AArch64: enable new predicate tuning for Neoverse cores.

This enables the new tuning flag for Neoverse V1, Neoverse V2 and Neoverse N2.
It is kept off for generic codegen.

Note the reason for the +sve even though they are in aarch64-sve.exp is if the
testsuite is ran with a forced SVE off option, e.g. -march=armv8-a+nosve then
the intrinsics end up being disabled because the -march is preferred over the
-mcpu even though the -mcpu comes later.

This prevents the tests from failing in such runs.

gcc/ChangeLog:

	* config/aarch64/tuning_models/neoversen2.h (neoversen2_tunings): Add
	AARCH64_EXTRA_TUNE_AVOID_PRED_RMW.
	* config/aarch64/tuning_models/neoversev1.h (neoversev1_tunings): Add
	AARCH64_EXTRA_TUNE_AVOID_PRED_RMW.
	* config/aarch64/tuning_models/neoversev2.h (neoversev2_tunings): Add
	AARCH64_EXTRA_TUNE_AVOID_PRED_RMW.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/sve/pred_clobber_1.c: New test.
	* gcc.target/aarch64/sve/pred_clobber_2.c: New test.
	* gcc.target/aarch64/sve/pred_clobber_3.c: New test.
	* gcc.target/aarch64/sve/pred_clobber_4.c: New test.

7 files changed, 95 insertions, 3 deletions

diff --git a/gcc/config/aarch64/tuning_models/neoversen2.h b/gcc/config/aarch64/tuning_models/neoversen2.h
index 7e799bbe..be9a48a 100644
--- a/gcc/config/aarch64/tuning_models/neoversen2.h
+++ b/gcc/config/aarch64/tuning_models/neoversen2.h
@@ -236,7 +236,8 @@ static const struct tune_params neoversen2_tunings =
   (AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND
    | AARCH64_EXTRA_TUNE_CSE_SVE_VL_CONSTANTS
    | AARCH64_EXTRA_TUNE_USE_NEW_VECTOR_COSTS
-   | AARCH64_EXTRA_TUNE_MATCHED_VECTOR_THROUGHPUT),	/* tune_flags.  */
+   | AARCH64_EXTRA_TUNE_MATCHED_VECTOR_THROUGHPUT
+   | AARCH64_EXTRA_TUNE_AVOID_PRED_RMW),	/* tune_flags.  */
   &generic_prefetch_tune,
   AARCH64_LDP_STP_POLICY_ALWAYS,   /* ldp_policy_model.  */
   AARCH64_LDP_STP_POLICY_ALWAYS	   /* stp_policy_model.  */
diff --git a/gcc/config/aarch64/tuning_models/neoversev1.h b/gcc/config/aarch64/tuning_models/neoversev1.h
index 9363f2a..0fc41ce 100644
--- a/gcc/config/aarch64/tuning_models/neoversev1.h
+++ b/gcc/config/aarch64/tuning_models/neoversev1.h
@@ -227,7 +227,8 @@ static const struct tune_params neoversev1_tunings =
   (AARCH64_EXTRA_TUNE_CSE_SVE_VL_CONSTANTS
    | AARCH64_EXTRA_TUNE_USE_NEW_VECTOR_COSTS
    | AARCH64_EXTRA_TUNE_MATCHED_VECTOR_THROUGHPUT
-   | AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND),	/* tune_flags.  */
+   | AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND
+   | AARCH64_EXTRA_TUNE_AVOID_PRED_RMW),	/* tune_flags.  */
   &generic_prefetch_tune,
   AARCH64_LDP_STP_POLICY_ALWAYS,   /* ldp_policy_model.  */
   AARCH64_LDP_STP_POLICY_ALWAYS    /* stp_policy_model.  */
diff --git a/gcc/config/aarch64/tuning_models/neoversev2.h b/gcc/config/aarch64/tuning_models/neoversev2.h
index bc01ed7..f76e4ef 100644
--- a/gcc/config/aarch64/tuning_models/neoversev2.h
+++ b/gcc/config/aarch64/tuning_models/neoversev2.h
@@ -236,7 +236,8 @@ static const struct tune_params neoversev2_tunings =
   (AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND
    | AARCH64_EXTRA_TUNE_CSE_SVE_VL_CONSTANTS
    | AARCH64_EXTRA_TUNE_USE_NEW_VECTOR_COSTS
-   | AARCH64_EXTRA_TUNE_MATCHED_VECTOR_THROUGHPUT),	/* tune_flags.  */
+   | AARCH64_EXTRA_TUNE_MATCHED_VECTOR_THROUGHPUT
+   | AARCH64_EXTRA_TUNE_AVOID_PRED_RMW),	/* tune_flags.  */
   &generic_prefetch_tune,
   AARCH64_LDP_STP_POLICY_ALWAYS,   /* ldp_policy_model.  */
   AARCH64_LDP_STP_POLICY_ALWAYS	   /* stp_policy_model.  */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_1.c b/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_1.c
new file mode 100644
index 0000000..25129e8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_1.c
@@ -0,0 +1,22 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mcpu=neoverse-n2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#pragma GCC target "+sve"
+
+#include <arm_sve.h>
+
+extern void use(svbool_t);
+
+/*
+** foo:
+**	...
+**	ptrue	p([1-3]).b, all
+**	cmplo	p0.h, p\1/z, z0.h, z[0-9]+.h
+**	...
+*/
+void foo (svuint16_t a, uint16_t b)
+{
+    svbool_t p0 = svcmplt_n_u16 (svptrue_b16 (), a, b);
+    use (p0);
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_2.c b/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_2.c
new file mode 100644
index 0000000..58badb6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_2.c
@@ -0,0 +1,22 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mcpu=neoverse-v2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#pragma GCC target "+sve"
+
+#include <arm_sve.h>
+
+extern void use(svbool_t);
+
+/*
+** foo:
+**	...
+**	ptrue	p([1-9][0-9]?).b, all
+**	cmplo	p0.h, p\1/z, z0.h, z[0-9]+.h
+**	...
+*/
+void foo (svuint16_t a, uint16_t b)
+{
+    svbool_t p0 = svcmplt_n_u16 (svptrue_b16 (), a, b);
+    use (p0);
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_3.c b/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_3.c
new file mode 100644
index 0000000..c67c2bd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_3.c
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mcpu=neoverse-v1" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#pragma GCC target "+sve"
+
+#include <arm_sve.h>
+
+extern void use(svbool_t);
+
+/*
+** foo:
+**	...
+**	ptrue	p([1-9][0-9]?).b, all
+**	cmplo	p0.h, p\1/z, z0.h, z[0-9]+.h
+**	...
+*/
+void foo (svuint16_t a, uint16_t b)
+{
+    svbool_t p0 = svcmplt_n_u16 (svptrue_b16 (), a, b);
+    use (p0);
+}
+
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_4.c b/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_4.c
new file mode 100644
index 0000000..c0120af
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/pred_clobber_4.c
@@ -0,0 +1,22 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#pragma GCC target "+sve"
+
+#include <arm_sve.h>
+
+extern void use(svbool_t);
+
+/*
+** foo:
+**	...
+**	ptrue	p0.b, all
+**	cmplo	p0.h, p0/z, z0.h, z[0-9]+.h
+**	...
+*/
+void foo (svuint16_t a, uint16_t b)
+{
+    svbool_t p0 = svcmplt_n_u16 (svptrue_b16 (), a, b);
+    use (p0);
+}