Merge branch 'releases/gcc-12' into devel/omp/gcc-12

Merged up to r12-8794-g85adc2ec2b0736d07c0df35ad9a450f97ff59a7c (29th Sept 2022)

This includes r12-8793-gafea1ae84f0 (cherry-picked from r13-2868-gd3df98807b5)
"OpenACC: Fix reduction tree-sharing issue [PR106982]".  However, due to
omp-low.cc changes, it neither applies cleanly nor it required to make the
testcases pass. This merge adds the testcases - but due to conflicts under a
different filename: gcc/testsuite/c-c++-common/goacc/reduction-7.c added as
...-9.c and ...-8.c added as ...-10.c.

9 files changed, 85 insertions, 25 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index dabbe18..cb12da9 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,27 @@
+2022-09-28  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
+
+	Backported from master:
+	2022-09-23  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
+
+	* config/aarch64/aarch64-cores.def (neoverse-v2): New entry.
+	(demeter): Update tunings to neoversev2.
+	* config/aarch64/aarch64-tune.md: Regenerate.
+	* config/aarch64/aarch64.cc (demeter_addrcost_table): Rename to
+	neoversev2_addrcost_table.
+	(demeter_regmove_cost): Rename to neoversev2_addrcost_table.
+	(demeter_advsimd_vector_cost): Rename to neoversev2_advsimd_vector_cost.
+	(demeter_sve_vector_cost): Rename to neoversev2_sve_vector_cost.
+	(demeter_scalar_issue_info): Rename to neoversev2_scalar_issue_info.
+	(demeter_advsimd_issue_info): Rename to neoversev2_advsimd_issue_info.
+	(demeter_sve_issue_info): Rename to neoversev2_sve_issue_info.
+	(demeter_vec_issue_info): Rename to neoversev2_vec_issue_info.
+	Update references to above.
+	(demeter_vector_cost): Rename to neoversev2_vector_cost.
+	(demeter_tunings): Rename to neoversev2_tunings.
+	(aarch64_vec_op_count::rename_cycles_per_iter): Use
+	neoversev2_sve_issue_info instead of demeter_sve_issue_info.
+	* doc/invoke.texi (AArch64 Options): Document neoverse-v2.
+
 2022-09-21  Richard Sandiford  <richard.sandiford@arm.com>
 
 	Backported from master:
diff --git a/gcc/DATESTAMP b/gcc/DATESTAMP
index 8830fa8..ea4b4d1 100644
--- a/gcc/DATESTAMP
+++ b/gcc/DATESTAMP
@@ -1 +1 @@
-20220928
+20220929
diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def
index 41d9535..0402bfb 100644
--- a/gcc/config/aarch64/aarch64-cores.def
+++ b/gcc/config/aarch64/aarch64-cores.def
@@ -171,6 +171,7 @@ AARCH64_CORE("cortex-x2",  cortexx2, cortexa57, 9A,  AARCH64_FL_FOR_ARCH9 | AARC
 
 AARCH64_CORE("neoverse-n2", neoversen2, cortexa57, 9A, AARCH64_FL_FOR_ARCH9 | AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_SVE2_BITPERM | AARCH64_FL_RNG | AARCH64_FL_MEMTAG | AARCH64_FL_PROFILE, neoversen2, 0x41, 0xd49, -1)
 
-AARCH64_CORE("demeter", demeter, cortexa57, 9A, AARCH64_FL_FOR_ARCH9 | AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_SVE2_BITPERM | AARCH64_FL_RNG | AARCH64_FL_MEMTAG | AARCH64_FL_PROFILE, demeter, 0x41, 0xd4f, -1)
+AARCH64_CORE("demeter", demeter, cortexa57, 9A, AARCH64_FL_FOR_ARCH9 | AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_SVE2_BITPERM | AARCH64_FL_RNG | AARCH64_FL_MEMTAG | AARCH64_FL_PROFILE, neoversev2, 0x41, 0xd4f, -1)
+AARCH64_CORE("neoverse-v2", neoversev2, cortexa57, 9A, AARCH64_FL_FOR_ARCH9 | AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_SVE2_BITPERM | AARCH64_FL_RNG | AARCH64_FL_MEMTAG | AARCH64_FL_PROFILE, neoversev2, 0x41, 0xd4f, -1)
 
 #undef AARCH64_CORE
diff --git a/gcc/config/aarch64/aarch64-tune.md b/gcc/config/aarch64/aarch64-tune.md
index 27da961..84e9bbf 100644
--- a/gcc/config/aarch64/aarch64-tune.md
+++ b/gcc/config/aarch64/aarch64-tune.md
@@ -1,5 +1,5 @@
 ;; -*- buffer-read-only: t -*-
 ;; Generated automatically by gentune.sh from aarch64-cores.def
 (define_attr "tune"
-	"cortexa34,cortexa35,cortexa53,cortexa57,cortexa72,cortexa73,thunderx,thunderxt88p1,thunderxt88,octeontx,octeontxt81,octeontxt83,thunderxt81,thunderxt83,ampere1,emag,xgene1,falkor,qdf24xx,exynosm1,phecda,thunderx2t99p1,vulcan,thunderx2t99,cortexa55,cortexa75,cortexa76,cortexa76ae,cortexa77,cortexa78,cortexa78ae,cortexa78c,cortexa65,cortexa65ae,cortexx1,ares,neoversen1,neoversee1,octeontx2,octeontx2t98,octeontx2t96,octeontx2t93,octeontx2f95,octeontx2f95n,octeontx2f95mm,a64fx,tsv110,thunderx3t110,zeus,neoversev1,neoverse512tvb,saphira,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55,cortexa76cortexa55,cortexr82,cortexa510,cortexa710,cortexx2,neoversen2,demeter"
+	"cortexa34,cortexa35,cortexa53,cortexa57,cortexa72,cortexa73,thunderx,thunderxt88p1,thunderxt88,octeontx,octeontxt81,octeontxt83,thunderxt81,thunderxt83,ampere1,emag,xgene1,falkor,qdf24xx,exynosm1,phecda,thunderx2t99p1,vulcan,thunderx2t99,cortexa55,cortexa75,cortexa76,cortexa76ae,cortexa77,cortexa78,cortexa78ae,cortexa78c,cortexa65,cortexa65ae,cortexx1,ares,neoversen1,neoversee1,octeontx2,octeontx2t98,octeontx2t96,octeontx2t93,octeontx2f95,octeontx2f95n,octeontx2f95mm,a64fx,tsv110,thunderx3t110,zeus,neoversev1,neoverse512tvb,saphira,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55,cortexa76cortexa55,cortexr82,cortexa510,cortexa710,cortexx2,neoversen2,demeter,neoversev2"
 	(const (symbol_ref "((enum attr_tune) aarch64_tune)")))
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index f85bf2f..0946864 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -537,7 +537,7 @@ static const struct cpu_addrcost_table neoversen2_addrcost_table =
   0 /* imm_offset  */
 };
 
-static const struct cpu_addrcost_table demeter_addrcost_table =
+static const struct cpu_addrcost_table neoversev2_addrcost_table =
 {
     {
       1, /* hi  */
@@ -680,7 +680,7 @@ static const struct cpu_regmove_cost neoversev1_regmove_cost =
   2 /* FP2FP  */
 };
 
-static const struct cpu_regmove_cost demeter_regmove_cost =
+static const struct cpu_regmove_cost neoversev2_regmove_cost =
 {
   1, /* GP2GP  */
   /* Spilling to int<->fp instead of memory is recommended so set
@@ -2429,7 +2429,7 @@ static const struct tune_params neoversen2_tunings =
   &generic_prefetch_tune
 };
 
-static const advsimd_vec_cost demeter_advsimd_vector_cost =
+static const advsimd_vec_cost neoversev2_advsimd_vector_cost =
 {
   2, /* int_stmt_cost  */
   2, /* fp_stmt_cost  */
@@ -2460,7 +2460,7 @@ static const advsimd_vec_cost demeter_advsimd_vector_cost =
   1  /* store_cost  */
 };
 
-static const sve_vec_cost demeter_sve_vector_cost =
+static const sve_vec_cost neoversev2_sve_vector_cost =
 {
   {
     2, /* int_stmt_cost  */
@@ -2517,7 +2517,7 @@ static const sve_vec_cost demeter_sve_vector_cost =
   3 /* scatter_store_elt_cost  */
 };
 
-static const aarch64_scalar_vec_issue_info demeter_scalar_issue_info =
+static const aarch64_scalar_vec_issue_info neoversev2_scalar_issue_info =
 {
   3, /* loads_stores_per_cycle  */
   2, /* stores_per_cycle  */
@@ -2526,7 +2526,7 @@ static const aarch64_scalar_vec_issue_info demeter_scalar_issue_info =
   1 /* fp_simd_store_general_ops  */
 };
 
-static const aarch64_advsimd_vec_issue_info demeter_advsimd_issue_info =
+static const aarch64_advsimd_vec_issue_info neoversev2_advsimd_issue_info =
 {
   {
     3, /* loads_stores_per_cycle  */
@@ -2540,7 +2540,7 @@ static const aarch64_advsimd_vec_issue_info demeter_advsimd_issue_info =
   3 /* ld4_st4_general_ops  */
 };
 
-static const aarch64_sve_vec_issue_info demeter_sve_issue_info =
+static const aarch64_sve_vec_issue_info neoversev2_sve_issue_info =
 {
   {
     {
@@ -2562,15 +2562,15 @@ static const aarch64_sve_vec_issue_info demeter_sve_issue_info =
   1 /* gather_scatter_pair_pred_ops  */
 };
 
-static const aarch64_vec_issue_info demeter_vec_issue_info =
+static const aarch64_vec_issue_info neoversev2_vec_issue_info =
 {
-  &demeter_scalar_issue_info,
-  &demeter_advsimd_issue_info,
-  &demeter_sve_issue_info
+  &neoversev2_scalar_issue_info,
+  &neoversev2_advsimd_issue_info,
+  &neoversev2_sve_issue_info
 };
 
 /* Demeter costs for vector insn classes.  */
-static const struct cpu_vector_cost demeter_vector_cost =
+static const struct cpu_vector_cost neoversev2_vector_cost =
 {
   1, /* scalar_int_stmt_cost  */
   2, /* scalar_fp_stmt_cost  */
@@ -2578,17 +2578,17 @@ static const struct cpu_vector_cost demeter_vector_cost =
   1, /* scalar_store_cost  */
   1, /* cond_taken_branch_cost  */
   1, /* cond_not_taken_branch_cost  */
-  &demeter_advsimd_vector_cost, /* advsimd  */
-  &demeter_sve_vector_cost, /* sve  */
-  &demeter_vec_issue_info /* issue_info  */
+  &neoversev2_advsimd_vector_cost, /* advsimd  */
+  &neoversev2_sve_vector_cost, /* sve  */
+  &neoversev2_vec_issue_info /* issue_info  */
 };
 
-static const struct tune_params demeter_tunings =
+static const struct tune_params neoversev2_tunings =
 {
   &cortexa76_extra_costs,
-  &demeter_addrcost_table,
-  &demeter_regmove_cost,
-  &demeter_vector_cost,
+  &neoversev2_addrcost_table,
+  &neoversev2_regmove_cost,
+  &neoversev2_vector_cost,
   &generic_branch_cost,
   &generic_approx_modes,
   SVE_128, /* sve_width  */
@@ -15532,7 +15532,7 @@ aarch64_vec_op_count::rename_cycles_per_iter () const
 {
   if (sve_issue_info () == &neoverse512tvb_sve_issue_info
       || sve_issue_info () == &neoversen2_sve_issue_info
-      || sve_issue_info () == &demeter_sve_issue_info)
+      || sve_issue_info () == &neoversev2_sve_issue_info)
     /* + 1 for an addition.  We've already counted a general op for each
        store, so we don't need to account for stores separately.  The branch
        reads no registers and so does not need to be counted either.
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 281cafc..52ba1c8 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -19260,7 +19260,7 @@ performance of the code.  Permissible values for this option are:
 @samp{cortex-a78}, @samp{cortex-a78ae}, @samp{cortex-a78c},
 @samp{ares}, @samp{exynos-m1}, @samp{emag}, @samp{falkor},
 @samp{neoverse-512tvb}, @samp{neoverse-e1}, @samp{neoverse-n1},
-@samp{neoverse-n2}, @samp{neoverse-v1}, @samp{qdf24xx},
+@samp{neoverse-n2}, @samp{neoverse-v1}, @samp{neoverse-v2}, @samp{qdf24xx},
 @samp{saphira}, @samp{phecda}, @samp{xgene1}, @samp{vulcan},
 @samp{octeontx}, @samp{octeontx81},  @samp{octeontx83},
 @samp{octeontx2}, @samp{octeontx2t98}, @samp{octeontx2t96}
diff --git a/gcc/omp-low.cc b/gcc/omp-low.cc
index 85a462a..d726eea 100644
--- a/gcc/omp-low.cc
+++ b/gcc/omp-low.cc
@@ -8197,7 +8197,8 @@ lower_oacc_reductions (location_t loc, tree clauses, tree level, bool inner,
 	  = build_call_expr_internal_loc (loc, IFN_GOACC_REDUCTION,
 					  TREE_TYPE (var), 6, setup_code,
 					  unshare_expr (ref_to_res),
-					  incoming, level, op, off);
+					  unshare_expr (incoming),
+					  level, op, off);
 	tree init_call
 	  = build_call_expr_internal_loc (loc, IFN_GOACC_REDUCTION,
 					  TREE_TYPE (var), 6, init_code,
diff --git a/gcc/testsuite/c-c++-common/goacc/reduction-10.c b/gcc/testsuite/c-c++-common/goacc/reduction-10.c
new file mode 100644
index 0000000..2c3ed49
--- /dev/null
+++ b/gcc/testsuite/c-c++-common/goacc/reduction-10.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+
+/* PR middle-end/106982 */
+
+void test1(double *c)
+{
+    double reduced[5];
+#pragma acc parallel loop gang private(reduced)
+    for (int x = 0; x < 5; ++x)
+#pragma acc loop worker reduction(*:reduced)
+      for (int y = 0; y < 5; ++y) { }
+}
diff --git a/gcc/testsuite/c-c++-common/goacc/reduction-9.c b/gcc/testsuite/c-c++-common/goacc/reduction-9.c
new file mode 100644
index 0000000..482b0ab
--- /dev/null
+++ b/gcc/testsuite/c-c++-common/goacc/reduction-9.c
@@ -0,0 +1,22 @@
+/* { dg-do compile } */
+
+/* PR middle-end/106982 */
+
+long long n = 100;
+int multiplicitive_n = 128;
+
+void test1(double *rand, double *a, double *b, double *c)
+{
+#pragma acc data copyin(a[0:10*multiplicitive_n], b[0:10*multiplicitive_n]) copyout(c[0:10])
+    {
+#pragma acc parallel loop
+        for (int i = 0; i < 10; ++i)
+        {
+        double temp = 1.0;
+#pragma acc loop vector reduction(*:temp)
+        for (int j = 0; j < multiplicitive_n; ++j)
+          temp *= a[(i * multiplicitive_n) + j] + b[(i * multiplicitive_n) + j];
+        c[i] = temp;
+        }
+    }
+}