arm: Add new tests for comparison vectorization with Neon and MVE

This patch mainly adds Neon tests similar to existing MVE ones,
to make sure we do not break Neon when fixing MVE.

mve-vcmp-f32-2.c is similar to mve-vcmp-f32.c but uses a conditional
with 2.0f and 3.0f constants to help scan-assembler-times.

Most of the work of this patch series was carried out while I was
working at STMicroelectronics as a Linaro assignee.

2022-02-22  Christophe Lyon <christophe.lyon@arm.com>

	gcc/testsuite/
	* gcc.target/arm/simd/mve-vcmp-f32-2.c: New.
	* gcc.target/arm/simd/neon-compare-1.c: New.
	* gcc.target/arm/simd/neon-compare-2.c: New.
	* gcc.target/arm/simd/neon-compare-3.c: New.
	* gcc.target/arm/simd/neon-compare-scalar-1.c: New.
	* gcc.target/arm/simd/neon-vcmp-f16.c: New.
	* gcc.target/arm/simd/neon-vcmp-f32-2.c: New.
	* gcc.target/arm/simd/neon-vcmp-f32-3.c: New.
	* gcc.target/arm/simd/neon-vcmp-f32.c: New.
	* gcc.target/arm/simd/neon-vcmp.c: New.

10 files changed, 267 insertions, 0 deletions

diff --git a/gcc/testsuite/gcc.target/arm/simd/mve-vcmp-f32-2.c b/gcc/testsuite/gcc.target/arm/simd/mve-vcmp-f32-2.c
new file mode 100644
index 0000000..917a95b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/mve-vcmp-f32-2.c
@@ -0,0 +1,32 @@
+/* { dg-do assemble } */
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O3 -funsafe-math-optimizations" } */
+
+#include <stdint.h>
+
+#define NB 4
+
+#define FUNC(OP, NAME)							\
+  void test_ ## NAME ##_f (float * __restrict__ dest, float *a, float *b) { \
+    int i;								\
+    for (i=0; i<NB; i++) {						\
+      dest[i] = (a[i] OP b[i]) ? 2.0f : 3.0f;				\
+    }									\
+  }
+
+FUNC(==, vcmpeq)
+FUNC(!=, vcmpne)
+FUNC(<, vcmplt)
+FUNC(<=, vcmple)
+FUNC(>, vcmpgt)
+FUNC(>=, vcmpge)
+
+/* { dg-final { scan-assembler-times {\tvcmp.f32\teq, q[0-9]+, q[0-9]+\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcmp.f32\tne, q[0-9]+, q[0-9]+\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcmp.f32\tlt, q[0-9]+, q[0-9]+\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcmp.f32\tle, q[0-9]+, q[0-9]+\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcmp.f32\tgt, q[0-9]+, q[0-9]+\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcmp.f32\tge, q[0-9]+, q[0-9]+\n} 1 } } */
+/* { dg-final { scan-assembler-times {\t.word\t1073741824\n} 24 } } */ /* Constant 2.0f.  */
+/* { dg-final { scan-assembler-times {\t.word\t1077936128\n} 24 } } */ /* Constant 3.0f.  */
diff --git a/gcc/testsuite/gcc.target/arm/simd/neon-compare-1.c b/gcc/testsuite/gcc.target/arm/simd/neon-compare-1.c
new file mode 100644
index 0000000..2e0222a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/neon-compare-1.c
@@ -0,0 +1,78 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-add-options arm_neon } */
+/* { dg-additional-options "-O3" } */
+
+#include "mve-compare-1.c"
+
+/* 64-bit vectors.  */
+/* vmvn is used by 'ne' comparisons: 3 sizes * 2 (signed/unsigned) * 2
+   (register/zero) = 12.  */
+/* { dg-final { scan-assembler-times {\tvmvn\td[0-9]+, d[0-9]+\n} 12 } } */
+
+/* { 8 bits } x { eq, ne, lt, le, gt, ge }. */
+/* ne uses eq, lt/le only apply to comparison with zero, they use gt/ge
+   otherwise.  */
+/* { dg-final { scan-assembler-times {\tvceq.i8\td[0-9]+, d[0-9]+, d[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvceq.i8\td[0-9]+, d[0-9]+, #0\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvclt.s8\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcle.s8\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s8\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s8\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s8\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s8\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+
+/* { 16 bits } x { eq, ne, lt, le, gt, ge }. */
+/* { dg-final { scan-assembler-times {\tvceq.i16\td[0-9]+, d[0-9]+, d[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvceq.i16\td[0-9]+, d[0-9]+, #0\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvclt.s16\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcle.s16\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s16\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s16\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s16\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s16\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+
+/* { 32 bits } x { eq, ne, lt, le, gt, ge }. */
+/* { dg-final { scan-assembler-times {\tvceq.i32\td[0-9]+, d[0-9]+, d[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvceq.i32\td[0-9]+, d[0-9]+, #0\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvclt.s32\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcle.s32\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s32\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s32\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s32\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s32\td[0-9]+, d[0-9]+, #0\n} 1 } } */
+
+/* 128-bit vectors.  */
+
+/* vmvn is used by 'ne' comparisons.  */
+/* { dg-final { scan-assembler-times {\tvmvn\tq[0-9]+, q[0-9]+\n} 12 } } */
+
+/* { 8 bits } x { eq, ne, lt, le, gt, ge }.  */
+/* { dg-final { scan-assembler-times {\tvceq.i8\tq[0-9]+, q[0-9]+, q[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvceq.i8\tq[0-9]+, q[0-9]+, #0\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvclt.s8\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcle.s8\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s8\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s8\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s8\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s8\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
+
+/* { 16 bits } x { eq, ne, lt, le, gt, ge }.  */
+/* { dg-final { scan-assembler-times {\tvceq.i16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvceq.i16\tq[0-9]+, q[0-9]+, #0\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvclt.s16\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcle.s16\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s16\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s16\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
+
+/* { 32 bits } x { eq, ne, lt, le, gt, ge }.  */
+/* { dg-final { scan-assembler-times {\tvceq.i32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvceq.i32\tq[0-9]+, q[0-9]+, #0\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvclt.s32\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcle.s32\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s32\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s32\tq[0-9]+, q[0-9]+, #0\n} 1 } } */
diff --git a/gcc/testsuite/gcc.target/arm/simd/neon-compare-2.c b/gcc/testsuite/gcc.target/arm/simd/neon-compare-2.c
new file mode 100644
index 0000000..06f3c14
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/neon-compare-2.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-add-options arm_neon } */
+/* { dg-additional-options "-O3 -funsafe-math-optimizations" } */
+
+#include "mve-compare-2.c"
+
+/* eq, ne, lt, le, gt, ge.  */
+/* ne uses eq+vmvn, lt/le use gt/ge with swapped operands.  */
+/* { dg-final { scan-assembler-times {\tvceq.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvmvn\tq[0-9]+, q[0-9]+\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
diff --git a/gcc/testsuite/gcc.target/arm/simd/neon-compare-3.c b/gcc/testsuite/gcc.target/arm/simd/neon-compare-3.c
new file mode 100644
index 0000000..9c9f108
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/neon-compare-3.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_2a_fp16_neon_ok } */
+/* { dg-add-options arm_v8_2a_fp16_neon } */
+/* { dg-additional-options "-O3 -funsafe-math-optimizations" } */
+
+#include "mve-compare-3.c"
+
+
+/* eq, ne, lt, le, gt, ge.  */
+/* ne uses eq+vmvn, lt/le use gt/ge with swapped operands.  */
+/* { dg-final { scan-assembler-times {\tvceq.f16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvmvn\tq[0-9]+, q[0-9]+\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.f16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.f16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
diff --git a/gcc/testsuite/gcc.target/arm/simd/neon-compare-scalar-1.c b/gcc/testsuite/gcc.target/arm/simd/neon-compare-scalar-1.c
new file mode 100644
index 0000000..0783624
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/neon-compare-scalar-1.c
@@ -0,0 +1,57 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-add-options arm_neon } */
+/* { dg-additional-options "-O3" } */
+
+#include "mve-compare-scalar-1.c"
+
+/* 64-bit vectors.  */
+/* vmvn is used by 'ne' comparisons.  */
+/* { dg-final { scan-assembler-times {\tvmvn\td[0-9]+, d[0-9]+\n} 6 } } */
+
+/* { 8 bits } x { eq, ne, lt, le, gt, ge }.  */
+/* { dg-final { scan-assembler-times {\tvceq.i8\td[0-9]+, d[0-9]+, d[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s8\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.u8\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s8\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.u8\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+
+/* { 16 bits } x { eq, ne, lt, le, gt, ge }.  */
+/* { dg-final { scan-assembler-times {\tvceq.i16\td[0-9]+, d[0-9]+, d[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s16\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.u16\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s16\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.u16\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+
+/* { 32 bits } x { eq, ne, lt, le, gt, ge }.  */
+/* { dg-final { scan-assembler-times {\tvceq.i32\td[0-9]+, d[0-9]+, d[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s32\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.u32\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s32\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.u32\td[0-9]+, d[0-9]+, d[0-9]+\n} 2 } } */
+
+/* 128-bit vectors.  */
+
+/* vmvn is used by 'ne' comparisons.  */
+/* { dg-final { scan-assembler-times {\tvmvn\tq[0-9]+, q[0-9]+\n} 6 } } */
+
+/* { 8 bits } x { eq, ne, lt, le, gt, ge }.  */
+/* { dg-final { scan-assembler-times {\tvceq.i8\tq[0-9]+, q[0-9]+, q[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s8\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.u8\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s8\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.u8\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+
+/* { 16 bits } x { eq, ne, lt, le, gt, ge }.  */
+/* { dg-final { scan-assembler-times {\tvceq.i16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.u16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.u16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+
+/* { 32 bits } x { eq, ne, lt, le, gt, ge }.  */
+/* { dg-final { scan-assembler-times {\tvceq.i32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 4 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.u32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.u32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
diff --git a/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f16.c b/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f16.c
new file mode 100644
index 0000000..688fd9a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f16.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_2a_fp16_neon_ok } */
+/* { dg-add-options arm_v8_2a_fp16_neon } */
+/* { dg-additional-options "-O3 -funsafe-math-optimizations" } */
+
+#include "mve-vcmp-f16.c"
+
+/* 'ne' uses vceq.  */
+/* le and lt use ge and gt with inverted operands.  */
+/* { dg-final { scan-assembler-times {\tvceq.f16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.f16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.f16\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
diff --git a/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f32-2.c b/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f32-2.c
new file mode 100644
index 0000000..a22923e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f32-2.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-add-options arm_neon } */
+/* { dg-additional-options "-O3 -funsafe-math-optimizations" } */
+
+#include "mve-vcmp-f32-2.c"
+
+/* 'ne' uses vceq.  */
+/* le and lt use ge and gt with inverted operands.  */
+/* { dg-final { scan-assembler-times {\tvceq.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tvmov.f32\tq[0-9]+, #2.0e\+0} 6 } } */
+/* { dg-final { scan-assembler-times {\tvmov.f32\tq[0-9]+, #3.0e\+0} 6 } } */
diff --git a/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f32-3.c b/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f32-3.c
new file mode 100644
index 0000000..4f12f04
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f32-3.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-add-options arm_neon } */
+/* { dg-additional-options "-O3" } */
+
+#include "mve-vcmp-f32.c"
+
+/* Should not be vectorized, since we do not use -funsafe-math-optimizations.  */
+
+/* { dg-final { scan-assembler-not {\tvceq.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} } } */
+/* { dg-final { scan-assembler-not {\tvcge.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} } } */
+/* { dg-final { scan-assembler-not {\tvcgt.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} } } */
diff --git a/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f32.c b/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f32.c
new file mode 100644
index 0000000..06e5c4f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/neon-vcmp-f32.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-add-options arm_neon } */
+/* { dg-additional-options "-O3 -funsafe-math-optimizations" } */
+
+#include "mve-vcmp-f32.c"
+
+/* 'ne' uses vceq.  */
+/* le and lt use ge and gt with inverted operands.  */
+/* { dg-final { scan-assembler-times {\tvceq.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcge.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.f32\tq[0-9]+, q[0-9]+, q[0-9]+\n} 2 } } */
diff --git a/gcc/testsuite/gcc.target/arm/simd/neon-vcmp.c b/gcc/testsuite/gcc.target/arm/simd/neon-vcmp.c
new file mode 100644
index 0000000..f2b92b1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/neon-vcmp.c
@@ -0,0 +1,22 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-add-options arm_neon } */
+/* { dg-additional-options "-O3" } */
+
+#include "mve-vcmp.c"
+
+/* vceq is also used for 'ne' comparisons.  */
+/* { dg-final { scan-assembler-times {\tvceq.i[0-9]+\td[0-9]+, d[0-9]+, d[0-9]+\n} 12 } } */
+/* { dg-final { scan-assembler-times {\tvceq.i[0-9]+\tq[0-9]+, q[0-9]+, q[0-9]+\n} 12 } } */
+
+/* lt and le are replaced with the opposite condition, hence the double number
+   of matches for gt and ge.  */
+/* { dg-final { scan-assembler-times {\tvcge.s[0-9]+\td[0-9]+, d[0-9]+, d[0-9]+\n} 6 } } */
+/* { dg-final { scan-assembler-times {\tvcge.s[0-9]+\tq[0-9]+, q[0-9]+, q[0-9]+\n} 6 } } */
+/* { dg-final { scan-assembler-times {\tvcge.u[0-9]+\td[0-9]+, d[0-9]+, d[0-9]+\n} 6 } } */
+/* { dg-final { scan-assembler-times {\tvcge.u[0-9]+\tq[0-9]+, q[0-9]+, q[0-9]+\n} 6 } } */
+
+/* { dg-final { scan-assembler-times {\tvcgt.s[0-9]+\td[0-9]+, d[0-9]+, d[0-9]+\n} 6 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.s[0-9]+\tq[0-9]+, q[0-9]+, q[0-9]+\n} 6 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.u[0-9]+\td[0-9]+, d[0-9]+, d[0-9]+\n} 6 } } */
+/* { dg-final { scan-assembler-times {\tvcgt.u[0-9]+\tq[0-9]+, q[0-9]+, q[0-9]+\n} 6 } } */