rs6000: support vector int type rotatert

gcc/ChangeLog

2019-08-07  Kewen Lin  <linkw@gcc.gnu.org>

    * config/rs6000/vector.md (vrotr<mode>3): New define_expand.

gcc/testsuite/ChangeLog

2019-08-07  Kewen Lin  <linkw@gcc.gnu.org>

    * gcc.target/powerpc/vec_rotate-1.c: New test.
    * gcc.target/powerpc/vec_rotate-2.c: New test.
    * gcc.target/powerpc/vec_rotate-3.c: New test.
    * gcc.target/powerpc/vec_rotate-4.c: New test.

From-SVN: r274158

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 0fc0a21..b85a1db 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,7 @@
+2019-08-07  Kewen Lin  <linkw@gcc.gnu.org>
+
+       * config/rs6000/vector.md (vrotr<mode>3): New define_expand.
+
 2019-08-07  Kito Cheng  <kito.cheng@sifive.com>
 
        * gcc/config/riscv/multilib-generator: (canonical_order): Add 'g'.

diff --git a/gcc/config/rs6000/vector.md b/gcc/config/rs6000/vector.md
index 70bcfe0..886cbad 100644 (file)
--- a/gcc/config/rs6000/vector.md
+++ b/gcc/config/rs6000/vector.md
@@ -1260,6 +1260,19 @@
   "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
   "")
 
+;; Expanders for rotatert to make use of vrotl
+(define_expand "vrotr<mode>3"
+  [(set (match_operand:VEC_I 0 "vint_operand")
+       (rotatert:VEC_I (match_operand:VEC_I 1 "vint_operand")
+               (match_operand:VEC_I 2 "vint_operand")))]
+  "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+  rtx rot_count = gen_reg_rtx (<MODE>mode);
+  emit_insn (gen_neg<mode>2 (rot_count, operands[2]));
+  emit_insn (gen_vrotl<mode>3 (operands[0], operands[1], rot_count));
+  DONE;
+})
+
 ;; Expanders for arithmetic shift left on each vector element
 (define_expand "vashl<mode>3"
   [(set (match_operand:VEC_I 0 "vint_operand")

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index d7eda8e..a372d7f 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,10 @@
+2019-08-07  Kewen Lin  <linkw@gcc.gnu.org>
+
+       * gcc.target/powerpc/vec_rotate-1.c: New test.
+       * gcc.target/powerpc/vec_rotate-2.c: New test.
+       * gcc.target/powerpc/vec_rotate-3.c: New test.
+       * gcc.target/powerpc/vec_rotate-4.c: New test.
+
 2019-08-07  Alexandre Oliva <oliva@adacore.com>
 
        * gcc.target/i386/math_m_pi.h: New.

diff --git a/gcc/testsuite/gcc.target/powerpc/vec_rotate-1.c b/gcc/testsuite/gcc.target/powerpc/vec_rotate-1.c
new file mode 100644 (file)
index 0000000..f035a57
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_rotate-1.c
@@ -0,0 +1,39 @@
+/* { dg-options "-O3" } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+
+/* Check vectorizer can exploit vector rotation instructions on Power, mainly
+   for the case rotation count is const number.
+
+   Check for instructions vrlb/vrlh/vrlw only available if altivec supported. */
+
+#define N 256
+unsigned int suw[N], ruw[N];
+unsigned short suh[N], ruh[N];
+unsigned char sub[N], rub[N];
+
+void
+testUW ()
+{
+  for (int i = 0; i < 256; ++i)
+    ruw[i] = (suw[i] >> 8) | (suw[i] << (sizeof (suw[0]) * 8 - 8));
+}
+
+void
+testUH ()
+{
+  for (int i = 0; i < 256; ++i)
+    ruh[i] = (unsigned short) (suh[i] >> 9)
+            | (unsigned short) (suh[i] << (sizeof (suh[0]) * 8 - 9));
+}
+
+void
+testUB ()
+{
+  for (int i = 0; i < 256; ++i)
+    rub[i] = (unsigned char) (sub[i] >> 5)
+            | (unsigned char) (sub[i] << (sizeof (sub[0]) * 8 - 5));
+}
+
+/* { dg-final { scan-assembler {\mvrlw\M} } } */
+/* { dg-final { scan-assembler {\mvrlh\M} } } */
+/* { dg-final { scan-assembler {\mvrlb\M} } } */

diff --git a/gcc/testsuite/gcc.target/powerpc/vec_rotate-2.c b/gcc/testsuite/gcc.target/powerpc/vec_rotate-2.c
new file mode 100644 (file)
index 0000000..2359895
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_rotate-2.c
@@ -0,0 +1,18 @@
+/* { dg-options "-O3 -mdejagnu-cpu=power8" } */
+
+/* Check vectorizer can exploit vector rotation instructions on Power8, mainly
+   for the case rotation count is const number.
+
+   Check for vrld which is available on Power8 and above.  */
+
+#define N 256
+unsigned long long sud[N], rud[N];
+
+void
+testULL ()
+{
+  for (int i = 0; i < 256; ++i)
+    rud[i] = (sud[i] >> 8) | (sud[i] << (sizeof (sud[0]) * 8 - 8));
+}
+
+/* { dg-final { scan-assembler {\mvrld\M} } } */

diff --git a/gcc/testsuite/gcc.target/powerpc/vec_rotate-3.c b/gcc/testsuite/gcc.target/powerpc/vec_rotate-3.c
new file mode 100644 (file)
index 0000000..5e90ae6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_rotate-3.c
@@ -0,0 +1,40 @@
+/* { dg-options "-O3" } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+
+/* Check vectorizer can exploit vector rotation instructions on Power, mainly
+   for the case rotation count isn't const number.
+
+   Check for instructions vrlb/vrlh/vrlw only available if altivec supported. */
+
+#define N 256
+unsigned int suw[N], ruw[N];
+unsigned short suh[N], ruh[N];
+unsigned char sub[N], rub[N];
+extern unsigned char rot_cnt;
+
+void
+testUW ()
+{
+  for (int i = 0; i < 256; ++i)
+    ruw[i] = (suw[i] >> rot_cnt) | (suw[i] << (sizeof (suw[0]) * 8 - rot_cnt));
+}
+
+void
+testUH ()
+{
+  for (int i = 0; i < 256; ++i)
+    ruh[i] = (unsigned short) (suh[i] >> rot_cnt)
+            | (unsigned short) (suh[i] << (sizeof (suh[0]) * 8 - rot_cnt));
+}
+
+void
+testUB ()
+{
+  for (int i = 0; i < 256; ++i)
+    rub[i] = (unsigned char) (sub[i] >> rot_cnt)
+            | (unsigned char) (sub[i] << (sizeof (sub[0]) * 8 - rot_cnt));
+}
+
+/* { dg-final { scan-assembler {\mvrlw\M} } } */
+/* { dg-final { scan-assembler {\mvrlh\M} } } */
+/* { dg-final { scan-assembler {\mvrlb\M} } } */

diff --git a/gcc/testsuite/gcc.target/powerpc/vec_rotate-4.c b/gcc/testsuite/gcc.target/powerpc/vec_rotate-4.c
new file mode 100644 (file)
index 0000000..75f08f0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_rotate-4.c
@@ -0,0 +1,19 @@
+/* { dg-options "-O3 -mdejagnu-cpu=power8" } */
+
+/* Check vectorizer can exploit vector rotation instructions on Power8, mainly
+   for the case rotation count isn't const number.
+
+   Check for vrld which is available on Power8 and above.  */
+
+#define N 256
+unsigned long long sud[N], rud[N];
+extern unsigned char rot_cnt;
+
+void
+testULL ()
+{
+  for (int i = 0; i < 256; ++i)
+    rud[i] = (sud[i] >> rot_cnt) | (sud[i] << (sizeof (sud[0]) * 8 - rot_cnt));
+}
+
+/* { dg-final { scan-assembler {\mvrld\M} } } */