AArch64+SVE: Add support for unpacked unary ops and BIC

MD patterns extended for unary ops ABS, CLS, CLZ, CNT, NEG and NOT
to support unpacked vectors. Also extended patterns for BIC to
support unpacked vectors where input elements are of the same width.

gcc/ChangeLog:

2020-06-09  Joe Ramsay  <joe.ramsay@arm.com>

	* config/aarch64/aarch64-sve.md (<optab><mode>2): Add support for
	unpacked vectors.
	(@aarch64_pred_<optab><mode>): Add support for unpacked vectors.
	(@aarch64_bic<mode>): Enable unpacked BIC.
	(*bic<mode>3): Enable unpacked BIC.

gcc/testsuite/ChangeLog:

2020-06-09  Joe Ramsay  <joe.ramsay@arm.com>

	* gcc.target/aarch64/sve/logical_unpacked_abs.c: New test.
	* gcc.target/aarch64/sve/logical_unpacked_bic_1.c: New test.
	* gcc.target/aarch64/sve/logical_unpacked_bic_2.c: New test.
	* gcc.target/aarch64/sve/logical_unpacked_bic_3.c: New test.
	* gcc.target/aarch64/sve/logical_unpacked_bic_4.c: New test.
	* gcc.target/aarch64/sve/logical_unpacked_neg.c: New test.
	* gcc.target/aarch64/sve/logical_unpacked_not.c: New test.

8 files changed, 127 insertions, 19 deletions

diff --git a/gcc/config/aarch64/aarch64-sve.md b/gcc/config/aarch64/aarch64-sve.md
index 8f0944c..9d06bf7 100644
--- a/gcc/config/aarch64/aarch64-sve.md
+++ b/gcc/config/aarch64/aarch64-sve.md
@@ -2822,11 +2822,11 @@
 
 ;; Unpredicated integer unary arithmetic.
 (define_expand "<optab><mode>2"
-  [(set (match_operand:SVE_FULL_I 0 "register_operand")
-	(unspec:SVE_FULL_I
+  [(set (match_operand:SVE_I 0 "register_operand")
+	(unspec:SVE_I
 	  [(match_dup 2)
-	   (SVE_INT_UNARY:SVE_FULL_I
-	     (match_operand:SVE_FULL_I 1 "register_operand"))]
+	   (SVE_INT_UNARY:SVE_I
+	     (match_operand:SVE_I 1 "register_operand"))]
 	  UNSPEC_PRED_X))]
   "TARGET_SVE"
   {
@@ -2836,11 +2836,11 @@
 
 ;; Integer unary arithmetic predicated with a PTRUE.
 (define_insn "@aarch64_pred_<optab><mode>"
-  [(set (match_operand:SVE_FULL_I 0 "register_operand" "=w")
-	(unspec:SVE_FULL_I
+  [(set (match_operand:SVE_I 0 "register_operand" "=w")
+	(unspec:SVE_I
 	  [(match_operand:<VPRED> 1 "register_operand" "Upl")
-	   (SVE_INT_UNARY:SVE_FULL_I
-	     (match_operand:SVE_FULL_I 2 "register_operand" "w"))]
+	   (SVE_INT_UNARY:SVE_I
+	     (match_operand:SVE_I 2 "register_operand" "w"))]
 	  UNSPEC_PRED_X))]
   "TARGET_SVE"
   "<sve_int_op>\t%0.<Vetype>, %1/m, %2.<Vetype>"
@@ -4234,13 +4234,13 @@
 
 ;; Unpredicated BIC.
 (define_expand "@aarch64_bic<mode>"
-  [(set (match_operand:SVE_FULL_I 0 "register_operand")
-	(and:SVE_FULL_I
-	  (unspec:SVE_FULL_I
+  [(set (match_operand:SVE_I 0 "register_operand")
+	(and:SVE_I
+	  (unspec:SVE_I
 	    [(match_dup 3)
-	     (not:SVE_FULL_I (match_operand:SVE_FULL_I 2 "register_operand"))]
+	     (not:SVE_I (match_operand:SVE_I 2 "register_operand"))]
 	    UNSPEC_PRED_X)
-	  (match_operand:SVE_FULL_I 1 "register_operand")))]
+	  (match_operand:SVE_I 1 "register_operand")))]
   "TARGET_SVE"
   {
     operands[3] = CONSTM1_RTX (<VPRED>mode);
@@ -4249,14 +4249,14 @@
 
 ;; Predicated BIC.
 (define_insn_and_rewrite "*bic<mode>3"
-  [(set (match_operand:SVE_FULL_I 0 "register_operand" "=w")
-	(and:SVE_FULL_I
-	  (unspec:SVE_FULL_I
+  [(set (match_operand:SVE_I 0 "register_operand" "=w")
+	(and:SVE_I
+	  (unspec:SVE_I
 	    [(match_operand 3)
-	     (not:SVE_FULL_I
-	       (match_operand:SVE_FULL_I 2 "register_operand" "w"))]
+	     (not:SVE_I
+	       (match_operand:SVE_I 2 "register_operand" "w"))]
 	    UNSPEC_PRED_X)
-	  (match_operand:SVE_FULL_I 1 "register_operand" "w")))]
+	  (match_operand:SVE_I 1 "register_operand" "w")))]
   "TARGET_SVE"
   "bic\t%0.d, %1.d, %2.d"
   "&& !CONSTANT_P (operands[3])"
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_abs.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_abs.c
new file mode 100644
index 0000000..814e44c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_abs.c
@@ -0,0 +1,16 @@
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+#include <stdlib.h>
+
+void
+f (uint32_t *restrict dst, int8_t *restrict src)
+{
+  for (int i = 0; i < 7; ++i)
+    dst[i] = (int8_t) abs(src[i]);
+}
+
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tabs\tz[0-9]+\.b, p[0-9]+/m, z[0-9]+\.b\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tsxtb\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tst1w\tz[0-9]+\.s,} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_1.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_1.c
new file mode 100644
index 0000000..2460305
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_1.c
@@ -0,0 +1,15 @@
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint32_t *restrict src1, uint32_t *restrict src2)
+{
+  for (int i = 0; i < 3; ++i)
+    dst[i] = (uint32_t) (src1[i] & ~src2[i]);
+}
+
+/* { dg-final { scan-assembler-times {\tld1w\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tbic\tz[0-9]+\.d, z[0-9]+\.d, z[0-9]+\.d\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 1 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_2.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_2.c
new file mode 100644
index 0000000..61066a9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_2.c
@@ -0,0 +1,15 @@
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint8_t *restrict src1, uint8_t *restrict src2)
+{
+  for (int i = 0; i < 3; ++i)
+    dst[i] = (uint8_t) (src1[i] & ~src2[i]);
+}
+
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tbic\tz[0-9]+\.d, z[0-9]+\.d, z[0-9]+\.d\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.d,} 1 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_3.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_3.c
new file mode 100644
index 0000000..2c9586a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_3.c
@@ -0,0 +1,15 @@
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint32_t *restrict dst, uint16_t *restrict src1, uint16_t *restrict src2)
+{
+  for (int i = 0; i < 7; ++i)
+    dst[i] = (uint16_t) (src1[i] & ~src2[i]);
+}
+
+/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.s,} 2 } } */
+/* { dg-final { scan-assembler-times {\tbic\tz[0-9]+\.d, z[0-9]+\.d, z[0-9]+\.d\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tst1w\tz[0-9]+\.s,} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_4.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_4.c
new file mode 100644
index 0000000..5fca214
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_4.c
@@ -0,0 +1,15 @@
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint16_t *restrict dst, uint8_t *restrict src1, uint8_t *restrict src2)
+{
+  for (int i = 0; i < 15; ++i)
+    dst[i] = (uint8_t) (src1[i] & ~src2[i]);
+}
+
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.h,} 2 } } */
+/* { dg-final { scan-assembler-times {\tbic\tz[0-9]+\.d, z[0-9]+\.d, z[0-9]+\.d\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
+/* { dg-final { scan-assembler-times {\tst1h\tz[0-9]+\.h,} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_neg.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_neg.c
new file mode 100644
index 0000000..1f8b3d3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_neg.c
@@ -0,0 +1,16 @@
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+#include <stdlib.h>
+
+void
+f (uint32_t *restrict dst, int8_t *restrict src)
+{
+  for (int i = 0; i < 7; ++i)
+    dst[i] = (int8_t) -src[i];
+}
+
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tneg\tz[0-9]+\.b, p[0-9]+/m, z[0-9]+\.b\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tsxtb\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tst1w\tz[0-9]+\.s,} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_not.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_not.c
new file mode 100644
index 0000000..a9d36b8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_not.c
@@ -0,0 +1,16 @@
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+#include <stdlib.h>
+
+void
+f (uint32_t *restrict dst, int8_t *restrict src)
+{
+  for (int i = 0; i < 7; ++i)
+    dst[i] = (int8_t) ~src[i];
+}
+
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tnot\tz[0-9]+\.b, p[0-9]+/m, z[0-9]+\.b\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tsxtb\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tst1w\tz[0-9]+\.s,} 1 } } */