2.h
+++ b/gcc/config/aarch64/tuning_models/neoversev2.h
@@ -234,8 +234,7 @@ static const struct tune_params neoversev2_tunings =
    | AARCH64_EXTRA_TUNE_CSE_SVE_VL_CONSTANTS
    | AARCH64_EXTRA_TUNE_USE_NEW_VECTOR_COSTS
    | AARCH64_EXTRA_TUNE_MATCHED_VECTOR_THROUGHPUT
-   | AARCH64_EXTRA_TUNE_AVOID_PRED_RMW
-   | AARCH64_EXTRA_TUNE_FULLY_PIPELINED_FMA),  /* tune_flags.  */
+   | AARCH64_EXTRA_TUNE_AVOID_PRED_RMW),       /* tune_flags.  */
   &neoversev2_prefetch_tune,
   AARCH64_LDP_STP_POLICY_ALWAYS,   /* ldp_policy_model.  */
   AARCH64_LDP_STP_POLICY_ALWAYS           /* stp_policy_model.  */