test/rs6000: Add cases to cover vector multiply

This patch is to add test cases to check if vectorizer
can exploit vector multiply instrutions on Power, some
of them are supported since Power8, the others are newly
introduced by Power10.

gcc/testsuite/ChangeLog:

	* gcc.target/powerpc/mul-vectorize-1.c: New test.
	* gcc.target/powerpc/mul-vectorize-2.c: New test.

diff --git a/gcc/testsuite/gcc.target/powerpc/mul-vectorize-1.c b/gcc/testsuite/gcc.target/powerpc/mul-vectorize-1.c
new file mode 100644 (file)
index 0000000..ba01d5c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/mul-vectorize-1.c
@@ -0,0 +1,27 @@
+/* { dg-require-effective-target powerpc_p8vector_ok } */
+/* { dg-options "-mdejagnu-cpu=power8 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fdump-tree-vect-details" } */
+
+/* Test vectorizer can exploit ISA 2.07 instruction vmuluwm (Vector Multiply
+   Unsigned Word Modulo) for both signed and unsigned word multiplication.  */
+
+#define N 128
+
+extern signed int si_a[N], si_b[N], si_c[N];
+extern unsigned int ui_a[N], ui_b[N], ui_c[N];
+
+__attribute__ ((noipa)) void
+test_si ()
+{
+  for (int i = 0; i < N; i++)
+    si_c[i] = si_a[i] * si_b[i];
+}
+
+__attribute__ ((noipa)) void
+test_ui ()
+{
+  for (int i = 0; i < N; i++)
+    ui_c[i] = ui_a[i] * ui_b[i];
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" } } */
+/* { dg-final { scan-assembler-times {\mvmuluwm\M} 2 } } */

diff --git a/gcc/testsuite/gcc.target/powerpc/mul-vectorize-2.c b/gcc/testsuite/gcc.target/powerpc/mul-vectorize-2.c
new file mode 100644 (file)
index 0000000..12ca97a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/mul-vectorize-2.c
@@ -0,0 +1,27 @@
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2 -ftree-vectorize -fno-vect-cost-model -fno-unroll-loops -fdump-tree-vect-details" } */
+
+/* Test vectorizer can exploit ISA 3.1 instruction vmulld (Vector Multiply
+   Low Doubleword) for both signed and unsigned doubleword multiplication.  */
+
+#define N 128
+
+extern signed long long sd_a[N], sd_b[N], sd_c[N];
+extern unsigned long long ud_a[N], ud_b[N], ud_c[N];
+
+__attribute__ ((noipa)) void
+test_sd ()
+{
+  for (int i = 0; i < N; i++)
+    sd_c[i] = sd_a[i] * sd_b[i];
+}
+
+__attribute__ ((noipa)) void
+test_ud ()
+{
+  for (int i = 0; i < N; i++)
+    ud_c[i] = ud_a[i] * ud_b[i];
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" } } */
+/* { dg-final { scan-assembler-times {\mvmulld\M} 2 } } */