diff mbox series

aarch64: add support for unpacked EOR, ORR and AND

Message ID B992BCD5-2006-4A8A-9F5F-B7103E1BBD44@arm.com
State New
Headers show
Series aarch64: add support for unpacked EOR, ORR and AND | expand

Commit Message

Joe Ramsay May 27, 2020, 9:35 a.m. UTC 
Hi!

This patch improves code generation for EOR, ORR and AND on unpacked vectors with SVE. The following function:
void f (unsigned int *x, unsigned short *y, unsigned short *z) {
  for (int i = 0; i < 7; ++i)
    x[i] = (unsigned short) (y[i] & z[i]);
}

previously compiled to
ptrue   p1.d, vl3
ld1h    z0.d, p1/z, [x1, #1, mul vl]
ptrue   p0.b, vl32
st1h    z0.d, p0, [sp, #1, mul vl]
ld1h    z0.d, p1/z, [x2, #1, mul vl]
st1h    z0.d, p0, [sp]
ldr     x3, [x2]
ldp     x4, x2, [sp]
ldr     x1, [x1]
and     x1, x3, x1
and     x2, x2, x4
str     x2, [sp]
ld1h    z0.d, p0/z, [sp]
str     x1, [sp]
uxth    z0.s, p0/m, z0.s
st1w    z0.d, p1, [x0, #1, mul vl]
ld1h    z0.d, p0/z, [sp]
uxth    z0.s, p0/m, z0.s
st1w    z0.d, p0, [x0]
add     sp, sp, 16
ret

and now compiles to:

ptrue   p0.s, vl7

ptrue   p1.b, vl32

ld1h    z1.s, p0/z, [x1]

ld1h    z0.s, p0/z, [x2]

add     z0.h, z0.h, z1.h

uxth    z0.s, p1/m, z0.s

st1w    z0.s, p0, [x0]

ret



Tested on aarch64-linux-gnu and x86_64-linux-gnu hosts.

Thanks,
Joe


2020-05-20  Joe Ramsay  <joe.ramsay@arm.com>



                    * config/aarch64/aarch64-sve.md (<LOGICAL:optab><mode>3): Add support for unpacked EOR, ORR, AND.



gcc/testsuite/ChangeLog



2020-05-20  Joe Ramsay  <joe.ramsay@arm.com>



                    * gcc.target/aarch64/sve/logical_unpacked_and_1.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_and_2.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_and_3.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_and_4.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_and_5.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_and_6.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_and_7.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_eor_1.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_eor_2.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_eor_3.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_eor_4.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_eor_5.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_eor_6.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_eor_7.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_orr_1.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_orr_2.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_orr_3.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_orr_4.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_orr_5.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_orr_6.c: New test.

                    * gcc.target/aarch64/sve/logical_unpacked_orr_7.c: New test.
---
diff mbox series

Patch

diff --git a/gcc/config/aarch64/aarch64-sve.md b/gcc/config/aarch64/aarch64-sve.md
index f7a0893..8f0944c 100644
--- a/gcc/config/aarch64/aarch64-sve.md
+++ b/gcc/config/aarch64/aarch64-sve.md
@@ -4211,10 +4211,10 @@ 
 ;; Unpredicated integer binary logical operations.
(define_insn "<optab><mode>3"
-  [(set (match_operand:SVE_FULL_I 0 "register_operand" "=w, ?w, w")
-               (LOGICAL:SVE_FULL_I
-                 (match_operand:SVE_FULL_I 1 "register_operand" "%0, w, w")
-                 (match_operand:SVE_FULL_I 2 "aarch64_sve_logical_operand" "vsl, vsl, w")))]
+  [(set (match_operand:SVE_I 0 "register_operand" "=w, ?w, w")
+              (LOGICAL:SVE_I
+                (match_operand:SVE_I 1 "register_operand" "%0, w, w")
+                (match_operand:SVE_I 2 "aarch64_sve_logical_operand" "vsl, vsl, w")))]
   "TARGET_SVE"
   "@
    <logical>\t%0.<Vetype>, %0.<Vetype>, #%C2
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_1.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_1.c
new file mode 100644
index 0000000..7840355
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_1.c
@@ -0,0 +1,16 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint32_t *restrict dst, uint16_t *restrict src1, uint8_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,} 1 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tand\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_and_2.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_2.c
new file mode 100644
index 0000000..08b2745
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_2.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_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]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
+/* { dg-final { scan-assembler-times {\tand\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_3.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_3.c
new file mode 100644
index 0000000..c823470
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_3.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint32_t *restrict src1, uint8_t *restrict src2)
+{
+  for (int i = 0; i < 7; ++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 {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tand\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_4.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_4.c
new file mode 100644
index 0000000..52c9291
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_4.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint32_t *restrict src1, uint16_t *restrict src2)
+{
+  for (int i = 0; i < 7; ++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 {\tld1h\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tand\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_5.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_5.c
new file mode 100644
index 0000000..7840355
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_5.c
@@ -0,0 +1,16 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint32_t *restrict dst, uint16_t *restrict src1, uint8_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,} 1 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tand\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_and_6.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_6.c
new file mode 100644
index 0000000..1552ed8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_6.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_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]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
+/* { dg-final { scan-assembler-times {\tand\tz[0-9]+\.d, z[0-9]+\.d, z[0-9]+\.d\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_7.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_7.c
new file mode 100644
index 0000000..484d9da
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_7.c
@@ -0,0 +1,16 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint32_t *restrict src1, uint8_t *restrict src2){
+  for (int i = 0; i < 7; ++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 {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tand\tz[0-9]+\.d, z[0-9]+\.d, z[0-9]+\.d\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_1.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_1.c
new file mode 100644
index 0000000..36a0b8c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_1.c
@@ -0,0 +1,16 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint32_t *restrict dst, uint16_t *restrict src1, uint8_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,} 1 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\teor\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_eor_2.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_2.c
new file mode 100644
index 0000000..23ddeb9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_2.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_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]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
+/* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_3.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_3.c
new file mode 100644
index 0000000..4dd1e08
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_3.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint32_t *restrict src1, uint8_t *restrict src2)
+{
+  for (int i = 0; i < 7; ++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 {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_4.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_4.c
new file mode 100644
index 0000000..a31a2d4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_4.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint32_t *restrict src1, uint16_t *restrict src2)
+{
+  for (int i = 0; i < 7; ++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 {\tld1h\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_5.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_5.c
new file mode 100644
index 0000000..36a0b8c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_5.c
@@ -0,0 +1,16 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint32_t *restrict dst, uint16_t *restrict src1, uint8_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,} 1 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\teor\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_eor_6.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_6.c
new file mode 100644
index 0000000..416567b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_6.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_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]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
+/* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.d, z[0-9]+\.d, z[0-9]+\.d\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_7.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_7.c
new file mode 100644
index 0000000..3f7c3dd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_7.c
@@ -0,0 +1,16 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint32_t *restrict src1, uint8_t *restrict src2){
+  for (int i = 0; i < 7; ++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 {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.d, z[0-9]+\.d, z[0-9]+\.d\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_1.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_1.c
new file mode 100644
index 0000000..6131792
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_1.c
@@ -0,0 +1,16 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint32_t *restrict dst, uint16_t *restrict src1, uint8_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,} 1 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\torr\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_orr_2.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_2.c
new file mode 100644
index 0000000..593de65
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_2.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_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]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
+/* { dg-final { scan-assembler-times {\torr\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_3.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_3.c
new file mode 100644
index 0000000..ec34e75
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_3.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint32_t *restrict src1, uint8_t *restrict src2)
+{
+  for (int i = 0; i < 7; ++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 {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\torr\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_4.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_4.c
new file mode 100644
index 0000000..561a104
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_4.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint32_t *restrict src1, uint16_t *restrict src2)
+{
+  for (int i = 0; i < 7; ++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 {\tld1h\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\torr\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_5.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_5.c
new file mode 100644
index 0000000..6131792
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_5.c
@@ -0,0 +1,16 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint32_t *restrict dst, uint16_t *restrict src1, uint8_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,} 1 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\torr\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_orr_6.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_6.c
new file mode 100644
index 0000000..3ce1c3f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_6.c
@@ -0,0 +1,17 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_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]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
+/* { dg-final { scan-assembler-times {\torr\tz[0-9]+\.d, z[0-9]+\.d, z[0-9]+\.d\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_7.c b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_7.c
new file mode 100644
index 0000000..e6a4291
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_7.c
@@ -0,0 +1,16 @@ 
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include <stdint.h>
+
+void
+f (uint64_t *restrict dst, uint32_t *restrict src1, uint8_t *restrict src2){
+  for (int i = 0; i < 7; ++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 {\tld1b\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\torr\tz[0-9]+\.d, z[0-9]+\.d, z[0-9]+\.d\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
+/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */